From 64b6a4e91ef735c8d07e93c4e670a01bcb10e7bb Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Fri, 9 Aug 2019 08:16:53 +0100 Subject: [PATCH 001/422] [youtube] fix annotations extraction(closes #22045) --- youtube_dl/extractor/youtube.py | 27 +++++++++++++++------------ 1 file changed, 15 insertions(+), 12 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 44740cb75..0a0d2f41a 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1595,17 +1595,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): video_id = mobj.group(2) return video_id - def _extract_annotations(self, video_id): - return self._download_webpage( - 'https://www.youtube.com/annotations_invideo', video_id, - note='Downloading annotations', - errnote='Unable to download video annotations', fatal=False, - query={ - 'features': 1, - 'legacy': 1, - 'video_id': video_id, - }) - @staticmethod def _extract_chapters(description, duration): if not description: @@ -2277,7 +2266,21 @@ class YoutubeIE(YoutubeBaseInfoExtractor): # annotations video_annotations = None if self._downloader.params.get('writeannotations', False): - video_annotations = self._extract_annotations(video_id) + xsrf_token = self._search_regex( + r'([\'"])XSRF_TOKEN\1\s*:\s*([\'"])(?P[A-Za-z0-9+/=]+)\2', + video_webpage, 'xsrf token', group='xsrf_token', fatal=False) + invideo_url = try_get( + player_response, lambda x: x['annotations'][0]['playerAnnotationsUrlsRenderer']['invideoUrl'], compat_str) + if xsrf_token and invideo_url: + xsrf_field_name = self._search_regex( + r'([\'"])XSRF_FIELD_NAME\1\s*:\s*([\'"])(?P\w+)\2', + video_webpage, 'xsrf field name', + group='xsrf_field_name', default='session_token') + video_annotations = self._download_webpage( + self._proto_relative_url(invideo_url), + video_id, note='Downloading annotations', + errnote='Unable to download video annotations', fatal=False, + data=urlencode_postdata({xsrf_field_name: xsrf_token})) chapters = self._extract_chapters(description_original, video_duration) From ffddb112642ab394ecc11db055a064368eed42f7 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Fri, 9 Aug 2019 08:19:41 +0100 Subject: [PATCH 002/422] [YoutubeDL] check annotations availabilty(closes #18582) --- youtube_dl/YoutubeDL.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 3e832fec2..6a44bc7ba 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -1783,6 +1783,8 @@ class YoutubeDL(object): annofn = replace_extension(filename, 'annotations.xml', info_dict.get('ext')) if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(annofn)): self.to_screen('[info] Video annotations are already present') + elif not info_dict.get('annotations'): + self.report_warning('There are no annotations to write.') else: try: self.to_screen('[info] Writing video annotations to: ' + annofn) From 3bce4ff7d96d845ec67ffe8e9e2715474f190d89 Mon Sep 17 00:00:00 2001 From: lightmare Date: Sun, 11 Aug 2019 01:57:43 +0200 Subject: [PATCH 003/422] [downloader/fragment] Fix ETA calculation of resumed download (#21992) --- youtube_dl/downloader/fragment.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/youtube_dl/downloader/fragment.py b/youtube_dl/downloader/fragment.py index f2e5733b6..02f35459e 100644 --- a/youtube_dl/downloader/fragment.py +++ b/youtube_dl/downloader/fragment.py @@ -190,12 +190,13 @@ class FragmentFD(FileDownloader): }) def _start_frag_download(self, ctx): + resume_len = ctx['complete_frags_downloaded_bytes'] total_frags = ctx['total_frags'] # This dict stores the download progress, it's updated by the progress # hook state = { 'status': 'downloading', - 'downloaded_bytes': ctx['complete_frags_downloaded_bytes'], + 'downloaded_bytes': resume_len, 'fragment_index': ctx['fragment_index'], 'fragment_count': total_frags, 'filename': ctx['filename'], @@ -234,8 +235,8 @@ class FragmentFD(FileDownloader): state['downloaded_bytes'] += frag_downloaded_bytes - ctx['prev_frag_downloaded_bytes'] if not ctx['live']: state['eta'] = self.calc_eta( - start, time_now, estimated_size, - state['downloaded_bytes']) + start, time_now, estimated_size - resume_len, + state['downloaded_bytes'] - resume_len) state['speed'] = s.get('speed') or ctx.get('speed') ctx['speed'] = state['speed'] ctx['prev_frag_downloaded_bytes'] = frag_downloaded_bytes From 351f37c022b24144c064fab39bd6d134e166c31c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 13 Aug 2019 05:02:52 +0700 Subject: [PATCH 004/422] [youtube:playlist] Improve flat extraction (closes #21927) --- youtube_dl/extractor/youtube.py | 49 +++++++++++++++++++++++++++++---- 1 file changed, 43 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 0a0d2f41a..b63f19bb0 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -31,6 +31,7 @@ from ..utils import ( clean_html, dict_get, error_to_compat_str, + extract_attributes, ExtractorError, float_or_none, get_element_by_attribute, @@ -324,17 +325,18 @@ class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor): for video_id, video_title in self.extract_videos_from_page(content): yield self.url_result(video_id, 'Youtube', video_id, video_title) - def extract_videos_from_page(self, page): - ids_in_page = [] - titles_in_page = [] - for mobj in re.finditer(self._VIDEO_RE, page): + def extract_videos_from_page_impl(self, video_re, page, ids_in_page, titles_in_page): + for mobj in re.finditer(video_re, page): # The link with index 0 is not the first video of the playlist (not sure if still actual) if 'index' in mobj.groupdict() and mobj.group('id') == '0': continue video_id = mobj.group('id') - video_title = unescapeHTML(mobj.group('title')) + video_title = unescapeHTML( + mobj.group('title')) if 'title' in mobj.groupdict() else None if video_title: video_title = video_title.strip() + if video_title == '► Play all': + video_title = None try: idx = ids_in_page.index(video_id) if video_title and not titles_in_page[idx]: @@ -342,6 +344,12 @@ class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor): except ValueError: ids_in_page.append(video_id) titles_in_page.append(video_title) + + def extract_videos_from_page(self, page): + ids_in_page = [] + titles_in_page = [] + self.extract_videos_from_page_impl( + self._VIDEO_RE, page, ids_in_page, titles_in_page) return zip(ids_in_page, titles_in_page) @@ -2438,7 +2446,8 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): (%(playlist_id)s) )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE} _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s' - _VIDEO_RE = r'href="\s*/watch\?v=(?P[0-9A-Za-z_-]{11})(?:&(?:[^"]*?index=(?P\d+))?(?:[^>]+>(?P[^<]+))?)?' + _VIDEO_RE_TPL = r'href="\s*/watch\?v=%s(?:&(?:[^"]*?index=(?P<index>\d+))?(?:[^>]+>(?P<title>[^<]+))?)?' + _VIDEO_RE = _VIDEO_RE_TPL % r'(?P<id>[0-9A-Za-z_-]{11})' IE_NAME = 'youtube:playlist' _TESTS = [{ 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', @@ -2603,6 +2612,34 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): def _real_initialize(self): self._login() + def extract_videos_from_page(self, page): + ids_in_page = [] + titles_in_page = [] + + for item in re.findall( + r'(<[^>]*\bdata-video-id\s*=\s*["\'][0-9A-Za-z_-]{11}[^>]+>)', page): + attrs = extract_attributes(item) + video_id = attrs['data-video-id'] + video_title = unescapeHTML(attrs.get('data-title')) + if video_title: + video_title = video_title.strip() + ids_in_page.append(video_id) + titles_in_page.append(video_title) + + # Fallback with old _VIDEO_RE + self.extract_videos_from_page_impl( + self._VIDEO_RE, page, ids_in_page, titles_in_page) + + # Relaxed fallbacks + self.extract_videos_from_page_impl( + r'href="\s*/watch\?v\s*=\s*(?P<id>[0-9A-Za-z_-]{11})', page, + ids_in_page, titles_in_page) + self.extract_videos_from_page_impl( + r'data-video-ids\s*=\s*["\'](?P<id>[0-9A-Za-z_-]{11})', page, + ids_in_page, titles_in_page) + + return zip(ids_in_page, titles_in_page) + def _extract_mix(self, playlist_id): # The mixes are generated from a single video # the id of the playlist is just 'RD' + video_id From 69611a1616774011278007b1429e0151481f8879 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 13 Aug 2019 23:10:05 +0700 Subject: [PATCH 005/422] [ChangeLog] Actualize [ci skip] --- ChangeLog | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/ChangeLog b/ChangeLog index 7db147498..8c938ccd5 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,19 @@ +version <unreleased> + +Core +* [downloader/fragment] Fix ETA calculation of resumed download (#21992) +* [YoutubeDL] Check annotations availability (#18582) + +Extractors +* [youtube:playlist] Improve flat extraction (#21927) +* [youtube] Fix annotations extraction (#22045) ++ [discovery] Extract series meta field (#21808) +* [youtube] Improve error detection (#16445) +* [vimeo] Fix album extraction (#1933, #15704, #15855, #18967, #21986) ++ [roosterteeth] Add support for watch URLs +* [discovery] Limit video data by show slug (#21980) + + version 2019.08.02 Extractors From def849e0e61ec7ff0d59557e7950147557138a85 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 13 Aug 2019 23:18:38 +0700 Subject: [PATCH 006/422] release 2019.08.13 --- .github/ISSUE_TEMPLATE/1_broken_site.md | 6 +- .../ISSUE_TEMPLATE/2_site_support_request.md | 4 +- .../ISSUE_TEMPLATE/3_site_feature_request.md | 4 +- .github/ISSUE_TEMPLATE/4_bug_report.md | 6 +- .github/ISSUE_TEMPLATE/5_feature_request.md | 4 +- CONTRIBUTING.md | 66 +++++++++++++++++++ ChangeLog | 2 +- youtube_dl/version.py | 2 +- 8 files changed, 80 insertions(+), 14 deletions(-) diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.md b/.github/ISSUE_TEMPLATE/1_broken_site.md index 4d3894ad3..4c75c8d5d 100644 --- a/.github/ISSUE_TEMPLATE/1_broken_site.md +++ b/.github/ISSUE_TEMPLATE/1_broken_site.md @@ -18,7 +18,7 @@ title: '' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.08.02. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.08.13. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape. - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates. @@ -26,7 +26,7 @@ Carefully read and work through this check list in order to prevent the most com --> - [ ] I'm reporting a broken site support -- [ ] I've verified that I'm running youtube-dl version **2019.08.02** +- [ ] I've verified that I'm running youtube-dl version **2019.08.13** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar issues including closed ones @@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.08.02 + [debug] youtube-dl version 2019.08.13 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/2_site_support_request.md b/.github/ISSUE_TEMPLATE/2_site_support_request.md index 796e11e54..8e8c43c47 100644 --- a/.github/ISSUE_TEMPLATE/2_site_support_request.md +++ b/.github/ISSUE_TEMPLATE/2_site_support_request.md @@ -19,7 +19,7 @@ labels: 'site-support-request' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.08.02. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.08.13. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that site you are requesting is not dedicated to copyright infringement, see https://yt-dl.org/copyright-infringement. youtube-dl does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights. - Search the bugtracker for similar site support requests: http://yt-dl.org/search-issues. DO NOT post duplicates. @@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com --> - [ ] I'm reporting a new site support request -- [ ] I've verified that I'm running youtube-dl version **2019.08.02** +- [ ] I've verified that I'm running youtube-dl version **2019.08.13** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that none of provided URLs violate any copyrights - [ ] I've searched the bugtracker for similar site support requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/3_site_feature_request.md b/.github/ISSUE_TEMPLATE/3_site_feature_request.md index aa2348548..df719a29c 100644 --- a/.github/ISSUE_TEMPLATE/3_site_feature_request.md +++ b/.github/ISSUE_TEMPLATE/3_site_feature_request.md @@ -18,13 +18,13 @@ title: '' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.08.02. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.08.13. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Search the bugtracker for similar site feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates. - Finally, put x into all relevant boxes (like this [x]) --> - [ ] I'm reporting a site feature request -- [ ] I've verified that I'm running youtube-dl version **2019.08.02** +- [ ] I've verified that I'm running youtube-dl version **2019.08.13** - [ ] I've searched the bugtracker for similar site feature requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/4_bug_report.md b/.github/ISSUE_TEMPLATE/4_bug_report.md index 5b2501a65..3616db1a7 100644 --- a/.github/ISSUE_TEMPLATE/4_bug_report.md +++ b/.github/ISSUE_TEMPLATE/4_bug_report.md @@ -18,7 +18,7 @@ title: '' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.08.02. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.08.13. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape. - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates. @@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com --> - [ ] I'm reporting a broken site support issue -- [ ] I've verified that I'm running youtube-dl version **2019.08.02** +- [ ] I've verified that I'm running youtube-dl version **2019.08.13** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar bug reports including closed ones @@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.08.02 + [debug] youtube-dl version 2019.08.13 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/5_feature_request.md b/.github/ISSUE_TEMPLATE/5_feature_request.md index d1758a95c..0fa37aef1 100644 --- a/.github/ISSUE_TEMPLATE/5_feature_request.md +++ b/.github/ISSUE_TEMPLATE/5_feature_request.md @@ -19,13 +19,13 @@ labels: 'request' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.08.02. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.08.13. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Search the bugtracker for similar feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates. - Finally, put x into all relevant boxes (like this [x]) --> - [ ] I'm reporting a feature request -- [ ] I've verified that I'm running youtube-dl version **2019.08.02** +- [ ] I've verified that I'm running youtube-dl version **2019.08.13** - [ ] I've searched the bugtracker for similar feature requests including closed ones diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index cd9ccbe96..ac759ddc4 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -339,6 +339,72 @@ Incorrect: 'PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4' ``` +### Inline values + +Extracting variables is acceptable for reducing code duplication and improving readability of complex expressions. However, you should avoid extracting variables used only once and moving them to opposite parts of the extractor file, which makes reading the linear flow difficult. + +#### Example + +Correct: + +```python +title = self._html_search_regex(r'<title>([^<]+)', webpage, 'title') +``` + +Incorrect: + +```python +TITLE_RE = r'([^<]+)' +# ...some lines of code... +title = self._html_search_regex(TITLE_RE, webpage, 'title') +``` + +### Collapse fallbacks + +Multiple fallback values can quickly become unwieldy. Collapse multiple fallback values into a single expression via a list of patterns. + +#### Example + +Good: + +```python +description = self._html_search_meta( + ['og:description', 'description', 'twitter:description'], + webpage, 'description', default=None) +``` + +Unwieldy: + +```python +description = ( + self._og_search_description(webpage, default=None) + or self._html_search_meta('description', webpage, default=None) + or self._html_search_meta('twitter:description', webpage, default=None)) +``` + +Methods supporting list of patterns are: `_search_regex`, `_html_search_regex`, `_og_search_property`, `_html_search_meta`. + +### Trailing parentheses + +Always move trailing parentheses after the last argument. + +#### Example + +Correct: + +```python + lambda x: x['ResultSet']['Result'][0]['VideoUrlSet']['VideoUrl'], + list) +``` + +Incorrect: + +```python + lambda x: x['ResultSet']['Result'][0]['VideoUrlSet']['VideoUrl'], + list, +) +``` + ### Use convenience conversion and parsing functions Wrap all extracted numeric data into safe functions from [`youtube_dl/utils.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/utils.py): `int_or_none`, `float_or_none`. Use them for string to number conversions as well. diff --git a/ChangeLog b/ChangeLog index 8c938ccd5..9b9e2e149 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version +version 2019.08.13 Core * [downloader/fragment] Fix ETA calculation of resumed download (#21992) diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 0f7fdb23d..b53a08cae 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.08.02' +__version__ = '2019.08.13' From 0326bcb6c1a45067a804d2f32aa854a3fcd9b4ce Mon Sep 17 00:00:00 2001 From: Chuck Cho Date: Thu, 15 Aug 2019 15:14:47 -0700 Subject: [PATCH 007/422] [piksel] add subtitle capability (#20506) --- youtube_dl/extractor/piksel.py | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/piksel.py b/youtube_dl/extractor/piksel.py index c0c276a50..401298cb8 100644 --- a/youtube_dl/extractor/piksel.py +++ b/youtube_dl/extractor/piksel.py @@ -18,15 +18,14 @@ class PikselIE(InfoExtractor): _VALID_URL = r'https?://player\.piksel\.com/v/(?P[a-z0-9]+)' _TESTS = [ { - 'url': 'http://player.piksel.com/v/nv60p12f', - 'md5': 'd9c17bbe9c3386344f9cfd32fad8d235', + 'url': 'http://player.piksel.com/v/ums2867l', + 'md5': '34e34c8d89dc2559976a6079db531e85', 'info_dict': { - 'id': 'nv60p12f', + 'id': 'ums2867l', 'ext': 'mp4', - 'title': 'فن الحياة - الحلقة 1', - 'description': 'احدث برامج الداعية الاسلامي " مصطفي حسني " فى رمضان 2016علي النهار نور', - 'timestamp': 1465231790, - 'upload_date': '20160606', + 'title': 'GX-005 with Caption', + 'timestamp': 1481335659, + 'upload_date': '20161210' } }, { @@ -39,7 +38,7 @@ class PikselIE(InfoExtractor): 'title': 'WAW- State of Washington vs. Donald J. Trump, et al', 'description': 'State of Washington vs. Donald J. Trump, et al, Case Number 17-CV-00141-JLR, TRO Hearing, Civil Rights Case, 02/3/2017, 1:00 PM (PST), Seattle Federal Courthouse, Seattle, WA, Judge James L. Robart presiding.', 'timestamp': 1486171129, - 'upload_date': '20170204', + 'upload_date': '20170204' } } ] @@ -113,6 +112,13 @@ class PikselIE(InfoExtractor): }) self._sort_formats(formats) + subtitles = {} + for caption in video_data.get('captions', []): + caption_url = caption.get('url') + if caption_url: + subtitles.setdefault(caption.get('locale', 'en'), []).append({ + 'url': caption_url}) + return { 'id': video_id, 'title': title, @@ -120,4 +126,5 @@ class PikselIE(InfoExtractor): 'thumbnail': video_data.get('thumbnailUrl'), 'timestamp': parse_iso8601(video_data.get('dateadd')), 'formats': formats, + 'subtitles': subtitles, } From 0add33abcb9eb3ac93f7af312940b033b4ae4168 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 16 Aug 2019 23:36:23 +0700 Subject: [PATCH 008/422] [youtube] Improve unavailable message extraction (refs #22117) --- youtube_dl/extractor/youtube.py | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index b63f19bb0..57d76a5a2 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1809,10 +1809,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor): break def extract_unavailable_message(): - return self._html_search_regex( - (r'(?s)]+id=["\']unavailable-submessage["\'][^>]+>(.+?)]+id=["\']unavailable-message["\'][^>]*>(.+?)'), - video_webpage, 'unavailable message', default=None) + messages = [] + for tag, kind in (('h1', 'message'), ('div', 'submessage')): + msg = self._html_search_regex( + r'(?s)<{tag}[^>]+id=["\']unavailable-{kind}["\'][^>]*>(.+?)'.format(tag=tag, kind=kind), + video_webpage, 'unavailable %s' % kind, default=None) + if msg: + messages.append(msg) + if messages: + return '\n'.join(messages) if not video_info: unavailable_message = extract_unavailable_message() From 393cc31d5eba52018b3de4dd76361d79cb1b5f49 Mon Sep 17 00:00:00 2001 From: supritkumar Date: Tue, 20 Aug 2019 22:52:59 -0400 Subject: [PATCH 009/422] [einthusan] Add support for einthusan.ca (#22171) --- youtube_dl/extractor/einthusan.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/einthusan.py b/youtube_dl/extractor/einthusan.py index 1fb00c9b0..4e0f8bc81 100644 --- a/youtube_dl/extractor/einthusan.py +++ b/youtube_dl/extractor/einthusan.py @@ -19,7 +19,7 @@ from ..utils import ( class EinthusanIE(InfoExtractor): - _VALID_URL = r'https?://(?Peinthusan\.(?:tv|com))/movie/watch/(?P[^/?#&]+)' + _VALID_URL = r'https?://(?Peinthusan\.(?:tv|com|ca))/movie/watch/(?P[^/?#&]+)' _TESTS = [{ 'url': 'https://einthusan.tv/movie/watch/9097/', 'md5': 'ff0f7f2065031b8a2cf13a933731c035', @@ -36,6 +36,9 @@ class EinthusanIE(InfoExtractor): }, { 'url': 'https://einthusan.com/movie/watch/9097/', 'only_matching': True, + }, { + 'url': 'https://einthusan.ca/movie/watch/4E9n/?lang=hindi', + 'only_matching': True, }] # reversed from jsoncrypto.prototype.decrypt() in einthusan-PGMovieWatcher.js From 183a18c4e7dad802404e932f3a7c33fad8db7891 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 26 Aug 2019 03:35:09 +0700 Subject: [PATCH 010/422] [usanetwork] Fix extraction (closes #22105) --- youtube_dl/extractor/usanetwork.py | 28 +++++++++++++--------------- 1 file changed, 13 insertions(+), 15 deletions(-) diff --git a/youtube_dl/extractor/usanetwork.py b/youtube_dl/extractor/usanetwork.py index 823340776..54c7495cc 100644 --- a/youtube_dl/extractor/usanetwork.py +++ b/youtube_dl/extractor/usanetwork.py @@ -1,11 +1,9 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .adobepass import AdobePassIE from ..utils import ( - extract_attributes, + NO_DEFAULT, smuggle_url, update_url_query, ) @@ -31,22 +29,22 @@ class USANetworkIE(AdobePassIE): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) - player_params = extract_attributes(self._search_regex( - r'(]+data-usa-tve-player-container[^>]*>)', webpage, 'player params')) - video_id = player_params['data-mpx-guid'] - title = player_params['data-episode-title'] + def _x(name, default=NO_DEFAULT): + return self._search_regex( + r'data-%s\s*=\s*(["\'])(?P(?:(?!\1).)+)\1' % name, + webpage, name, default=default, group='value') - account_pid, path = re.search( - r'data-src="(?:https?)?//player\.theplatform\.com/p/([^/]+)/.*?/(media/guid/\d+/\d+)', - webpage).groups() + video_id = _x('mpx-guid') + title = _x('episode-title') + mpx_account_id = _x('mpx-account-id', '2304992029') query = { 'mbr': 'true', } - if player_params.get('data-is-full-episode') == '1': + if _x('is-full-episode', None) == '1': query['manifest'] = 'm3u' - if player_params.get('data-entitlement') == 'auth': + if _x('is-entitlement', None) == '1': adobe_pass = {} drupal_settings = self._search_regex( r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);', @@ -57,7 +55,7 @@ class USANetworkIE(AdobePassIE): adobe_pass = drupal_settings.get('adobePass', {}) resource = self._get_mvpd_resource( adobe_pass.get('adobePassResourceId', 'usa'), - title, video_id, player_params.get('data-episode-rating', 'TV-14')) + title, video_id, _x('episode-rating', 'TV-14')) query['auth'] = self._extract_mvpd_auth( url, video_id, adobe_pass.get('adobePassRequestorId', 'usa'), resource) @@ -65,11 +63,11 @@ class USANetworkIE(AdobePassIE): info.update({ '_type': 'url_transparent', 'url': smuggle_url(update_url_query( - 'http://link.theplatform.com/s/%s/%s' % (account_pid, path), + 'http://link.theplatform.com/s/HNK2IC/media/guid/%s/%s' % (mpx_account_id, video_id), query), {'force_smil_url': True}), 'id': video_id, 'title': title, - 'series': player_params.get('data-show-title'), + 'series': _x('show-title', None), 'episode': title, 'ie_key': 'ThePlatform', }) From d1fcf255c5402d75a3f7b450bd1e795196d5817a Mon Sep 17 00:00:00 2001 From: phan-ctrl <54398886+phan-ctrl@users.noreply.github.com> Date: Tue, 27 Aug 2019 10:16:04 +0700 Subject: [PATCH 011/422] [safari] Fix authentication (closes #22161) (#22184) --- youtube_dl/extractor/safari.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/safari.py b/youtube_dl/extractor/safari.py index 8d4806794..bd9ee1647 100644 --- a/youtube_dl/extractor/safari.py +++ b/youtube_dl/extractor/safari.py @@ -68,9 +68,10 @@ class SafariBaseIE(InfoExtractor): raise ExtractorError( 'Unable to login: %s' % credentials, expected=True) - # oreilly serves two same groot_sessionid cookies in Set-Cookie header - # and expects first one to be actually set - self._apply_first_set_cookie_header(urlh, 'groot_sessionid') + # oreilly serves two same instances of the following cookies + # in Set-Cookie header and expects first one to be actually set + for cookie in ('groot_sessionid', 'orm-jwt', 'orm-rt'): + self._apply_first_set_cookie_header(urlh, cookie) _, urlh = self._download_webpage_handle( auth.get('redirect_uri') or next_uri, None, 'Completing login',) From 494d664e679c5b0f85e3c899579e7eb8a1cc8246 Mon Sep 17 00:00:00 2001 From: sofutru <54445344+sofutru@users.noreply.github.com> Date: Wed, 28 Aug 2019 01:39:59 +0700 Subject: [PATCH 012/422] [youtube] Add support for invidious.nixnet.xyz and yt.elukerio.org (#22223) --- youtube_dl/extractor/youtube.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 57d76a5a2..25d056b3c 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -387,8 +387,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): (?:www\.)?invidious\.enkirton\.net/| (?:www\.)?invidious\.13ad\.de/| (?:www\.)?invidious\.mastodon\.host/| + (?:www\.)?invidious\.nixnet\.xyz/| (?:www\.)?tube\.poal\.co/| (?:www\.)?vid\.wxzm\.sx/| + (?:www\.)?yt\.elukerio\.org/| youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains (?:.*?\#/)? # handle anchor (#/) redirect urls (?: # the various things that can precede the ID: From b72305f07892daa287bd51b70dd8eeeed627e7d6 Mon Sep 17 00:00:00 2001 From: Jay Date: Mon, 26 Aug 2019 23:16:18 +0800 Subject: [PATCH 013/422] [bbccouk] Extend _VALID_URL (closes #19200) --- youtube_dl/extractor/bbc.py | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index e76507951..3f820eed2 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -40,6 +40,7 @@ class BBCCoUkIE(InfoExtractor): iplayer(?:/[^/]+)?/(?:episode/|playlist/)| music/(?:clips|audiovideo/popular)[/#]| radio/player/| + sounds/play/| events/[^/]+/play/[^/]+/ ) (?P%s)(?!/(?:episodes|broadcasts|clips)) @@ -220,6 +221,20 @@ class BBCCoUkIE(InfoExtractor): # rtmp download 'skip_download': True, }, + }, { + 'url': 'https://www.bbc.co.uk/sounds/play/m0007jzb', + 'note': 'Audio', + 'info_dict': { + 'id': 'm0007jz9', + 'ext': 'mp4', + 'title': 'BBC Proms, 2019, Prom 34: West–Eastern Divan Orchestra', + 'description': "Live BBC Proms. West–Eastern Divan Orchestra with Daniel Barenboim and Martha Argerich.", + 'duration': 9840, + }, + 'params': { + # rtmp download + 'skip_download': True, + } }, { 'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4', 'only_matching': True, From acc86c9a978a916fed1d1ed9ecf201d2c1a3060c Mon Sep 17 00:00:00 2001 From: Jay Date: Mon, 26 Aug 2019 23:04:38 +0800 Subject: [PATCH 014/422] [bbc] Fix some tests --- youtube_dl/extractor/bbc.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index 3f820eed2..901c5a54f 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -71,7 +71,7 @@ class BBCCoUkIE(InfoExtractor): 'info_dict': { 'id': 'b039d07m', 'ext': 'flv', - 'title': 'Leonard Cohen, Kaleidoscope - BBC Radio 4', + 'title': 'Kaleidoscope, Leonard Cohen', 'description': 'The Canadian poet and songwriter reflects on his musical career.', }, 'params': { @@ -624,7 +624,7 @@ class BBCIE(BBCCoUkIE): 'url': 'http://www.bbc.com/news/world-europe-32668511', 'info_dict': { 'id': 'world-europe-32668511', - 'title': 'Russia stages massive WW2 parade despite Western boycott', + 'title': 'Russia stages massive WW2 parade', 'description': 'md5:00ff61976f6081841f759a08bf78cc9c', }, 'playlist_count': 2, From b500955a58efb019133b3214ea81635342728f1f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 28 Aug 2019 01:58:07 +0700 Subject: [PATCH 015/422] [openload] Add support for oload.vip (closes #22205) --- youtube_dl/extractor/openload.py | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index 030355257..ab4980d4d 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -243,7 +243,12 @@ class PhantomJSwrapper(object): class OpenloadIE(InfoExtractor): - _DOMAINS = r'(?:openload\.(?:co|io|link|pw)|oload\.(?:tv|best|biz|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|press|pw|life|live|space|services|website)|oladblock\.(?:services|xyz|me)|openloed\.co)' + _DOMAINS = r'''(?x) + (?: + openload\.(?:co|io|link|pw)| + oload\.(?:tv|best|biz|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|press|pw|life|live|space|services|website|vip)| + oladblock\.(?:services|xyz|me)|openloed\.co) + ''' _VALID_URL = r'''(?x) https?:// (?P @@ -383,6 +388,9 @@ class OpenloadIE(InfoExtractor): }, { 'url': 'https://openloed.co/f/b8NWEgkqNLI/', 'only_matching': True, + }, { + 'url': 'https://oload.vip/f/kUEfGclsU9o', + 'only_matching': True, }] @classmethod From 9d058b3206e431f19c955f9df3eaad34e7446f27 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 29 Aug 2019 23:08:19 +0700 Subject: [PATCH 016/422] [dailymotion] Add support for lequipe.fr (closes #21328, closes #22152) --- youtube_dl/extractor/dailymotion.py | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 3d3d78041..745971900 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -48,7 +48,14 @@ class DailymotionBaseInfoExtractor(InfoExtractor): class DailymotionIE(DailymotionBaseInfoExtractor): - _VALID_URL = r'(?i)https?://(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(?:(?:embed|swf|#)/)?video|swf)/(?P[^/?_]+)' + _VALID_URL = r'''(?ix) + https?:// + (?: + (?:(?:www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(?:(?:embed|swf|\#)/)?video|swf)| + (?:www\.)?lequipe\.fr/video + ) + /(?P[^/?_]+) + ''' IE_NAME = 'dailymotion' _FORMATS = [ @@ -133,6 +140,12 @@ class DailymotionIE(DailymotionBaseInfoExtractor): }, { 'url': 'http://www.dailymotion.com/swf/x3ss1m_funny-magic-trick-barry-and-stuart_fun', 'only_matching': True, + }, { + 'url': 'https://www.lequipe.fr/video/x791mem', + 'only_matching': True, + }, { + 'url': 'https://www.lequipe.fr/video/k7MtHciueyTcrFtFKA2', + 'only_matching': True, }] @staticmethod From 3f46a25a971b6c1e56747cc4813c1ccdfb18aaa2 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sat, 31 Aug 2019 10:02:09 +0100 Subject: [PATCH 017/422] [verystream] add support for woof.tube (closes #22217) --- youtube_dl/extractor/openload.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index ab4980d4d..b638450af 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -462,7 +462,7 @@ class OpenloadIE(InfoExtractor): class VerystreamIE(OpenloadIE): IE_NAME = 'verystream' - _DOMAINS = r'(?:verystream\.com)' + _DOMAINS = r'(?:verystream\.com|woof\.tube)' _VALID_URL = r'''(?x) https?:// (?P From 71f47617c8845900c1a3c2da79f9f7654199fedb Mon Sep 17 00:00:00 2001 From: telephono Date: Sat, 31 Aug 2019 19:24:43 +0200 Subject: [PATCH 018/422] [downloader/external] Respect mtime option for aria2c (#22242) --- youtube_dl/downloader/external.py | 1 + 1 file changed, 1 insertion(+) diff --git a/youtube_dl/downloader/external.py b/youtube_dl/downloader/external.py index acdb27712..c31f8910a 100644 --- a/youtube_dl/downloader/external.py +++ b/youtube_dl/downloader/external.py @@ -194,6 +194,7 @@ class Aria2cFD(ExternalFD): cmd += self._option('--interface', 'source_address') cmd += self._option('--all-proxy', 'proxy') cmd += self._bool_option('--check-certificate', 'nocheckcertificate', 'false', 'true', '=') + cmd += self._bool_option('--remote-time', 'updatetime', 'true', 'false', '=') cmd += ['--', info_dict['url']] return cmd From cc73d5ad15aed96f6462b8079ccb6716c2ef9f85 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 1 Sep 2019 01:18:25 +0700 Subject: [PATCH 019/422] [openload] Fix domains regex --- youtube_dl/extractor/openload.py | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index b638450af..679eaf6c3 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -243,12 +243,13 @@ class PhantomJSwrapper(object): class OpenloadIE(InfoExtractor): - _DOMAINS = r'''(?x) + _DOMAINS = r''' (?: openload\.(?:co|io|link|pw)| oload\.(?:tv|best|biz|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|press|pw|life|live|space|services|website|vip)| - oladblock\.(?:services|xyz|me)|openloed\.co) - ''' + oladblock\.(?:services|xyz|me)|openloed\.co + ) + ''' _VALID_URL = r'''(?x) https?:// (?P @@ -396,7 +397,7 @@ class OpenloadIE(InfoExtractor): @classmethod def _extract_urls(cls, webpage): return re.findall( - r']+src=["\']((?:https?://)?%s/%s/[a-zA-Z0-9-_]+)' + r'(?x)]+src=["\']((?:https?://)?%s/%s/[a-zA-Z0-9-_]+)' % (cls._DOMAINS, cls._EMBED_WORD), webpage) def _extract_decrypted_page(self, page_url, webpage, video_id): From d78657fd18ae6413239137298eee4c54f3efee32 Mon Sep 17 00:00:00 2001 From: Barbara Miller Date: Mon, 22 Jul 2019 14:09:21 -0700 Subject: [PATCH 020/422] [extractor/generic] Add support for squarespace embeds (closes #21294) --- youtube_dl/extractor/generic.py | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index d34fc4b15..7dd2e2d5f 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -2075,6 +2075,17 @@ class GenericIE(InfoExtractor): }, 'playlist_count': 6, }, + { + # Squarespace video embed, 2019-08-28 + 'url': 'http://ootboxford.com', + 'info_dict': { + 'id': 'Tc7b_JGdZfw', + 'title': 'Out of the Blue, at Childish Things 10', + }, + 'params': { + 'skip_download': True, + }, + }, { # Zype embed 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites', @@ -2395,6 +2406,13 @@ class GenericIE(InfoExtractor): # Unescaping the whole page allows to handle those cases in a generic way webpage = compat_urllib_parse_unquote(webpage) + # unescape re.sub replacement + def unescape_resub(m): + return unescapeHTML(m.group(0)) + + # unescape squarespace video embeds + webpage = re.sub(r']+class=[^>]*?sqs-video-wrapper[^>]*>', unescape_resub, webpage) + # it's tempting to parse this further, but you would # have to take into account all the variations like # Video Title - Site Name From 7cb51b5daf07a6a627a9084394636c570194cc4e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 1 Sep 2019 01:23:58 +0700 Subject: [PATCH 021/422] [extractor/generic] Improve squarespace detection and fix test (closes #21859, refs #21294, refs #21802) --- youtube_dl/extractor/generic.py | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 7dd2e2d5f..d1725d98b 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -2081,6 +2081,11 @@ class GenericIE(InfoExtractor): 'info_dict': { 'id': 'Tc7b_JGdZfw', 'title': 'Out of the Blue, at Childish Things 10', + 'ext': 'mp4', + 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f', + 'uploader_id': 'helendouglashouse', + 'uploader': 'Helen & Douglas House', + 'upload_date': '20140328', }, 'params': { 'skip_download': True, @@ -2406,12 +2411,11 @@ class GenericIE(InfoExtractor): # Unescaping the whole page allows to handle those cases in a generic way webpage = compat_urllib_parse_unquote(webpage) - # unescape re.sub replacement - def unescape_resub(m): - return unescapeHTML(m.group(0)) - - # unescape squarespace video embeds - webpage = re.sub(r']+class=[^>]*?sqs-video-wrapper[^>]*>', unescape_resub, webpage) + # Unescape squarespace embeds to be detected by generic extractor, + # see https://github.com/ytdl-org/youtube-dl/issues/21294 + webpage = re.sub( + r']+class=[^>]*?\bsqs-video-wrapper\b[^>]*>', + lambda x: unescapeHTML(x.group(0)), webpage) # it's tempting to parse this further, but you would # have to take into account all the variations like From 8945b10f6e10337db0c9bf7a70758c8ecbb6c830 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 1 Sep 2019 02:59:40 +0700 Subject: [PATCH 022/422] [xhamster] Add support for more domains --- youtube_dl/extractor/xhamster.py | 35 ++++++++++++++++++++------------ 1 file changed, 22 insertions(+), 13 deletions(-) diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index d268372e6..4297dffee 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -18,21 +18,21 @@ from ..utils import ( class XHamsterIE(InfoExtractor): + _DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster[27]\.com)' _VALID_URL = r'''(?x) https?:// - (?:.+?\.)?xhamster\.(?:com|one)/ + (?:.+?\.)?%s/ (?: movies/(?P\d+)/(?P[^/]*)\.html| videos/(?P[^/]*)-(?P\d+) ) - ''' - + ''' % _DOMAINS _TESTS = [{ - 'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html', - 'md5': '8281348b8d3c53d39fffb377d24eac4e', + 'url': 'https://xhamster.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445', + 'md5': '98b4687efb1ffd331c4197854dc09e8f', 'info_dict': { 'id': '1509445', - 'display_id': 'femaleagent_shy_beauty_takes_the_bait', + 'display_id': 'femaleagent-shy-beauty-takes-the-bait', 'ext': 'mp4', 'title': 'FemaleAgent Shy beauty takes the bait', 'timestamp': 1350194821, @@ -40,13 +40,12 @@ class XHamsterIE(InfoExtractor): 'uploader': 'Ruseful2011', 'duration': 893, 'age_limit': 18, - 'categories': ['Fake Hub', 'Amateur', 'MILFs', 'POV', 'Beauti', 'Beauties', 'Beautiful', 'Boss', 'Office', 'Oral', 'Reality', 'Sexy', 'Taking'], }, }, { - 'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd', + 'url': 'https://xhamster.com/videos/britney-spears-sexy-booty-2221348?hd=', 'info_dict': { 'id': '2221348', - 'display_id': 'britney_spears_sexy_booty', + 'display_id': 'britney-spears-sexy-booty', 'ext': 'mp4', 'title': 'Britney Spears Sexy Booty', 'timestamp': 1379123460, @@ -54,13 +53,12 @@ class XHamsterIE(InfoExtractor): 'uploader': 'jojo747400', 'duration': 200, 'age_limit': 18, - 'categories': ['Britney Spears', 'Celebrities', 'HD Videos', 'Sexy', 'Sexy Booty'], }, 'params': { 'skip_download': True, }, }, { - # empty seo + # empty seo, unavailable via new URL schema 'url': 'http://xhamster.com/movies/5667973/.html', 'info_dict': { 'id': '5667973', @@ -71,7 +69,6 @@ class XHamsterIE(InfoExtractor): 'uploader': 'parejafree', 'duration': 72, 'age_limit': 18, - 'categories': ['Amateur', 'Blowjobs'], }, 'params': { 'skip_download': True, @@ -94,6 +91,18 @@ class XHamsterIE(InfoExtractor): }, { 'url': 'https://xhamster.one/videos/femaleagent-shy-beauty-takes-the-bait-1509445', 'only_matching': True, + }, { + 'url': 'https://xhamster.desi/videos/femaleagent-shy-beauty-takes-the-bait-1509445', + 'only_matching': True, + }, { + 'url': 'https://xhamster2.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445', + 'only_matching': True, + }, { + 'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html', + 'only_matching': True, + }, { + 'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd', + 'only_matching': True, }] def _real_extract(self, url): @@ -285,7 +294,7 @@ class XHamsterIE(InfoExtractor): class XHamsterEmbedIE(InfoExtractor): - _VALID_URL = r'https?://(?:.+?\.)?xhamster\.com/xembed\.php\?video=(?P\d+)' + _VALID_URL = r'https?://(?:.+?\.)?%s/xembed\.php\?video=(?P\d+)' % XHamsterIE._DOMAINS _TEST = { 'url': 'http://xhamster.com/xembed.php?video=3328539', 'info_dict': { From df228355fd752400ada21d9e202c96932b3ac6e5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 1 Sep 2019 03:12:56 +0700 Subject: [PATCH 023/422] [xhamster:user] Add extractor (closes #16330, closes #18454) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/xhamster.py | 48 ++++++++++++++++++++++++++++++ 2 files changed, 49 insertions(+) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 06de556b7..4adcae1e5 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1425,6 +1425,7 @@ from .xfileshare import XFileShareIE from .xhamster import ( XHamsterIE, XHamsterEmbedIE, + XHamsterUserIE, ) from .xiami import ( XiamiSongIE, diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index 4297dffee..a5b94d279 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -1,5 +1,6 @@ from __future__ import unicode_literals +import itertools import re from .common import InfoExtractor @@ -8,6 +9,7 @@ from ..utils import ( clean_html, determine_ext, dict_get, + extract_attributes, ExtractorError, int_or_none, parse_duration, @@ -331,3 +333,49 @@ class XHamsterEmbedIE(InfoExtractor): video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl')) return self.url_result(video_url, 'XHamster') + + +class XHamsterUserIE(InfoExtractor): + _VALID_URL = r'https?://(?:.+?\.)?%s/users/(?P[^/?#&]+)' % XHamsterIE._DOMAINS + _TESTS = [{ + # Paginated user profile + 'url': 'https://xhamster.com/users/netvideogirls/videos', + 'info_dict': { + 'id': 'netvideogirls', + }, + 'playlist_mincount': 267, + }, { + # Non-paginated user profile + 'url': 'https://xhamster.com/users/firatkaan/videos', + 'info_dict': { + 'id': 'firatkaan', + }, + 'playlist_mincount': 1, + }] + + def _entries(self, user_id): + next_page_url = 'https://xhamster.com/users/%s/videos/1' % user_id + for pagenum in itertools.count(1): + page = self._download_webpage( + next_page_url, user_id, 'Downloading page %s' % pagenum) + for video_tag in re.findall( + r'(]+class=["\'].*?\bvideo-thumb__image-container[^>]+>)', + page): + video = extract_attributes(video_tag) + video_url = url_or_none(video.get('href')) + if not video_url or not XHamsterIE.suitable(video_url): + continue + video_id = XHamsterIE._match_id(video_url) + yield self.url_result( + video_url, ie=XHamsterIE.ie_key(), video_id=video_id) + mobj = re.search(r']+data-page=["\']next[^>]+>', page) + if not mobj: + break + next_page = extract_attributes(mobj.group(0)) + next_page_url = url_or_none(next_page.get('href')) + if not next_page_url: + break + + def _real_extract(self, url): + user_id = self._match_id(url) + return self.playlist_result(self._entries(user_id), user_id) From 79dd8884bb83ae7244f11c928fd9af6abf1f97f9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 1 Sep 2019 03:18:35 +0700 Subject: [PATCH 024/422] [ChangeLog] Actualize [ci skip] --- ChangeLog | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/ChangeLog b/ChangeLog index 9b9e2e149..d4d8fc980 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,25 @@ +version + +Core ++ [extractor/generic] Add support for squarespace embeds (#21294, #21802, + #21859) ++ [downloader/external] Respect mtime option for aria2c (#22242) + +Extractors ++ [xhamster:user] Add support for user pages (#16330, #18454) ++ [xhamster] Add support for more domains ++ [verystream] Add support for woof.tube (#22217) ++ [dailymotion] Add support for lequipe.fr (#21328, #22152) ++ [openload] Add support for oload.vip (#22205) ++ [bbccouk] Extend URL regular expression (#19200) ++ [youtube] Add support for invidious.nixnet.xyz and yt.elukerio.org (#22223) +* [safari] Fix authentication (#22161, #22184) +* [usanetwork] Fix extraction (#22105) ++ [einthusan] Add support for einthusan.ca (#22171) +* [youtube] Improve unavailable message extraction (#22117) ++ [piksel] Extract subtitles (#20506) + + version 2019.08.13 Core From f620d0d860c34cd34e421247ed637a9d03f730ba Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 1 Sep 2019 03:33:02 +0700 Subject: [PATCH 025/422] release 2019.09.01 --- .github/ISSUE_TEMPLATE/1_broken_site.md | 6 +++--- .github/ISSUE_TEMPLATE/2_site_support_request.md | 4 ++-- .github/ISSUE_TEMPLATE/3_site_feature_request.md | 4 ++-- .github/ISSUE_TEMPLATE/4_bug_report.md | 6 +++--- .github/ISSUE_TEMPLATE/5_feature_request.md | 4 ++-- ChangeLog | 2 +- docs/supportedsites.md | 1 + youtube_dl/version.py | 2 +- 8 files changed, 15 insertions(+), 14 deletions(-) diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.md b/.github/ISSUE_TEMPLATE/1_broken_site.md index 4c75c8d5d..52c5c1c32 100644 --- a/.github/ISSUE_TEMPLATE/1_broken_site.md +++ b/.github/ISSUE_TEMPLATE/1_broken_site.md @@ -18,7 +18,7 @@ title: '' - [ ] I'm reporting a broken site support -- [ ] I've verified that I'm running youtube-dl version **2019.08.13** +- [ ] I've verified that I'm running youtube-dl version **2019.09.01** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar issues including closed ones @@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.08.13 + [debug] youtube-dl version 2019.09.01 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/2_site_support_request.md b/.github/ISSUE_TEMPLATE/2_site_support_request.md index 8e8c43c47..000d2f55a 100644 --- a/.github/ISSUE_TEMPLATE/2_site_support_request.md +++ b/.github/ISSUE_TEMPLATE/2_site_support_request.md @@ -19,7 +19,7 @@ labels: 'site-support-request' - [ ] I'm reporting a new site support request -- [ ] I've verified that I'm running youtube-dl version **2019.08.13** +- [ ] I've verified that I'm running youtube-dl version **2019.09.01** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that none of provided URLs violate any copyrights - [ ] I've searched the bugtracker for similar site support requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/3_site_feature_request.md b/.github/ISSUE_TEMPLATE/3_site_feature_request.md index df719a29c..77b710606 100644 --- a/.github/ISSUE_TEMPLATE/3_site_feature_request.md +++ b/.github/ISSUE_TEMPLATE/3_site_feature_request.md @@ -18,13 +18,13 @@ title: '' - [ ] I'm reporting a site feature request -- [ ] I've verified that I'm running youtube-dl version **2019.08.13** +- [ ] I've verified that I'm running youtube-dl version **2019.09.01** - [ ] I've searched the bugtracker for similar site feature requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/4_bug_report.md b/.github/ISSUE_TEMPLATE/4_bug_report.md index 3616db1a7..ae112d965 100644 --- a/.github/ISSUE_TEMPLATE/4_bug_report.md +++ b/.github/ISSUE_TEMPLATE/4_bug_report.md @@ -18,7 +18,7 @@ title: '' - [ ] I'm reporting a broken site support issue -- [ ] I've verified that I'm running youtube-dl version **2019.08.13** +- [ ] I've verified that I'm running youtube-dl version **2019.09.01** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar bug reports including closed ones @@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.08.13 + [debug] youtube-dl version 2019.09.01 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/5_feature_request.md b/.github/ISSUE_TEMPLATE/5_feature_request.md index 0fa37aef1..fccfdf71a 100644 --- a/.github/ISSUE_TEMPLATE/5_feature_request.md +++ b/.github/ISSUE_TEMPLATE/5_feature_request.md @@ -19,13 +19,13 @@ labels: 'request' - [ ] I'm reporting a feature request -- [ ] I've verified that I'm running youtube-dl version **2019.08.13** +- [ ] I've verified that I'm running youtube-dl version **2019.09.01** - [ ] I've searched the bugtracker for similar feature requests including closed ones diff --git a/ChangeLog b/ChangeLog index d4d8fc980..e91e49854 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version +version 2019.09.01 Core + [extractor/generic] Add support for squarespace embeds (#21294, #21802, diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 7cf60eefe..18bddc138 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -1100,6 +1100,7 @@ - **XFileShare**: XFileShare based sites: DaClips, FileHoot, GorillaVid, MovPod, PowerWatch, Rapidvideo.ws, TheVideoBee, Vidto, Streamin.To, XVIDSTAGE, Vid ABC, VidBom, vidlo, RapidVideo.TV, FastVideo.me - **XHamster** - **XHamsterEmbed** + - **XHamsterUser** - **xiami:album**: 虾米音乐 - 专辑 - **xiami:artist**: 虾米音乐 - 歌手 - **xiami:collection**: 虾米音乐 - 精选集 diff --git a/youtube_dl/version.py b/youtube_dl/version.py index b53a08cae..98fa32286 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.08.13' +__version__ = '2019.09.01' From d7da1e37c72d931f7bdce9121a38e85bdadb9dc1 Mon Sep 17 00:00:00 2001 From: Patrick Dessalle Date: Sun, 1 Sep 2019 19:59:57 +0200 Subject: [PATCH 026/422] [nickjr] Add support for nickelodeonjunior.fr (#22246) --- youtube_dl/extractor/nick.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/nick.py b/youtube_dl/extractor/nick.py index 5e34d776b..2e8b302ac 100644 --- a/youtube_dl/extractor/nick.py +++ b/youtube_dl/extractor/nick.py @@ -85,7 +85,8 @@ class NickBrIE(MTVServicesInfoExtractor): https?:// (?: (?P(?:www\.)?nickjr|mundonick\.uol)\.com\.br| - (?:www\.)?nickjr\.[a-z]{2} + (?:www\.)?nickjr\.[a-z]{2}| + (?:www\.)?nickelodeonjunior\.fr ) /(?:programas/)?[^/]+/videos/(?:episodios/)?(?P[^/?\#.]+) ''' @@ -101,6 +102,9 @@ class NickBrIE(MTVServicesInfoExtractor): }, { 'url': 'http://www.nickjr.de/blaze-und-die-monster-maschinen/videos/f6caaf8f-e4e8-4cc1-b489-9380d6dcd059/', 'only_matching': True, + }, { + 'url': 'http://www.nickelodeonjunior.fr/paw-patrol-la-pat-patrouille/videos/episode-401-entier-paw-patrol/', + 'only_matching': True, }] def _real_extract(self, url): From 66d04c74e097c03e4d644d7292546884cbee3d2b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 3 Sep 2019 01:23:22 +0700 Subject: [PATCH 027/422] [platzi:course] Add support for authentication --- youtube_dl/extractor/platzi.py | 73 ++++++++++++++++++---------------- 1 file changed, 38 insertions(+), 35 deletions(-) diff --git a/youtube_dl/extractor/platzi.py b/youtube_dl/extractor/platzi.py index 557b2b5ad..cd6b966c5 100644 --- a/youtube_dl/extractor/platzi.py +++ b/youtube_dl/extractor/platzi.py @@ -18,43 +18,10 @@ from ..utils import ( ) -class PlatziIE(InfoExtractor): - _VALID_URL = r'''(?x) - https?:// - (?: - platzi\.com/clases| # es version - courses\.platzi\.com/classes # en version - )/[^/]+/(?P\d+)-[^/?\#&]+ - ''' +class PlatziBaseIE(InfoExtractor): _LOGIN_URL = 'https://platzi.com/login/' _NETRC_MACHINE = 'platzi' - _TESTS = [{ - 'url': 'https://platzi.com/clases/1311-next-js/12074-creando-nuestra-primera-pagina/', - 'md5': '8f56448241005b561c10f11a595b37e3', - 'info_dict': { - 'id': '12074', - 'ext': 'mp4', - 'title': 'Creando nuestra primera página', - 'description': 'md5:4c866e45034fc76412fbf6e60ae008bc', - 'duration': 420, - }, - 'skip': 'Requires platzi account credentials', - }, { - 'url': 'https://courses.platzi.com/classes/1367-communication-codestream/13430-background/', - 'info_dict': { - 'id': '13430', - 'ext': 'mp4', - 'title': 'Background', - 'description': 'md5:49c83c09404b15e6e71defaf87f6b305', - 'duration': 360, - }, - 'skip': 'Requires platzi account credentials', - 'params': { - 'skip_download': True, - }, - }] - def _real_initialize(self): self._login() @@ -97,6 +64,42 @@ class PlatziIE(InfoExtractor): 'Unable to login: %s' % error, expected=True) raise ExtractorError('Unable to log in') + +class PlatziIE(PlatziBaseIE): + _VALID_URL = r'''(?x) + https?:// + (?: + platzi\.com/clases| # es version + courses\.platzi\.com/classes # en version + )/[^/]+/(?P\d+)-[^/?\#&]+ + ''' + + _TESTS = [{ + 'url': 'https://platzi.com/clases/1311-next-js/12074-creando-nuestra-primera-pagina/', + 'md5': '8f56448241005b561c10f11a595b37e3', + 'info_dict': { + 'id': '12074', + 'ext': 'mp4', + 'title': 'Creando nuestra primera página', + 'description': 'md5:4c866e45034fc76412fbf6e60ae008bc', + 'duration': 420, + }, + 'skip': 'Requires platzi account credentials', + }, { + 'url': 'https://courses.platzi.com/classes/1367-communication-codestream/13430-background/', + 'info_dict': { + 'id': '13430', + 'ext': 'mp4', + 'title': 'Background', + 'description': 'md5:49c83c09404b15e6e71defaf87f6b305', + 'duration': 360, + }, + 'skip': 'Requires platzi account credentials', + 'params': { + 'skip_download': True, + }, + }] + def _real_extract(self, url): lecture_id = self._match_id(url) @@ -146,7 +149,7 @@ class PlatziIE(InfoExtractor): } -class PlatziCourseIE(InfoExtractor): +class PlatziCourseIE(PlatziBaseIE): _VALID_URL = r'''(?x) https?:// (?: From 31dbd054c801ec14c1ea29a2167b70c980f1d782 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 3 Sep 2019 01:24:20 +0700 Subject: [PATCH 028/422] [platzi] Improve client data extraction (closes #22290) --- youtube_dl/extractor/platzi.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/platzi.py b/youtube_dl/extractor/platzi.py index cd6b966c5..602207beb 100644 --- a/youtube_dl/extractor/platzi.py +++ b/youtube_dl/extractor/platzi.py @@ -107,7 +107,11 @@ class PlatziIE(PlatziBaseIE): data = self._parse_json( self._search_regex( - r'client_data\s*=\s*({.+?})\s*;', webpage, 'client data'), + # client_data may contain "};" so that we have to try more + # strict regex first + (r'client_data\s*=\s*({.+?})\s*;\s*\n', + r'client_data\s*=\s*({.+?})\s*;'), + webpage, 'client data'), lecture_id) material = data['initialState']['material'] From bff90fc518d6ccadaafc26407a688dc1bbd32dff Mon Sep 17 00:00:00 2001 From: sofutru <54445344+sofutru@users.noreply.github.com> Date: Tue, 3 Sep 2019 01:35:32 +0700 Subject: [PATCH 029/422] [youtube] Add support for invidious tor instances (#22268) --- youtube_dl/extractor/youtube.py | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 25d056b3c..abafd5157 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -391,6 +391,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor): (?:www\.)?tube\.poal\.co/| (?:www\.)?vid\.wxzm\.sx/| (?:www\.)?yt\.elukerio\.org/| + (?:www\.)?kgg2m7yk5aybusll\.onion/| + (?:www\.)?qklhadlycap4cnod\.onion/| + (?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion/| + (?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion/| + (?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion/| + (?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion/| youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains (?:.*?\#/)? # handle anchor (#/) redirect urls (?: # the various things that can precede the ID: From bf1317d257d13188601c837c983830355c6203e5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 11 Sep 2019 22:44:47 +0700 Subject: [PATCH 030/422] [youtube] Quick extraction tempfix (closes #22367, closes #22163) --- youtube_dl/extractor/youtube.py | 184 ++++++++++++++++++-------------- 1 file changed, 106 insertions(+), 78 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index abafd5157..9d0058b2a 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1915,6 +1915,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor): return int_or_none(self._search_regex( r'\bclen[=/](\d+)', media_url, 'filesize', default=None)) + streaming_formats = try_get(player_response, lambda x: x['streamingData']['formats'], list) or [] + streaming_formats.extend(try_get(player_response, lambda x: x['streamingData']['adaptiveFormats'], list) or []) + if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): self.report_rtmp_download() formats = [{ @@ -1923,10 +1926,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'url': video_info['conn'][0], 'player_url': player_url, }] - elif not is_live and (len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1): + elif not is_live and (streaming_formats or len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1): encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0] if 'rtmpe%3Dyes' in encoded_url_map: raise ExtractorError('rtmpe downloads are not supported, see https://github.com/ytdl-org/youtube-dl/issues/343 for more information.', expected=True) + formats = [] formats_spec = {} fmt_list = video_info.get('fmt_list', [''])[0] if fmt_list: @@ -1941,90 +1945,105 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'height': int_or_none(width_height[1]), } q = qualities(['small', 'medium', 'hd720']) - streaming_formats = try_get(player_response, lambda x: x['streamingData']['formats'], list) - if streaming_formats: - for fmt in streaming_formats: - itag = str_or_none(fmt.get('itag')) - if not itag: - continue - quality = fmt.get('quality') - quality_label = fmt.get('qualityLabel') or quality - formats_spec[itag] = { - 'asr': int_or_none(fmt.get('audioSampleRate')), - 'filesize': int_or_none(fmt.get('contentLength')), - 'format_note': quality_label, - 'fps': int_or_none(fmt.get('fps')), - 'height': int_or_none(fmt.get('height')), - 'quality': q(quality), - # bitrate for itag 43 is always 2147483647 - 'tbr': float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) if itag != '43' else None, - 'width': int_or_none(fmt.get('width')), - } - formats = [] - for url_data_str in encoded_url_map.split(','): - url_data = compat_parse_qs(url_data_str) - if 'itag' not in url_data or 'url' not in url_data or url_data.get('drm_families'): + for fmt in streaming_formats: + itag = str_or_none(fmt.get('itag')) + if not itag: continue + quality = fmt.get('quality') + quality_label = fmt.get('qualityLabel') or quality + formats_spec[itag] = { + 'asr': int_or_none(fmt.get('audioSampleRate')), + 'filesize': int_or_none(fmt.get('contentLength')), + 'format_note': quality_label, + 'fps': int_or_none(fmt.get('fps')), + 'height': int_or_none(fmt.get('height')), + 'quality': q(quality), + # bitrate for itag 43 is always 2147483647 + 'tbr': float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) if itag != '43' else None, + 'width': int_or_none(fmt.get('width')), + } + + for fmt in streaming_formats: + if fmt.get('drm_families'): + continue + url = url_or_none(fmt.get('url')) + + if not url: + cipher = fmt.get('cipher') + if not cipher: + continue + url_data = compat_parse_qs(cipher) + url = url_or_none(try_get(url_data, lambda x: x['url'][0], compat_str)) + if not url: + continue + else: + cipher = None + url_data = compat_parse_qs(compat_urllib_parse_urlparse(url).query) + stream_type = int_or_none(try_get(url_data, lambda x: x['stream_type'][0])) # Unsupported FORMAT_STREAM_TYPE_OTF if stream_type == 3: continue - format_id = url_data['itag'][0] - url = url_data['url'][0] - if 's' in url_data or self._downloader.params.get('youtube_include_dash_manifest', True): - ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")' - jsplayer_url_json = self._search_regex( - ASSETS_RE, - embed_webpage if age_gate else video_webpage, - 'JS player URL (1)', default=None) - if not jsplayer_url_json and not age_gate: - # We need the embed website after all - if embed_webpage is None: - embed_url = proto + '://www.youtube.com/embed/%s' % video_id - embed_webpage = self._download_webpage( - embed_url, video_id, 'Downloading embed webpage') + format_id = fmt.get('itag') or url_data['itag'][0] + if not format_id: + continue + format_id = compat_str(format_id) + + if cipher: + if 's' in url_data or self._downloader.params.get('youtube_include_dash_manifest', True): + ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")' jsplayer_url_json = self._search_regex( - ASSETS_RE, embed_webpage, 'JS player URL') + ASSETS_RE, + embed_webpage if age_gate else video_webpage, + 'JS player URL (1)', default=None) + if not jsplayer_url_json and not age_gate: + # We need the embed website after all + if embed_webpage is None: + embed_url = proto + '://www.youtube.com/embed/%s' % video_id + embed_webpage = self._download_webpage( + embed_url, video_id, 'Downloading embed webpage') + jsplayer_url_json = self._search_regex( + ASSETS_RE, embed_webpage, 'JS player URL') - player_url = json.loads(jsplayer_url_json) - if player_url is None: - player_url_json = self._search_regex( - r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")', - video_webpage, 'age gate player URL') - player_url = json.loads(player_url_json) - - if 'sig' in url_data: - url += '&signature=' + url_data['sig'][0] - elif 's' in url_data: - encrypted_sig = url_data['s'][0] - - if self._downloader.params.get('verbose'): + player_url = json.loads(jsplayer_url_json) if player_url is None: - player_version = 'unknown' - player_desc = 'unknown' - else: - if player_url.endswith('swf'): - player_version = self._search_regex( - r'-(.+?)(?:/watch_as3)?\.swf$', player_url, - 'flash player', fatal=False) - player_desc = 'flash player %s' % player_version + player_url_json = self._search_regex( + r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")', + video_webpage, 'age gate player URL') + player_url = json.loads(player_url_json) + + if 'sig' in url_data: + url += '&signature=' + url_data['sig'][0] + elif 's' in url_data: + encrypted_sig = url_data['s'][0] + + if self._downloader.params.get('verbose'): + if player_url is None: + player_version = 'unknown' + player_desc = 'unknown' else: - player_version = self._search_regex( - [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', - r'(?:www|player(?:_ias)?)-([^/]+)(?:/[a-z]{2,3}_[A-Z]{2})?/base\.js'], - player_url, - 'html5 player', fatal=False) - player_desc = 'html5 player %s' % player_version + if player_url.endswith('swf'): + player_version = self._search_regex( + r'-(.+?)(?:/watch_as3)?\.swf$', player_url, + 'flash player', fatal=False) + player_desc = 'flash player %s' % player_version + else: + player_version = self._search_regex( + [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', + r'(?:www|player(?:_ias)?)-([^/]+)(?:/[a-z]{2,3}_[A-Z]{2})?/base\.js'], + player_url, + 'html5 player', fatal=False) + player_desc = 'html5 player %s' % player_version - parts_sizes = self._signature_cache_id(encrypted_sig) - self.to_screen('{%s} signature length %s, %s' % - (format_id, parts_sizes, player_desc)) + parts_sizes = self._signature_cache_id(encrypted_sig) + self.to_screen('{%s} signature length %s, %s' % + (format_id, parts_sizes, player_desc)) - signature = self._decrypt_signature( - encrypted_sig, video_id, player_url, age_gate) - sp = try_get(url_data, lambda x: x['sp'][0], compat_str) or 'signature' - url += '&%s=%s' % (sp, signature) + signature = self._decrypt_signature( + encrypted_sig, video_id, player_url, age_gate) + sp = try_get(url_data, lambda x: x['sp'][0], compat_str) or 'signature' + url += '&%s=%s' % (sp, signature) if 'ratebypass' not in url: url += '&ratebypass=yes' @@ -2044,24 +2063,33 @@ class YoutubeIE(YoutubeBaseInfoExtractor): mobj = re.search(r'^(?P\d+)[xX](?P\d+)$', url_data.get('size', [''])[0]) width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None) + if width is None: + width = int_or_none(fmt.get('width')) + if height is None: + height = int_or_none(fmt.get('height')) + filesize = int_or_none(url_data.get( 'clen', [None])[0]) or _extract_filesize(url) - quality = url_data.get('quality', [None])[0] + quality = url_data.get('quality', [None])[0] or fmt.get('quality') + quality_label = url_data.get('quality_label', [None])[0] or fmt.get('qualityLabel') + + tbr = float_or_none(url_data.get('bitrate', [None])[0], 1000) or float_or_none(fmt.get('bitrate'), 1000) + fps = int_or_none(url_data.get('fps', [None])[0]) or int_or_none(fmt.get('fps')) more_fields = { 'filesize': filesize, - 'tbr': float_or_none(url_data.get('bitrate', [None])[0], 1000), + 'tbr': tbr, 'width': width, 'height': height, - 'fps': int_or_none(url_data.get('fps', [None])[0]), - 'format_note': url_data.get('quality_label', [None])[0] or quality, + 'fps': fps, + 'format_note': quality_label or quality, 'quality': q(quality), } for key, value in more_fields.items(): if value: dct[key] = value - type_ = url_data.get('type', [None])[0] + type_ = url_data.get('type', [None])[0] or fmt.get('mimeType') if type_: type_split = type_.split(';') kind_ext = type_split[0].split('/') From 035c7a59e8eeb8725740b91f7cdd561e2d288a90 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 12 Sep 2019 01:18:25 +0700 Subject: [PATCH 031/422] [ChangeLog] Actualize [ci skip] --- ChangeLog | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/ChangeLog b/ChangeLog index e91e49854..c9e74e86d 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,9 @@ +version + +Extractors +* [youtube] Quick extraction tempfix (#22367, #22163) + + version 2019.09.01 Core From bd10b229c0311c668a65ce32ed99836237d9896b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 12 Sep 2019 01:21:21 +0700 Subject: [PATCH 032/422] release 2019.09.12 --- .github/ISSUE_TEMPLATE/1_broken_site.md | 6 +++--- .github/ISSUE_TEMPLATE/2_site_support_request.md | 4 ++-- .github/ISSUE_TEMPLATE/3_site_feature_request.md | 4 ++-- .github/ISSUE_TEMPLATE/4_bug_report.md | 6 +++--- .github/ISSUE_TEMPLATE/5_feature_request.md | 4 ++-- youtube_dl/version.py | 2 +- 6 files changed, 13 insertions(+), 13 deletions(-) diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.md b/.github/ISSUE_TEMPLATE/1_broken_site.md index 52c5c1c32..01f5095ed 100644 --- a/.github/ISSUE_TEMPLATE/1_broken_site.md +++ b/.github/ISSUE_TEMPLATE/1_broken_site.md @@ -18,7 +18,7 @@ title: '' - [ ] I'm reporting a broken site support -- [ ] I've verified that I'm running youtube-dl version **2019.09.01** +- [ ] I've verified that I'm running youtube-dl version **2019.09.12** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar issues including closed ones @@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.09.01 + [debug] youtube-dl version 2019.09.12 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/2_site_support_request.md b/.github/ISSUE_TEMPLATE/2_site_support_request.md index 000d2f55a..88c8b5cc6 100644 --- a/.github/ISSUE_TEMPLATE/2_site_support_request.md +++ b/.github/ISSUE_TEMPLATE/2_site_support_request.md @@ -19,7 +19,7 @@ labels: 'site-support-request' - [ ] I'm reporting a new site support request -- [ ] I've verified that I'm running youtube-dl version **2019.09.01** +- [ ] I've verified that I'm running youtube-dl version **2019.09.12** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that none of provided URLs violate any copyrights - [ ] I've searched the bugtracker for similar site support requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/3_site_feature_request.md b/.github/ISSUE_TEMPLATE/3_site_feature_request.md index 77b710606..d99c7e32d 100644 --- a/.github/ISSUE_TEMPLATE/3_site_feature_request.md +++ b/.github/ISSUE_TEMPLATE/3_site_feature_request.md @@ -18,13 +18,13 @@ title: '' - [ ] I'm reporting a site feature request -- [ ] I've verified that I'm running youtube-dl version **2019.09.01** +- [ ] I've verified that I'm running youtube-dl version **2019.09.12** - [ ] I've searched the bugtracker for similar site feature requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/4_bug_report.md b/.github/ISSUE_TEMPLATE/4_bug_report.md index ae112d965..346139f3e 100644 --- a/.github/ISSUE_TEMPLATE/4_bug_report.md +++ b/.github/ISSUE_TEMPLATE/4_bug_report.md @@ -18,7 +18,7 @@ title: '' - [ ] I'm reporting a broken site support issue -- [ ] I've verified that I'm running youtube-dl version **2019.09.01** +- [ ] I've verified that I'm running youtube-dl version **2019.09.12** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar bug reports including closed ones @@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.09.01 + [debug] youtube-dl version 2019.09.12 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/5_feature_request.md b/.github/ISSUE_TEMPLATE/5_feature_request.md index fccfdf71a..cce5bb037 100644 --- a/.github/ISSUE_TEMPLATE/5_feature_request.md +++ b/.github/ISSUE_TEMPLATE/5_feature_request.md @@ -19,13 +19,13 @@ labels: 'request' - [ ] I'm reporting a feature request -- [ ] I've verified that I'm running youtube-dl version **2019.09.01** +- [ ] I've verified that I'm running youtube-dl version **2019.09.12** - [ ] I've searched the bugtracker for similar feature requests including closed ones diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 98fa32286..212b5a7bc 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.09.01' +__version__ = '2019.09.12' From 303d3e142cfface18e02fda4087661e3bbab9343 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 12 Sep 2019 02:05:54 +0700 Subject: [PATCH 033/422] [ChangeLog] Actualize [ci skip] --- ChangeLog | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ChangeLog b/ChangeLog index c9e74e86d..d0283cacb 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version +version 2019.09.12 Extractors * [youtube] Quick extraction tempfix (#22367, #22163) From 4878759f3bcdbf0ed80ff9fe9aa9f682772d1a0a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 12 Sep 2019 02:45:30 +0700 Subject: [PATCH 034/422] [youtube] Remove quality and tbr for itag 43 (closes #22372) --- youtube_dl/extractor/youtube.py | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 9d0058b2a..f002d870e 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -41,7 +41,6 @@ from ..utils import ( orderedSet, parse_codecs, parse_duration, - qualities, remove_quotes, remove_start, smuggle_url, @@ -1944,7 +1943,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'width': int_or_none(width_height[0]), 'height': int_or_none(width_height[1]), } - q = qualities(['small', 'medium', 'hd720']) for fmt in streaming_formats: itag = str_or_none(fmt.get('itag')) if not itag: @@ -1957,7 +1955,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'format_note': quality_label, 'fps': int_or_none(fmt.get('fps')), 'height': int_or_none(fmt.get('height')), - 'quality': q(quality), # bitrate for itag 43 is always 2147483647 'tbr': float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) if itag != '43' else None, 'width': int_or_none(fmt.get('width')), @@ -2074,7 +2071,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): quality = url_data.get('quality', [None])[0] or fmt.get('quality') quality_label = url_data.get('quality_label', [None])[0] or fmt.get('qualityLabel') - tbr = float_or_none(url_data.get('bitrate', [None])[0], 1000) or float_or_none(fmt.get('bitrate'), 1000) + tbr = (float_or_none(url_data.get('bitrate', [None])[0], 1000) + or float_or_none(fmt.get('bitrate'), 1000)) if format_id != '43' else None fps = int_or_none(url_data.get('fps', [None])[0]) or int_or_none(fmt.get('fps')) more_fields = { @@ -2084,7 +2082,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'height': height, 'fps': fps, 'format_note': quality_label or quality, - 'quality': q(quality), } for key, value in more_fields.items(): if value: From 2f851a7d7dfbf2aabd78bd4863e2c6a33e3429bd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 12 Sep 2019 02:48:07 +0700 Subject: [PATCH 035/422] [ChangeLog] Actualize [ci skip] --- ChangeLog | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/ChangeLog b/ChangeLog index d0283cacb..ba5f37c73 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,9 @@ +version + +Extractors +* [youtube] Remove quality and tbr for itag 43 (#22372) + + version 2019.09.12 Extractors From e1f692f0b39ecec180bb291d0ae5ee4a9289402e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 12 Sep 2019 02:53:52 +0700 Subject: [PATCH 036/422] release 2019.09.12.1 --- .github/ISSUE_TEMPLATE/1_broken_site.md | 6 +++--- .github/ISSUE_TEMPLATE/2_site_support_request.md | 4 ++-- .github/ISSUE_TEMPLATE/3_site_feature_request.md | 4 ++-- .github/ISSUE_TEMPLATE/4_bug_report.md | 6 +++--- .github/ISSUE_TEMPLATE/5_feature_request.md | 4 ++-- ChangeLog | 2 +- youtube_dl/version.py | 2 +- 7 files changed, 14 insertions(+), 14 deletions(-) diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.md b/.github/ISSUE_TEMPLATE/1_broken_site.md index 01f5095ed..0c24155e6 100644 --- a/.github/ISSUE_TEMPLATE/1_broken_site.md +++ b/.github/ISSUE_TEMPLATE/1_broken_site.md @@ -18,7 +18,7 @@ title: '' - [ ] I'm reporting a broken site support -- [ ] I've verified that I'm running youtube-dl version **2019.09.12** +- [ ] I've verified that I'm running youtube-dl version **2019.09.12.1** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar issues including closed ones @@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.09.12 + [debug] youtube-dl version 2019.09.12.1 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/2_site_support_request.md b/.github/ISSUE_TEMPLATE/2_site_support_request.md index 88c8b5cc6..9babe0360 100644 --- a/.github/ISSUE_TEMPLATE/2_site_support_request.md +++ b/.github/ISSUE_TEMPLATE/2_site_support_request.md @@ -19,7 +19,7 @@ labels: 'site-support-request' - [ ] I'm reporting a new site support request -- [ ] I've verified that I'm running youtube-dl version **2019.09.12** +- [ ] I've verified that I'm running youtube-dl version **2019.09.12.1** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that none of provided URLs violate any copyrights - [ ] I've searched the bugtracker for similar site support requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/3_site_feature_request.md b/.github/ISSUE_TEMPLATE/3_site_feature_request.md index d99c7e32d..72322fe26 100644 --- a/.github/ISSUE_TEMPLATE/3_site_feature_request.md +++ b/.github/ISSUE_TEMPLATE/3_site_feature_request.md @@ -18,13 +18,13 @@ title: '' - [ ] I'm reporting a site feature request -- [ ] I've verified that I'm running youtube-dl version **2019.09.12** +- [ ] I've verified that I'm running youtube-dl version **2019.09.12.1** - [ ] I've searched the bugtracker for similar site feature requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/4_bug_report.md b/.github/ISSUE_TEMPLATE/4_bug_report.md index 346139f3e..da7f2cf93 100644 --- a/.github/ISSUE_TEMPLATE/4_bug_report.md +++ b/.github/ISSUE_TEMPLATE/4_bug_report.md @@ -18,7 +18,7 @@ title: '' - [ ] I'm reporting a broken site support issue -- [ ] I've verified that I'm running youtube-dl version **2019.09.12** +- [ ] I've verified that I'm running youtube-dl version **2019.09.12.1** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar bug reports including closed ones @@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.09.12 + [debug] youtube-dl version 2019.09.12.1 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/5_feature_request.md b/.github/ISSUE_TEMPLATE/5_feature_request.md index cce5bb037..d41022b9f 100644 --- a/.github/ISSUE_TEMPLATE/5_feature_request.md +++ b/.github/ISSUE_TEMPLATE/5_feature_request.md @@ -19,13 +19,13 @@ labels: 'request' - [ ] I'm reporting a feature request -- [ ] I've verified that I'm running youtube-dl version **2019.09.12** +- [ ] I've verified that I'm running youtube-dl version **2019.09.12.1** - [ ] I've searched the bugtracker for similar feature requests including closed ones diff --git a/ChangeLog b/ChangeLog index ba5f37c73..2aba02065 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version +version 2019.09.12.1 Extractors * [youtube] Remove quality and tbr for itag 43 (#22372) diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 212b5a7bc..df82cdf0f 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.09.12' +__version__ = '2019.09.12.1' From 20e11b70ac48fd5bffae194d829f7e31fcc65fca Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 18 Sep 2019 23:45:26 +0700 Subject: [PATCH 037/422] [tv4] Fix extraction and extract series metadata (closes #22443) --- youtube_dl/extractor/tv4.py | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/tv4.py b/youtube_dl/extractor/tv4.py index 51923e44a..a819d048c 100644 --- a/youtube_dl/extractor/tv4.py +++ b/youtube_dl/extractor/tv4.py @@ -72,8 +72,13 @@ class TV4IE(InfoExtractor): video_id = self._match_id(url) info = self._download_json( - 'http://www.tv4play.se/player/assets/%s.json' % video_id, - video_id, 'Downloading video info JSON') + 'https://playback-api.b17g.net/asset/%s' % video_id, + video_id, 'Downloading video info JSON', query={ + 'service': 'tv4', + 'device': 'browser', + 'protocol': 'hls,dash', + 'drm': 'widevine', + })['metadata'] title = info['title'] @@ -111,5 +116,9 @@ class TV4IE(InfoExtractor): 'timestamp': parse_iso8601(info.get('broadcast_date_time')), 'duration': int_or_none(info.get('duration')), 'thumbnail': info.get('image'), - 'is_live': info.get('is_live') is True, + 'is_live': info.get('isLive') is True, + 'series': info.get('seriesTitle'), + 'season_number': int_or_none(info.get('seasonNumber')), + 'episode': info.get('episodeTitle'), + 'episode_number': int_or_none(info.get('episodeNumber')), } From 9cf26b6e1d0658eb0b252872ef011d765b8341a5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 19 Sep 2019 01:11:52 +0700 Subject: [PATCH 038/422] [zdf] Bypass geo restriction --- youtube_dl/extractor/zdf.py | 1 + 1 file changed, 1 insertion(+) diff --git a/youtube_dl/extractor/zdf.py b/youtube_dl/extractor/zdf.py index afa3f6c47..145c123a4 100644 --- a/youtube_dl/extractor/zdf.py +++ b/youtube_dl/extractor/zdf.py @@ -41,6 +41,7 @@ class ZDFBaseIE(InfoExtractor): class ZDFIE(ZDFBaseIE): _VALID_URL = r'https?://www\.zdf\.de/(?:[^/]+/)*(?P[^/?]+)\.html' _QUALITIES = ('auto', 'low', 'med', 'high', 'veryhigh') + _GEO_COUNTRIES = ['DE'] _TESTS = [{ 'url': 'https://www.zdf.de/dokumentation/terra-x/die-magie-der-farben-von-koenigspurpur-und-jeansblau-100.html', From 6fd26a7d4a851b260c56974d77911804c09ff816 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 19 Sep 2019 02:31:39 +0700 Subject: [PATCH 039/422] [9now] Fix extraction (closes #22361) --- youtube_dl/extractor/ninenow.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/ninenow.py b/youtube_dl/extractor/ninenow.py index f32f530f7..6157dc7c1 100644 --- a/youtube_dl/extractor/ninenow.py +++ b/youtube_dl/extractor/ninenow.py @@ -45,7 +45,11 @@ class NineNowIE(InfoExtractor): webpage = self._download_webpage(url, display_id) page_data = self._parse_json(self._search_regex( r'window\.__data\s*=\s*({.*?});', webpage, - 'page data'), display_id) + 'page data', default='{}'), display_id, fatal=False) + if not page_data: + page_data = self._parse_json(self._parse_json(self._search_regex( + r'window\.__data\s*=\s*JSON\.parse\s*\(\s*(".+?")\s*\)\s*;', + webpage, 'page data'), display_id), display_id) for kind in ('episode', 'clip'): current_key = page_data.get(kind, {}).get( From 1cb812d3c257b3f6d3c07ccabcbdebd0190fbec4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 19 Sep 2019 03:00:19 +0700 Subject: [PATCH 040/422] [hotstar] Extract more formats (closes #22323) --- youtube_dl/extractor/hotstar.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/youtube_dl/extractor/hotstar.py b/youtube_dl/extractor/hotstar.py index 79d5bbb2e..c7545a1e6 100644 --- a/youtube_dl/extractor/hotstar.py +++ b/youtube_dl/extractor/hotstar.py @@ -3,6 +3,7 @@ from __future__ import unicode_literals import hashlib import hmac +import re import time import uuid @@ -126,6 +127,8 @@ class HotStarIE(HotStarBaseIE): format_url = url_or_none(playback_set.get('playbackUrl')) if not format_url: continue + format_url = re.sub( + r'(?<=//staragvod)(\d)', r'web\1', format_url) tags = str_or_none(playback_set.get('tagsCombination')) or '' if tags and 'encryption:plain' not in tags: continue From d9d3098675daf219e0e0f910fbd704beb1775ae7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 19 Sep 2019 03:02:15 +0700 Subject: [PATCH 041/422] [hotstar] Use native HLS downloader by default --- youtube_dl/extractor/hotstar.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/hotstar.py b/youtube_dl/extractor/hotstar.py index c7545a1e6..f9f7c5a64 100644 --- a/youtube_dl/extractor/hotstar.py +++ b/youtube_dl/extractor/hotstar.py @@ -136,7 +136,8 @@ class HotStarIE(HotStarBaseIE): try: if 'package:hls' in tags or ext == 'm3u8': formats.extend(self._extract_m3u8_formats( - format_url, video_id, 'mp4', m3u8_id='hls')) + format_url, video_id, 'mp4', + entry_protocol='m3u8_native', m3u8_id='hls')) elif 'package:dash' in tags or ext == 'mpd': formats.extend(self._extract_mpd_formats( format_url, video_id, mpd_id='dash')) From f455a934e9a44aaebdf925b5d78ffafa39e14c97 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Thu, 19 Sep 2019 18:02:26 +0100 Subject: [PATCH 042/422] [brightcove] delegate all supported BrightcoveLegacyIE URLs to BrightcoveNewIE closes #11523 closes #12842 closes #13912 closes #15669 closes #16303 --- youtube_dl/extractor/brightcove.py | 196 ++++------------------------- 1 file changed, 25 insertions(+), 171 deletions(-) diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index 58ec5c979..8e2f7217a 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -2,7 +2,6 @@ from __future__ import unicode_literals import base64 -import json import re import struct @@ -11,14 +10,12 @@ from .adobepass import AdobePassIE from ..compat import ( compat_etree_fromstring, compat_parse_qs, - compat_str, compat_urllib_parse_urlparse, compat_urlparse, compat_xml_parse_error, compat_HTTPError, ) from ..utils import ( - determine_ext, ExtractorError, extract_attributes, find_xpath_attr, @@ -27,18 +24,19 @@ from ..utils import ( js_to_json, int_or_none, parse_iso8601, + smuggle_url, unescapeHTML, unsmuggle_url, update_url_query, clean_html, mimetype2ext, + UnsupportedError, ) class BrightcoveLegacyIE(InfoExtractor): IE_NAME = 'brightcove:legacy' _VALID_URL = r'(?:https?://.*brightcove\.com/(services|viewer).*?\?|brightcove:)(?P.*)' - _FEDERATED_URL = 'http://c.brightcove.com/services/viewer/htmlFederated' _TESTS = [ { @@ -55,7 +53,8 @@ class BrightcoveLegacyIE(InfoExtractor): 'timestamp': 1368213670, 'upload_date': '20130510', 'uploader_id': '1589608506001', - } + }, + 'skip': 'The player has been deactivated by the content owner', }, { # From http://medianetwork.oracle.com/video/player/1785452137001 @@ -70,6 +69,7 @@ class BrightcoveLegacyIE(InfoExtractor): 'upload_date': '20120814', 'uploader_id': '1460825906', }, + 'skip': 'video not playable', }, { # From http://mashable.com/2013/10/26/thermoelectric-bracelet-lets-you-control-your-body-temperature/ @@ -79,7 +79,7 @@ class BrightcoveLegacyIE(InfoExtractor): 'ext': 'mp4', 'title': 'This Bracelet Acts as a Personal Thermostat', 'description': 'md5:547b78c64f4112766ccf4e151c20b6a0', - 'uploader': 'Mashable', + # 'uploader': 'Mashable', 'timestamp': 1382041798, 'upload_date': '20131017', 'uploader_id': '1130468786001', @@ -124,6 +124,7 @@ class BrightcoveLegacyIE(InfoExtractor): 'id': '3550319591001', }, 'playlist_mincount': 7, + 'skip': 'Unsupported URL', }, { # playlist with 'playlistTab' (https://github.com/ytdl-org/youtube-dl/issues/9965) @@ -133,6 +134,7 @@ class BrightcoveLegacyIE(InfoExtractor): 'title': 'Lesson 08', }, 'playlist_mincount': 10, + 'skip': 'Unsupported URL', }, { # playerID inferred from bcpid @@ -141,12 +143,6 @@ class BrightcoveLegacyIE(InfoExtractor): 'only_matching': True, # Tested in GenericIE } ] - FLV_VCODECS = { - 1: 'SORENSON', - 2: 'ON2', - 3: 'H264', - 4: 'VP8', - } @classmethod def _build_brighcove_url(cls, object_str): @@ -238,7 +234,8 @@ class BrightcoveLegacyIE(InfoExtractor): @classmethod def _make_brightcove_url(cls, params): - return update_url_query(cls._FEDERATED_URL, params) + return update_url_query( + 'http://c.brightcove.com/services/viewer/htmlFederated', params) @classmethod def _extract_brightcove_url(cls, webpage): @@ -297,38 +294,12 @@ class BrightcoveLegacyIE(InfoExtractor): videoPlayer = query.get('@videoPlayer') if videoPlayer: # We set the original url as the default 'Referer' header - referer = smuggled_data.get('Referer', url) + referer = query.get('linkBaseURL', [None])[0] or smuggled_data.get('Referer', url) + video_id = videoPlayer[0] if 'playerID' not in query: mobj = re.search(r'/bcpid(\d+)', url) if mobj is not None: query['playerID'] = [mobj.group(1)] - return self._get_video_info( - videoPlayer[0], query, referer=referer) - elif 'playerKey' in query: - player_key = query['playerKey'] - return self._get_playlist_info(player_key[0]) - else: - raise ExtractorError( - 'Cannot find playerKey= variable. Did you forget quotes in a shell invocation?', - expected=True) - - def _brightcove_new_url_result(self, publisher_id, video_id): - brightcove_new_url = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' % (publisher_id, video_id) - return self.url_result(brightcove_new_url, BrightcoveNewIE.ie_key(), video_id) - - def _get_video_info(self, video_id, query, referer=None): - headers = {} - linkBase = query.get('linkBaseURL') - if linkBase is not None: - referer = linkBase[0] - if referer is not None: - headers['Referer'] = referer - webpage = self._download_webpage(self._FEDERATED_URL, video_id, headers=headers, query=query) - - error_msg = self._html_search_regex( - r"

We're sorry.

([\s\n]*

.*?

)+", webpage, - 'error message', default=None) - if error_msg is not None: publisher_id = query.get('publisherId') if publisher_id and publisher_id[0].isdigit(): publisher_id = publisher_id[0] @@ -339,6 +310,9 @@ class BrightcoveLegacyIE(InfoExtractor): else: player_id = query.get('playerID') if player_id and player_id[0].isdigit(): + headers = {} + if referer: + headers['Referer'] = referer player_page = self._download_webpage( 'http://link.brightcove.com/services/player/bcpid' + player_id[0], video_id, headers=headers, fatal=False) @@ -349,136 +323,16 @@ class BrightcoveLegacyIE(InfoExtractor): if player_key: enc_pub_id = player_key.split(',')[1].replace('~', '=') publisher_id = struct.unpack('>Q', base64.urlsafe_b64decode(enc_pub_id))[0] - if publisher_id: - return self._brightcove_new_url_result(publisher_id, video_id) - raise ExtractorError( - 'brightcove said: %s' % error_msg, expected=True) - - self.report_extraction(video_id) - info = self._search_regex(r'var experienceJSON = ({.*});', webpage, 'json') - info = json.loads(info)['data'] - video_info = info['programmedContent']['videoPlayer']['mediaDTO'] - video_info['_youtubedl_adServerURL'] = info.get('adServerURL') - - return self._extract_video_info(video_info) - - def _get_playlist_info(self, player_key): - info_url = 'http://c.brightcove.com/services/json/experience/runtime/?command=get_programming_for_experience&playerKey=%s' % player_key - playlist_info = self._download_webpage( - info_url, player_key, 'Downloading playlist information') - - json_data = json.loads(playlist_info) - if 'videoList' in json_data: - playlist_info = json_data['videoList'] - playlist_dto = playlist_info['mediaCollectionDTO'] - elif 'playlistTabs' in json_data: - playlist_info = json_data['playlistTabs'] - playlist_dto = playlist_info['lineupListDTO']['playlistDTOs'][0] - else: - raise ExtractorError('Empty playlist') - - videos = [self._extract_video_info(video_info) for video_info in playlist_dto['videoDTOs']] - - return self.playlist_result(videos, playlist_id='%s' % playlist_info['id'], - playlist_title=playlist_dto['displayName']) - - def _extract_video_info(self, video_info): - video_id = compat_str(video_info['id']) - publisher_id = video_info.get('publisherId') - info = { - 'id': video_id, - 'title': video_info['displayName'].strip(), - 'description': video_info.get('shortDescription'), - 'thumbnail': video_info.get('videoStillURL') or video_info.get('thumbnailURL'), - 'uploader': video_info.get('publisherName'), - 'uploader_id': compat_str(publisher_id) if publisher_id else None, - 'duration': float_or_none(video_info.get('length'), 1000), - 'timestamp': int_or_none(video_info.get('creationDate'), 1000), - } - - renditions = video_info.get('renditions', []) + video_info.get('IOSRenditions', []) - if renditions: - formats = [] - for rend in renditions: - url = rend['defaultURL'] - if not url: - continue - ext = None - if rend['remote']: - url_comp = compat_urllib_parse_urlparse(url) - if url_comp.path.endswith('.m3u8'): - formats.extend( - self._extract_m3u8_formats( - url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) - continue - elif 'akamaihd.net' in url_comp.netloc: - # This type of renditions are served through - # akamaihd.net, but they don't use f4m manifests - url = url.replace('control/', '') + '?&v=3.3.0&fp=13&r=FEEFJ&g=RTSJIMBMPFPB' - ext = 'flv' - if ext is None: - ext = determine_ext(url) - tbr = int_or_none(rend.get('encodingRate'), 1000) - a_format = { - 'format_id': 'http%s' % ('-%s' % tbr if tbr else ''), - 'url': url, - 'ext': ext, - 'filesize': int_or_none(rend.get('size')) or None, - 'tbr': tbr, - } - if rend.get('audioOnly'): - a_format.update({ - 'vcodec': 'none', - }) - else: - a_format.update({ - 'height': int_or_none(rend.get('frameHeight')), - 'width': int_or_none(rend.get('frameWidth')), - 'vcodec': rend.get('videoCodec'), - }) - - # m3u8 manifests with remote == false are media playlists - # Not calling _extract_m3u8_formats here to save network traffic - if ext == 'm3u8': - a_format.update({ - 'format_id': 'hls%s' % ('-%s' % tbr if tbr else ''), - 'ext': 'mp4', - 'protocol': 'm3u8_native', - }) - - formats.append(a_format) - self._sort_formats(formats) - info['formats'] = formats - elif video_info.get('FLVFullLengthURL') is not None: - info.update({ - 'url': video_info['FLVFullLengthURL'], - 'vcodec': self.FLV_VCODECS.get(video_info.get('FLVFullCodec')), - 'filesize': int_or_none(video_info.get('FLVFullSize')), - }) - - if self._downloader.params.get('include_ads', False): - adServerURL = video_info.get('_youtubedl_adServerURL') - if adServerURL: - ad_info = { - '_type': 'url', - 'url': adServerURL, - } - if 'url' in info: - return { - '_type': 'playlist', - 'title': info['title'], - 'entries': [ad_info, info], - } - else: - return ad_info - - if not info.get('url') and not info.get('formats'): - uploader_id = info.get('uploader_id') - if uploader_id: - info.update(self._brightcove_new_url_result(uploader_id, video_id)) - else: - raise ExtractorError('Unable to extract video url for %s' % video_id) - return info + if publisher_id: + brightcove_new_url = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' % (publisher_id, video_id) + if referer: + brightcove_new_url = smuggle_url(brightcove_new_url, {'referrer': referer}) + return self.url_result(brightcove_new_url, BrightcoveNewIE.ie_key(), video_id) + # TODO: figure out if it's possible to extract playlistId from playerKey + # elif 'playerKey' in query: + # player_key = query['playerKey'] + # return self._get_playlist_info(player_key[0]) + raise UnsupportedError(url) class BrightcoveNewIE(AdobePassIE): From 6cf6b357f581af841a7d109aad47e40acf7d7795 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Fri, 20 Sep 2019 11:14:24 +0100 Subject: [PATCH 043/422] [mixcloud] allow uppercase letters in format urls(closes #19280) --- youtube_dl/extractor/mixcloud.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index bcac13ec5..bf5353ef9 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -164,7 +164,7 @@ class MixcloudIE(InfoExtractor): def decrypt_url(f_url): for k in (key, 'IFYOUWANTTHEARTISTSTOGETPAIDDONOTDOWNLOADFROMMIXCLOUD'): decrypted_url = self._decrypt_xor_cipher(k, f_url) - if re.search(r'^https?://[0-9a-z.]+/[0-9A-Za-z/.?=&_-]+$', decrypted_url): + if re.search(r'^https?://[0-9A-Za-z.]+/[0-9A-Za-z/.?=&_-]+$', decrypted_url): return decrypted_url for url_key in ('url', 'hlsUrl', 'dashUrl'): From edb2820ca5febb6bc88201e348bcdc904e7cbacb Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sat, 21 Sep 2019 21:57:45 +0100 Subject: [PATCH 044/422] [instagram] add support for tv URLs --- youtube_dl/extractor/instagram.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/instagram.py b/youtube_dl/extractor/instagram.py index ffd87b55f..b061850a1 100644 --- a/youtube_dl/extractor/instagram.py +++ b/youtube_dl/extractor/instagram.py @@ -22,7 +22,7 @@ from ..utils import ( class InstagramIE(InfoExtractor): - _VALID_URL = r'(?Phttps?://(?:www\.)?instagram\.com/p/(?P[^/?#&]+))' + _VALID_URL = r'(?Phttps?://(?:www\.)?instagram\.com/(?:p|tv)/(?P[^/?#&]+))' _TESTS = [{ 'url': 'https://instagram.com/p/aye83DjauH/?foo=bar#abc', 'md5': '0d2da106a9d2631273e192b372806516', @@ -92,6 +92,9 @@ class InstagramIE(InfoExtractor): }, { 'url': 'http://instagram.com/p/9o6LshA7zy/embed/', 'only_matching': True, + }, { + 'url': 'https://www.instagram.com/tv/aye83DjauH/', + 'only_matching': True, }] @staticmethod From 4bc15a68d1f7e2f38267081d3d764470da3439fa Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sun, 22 Sep 2019 17:14:18 +0100 Subject: [PATCH 045/422] [bilibili] add support audio albums and songs(closes #21094) --- youtube_dl/extractor/bilibili.py | 113 +++++++++++++++++++++++++++++ youtube_dl/extractor/extractors.py | 2 + 2 files changed, 115 insertions(+) diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py index 3746671d3..80bd696e2 100644 --- a/youtube_dl/extractor/bilibili.py +++ b/youtube_dl/extractor/bilibili.py @@ -15,6 +15,7 @@ from ..utils import ( float_or_none, parse_iso8601, smuggle_url, + str_or_none, strip_jsonp, unified_timestamp, unsmuggle_url, @@ -306,3 +307,115 @@ class BiliBiliBangumiIE(InfoExtractor): return self.playlist_result( entries, bangumi_id, season_info.get('bangumi_title'), season_info.get('evaluate')) + + +class BilibiliAudioBaseIE(InfoExtractor): + def _call_api(self, path, sid, query=None): + if not query: + query = {'sid': sid} + return self._download_json( + 'https://www.bilibili.com/audio/music-service-c/web/' + path, + sid, query=query)['data'] + + +class BilibiliAudioIE(BilibiliAudioBaseIE): + _VALID_URL = r'https?://(?:www\.)?bilibili\.com/audio/au(?P\d+)' + _TEST = { + 'url': 'https://www.bilibili.com/audio/au1003142', + 'md5': 'fec4987014ec94ef9e666d4d158ad03b', + 'info_dict': { + 'id': '1003142', + 'ext': 'm4a', + 'title': '【tsukimi】YELLOW / 神山羊', + 'artist': 'tsukimi', + 'comment_count': int, + 'description': 'YELLOW的mp3版！', + 'duration': 183, + 'subtitles': { + 'origin': [{ + 'ext': 'lrc', + }], + }, + 'thumbnail': r're:^https?://.+\.jpg', + 'timestamp': 1564836614, + 'upload_date': '20190803', + 'uploader': 'tsukimi-つきみぐー', + 'view_count': int, + }, + } + + def _real_extract(self, url): + au_id = self._match_id(url) + + play_data = self._call_api('url', au_id) + formats = [{ + 'url': play_data['cdns'][0], + 'filesize': int_or_none(play_data.get('size')), + }] + + song = self._call_api('song/info', au_id) + title = song['title'] + statistic = song.get('statistic') or {} + + subtitles = None + lyric = song.get('lyric') + if lyric: + subtitles = { + 'origin': [{ + 'url': lyric, + }] + } + + return { + 'id': au_id, + 'title': title, + 'formats': formats, + 'artist': song.get('author'), + 'comment_count': int_or_none(statistic.get('comment')), + 'description': song.get('intro'), + 'duration': int_or_none(song.get('duration')), + 'subtitles': subtitles, + 'thumbnail': song.get('cover'), + 'timestamp': int_or_none(song.get('passtime')), + 'uploader': song.get('uname'), + 'view_count': int_or_none(statistic.get('play')), + } + + +class BilibiliAudioAlbumIE(BilibiliAudioBaseIE): + _VALID_URL = r'https?://(?:www\.)?bilibili\.com/audio/am(?P\d+)' + _TEST = { + 'url': 'https://www.bilibili.com/audio/am10624', + 'info_dict': { + 'id': '10624', + 'title': '每日新曲推荐（每日11:00更新）', + 'description': '每天11:00更新，为你推送最新音乐', + }, + 'playlist_count': 19, + } + + def _real_extract(self, url): + am_id = self._match_id(url) + + songs = self._call_api( + 'song/of-menu', am_id, {'sid': am_id, 'pn': 1, 'ps': 100})['data'] + + entries = [] + for song in songs: + sid = str_or_none(song.get('id')) + if not sid: + continue + entries.append(self.url_result( + 'https://www.bilibili.com/audio/au' + sid, + BilibiliAudioIE.ie_key(), sid)) + + if entries: + album_data = self._call_api('menu/info', am_id) or {} + album_title = album_data.get('title') + if album_title: + for entry in entries: + entry['album'] = album_title + return self.playlist_result( + entries, am_id, album_title, album_data.get('intro')) + + return self.playlist_result(entries, am_id) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 4adcae1e5..44120cae2 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -104,6 +104,8 @@ from .bild import BildIE from .bilibili import ( BiliBiliIE, BiliBiliBangumiIE, + BilibiliAudioIE, + BilibiliAudioAlbumIE, ) from .biobiochiletv import BioBioChileTVIE from .bitchute import ( From 4e3f1f0469b4f3c64cde7105729f9c3acfd3f679 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 23 Sep 2019 00:20:52 +0700 Subject: [PATCH 046/422] [youtube:playlist] Unescape playlist uploader (closes #22483) --- youtube_dl/extractor/youtube.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index f002d870e..f3f0bf8db 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -2740,7 +2740,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): page, 'title', default=None) _UPLOADER_BASE = r'class=["\']pl-header-details[^>]+>\s*
  • \s*]+\bhref=' - uploader = self._search_regex( + uploader = self._html_search_regex( r'%s["\']/(?:user|channel)/[^>]+>([^<]+)' % _UPLOADER_BASE, page, 'uploader', default=None) mobj = re.search( From 7d327fea5b7a73dfa6bf0082aed5d96a7ceae9a6 Mon Sep 17 00:00:00 2001 From: ipaha Date: Mon, 23 Sep 2019 22:44:00 +0300 Subject: [PATCH 047/422] [jwplatfom] do not match video URLs(#20596) (#22148) --- youtube_dl/extractor/jwplatform.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/jwplatform.py b/youtube_dl/extractor/jwplatform.py index 647b905f1..2aabd98b5 100644 --- a/youtube_dl/extractor/jwplatform.py +++ b/youtube_dl/extractor/jwplatform.py @@ -7,7 +7,7 @@ from .common import InfoExtractor class JWPlatformIE(InfoExtractor): - _VALID_URL = r'(?:https?://(?:content\.jwplatform|cdn\.jwplayer)\.com/(?:(?:feed|player|thumb|preview|video)s|jw6|v2/media)/|jwplatform:)(?P[a-zA-Z0-9]{8})' + _VALID_URL = r'(?:https?://(?:content\.jwplatform|cdn\.jwplayer)\.com/(?:(?:feed|player|thumb|preview)s|jw6|v2/media)/|jwplatform:)(?P[a-zA-Z0-9]{8})' _TESTS = [{ 'url': 'http://content.jwplatform.com/players/nPripu9l-ALJ3XQCI.js', 'md5': 'fa8899fa601eb7c83a64e9d568bdf325', From 666d808e7096e782aa6e4ff456120cb91d868120 Mon Sep 17 00:00:00 2001 From: sofutru <54445344+sofutru@users.noreply.github.com> Date: Tue, 24 Sep 2019 23:16:46 +0700 Subject: [PATCH 048/422] [youtube] Add support for invidious.drycat.fr (#22451) --- youtube_dl/extractor/youtube.py | 1 + 1 file changed, 1 insertion(+) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index f3f0bf8db..05eea0e4e 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -387,6 +387,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): (?:www\.)?invidious\.13ad\.de/| (?:www\.)?invidious\.mastodon\.host/| (?:www\.)?invidious\.nixnet\.xyz/| + (?:www\.)?invidious\.drycat\.fr/| (?:www\.)?tube\.poal\.co/| (?:www\.)?vid\.wxzm\.sx/| (?:www\.)?yt\.elukerio\.org/| From 8e9fdcbe276d760ced8ac37120cd9e4687e5aa84 Mon Sep 17 00:00:00 2001 From: smed79 <1873139+smed79@users.noreply.github.com> Date: Tue, 24 Sep 2019 17:56:12 +0100 Subject: [PATCH 049/422] [openload] Add support for oload.online (#22304) --- youtube_dl/extractor/openload.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index 679eaf6c3..46956e550 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -246,7 +246,7 @@ class OpenloadIE(InfoExtractor): _DOMAINS = r''' (?: openload\.(?:co|io|link|pw)| - oload\.(?:tv|best|biz|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|press|pw|life|live|space|services|website|vip)| + oload\.(?:tv|best|biz|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|online|press|pw|life|live|space|services|website|vip)| oladblock\.(?:services|xyz|me)|openloed\.co ) ''' @@ -362,6 +362,9 @@ class OpenloadIE(InfoExtractor): }, { 'url': 'https://oload.services/embed/bs1NWj1dCag/', 'only_matching': True, +}, { + 'url': 'https://oload.online/f/W8o2UfN1vNY/', + 'only_matching': True, }, { 'url': 'https://oload.press/embed/drTBl1aOTvk/', 'only_matching': True, From d06daf23dae24b0811be704283b4b63689035af3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 25 Sep 2019 02:08:46 +0700 Subject: [PATCH 050/422] [YoutubeDL] Honour all --get-* options with --flat-playlist (closes #22493) --- youtube_dl/YoutubeDL.py | 62 +++++++++++++++++++++++------------------ 1 file changed, 35 insertions(+), 27 deletions(-) diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 6a44bc7ba..c3d1407f9 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -852,8 +852,9 @@ class YoutubeDL(object): extract_flat = self.params.get('extract_flat', False) if ((extract_flat == 'in_playlist' and 'playlist' in extra_info) or extract_flat is True): - if self.params.get('forcejson', False): - self.to_stdout(json.dumps(ie_result)) + self.__forced_printings( + ie_result, self.prepare_filename(ie_result), + incomplete=True) return ie_result if result_type == 'video': @@ -1693,6 +1694,36 @@ class YoutubeDL(object): subs[lang] = f return subs + def __forced_printings(self, info_dict, filename, incomplete): + def print_mandatory(field): + if (self.params.get('force%s' % field, False) + and (not incomplete or info_dict.get(field) is not None)): + self.to_stdout(info_dict[field]) + + def print_optional(field): + if (self.params.get('force%s' % field, False) + and info_dict.get(field) is not None): + self.to_stdout(info_dict[field]) + + print_mandatory('title') + print_mandatory('id') + if self.params.get('forceurl', False) and not incomplete: + if info_dict.get('requested_formats') is not None: + for f in info_dict['requested_formats']: + self.to_stdout(f['url'] + f.get('play_path', '')) + else: + # For RTMP URLs, also include the playpath + self.to_stdout(info_dict['url'] + info_dict.get('play_path', '')) + print_optional('thumbnail') + print_optional('description') + if self.params.get('forcefilename', False) and filename is not None: + self.to_stdout(filename) + if self.params.get('forceduration', False) and info_dict.get('duration') is not None: + self.to_stdout(formatSeconds(info_dict['duration'])) + print_mandatory('format') + if self.params.get('forcejson', False): + self.to_stdout(json.dumps(info_dict)) + def process_info(self, info_dict): """Process a single resolved IE result.""" @@ -1703,9 +1734,8 @@ class YoutubeDL(object): if self._num_downloads >= int(max_downloads): raise MaxDownloadsReached() + # TODO: backward compatibility, to be removed info_dict['fulltitle'] = info_dict['title'] - if len(info_dict['title']) > 200: - info_dict['title'] = info_dict['title'][:197] + '...' if 'format' not in info_dict: info_dict['format'] = info_dict['ext'] @@ -1720,29 +1750,7 @@ class YoutubeDL(object): info_dict['_filename'] = filename = self.prepare_filename(info_dict) # Forced printings - if self.params.get('forcetitle', False): - self.to_stdout(info_dict['fulltitle']) - if self.params.get('forceid', False): - self.to_stdout(info_dict['id']) - if self.params.get('forceurl', False): - if info_dict.get('requested_formats') is not None: - for f in info_dict['requested_formats']: - self.to_stdout(f['url'] + f.get('play_path', '')) - else: - # For RTMP URLs, also include the playpath - self.to_stdout(info_dict['url'] + info_dict.get('play_path', '')) - if self.params.get('forcethumbnail', False) and info_dict.get('thumbnail') is not None: - self.to_stdout(info_dict['thumbnail']) - if self.params.get('forcedescription', False) and info_dict.get('description') is not None: - self.to_stdout(info_dict['description']) - if self.params.get('forcefilename', False) and filename is not None: - self.to_stdout(filename) - if self.params.get('forceduration', False) and info_dict.get('duration') is not None: - self.to_stdout(formatSeconds(info_dict['duration'])) - if self.params.get('forceformat', False): - self.to_stdout(info_dict['format']) - if self.params.get('forcejson', False): - self.to_stdout(json.dumps(info_dict)) + self.__forced_printings(info_dict, filename, incomplete=False) # Do nothing else if in simulate mode if self.params.get('simulate', False): From df63cafe497d7530d887786d5a54ca11bf5e73db Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 25 Sep 2019 02:16:25 +0700 Subject: [PATCH 051/422] [byutv] Fix extraction (refs #22070) Downloading of new videos does not work due to DRM --- youtube_dl/extractor/byutv.py | 53 ++++++++++++++++++++++++++--------- 1 file changed, 39 insertions(+), 14 deletions(-) diff --git a/youtube_dl/extractor/byutv.py b/youtube_dl/extractor/byutv.py index 562c83af9..0b11bf11f 100644 --- a/youtube_dl/extractor/byutv.py +++ b/youtube_dl/extractor/byutv.py @@ -3,7 +3,12 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import parse_duration +from ..utils import ( + determine_ext, + merge_dicts, + parse_duration, + url_or_none, +) class BYUtvIE(InfoExtractor): @@ -51,7 +56,7 @@ class BYUtvIE(InfoExtractor): video_id = mobj.group('id') display_id = mobj.group('display_id') or video_id - info = self._download_json( + video = self._download_json( 'https://api.byutv.org/api3/catalog/getvideosforcontent', display_id, query={ 'contentid': video_id, @@ -62,7 +67,7 @@ class BYUtvIE(InfoExtractor): 'x-byutv-platformkey': 'xsaaw9c7y5', }) - ep = info.get('ooyalaVOD') + ep = video.get('ooyalaVOD') if ep: return { '_type': 'url_transparent', @@ -75,18 +80,38 @@ class BYUtvIE(InfoExtractor): 'thumbnail': ep.get('imageThumbnail'), } - ep = info['dvr'] - title = ep['title'] - formats = self._extract_m3u8_formats( - ep['videoUrl'], video_id, 'mp4', entry_protocol='m3u8_native', - m3u8_id='hls') + info = {} + formats = [] + for format_id, ep in video.items(): + if not isinstance(ep, dict): + continue + video_url = url_or_none(ep.get('videoUrl')) + if not video_url: + continue + ext = determine_ext(video_url) + if ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + video_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False)) + elif ext == 'mpd': + formats.extend(self._extract_mpd_formats( + video_url, video_id, mpd_id='dash', fatal=False)) + else: + formats.append({ + 'url': video_url, + 'format_id': format_id, + }) + merge_dicts(info, { + 'title': ep.get('title'), + 'description': ep.get('description'), + 'thumbnail': ep.get('imageThumbnail'), + 'duration': parse_duration(ep.get('length')), + }) self._sort_formats(formats) - return { + + return merge_dicts(info, { 'id': video_id, 'display_id': display_id, - 'title': title, - 'description': ep.get('description'), - 'thumbnail': ep.get('imageThumbnail'), - 'duration': parse_duration(ep.get('length')), + 'title': display_id, 'formats': formats, - } + }) From a373befa25bb521f94facb01c2cef45850c1e7c9 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Tue, 24 Sep 2019 20:23:56 +0100 Subject: [PATCH 052/422] [nhk] fix video extraction(closes #22249)(closes #22353) --- youtube_dl/extractor/nhk.py | 4 ++-- youtube_dl/extractor/piksel.py | 14 +++++++++++--- 2 files changed, 13 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/nhk.py b/youtube_dl/extractor/nhk.py index 241412f98..cce4bb472 100644 --- a/youtube_dl/extractor/nhk.py +++ b/youtube_dl/extractor/nhk.py @@ -60,8 +60,8 @@ class NhkVodIE(InfoExtractor): if is_video: info.update({ '_type': 'url_transparent', - 'ie_key': 'Ooyala', - 'url': 'ooyala:' + episode['vod_id'], + 'ie_key': 'Piksel', + 'url': 'https://player.piksel.com/v/refid/nhkworld/prefid/' + episode['vod_id'], }) else: audio = episode['audio'] diff --git a/youtube_dl/extractor/piksel.py b/youtube_dl/extractor/piksel.py index 401298cb8..88b6859b0 100644 --- a/youtube_dl/extractor/piksel.py +++ b/youtube_dl/extractor/piksel.py @@ -15,7 +15,7 @@ from ..utils import ( class PikselIE(InfoExtractor): - _VALID_URL = r'https?://player\.piksel\.com/v/(?P[a-z0-9]+)' + _VALID_URL = r'https?://player\.piksel\.com/v/(?:refid/[^/]+/prefid/)?(?P[a-z0-9_]+)' _TESTS = [ { 'url': 'http://player.piksel.com/v/ums2867l', @@ -40,6 +40,11 @@ class PikselIE(InfoExtractor): 'timestamp': 1486171129, 'upload_date': '20170204' } + }, + { + # https://www3.nhk.or.jp/nhkworld/en/ondemand/video/2019240/ + 'url': 'http://player.piksel.com/v/refid/nhkworld/prefid/nw_vod_v_en_2019_240_20190823233000_02_1566873477', + 'only_matching': True, } ] @@ -52,8 +57,11 @@ class PikselIE(InfoExtractor): return mobj.group('url') def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + video_id = self._search_regex( + r'data-de-program-uuid=[\'"]([a-z0-9]+)', + webpage, 'program uuid', default=display_id) app_token = self._search_regex([ r'clientAPI\s*:\s*"([^"]+)"', r'data-de-api-key\s*=\s*"([^"]+)"' From 21d3c21e6272d6ec089fc76461151f042f51aba0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 25 Sep 2019 02:39:25 +0700 Subject: [PATCH 053/422] [nhk] Add support for clips --- youtube_dl/extractor/nhk.py | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/nhk.py b/youtube_dl/extractor/nhk.py index cce4bb472..6a2c6cb7b 100644 --- a/youtube_dl/extractor/nhk.py +++ b/youtube_dl/extractor/nhk.py @@ -10,6 +10,18 @@ class NhkVodIE(InfoExtractor): # Content available only for a limited period of time. Visit # https://www3.nhk.or.jp/nhkworld/en/ondemand/ for working samples. _TESTS = [{ + # clip + 'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/9999011/', + 'md5': '256a1be14f48d960a7e61e2532d95ec3', + 'info_dict': { + 'id': 'a95j5iza', + 'ext': 'mp4', + 'title': "Dining with the Chef - Chef Saito's Family recipe: MENCHI-KATSU", + 'description': 'md5:5aee4a9f9d81c26281862382103b0ea5', + 'timestamp': 1565965194, + 'upload_date': '20190816', + }, + }, { 'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/2015173/', 'only_matching': True, }, { @@ -19,7 +31,7 @@ class NhkVodIE(InfoExtractor): 'url': 'https://www3.nhk.or.jp/nhkworld/fr/ondemand/audio/plugin-20190404-1/', 'only_matching': True, }] - _API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sodesdlist/v7/episode/%s/%s/all%s.json' + _API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sod%slist/v7/episode/%s/%s/all%s.json' def _real_extract(self, url): lang, m_type, episode_id = re.match(self._VALID_URL, url).groups() @@ -28,7 +40,10 @@ class NhkVodIE(InfoExtractor): is_video = m_type == 'video' episode = self._download_json( - self._API_URL_TEMPLATE % ('v' if is_video else 'r', episode_id, lang, '/all' if is_video else ''), + self._API_URL_TEMPLATE % ( + 'v' if is_video else 'r', + 'clip' if episode_id[:4] == '9999' else 'esd', + episode_id, lang, '/all' if is_video else ''), episode_id, query={'apikey': 'EJfK8jdS57GqlupFgAfAAwr573q01y6k'})['data']['episodes'][0] title = episode.get('sub_title_clean') or episode['sub_title'] From 33c1c7d80fd99024879a5f087b55b24374385e43 Mon Sep 17 00:00:00 2001 From: sofutru <54445344+sofutru@users.noreply.github.com> Date: Wed, 25 Sep 2019 02:43:34 +0700 Subject: [PATCH 054/422] [youtube] Add support for owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya.b32.i2p (#22292) --- youtube_dl/extractor/youtube.py | 1 + 1 file changed, 1 insertion(+) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 05eea0e4e..a3364a14e 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -397,6 +397,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): (?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion/| (?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion/| (?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion/| + (?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p/| youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains (?:.*?\#/)? # handle anchor (#/) redirect urls (?: # the various things that can precede the ID: From 2a88a0c44d4b13eda5874e9b790891acce11ccf7 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Thu, 26 Sep 2019 11:44:57 +0100 Subject: [PATCH 055/422] [ted] check for resources validity and extract subtitled downloads(closes #22513) --- youtube_dl/extractor/ted.py | 82 +++++++++++++++++++++---------------- 1 file changed, 47 insertions(+), 35 deletions(-) diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index db5a4f44e..63e2455b2 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -182,20 +182,29 @@ class TEDIE(InfoExtractor): title = talk_info['title'].strip() - native_downloads = try_get( - talk_info, - (lambda x: x['downloads']['nativeDownloads'], - lambda x: x['nativeDownloads']), - dict) or {} + downloads = talk_info.get('downloads') or {} + native_downloads = downloads.get('nativeDownloads') or talk_info.get('nativeDownloads') or {} formats = [{ 'url': format_url, 'format_id': format_id, - 'format': format_id, } for (format_id, format_url) in native_downloads.items() if format_url is not None] + + subtitled_downloads = downloads.get('subtitledDownloads') or {} + for lang, subtitled_download in subtitled_downloads.items(): + for q in self._NATIVE_FORMATS: + q_url = subtitled_download.get(q) + if not q_url: + continue + formats.append({ + 'url': q_url, + 'format_id': '%s-%s' % (q, lang), + 'language': lang, + }) + if formats: for f in formats: - finfo = self._NATIVE_FORMATS.get(f['format_id']) + finfo = self._NATIVE_FORMATS.get(f['format_id'].split('-')[0]) if finfo: f.update(finfo) @@ -215,34 +224,7 @@ class TEDIE(InfoExtractor): http_url = None for format_id, resources in resources_.items(): - if format_id == 'h264': - for resource in resources: - h264_url = resource.get('file') - if not h264_url: - continue - bitrate = int_or_none(resource.get('bitrate')) - formats.append({ - 'url': h264_url, - 'format_id': '%s-%sk' % (format_id, bitrate), - 'tbr': bitrate, - }) - if re.search(r'\d+k', h264_url): - http_url = h264_url - elif format_id == 'rtmp': - streamer = talk_info.get('streamer') - if not streamer: - continue - for resource in resources: - formats.append({ - 'format_id': '%s-%s' % (format_id, resource.get('name')), - 'url': streamer, - 'play_path': resource['file'], - 'ext': 'flv', - 'width': int_or_none(resource.get('width')), - 'height': int_or_none(resource.get('height')), - 'tbr': int_or_none(resource.get('bitrate')), - }) - elif format_id == 'hls': + if format_id == 'hls': if not isinstance(resources, dict): continue stream_url = url_or_none(resources.get('stream')) @@ -251,6 +233,36 @@ class TEDIE(InfoExtractor): formats.extend(self._extract_m3u8_formats( stream_url, video_name, 'mp4', m3u8_id=format_id, fatal=False)) + else: + if not isinstance(resources, list): + continue + if format_id == 'h264': + for resource in resources: + h264_url = resource.get('file') + if not h264_url: + continue + bitrate = int_or_none(resource.get('bitrate')) + formats.append({ + 'url': h264_url, + 'format_id': '%s-%sk' % (format_id, bitrate), + 'tbr': bitrate, + }) + if re.search(r'\d+k', h264_url): + http_url = h264_url + elif format_id == 'rtmp': + streamer = talk_info.get('streamer') + if not streamer: + continue + for resource in resources: + formats.append({ + 'format_id': '%s-%s' % (format_id, resource.get('name')), + 'url': streamer, + 'play_path': resource['file'], + 'ext': 'flv', + 'width': int_or_none(resource.get('width')), + 'height': int_or_none(resource.get('height')), + 'tbr': int_or_none(resource.get('bitrate')), + }) m3u8_formats = list(filter( lambda f: f.get('protocol') == 'm3u8' and f.get('vcodec') != 'none', From cb3e4a2947a2df64f1192384e2460a0ee52fc1e4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 26 Sep 2019 23:11:02 +0700 Subject: [PATCH 056/422] [heise] Fix kaltura embeds extraction (closes #22514) --- youtube_dl/extractor/heise.py | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/heise.py b/youtube_dl/extractor/heise.py index d8a2f9d76..cbe564a3c 100644 --- a/youtube_dl/extractor/heise.py +++ b/youtube_dl/extractor/heise.py @@ -105,8 +105,7 @@ class HeiseIE(InfoExtractor): webpage, default=None) or self._html_search_meta( 'description', webpage) - kaltura_url = KalturaIE._extract_url(webpage) - if kaltura_url: + def _make_kaltura_result(kaltura_url): return { '_type': 'url_transparent', 'url': smuggle_url(kaltura_url, {'source_url': url}), @@ -115,6 +114,16 @@ class HeiseIE(InfoExtractor): 'description': description, } + kaltura_url = KalturaIE._extract_url(webpage) + if kaltura_url: + return _make_kaltura_result(kaltura_url) + + kaltura_id = self._search_regex( + r'entry-id=(["\'])(?P(?:(?!\1).)+)\1', webpage, 'kaltura id', + default=None, group='id') + if kaltura_id: + return _make_kaltura_result('kaltura:2238431:%s' % kaltura_id) + yt_urls = YoutubeIE._extract_urls(webpage) if yt_urls: return self.playlist_from_matches( From 8130ac42e500643e03faaae512166fe71387473d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 26 Sep 2019 23:15:06 +0700 Subject: [PATCH 057/422] [openload] PEP 8 --- youtube_dl/extractor/openload.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index 46956e550..1fe581780 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -362,7 +362,7 @@ class OpenloadIE(InfoExtractor): }, { 'url': 'https://oload.services/embed/bs1NWj1dCag/', 'only_matching': True, -}, { + }, { 'url': 'https://oload.online/f/W8o2UfN1vNY/', 'only_matching': True, }, { From 6483fbd336839c45a376d08d8f4a34e97d581e5e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 28 Sep 2019 00:04:52 +0700 Subject: [PATCH 058/422] [vk] Fix extraction (closes #22522) --- youtube_dl/extractor/vk.py | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index f57ed2288..8b6dc0e24 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -403,8 +403,17 @@ class VKIE(VKBaseIE): data = self._parse_json( self._search_regex( r'var\s+playerParams\s*=\s*({.+?})\s*;\s*\n', info_page, - 'player params'), - video_id)['params'][0] + 'player params', default='{}'), + video_id) + if data: + data = data['params'][0] + + # - [ ] I'm reporting a broken site support -- [ ] I've verified that I'm running youtube-dl version **2019.09.12.1** +- [ ] I've verified that I'm running youtube-dl version **2019.09.28** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar issues including closed ones @@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.09.12.1 + [debug] youtube-dl version 2019.09.28 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/2_site_support_request.md b/.github/ISSUE_TEMPLATE/2_site_support_request.md index 9babe0360..6116acc79 100644 --- a/.github/ISSUE_TEMPLATE/2_site_support_request.md +++ b/.github/ISSUE_TEMPLATE/2_site_support_request.md @@ -19,7 +19,7 @@ labels: 'site-support-request' - [ ] I'm reporting a new site support request -- [ ] I've verified that I'm running youtube-dl version **2019.09.12.1** +- [ ] I've verified that I'm running youtube-dl version **2019.09.28** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that none of provided URLs violate any copyrights - [ ] I've searched the bugtracker for similar site support requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/3_site_feature_request.md b/.github/ISSUE_TEMPLATE/3_site_feature_request.md index 72322fe26..79d1a7f3c 100644 --- a/.github/ISSUE_TEMPLATE/3_site_feature_request.md +++ b/.github/ISSUE_TEMPLATE/3_site_feature_request.md @@ -18,13 +18,13 @@ title: '' - [ ] I'm reporting a site feature request -- [ ] I've verified that I'm running youtube-dl version **2019.09.12.1** +- [ ] I've verified that I'm running youtube-dl version **2019.09.28** - [ ] I've searched the bugtracker for similar site feature requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/4_bug_report.md b/.github/ISSUE_TEMPLATE/4_bug_report.md index da7f2cf93..9bda3d440 100644 --- a/.github/ISSUE_TEMPLATE/4_bug_report.md +++ b/.github/ISSUE_TEMPLATE/4_bug_report.md @@ -18,7 +18,7 @@ title: '' - [ ] I'm reporting a broken site support issue -- [ ] I've verified that I'm running youtube-dl version **2019.09.12.1** +- [ ] I've verified that I'm running youtube-dl version **2019.09.28** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar bug reports including closed ones @@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.09.12.1 + [debug] youtube-dl version 2019.09.28 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/5_feature_request.md b/.github/ISSUE_TEMPLATE/5_feature_request.md index d41022b9f..581344917 100644 --- a/.github/ISSUE_TEMPLATE/5_feature_request.md +++ b/.github/ISSUE_TEMPLATE/5_feature_request.md @@ -19,13 +19,13 @@ labels: 'request' - [ ] I'm reporting a feature request -- [ ] I've verified that I'm running youtube-dl version **2019.09.12.1** +- [ ] I've verified that I'm running youtube-dl version **2019.09.28** - [ ] I've searched the bugtracker for similar feature requests including closed ones diff --git a/ChangeLog b/ChangeLog index 20b0b9ae2..80681a9ae 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version +version 2019.09.28 Core * [YoutubeDL] Honour all --get-* options with --flat-playlist (#22493) diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 18bddc138..35275278b 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -98,6 +98,8 @@ - **Bigflix** - **Bild**: Bild.de - **BiliBili** + - **BilibiliAudio** + - **BilibiliAudioAlbum** - **BioBioChileTV** - **BIQLE** - **BitChute** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index df82cdf0f..c3eafb068 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.09.12.1' +__version__ = '2019.09.28' From 72fd4d0c6a926b4755dfb02a39c76766b0589213 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 29 Sep 2019 21:57:08 +0700 Subject: [PATCH 061/422] [nonktube] Fix extraction (closes #22544) --- youtube_dl/extractor/nonktube.py | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/nonktube.py b/youtube_dl/extractor/nonktube.py index 63e58aae2..ca1424e06 100644 --- a/youtube_dl/extractor/nonktube.py +++ b/youtube_dl/extractor/nonktube.py @@ -25,9 +25,14 @@ class NonkTubeIE(NuevoBaseIE): def _real_extract(self, url): video_id = self._match_id(url) - info = self._extract_nuevo( - 'https://www.nonktube.com/media/nuevo/econfig.php?key=%s' - % video_id, video_id) + webpage = self._download_webpage(url, video_id) - info['age_limit'] = 18 + title = self._og_search_title(webpage) + info = self._parse_html5_media_entries(url, webpage, video_id)[0] + + info.update({ + 'id': video_id, + 'title': title, + 'age_limit': 18, + }) return info From 326ae4ff96ca5663cca273126f95bd7eecf5a012 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 29 Sep 2019 23:03:39 +0700 Subject: [PATCH 062/422] [viewlift] Improve extraction (closes #22545) --- youtube_dl/extractor/viewlift.py | 46 +++++++++++++++++++++++++++----- 1 file changed, 39 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/viewlift.py b/youtube_dl/extractor/viewlift.py index c43d1a1e8..391419d9e 100644 --- a/youtube_dl/extractor/viewlift.py +++ b/youtube_dl/extractor/viewlift.py @@ -13,11 +13,12 @@ from ..utils import ( js_to_json, parse_age_limit, parse_duration, + try_get, ) class ViewLiftBaseIE(InfoExtractor): - _DOMAINS_REGEX = r'(?:snagfilms|snagxtreme|funnyforfree|kiddovid|winnersview|(?:monumental|lax)sportsnetwork|vayafilm)\.com|hoichoi\.tv' + _DOMAINS_REGEX = r'(?:(?:main\.)?snagfilms|snagxtreme|funnyforfree|kiddovid|winnersview|(?:monumental|lax)sportsnetwork|vayafilm)\.com|hoichoi\.tv' class ViewLiftEmbedIE(ViewLiftBaseIE): @@ -113,7 +114,7 @@ class ViewLiftEmbedIE(ViewLiftBaseIE): class ViewLiftIE(ViewLiftBaseIE): - _VALID_URL = r'https?://(?:www\.)?(?P%s)/(?:films/title|show|(?:news/)?videos?)/(?P[^?#]+)' % ViewLiftBaseIE._DOMAINS_REGEX + _VALID_URL = r'https?://(?:www\.)?(?P%s)(?:/(?:films/title|show|(?:news/)?videos?))?/(?P[^?#]+)' % ViewLiftBaseIE._DOMAINS_REGEX _TESTS = [{ 'url': 'http://www.snagfilms.com/films/title/lost_for_life', 'md5': '19844f897b35af219773fd63bdec2942', @@ -128,7 +129,7 @@ class ViewLiftIE(ViewLiftBaseIE): 'categories': 'mincount:3', 'age_limit': 14, 'upload_date': '20150421', - 'timestamp': 1429656819, + 'timestamp': 1429656820, } }, { 'url': 'http://www.snagfilms.com/show/the_world_cut_project/india', @@ -141,10 +142,26 @@ class ViewLiftIE(ViewLiftBaseIE): 'description': 'md5:5c168c5a8f4719c146aad2e0dfac6f5f', 'thumbnail': r're:^https?://.*\.jpg', 'duration': 979, - 'categories': 'mincount:2', 'timestamp': 1399478279, 'upload_date': '20140507', } + }, { + 'url': 'http://main.snagfilms.com/augie_alone/s_2_ep_12_love', + 'info_dict': { + 'id': '00000148-7b53-de26-a9fb-fbf306f70020', + 'display_id': 'augie_alone/s_2_ep_12_love', + 'ext': 'mp4', + 'title': 'Augie, Alone:S. 2 Ep. 12 - Love', + 'description': 'md5:db2a5c72d994f16a780c1eb353a8f403', + 'thumbnail': r're:^https?://.*\.jpg', + 'duration': 107, + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'http://main.snagfilms.com/films/title/the_freebie', + 'only_matching': True, }, { # Film is not playable in your area. 'url': 'http://www.snagfilms.com/films/title/inside_mecca', @@ -181,7 +198,21 @@ class ViewLiftIE(ViewLiftBaseIE): gist = content_data['gist'] film_id = gist['id'] title = gist['title'] - video_assets = content_data['streamingInfo']['videoAssets'] + video_assets = try_get( + content_data, lambda x: x['streamingInfo']['videoAssets'], dict) + if not video_assets: + token = self._download_json( + 'https://prod-api.viewlift.com/identity/anonymous-token', + film_id, 'Downloading authorization token', + query={'site': 'snagfilms'})['authorizationToken'] + video_assets = self._download_json( + 'https://prod-api.viewlift.com/entitlement/video/status', + film_id, headers={ + 'Authorization': token, + 'Referer': url, + }, query={ + 'id': film_id + })['video']['streamingInfo']['videoAssets'] formats = [] mpeg_video_assets = video_assets.get('mpeg') or [] @@ -241,8 +272,9 @@ class ViewLiftIE(ViewLiftBaseIE): if category.get('title')] break else: - title = self._search_regex( - r'itemprop="title">([^<]+)<', webpage, 'title') + title = self._html_search_regex( + (r'itemprop="title">([^<]+)<', + r'(?s)itemprop="title">(.+?)(.+?)', webpage, 'description', default=None) or self._og_search_description(webpage) From 2906631e1230617883cdef8e227b369a9c98c9fb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 1 Oct 2019 23:16:46 +0700 Subject: [PATCH 063/422] [viewlift] Fix URL matching --- youtube_dl/extractor/viewlift.py | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/youtube_dl/extractor/viewlift.py b/youtube_dl/extractor/viewlift.py index 391419d9e..851ad936c 100644 --- a/youtube_dl/extractor/viewlift.py +++ b/youtube_dl/extractor/viewlift.py @@ -179,6 +179,10 @@ class ViewLiftIE(ViewLiftBaseIE): 'only_matching': True, }] + @classmethod + def suitable(cls, url): + return False if ViewLiftEmbedIE.suitable(url) else super(ViewLiftIE, cls).suitable(url) + def _real_extract(self, url): domain, display_id = re.match(self._VALID_URL, url).groups() From 74bc299453884bc4e802ca225815d3134b9510cf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 2 Oct 2019 02:03:22 +0700 Subject: [PATCH 064/422] [teachable] Skip login when already logged in (closes #22572) --- youtube_dl/extractor/teachable.py | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/teachable.py b/youtube_dl/extractor/teachable.py index c1a9deafe..7d2e34b3b 100644 --- a/youtube_dl/extractor/teachable.py +++ b/youtube_dl/extractor/teachable.py @@ -48,6 +48,16 @@ class TeachableBaseIE(InfoExtractor): 'https://%s/sign_in' % site, None, 'Downloading %s login page' % site) + def is_logged(webpage): + return any(re.search(p, webpage) for p in ( + r'class=["\']user-signout', + r']+\bhref=["\']/sign_out', + r'Log\s+[Oo]ut\s*<')) + + if is_logged(login_page): + self._logged_in = True + return + login_url = compat_str(urlh.geturl()) login_form = self._hidden_inputs(login_page) @@ -78,10 +88,7 @@ class TeachableBaseIE(InfoExtractor): 'Go to https://%s/ and accept.' % (site, site), expected=True) # Successful login - if any(re.search(p, response) for p in ( - r'class=["\']user-signout', - r']+\bhref=["\']/sign_out', - r'>\s*Log out\s*<')): + if is_logged(response): self._logged_in = True return From 25e911a968f6675a2c06f0d60a09a86972aadc40 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 3 Oct 2019 00:53:07 +0700 Subject: [PATCH 065/422] [extractor/common] Make _is_valid_url more relaxed --- youtube_dl/extractor/common.py | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 859786617..50d48c40d 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1424,12 +1424,10 @@ class InfoExtractor(object): try: self._request_webpage(url, video_id, 'Checking %s URL' % item, headers=headers) return True - except ExtractorError as e: - if isinstance(e.cause, compat_urllib_error.URLError): - self.to_screen( - '%s: %s URL is invalid, skipping' % (video_id, item)) - return False - raise + except ExtractorError: + self.to_screen( + '%s: %s URL is invalid, skipping' % (video_id, item)) + return False def http_scheme(self): """ Either "http:" or "https:", depending on the user's preferences """ From aaf9d904aa77bfe60714393c0ab413c32cca8a39 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 3 Oct 2019 00:55:46 +0700 Subject: [PATCH 066/422] [orf:tvthek] Make manifest requests non fatal (refs #22578) --- youtube_dl/extractor/orf.py | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py index 499be0029..3425f7602 100644 --- a/youtube_dl/extractor/orf.py +++ b/youtube_dl/extractor/orf.py @@ -86,12 +86,13 @@ class ORFTVthekIE(InfoExtractor): if value: format_id_list.append(value) format_id = '-'.join(format_id_list) - if determine_ext(fd['src']) == 'm3u8': + ext = determine_ext(src) + if ext == 'm3u8': formats.extend(self._extract_m3u8_formats( - fd['src'], video_id, 'mp4', m3u8_id=format_id)) - elif determine_ext(fd['src']) == 'f4m': + src, video_id, 'mp4', m3u8_id=format_id, fatal=False)) + elif ext == 'f4m': formats.extend(self._extract_f4m_formats( - fd['src'], video_id, f4m_id=format_id)) + src, video_id, f4m_id=format_id, fatal=False)) else: formats.append({ 'format_id': format_id, From 894b3826f5a2e1742010c20554a6a1b9e98a51ee Mon Sep 17 00:00:00 2001 From: sofutru <54445344+sofutru@users.noreply.github.com> Date: Fri, 4 Oct 2019 18:52:15 +0700 Subject: [PATCH 067/422] [youtube] Add support for yt.lelux.fi (#22597) --- youtube_dl/extractor/youtube.py | 1 + 1 file changed, 1 insertion(+) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index a3364a14e..6bd56f340 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -391,6 +391,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): (?:www\.)?tube\.poal\.co/| (?:www\.)?vid\.wxzm\.sx/| (?:www\.)?yt\.elukerio\.org/| + (?:www\.)?yt\.lelux\.fi/| (?:www\.)?kgg2m7yk5aybusll\.onion/| (?:www\.)?qklhadlycap4cnod\.onion/| (?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion/| From ca20b1304818a8d2d8eadfbe6f5387284e7ebc4d Mon Sep 17 00:00:00 2001 From: Martin Polden Date: Fri, 4 Oct 2019 13:57:18 +0200 Subject: [PATCH 068/422] [nrktv:seriebase] Fix extraction (#22596) --- youtube_dl/extractor/nrk.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py index 5f43e692f..60933f069 100644 --- a/youtube_dl/extractor/nrk.py +++ b/youtube_dl/extractor/nrk.py @@ -406,7 +406,7 @@ class NRKTVSerieBaseIE(InfoExtractor): def _extract_series(self, webpage, display_id, fatal=True): config = self._parse_json( self._search_regex( - (r'INITIAL_DATA_*\s*=\s*({.+?})\s*;', + (r'INITIAL_DATA(?:_V\d)?_*\s*=\s*({.+?})\s*;', r'({.+?})\s*,\s*"[^"]+"\s*\)\s*'), webpage, 'config', default='{}' if not fatal else NO_DEFAULT), display_id, fatal=False) From 9679a62a283f1384c7572ec78f7996e1276d5d7a Mon Sep 17 00:00:00 2001 From: kr4ssi <44404263+kr4ssi@users.noreply.github.com> Date: Fri, 4 Oct 2019 13:57:51 +0200 Subject: [PATCH 069/422] [openload] Add support for oload.monster (#22592) --- youtube_dl/extractor/openload.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index 1fe581780..66e38cdb4 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -246,7 +246,7 @@ class OpenloadIE(InfoExtractor): _DOMAINS = r''' (?: openload\.(?:co|io|link|pw)| - oload\.(?:tv|best|biz|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|online|press|pw|life|live|space|services|website|vip)| + oload\.(?:tv|best|biz|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|online|monster|press|pw|life|live|space|services|website|vip)| oladblock\.(?:services|xyz|me)|openloed\.co ) ''' @@ -365,6 +365,9 @@ class OpenloadIE(InfoExtractor): }, { 'url': 'https://oload.online/f/W8o2UfN1vNY/', 'only_matching': True, + }, { + 'url': 'https://oload.monster/f/W8o2UfN1vNY/', + 'only_matching': True, }, { 'url': 'https://oload.press/embed/drTBl1aOTvk/', 'only_matching': True, From 76e510b92c4a1c4b0001f892504ba2cbb4b8d486 Mon Sep 17 00:00:00 2001 From: sofutru <54445344+sofutru@users.noreply.github.com> Date: Fri, 4 Oct 2019 19:01:03 +0700 Subject: [PATCH 070/422] [youtube] Remove support for invidious.enkirton.net (#22543) --- youtube_dl/extractor/youtube.py | 1 - 1 file changed, 1 deletion(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 6bd56f340..5e397324b 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -383,7 +383,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): (?:(?:www|no)\.)?invidiou\.sh/| (?:(?:www|fi|de)\.)?invidious\.snopyta\.org/| (?:www\.)?invidious\.kabi\.tk/| - (?:www\.)?invidious\.enkirton\.net/| (?:www\.)?invidious\.13ad\.de/| (?:www\.)?invidious\.mastodon\.host/| (?:www\.)?invidious\.nixnet\.xyz/| From 4e72d02f39f0d8e9ae9bbe8233c157bef3b58bdf Mon Sep 17 00:00:00 2001 From: Stephan Date: Fri, 4 Oct 2019 14:05:35 +0200 Subject: [PATCH 071/422] [xvideos] Extend _VALID_URL (#22471) --- youtube_dl/extractor/xvideos.py | 39 ++++++++++++++++++++++++++++++++- 1 file changed, 38 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/xvideos.py b/youtube_dl/extractor/xvideos.py index 166bcf443..8fc64914c 100644 --- a/youtube_dl/extractor/xvideos.py +++ b/youtube_dl/extractor/xvideos.py @@ -17,7 +17,8 @@ class XVideosIE(InfoExtractor): _VALID_URL = r'''(?x) https?:// (?: - (?:www\.)?xvideos\.com/video| + (?:[^/]+\.)?xvideos2?\.com/video| + (?:www\.)?xvideos\.es/video| flashservice\.xvideos\.com/embedframe/| static-hw\.xvideos\.com/swf/xv-player\.swf\?.*?\bid_video= ) @@ -39,6 +40,42 @@ class XVideosIE(InfoExtractor): }, { 'url': 'http://static-hw.xvideos.com/swf/xv-player.swf?id_video=4588838', 'only_matching': True, + }, { + 'url': 'http://xvideos.com/video4588838/biker_takes_his_girl', + 'only_matching': True + }, { + 'url': 'https://xvideos.com/video4588838/biker_takes_his_girl', + 'only_matching': True + }, { + 'url': 'https://xvideos.es/video4588838/biker_takes_his_girl', + 'only_matching': True + }, { + 'url': 'https://www.xvideos.es/video4588838/biker_takes_his_girl', + 'only_matching': True + }, { + 'url': 'http://xvideos.es/video4588838/biker_takes_his_girl', + 'only_matching': True + }, { + 'url': 'http://www.xvideos.es/video4588838/biker_takes_his_girl', + 'only_matching': True + }, { + 'url': 'http://fr.xvideos.com/video4588838/biker_takes_his_girl', + 'only_matching': True + }, { + 'url': 'https://fr.xvideos.com/video4588838/biker_takes_his_girl', + 'only_matching': True + }, { + 'url': 'http://it.xvideos.com/video4588838/biker_takes_his_girl', + 'only_matching': True + }, { + 'url': 'https://it.xvideos.com/video4588838/biker_takes_his_girl', + 'only_matching': True + }, { + 'url': 'http://de.xvideos.com/video4588838/biker_takes_his_girl', + 'only_matching': True + }, { + 'url': 'https://de.xvideos.com/video4588838/biker_takes_his_girl', + 'only_matching': True }] def _real_extract(self, url): From c2915de82e0ee793330d553899347ec54a4b834e Mon Sep 17 00:00:00 2001 From: Patrice Levesque Date: Fri, 4 Oct 2019 08:14:31 -0400 Subject: [PATCH 072/422] [telequebec] Add support for coucou.telequebec.tv (#22482) --- youtube_dl/extractor/telequebec.py | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/telequebec.py b/youtube_dl/extractor/telequebec.py index 6965c127b..911385d01 100644 --- a/youtube_dl/extractor/telequebec.py +++ b/youtube_dl/extractor/telequebec.py @@ -22,7 +22,13 @@ class TeleQuebecBaseIE(InfoExtractor): class TeleQuebecIE(TeleQuebecBaseIE): - _VALID_URL = r'https?://zonevideo\.telequebec\.tv/media/(?P\d+)' + _VALID_URL = r'''(?x) + https?:// + (?: + zonevideo\.telequebec\.tv/media| + coucou\.telequebec\.tv/videos + )/(?P\d+) + ''' _TESTS = [{ # available till 01.01.2023 'url': 'http://zonevideo.telequebec.tv/media/37578/un-petit-choc-et-puis-repart/un-chef-a-la-cabane', @@ -41,6 +47,9 @@ class TeleQuebecIE(TeleQuebecBaseIE): # no description 'url': 'http://zonevideo.telequebec.tv/media/30261', 'only_matching': True, + }, { + 'url': 'https://coucou.telequebec.tv/videos/41788/idee-de-genie/l-heure-du-bain', + 'only_matching': True, }] def _real_extract(self, url): From b64045cd2a564bb44ef917803678ca362f412eb4 Mon Sep 17 00:00:00 2001 From: Andrew Morgan <1342360+anoadragon453@users.noreply.github.com> Date: Fri, 4 Oct 2019 13:17:16 +0100 Subject: [PATCH 073/422] [peertube] Update instances (#22414) --- youtube_dl/extractor/peertube.py | 397 +++++++++++++++++++++++++++---- 1 file changed, 347 insertions(+), 50 deletions(-) diff --git a/youtube_dl/extractor/peertube.py b/youtube_dl/extractor/peertube.py index b50543e32..d3a83ea2b 100644 --- a/youtube_dl/extractor/peertube.py +++ b/youtube_dl/extractor/peertube.py @@ -18,81 +18,385 @@ from ..utils import ( class PeerTubeIE(InfoExtractor): _INSTANCES_RE = r'''(?: # Taken from https://instances.joinpeertube.org/instances + peertube\.rainbowswingers\.net| + tube\.stanisic\.nl| + peer\.suiri\.us| + medias\.libox\.fr| + videomensoif\.ynh\.fr| + peertube\.travelpandas\.eu| + peertube\.rachetjay\.fr| + peertube\.montecsys\.fr| + tube\.eskuero\.me| + peer\.tube| + peertube\.umeahackerspace\.se| + tube\.nx-pod\.de| + video\.monsieurbidouille\.fr| tube\.openalgeria\.org| - peertube\.pointsecu\.fr| + vid\.lelux\.fi| + video\.anormallostpod\.ovh| + tube\.crapaud-fou\.org| + peertube\.stemy\.me| + lostpod\.space| + exode\.me| + peertube\.snargol\.com| + vis\.ion\.ovh| + videosdulib\.re| + v\.mbius\.io| + videos\.judrey\.eu| + peertube\.osureplayviewer\.xyz| + peertube\.mathieufamily\.ovh| + www\.videos-libr\.es| + fightforinfo\.com| + peertube\.fediverse\.ru| + peertube\.oiseauroch\.fr| + video\.nesven\.eu| + v\.bearvideo\.win| + video\.qoto\.org| + justporn\.cc| + video\.vny\.fr| + peervideo\.club| + tube\.taker\.fr| + peertube\.chantierlibre\.org| + tube\.ipfixe\.info| + tube\.kicou\.info| + tube\.dodsorf\.as| + videobit\.cc| + video\.yukari\.moe| + videos\.elbinario\.net| + hkvideo\.live| + pt\.tux\.tf| + www\.hkvideo\.live| + FIGHTFORINFO\.com| + pt\.765racing\.com| + peertube\.gnumeria\.eu\.org| + nordenmedia\.com| + peertube\.co\.uk| + tube\.darfweb\.eu| + tube\.kalah-france\.org| + 0ch\.in| + vod\.mochi\.academy| + film\.node9\.org| + peertube\.hatthieves\.es| + video\.fitchfamily\.org| + peertube\.ddns\.net| + video\.ifuncle\.kr| + video\.fdlibre\.eu| + tube\.22decembre\.eu| + peertube\.harmoniescreatives\.com| + tube\.fabrigli\.fr| + video\.thedwyers\.co| + video\.bruitbruit\.com| + peertube\.foxfam\.club| + peer\.philoxweb\.be| + videos\.bugs\.social| + peertube\.malbert\.xyz| + peertube\.bilange\.ca| + libretube\.net| + diytelevision\.com| + peertube\.fedilab\.app| + libre\.video| + video\.mstddntfdn\.online| + us\.tv| + peertube\.sl-network\.fr| + peertube\.dynlinux\.io| + peertube\.david\.durieux\.family| + peertube\.linuxrocks\.online| + peerwatch\.xyz| + v\.kretschmann\.social| + tube\.otter\.sh| + yt\.is\.nota\.live| + tube\.dragonpsi\.xyz| + peertube\.boneheadmedia\.com| + videos\.funkwhale\.audio| + watch\.44con\.com| + peertube\.gcaillaut\.fr| + peertube\.icu| + pony\.tube| + spacepub\.space| + tube\.stbr\.io| + v\.mom-gay\.faith| + tube\.port0\.xyz| + peertube\.simounet\.net| + play\.jergefelt\.se| + peertube\.zeteo\.me| + tube\.danq\.me| + peertube\.kerenon\.com| + tube\.fab-l3\.org| + tube\.calculate\.social| + peertube\.mckillop\.org| + tube\.netzspielplatz\.de| + vod\.ksite\.de| + peertube\.laas\.fr| + tube\.govital\.net| + peertube\.stephenson\.cc| + bistule\.nohost\.me| + peertube\.kajalinifi\.de| + video\.ploud\.jp| + video\.omniatv\.com| + peertube\.ffs2play\.fr| + peertube\.leboulaire\.ovh| + peertube\.tronic-studio\.com| + peertube\.public\.cat| + peertube\.metalbanana\.net| + video\.1000i100\.fr| + peertube\.alter-nativ-voll\.de| + tube\.pasa\.tf| + tube\.worldofhauru\.xyz| + pt\.kamp\.site| + peertube\.teleassist\.fr| + videos\.mleduc\.xyz| + conf\.tube| + media\.privacyinternational\.org| + pt\.forty-two\.nl| + video\.halle-leaks\.de| + video\.grosskopfgames\.de| + peertube\.schaeferit\.de| + peertube\.jackbot\.fr| + tube\.extinctionrebellion\.fr| + peertube\.f-si\.org| + video\.subak\.ovh| + videos\.koweb\.fr| + peertube\.zergy\.net| + peertube\.roflcopter\.fr| + peertube\.floss-marketing-school\.com| + vloggers\.social| + peertube\.iriseden\.eu| + videos\.ubuntu-paris\.org| + peertube\.mastodon\.host| + armstube\.com| + peertube\.s2s\.video| + peertube\.lol| + tube\.open-plug\.eu| + open\.tube| + peertube\.ch| + peertube\.normandie-libre\.fr| + peertube\.slat\.org| + video\.lacaveatonton\.ovh| + peertube\.uno| + peertube\.servebeer\.com| + peertube\.fedi\.quebec| + tube\.h3z\.jp| + tube\.plus200\.com| + peertube\.eric\.ovh| + tube\.metadocs\.cc| + tube\.unmondemeilleur\.eu| + gouttedeau\.space| + video\.antirep\.net| + nrop\.cant\.at| + tube\.ksl-bmx\.de| + tube\.plaf\.fr| + tube\.tchncs\.de| + video\.devinberg\.com| + hitchtube\.fr| + peertube\.kosebamse\.com| + yunopeertube\.myddns\.me| + peertube\.varney\.fr| + peertube\.anon-kenkai\.com| + tube\.maiti\.info| + tubee\.fr| + videos\.dinofly\.com| + toobnix\.org| + videotape\.me| + voca\.tube| + video\.heromuster\.com| + video\.lemediatv\.fr| + video\.up\.edu\.ph| + balafon\.video| + video\.ivel\.fr| + thickrips\.cloud| + pt\.laurentkruger\.fr| + video\.monarch-pass\.net| + peertube\.artica\.center| + video\.alternanet\.fr| + indymotion\.fr| + fanvid\.stopthatimp\.net| + video\.farci\.org| + v\.lesterpig\.com| + video\.okaris\.de| + tube\.pawelko\.net| + peertube\.mablr\.org| + tube\.fede\.re| + pytu\.be| + evertron\.tv| + devtube\.dev-wiki\.de| + raptube\.antipub\.org| + video\.selea\.se| + peertube\.mygaia\.org| + video\.oh14\.de| + peertube\.livingutopia\.org| + peertube\.the-penguin\.de| + tube\.thechangebook\.org| + tube\.anjara\.eu| + pt\.pube\.tk| + video\.samedi\.pm| + mplayer\.demouliere\.eu| + widemus\.de| + peertube\.me| + peertube\.zapashcanon\.fr| + video\.latavernedejohnjohn\.fr| + peertube\.pcservice46\.fr| + peertube\.mazzonetto\.eu| + video\.irem\.univ-paris-diderot\.fr| + video\.livecchi\.cloud| + alttube\.fr| + video\.coop\.tools| + video\.cabane-libre\.org| + peertube\.openstreetmap\.fr| + videos\.alolise\.org| + irrsinn\.video| + video\.antopie\.org| + scitech\.video| + tube2\.nemsia\.org| + video\.amic37\.fr| + peertube\.freeforge\.eu| + video\.arbitrarion\.com| + video\.datsemultimedia\.com| + stoptrackingus\.tv| + peertube\.ricostrongxxx\.com| + docker\.videos\.lecygnenoir\.info| + peertube\.togart\.de| + tube\.postblue\.info| + videos\.domainepublic\.net| + peertube\.cyber-tribal\.com| + video\.gresille\.org| + peertube\.dsmouse\.net| + cinema\.yunohost\.support| + tube\.theocevaer\.fr| + repro\.video| + tube\.4aem\.com| + quaziinc\.com| + peertube\.metawurst\.space| + videos\.wakapo\.com| + video\.ploud\.fr| + video\.freeradical\.zone| + tube\.valinor\.fr| + refuznik\.video| + pt\.kircheneuenburg\.de| + peertube\.asrun\.eu| + peertube\.lagob\.fr| + videos\.side-ways\.net| + 91video\.online| + video\.valme\.io| + video\.taboulisme\.com| + videos-libr\.es| + tv\.mooh\.fr| + nuage\.acostey\.fr| + video\.monsieur-a\.fr| + peertube\.librelois\.fr| + videos\.pair2jeux\.tube| + videos\.pueseso\.club| + peer\.mathdacloud\.ovh| + media\.assassinate-you\.net| + vidcommons\.org| + ptube\.rousset\.nom\.fr| + tube\.cyano\.at| + videos\.squat\.net| + video\.iphodase\.fr| + peertube\.makotoworkshop\.org| + peertube\.serveur\.slv-valbonne\.fr| + vault\.mle\.party| + hostyour\.tv| + videos\.hack2g2\.fr| + libre\.tube| + pire\.artisanlogiciel\.net| + videos\.numerique-en-commun\.fr| + video\.netsyms\.com| + video\.die-partei\.social| + video\.writeas\.org| + peertube\.swarm\.solvingmaz\.es| + tube\.pericoloso\.ovh| + watching\.cypherpunk\.observer| + videos\.adhocmusic\.com| + tube\.rfc1149\.net| + peertube\.librelabucm\.org| + videos\.numericoop\.fr| + peertube\.koehn\.com| + peertube\.anarchmusicall\.net| + tube\.kampftoast\.de| + vid\.y-y\.li| + peertube\.xtenz\.xyz| + diode\.zone| + tube\.egf\.mn| + peertube\.nomagic\.uk| + visionon\.tv| + videos\.koumoul\.com| + video\.rastapuls\.com| + video\.mantlepro\.com| + video\.deadsuperhero\.com| + peertube\.musicstudio\.pro| + peertube\.we-keys\.fr| + artitube\.artifaille\.fr| + peertube\.ethernia\.net| + tube\.midov\.pl| + peertube\.fr| + watch\.snoot\.tube| + peertube\.donnadieu\.fr| + argos\.aquilenet\.fr| + tube\.nemsia\.org| + tube\.bruniau\.net| + videos\.darckoune\.moe| + tube\.traydent\.info| + dev\.videos\.lecygnenoir\.info| + peertube\.nayya\.org| + peertube\.live| + peertube\.mofgao\.space| + video\.lequerrec\.eu| + peertube\.amicale\.net| + aperi\.tube| + tube\.ac-lyon\.fr| + video\.lw1\.at| + www\.yiny\.org| + videos\.pofilo\.fr| + tube\.lou\.lt| + choob\.h\.etbus\.ch| + tube\.hoga\.fr| + peertube\.heberge\.fr| + video\.obermui\.de| + videos\.cloudfrancois\.fr| + betamax\.video| + video\.typica\.us| + tube\.piweb\.be| + video\.blender\.org| + peertube\.cat| + tube\.kdy\.ch| + pe\.ertu\.be| + peertube\.social| + videos\.lescommuns\.org| + tv\.datamol\.org| + videonaute\.fr| + dialup\.express| peertube\.nogafa\.org| - peertube\.pl| megatube\.lilomoino\.fr| peertube\.tamanoir\.foucry\.net| - peertube\.inapurna\.org| - peertube\.netzspielplatz\.de| - video\.deadsuperhero\.com| peertube\.devosi\.org| peertube\.1312\.media| - tube\.worldofhauru\.xyz| tube\.bootlicker\.party| skeptikon\.fr| - peertube\.geekshell\.fr| - tube\.opportunis\.me| - peertube\.peshane\.net| video\.blueline\.mg| tube\.homecomputing\.fr| - videos\.cloudfrancois\.fr| - peertube\.viviers-fibre\.net| tube\.ouahpiti\.info| video\.tedomum\.net| video\.g3l\.org| fontube\.fr| peertube\.gaialabs\.ch| - peertube\.extremely\.online| - peertube\.public-infrastructure\.eu| tube\.kher\.nl| peertube\.qtg\.fr| - tube\.22decembre\.eu| - facegirl\.me| video\.migennes\.net| - janny\.moe| tube\.p2p\.legal| - video\.atlanti\.se| troll\.tv| - peertube\.geekael\.fr| - vid\.leotindall\.com| - video\.anormallostpod\.ovh| - p-tube\.h3z\.jp| - tube\.darfweb\.eu| videos\.iut-orsay\.fr| peertube\.solidev\.net| - videos\.symphonie-of-code\.fr| - testtube\.ortg\.de| videos\.cemea\.org| - peertube\.gwendalavir\.eu| video\.passageenseine\.fr| videos\.festivalparminous\.org| peertube\.touhoppai\.moe| - peertube\.duckdns\.org| sikke\.fi| - peertube\.mastodon\.host| - firedragonvideos\.com| - vidz\.dou\.bet| - peertube\.koehn\.com| peer\.hostux\.social| share\.tube| peertube\.walkingmountains\.fr| - medias\.libox\.fr| - peertube\.moe| - peertube\.xyz| - jp\.peertube\.network| videos\.benpro\.fr| - tube\.otter\.sh| - peertube\.angristan\.xyz| peertube\.parleur\.net| - peer\.ecutsa\.fr| peertube\.heraut\.eu| - peertube\.tifox\.fr| - peertube\.maly\.io| - vod\.mochi\.academy| - exode\.me| - coste\.video| tube\.aquilenet\.fr| peertube\.gegeweb\.eu| framatube\.org| @@ -100,18 +404,11 @@ class PeerTubeIE(InfoExtractor): tube\.conferences-gesticulees\.net| peertube\.datagueule\.tv| video\.lqdn\.fr| - meilleurtube\.delire\.party| tube\.mochi\.academy| - peertube\.dav\.li| media\.zat\.im| - pytu\.be| - peertube\.valvin\.fr| - peertube\.nsa\.ovh| video\.colibris-outilslibres\.org| - video\.hispagatos\.org| tube\.svnet\.fr| peertube\.video| - videos\.lecygnenoir\.info| peertube3\.cpy\.re| peertube2\.cpy\.re| videos\.tcit\.fr| @@ -126,7 +423,7 @@ class PeerTubeIE(InfoExtractor): (?P%s) ''' % (_INSTANCES_RE, _UUID_RE) _TESTS = [{ - 'url': 'https://peertube.moe/videos/watch/2790feb0-8120-4e63-9af3-c943c69f5e6c', + 'url': 'https://peertube.cpy.re/videos/watch/2790feb0-8120-4e63-9af3-c943c69f5e6c', 'md5': '80f24ff364cc9d333529506a263e7feb', 'info_dict': { 'id': '2790feb0-8120-4e63-9af3-c943c69f5e6c', From fd4db1ebc231b65bea91add4cd55ce564b05eee3 Mon Sep 17 00:00:00 2001 From: axelerometer <54915681+axelerometer@users.noreply.github.com> Date: Fri, 4 Oct 2019 15:22:01 +0300 Subject: [PATCH 074/422] [chaturbate] Extend _VALID_URL (#22309) --- youtube_dl/extractor/chaturbate.py | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/chaturbate.py b/youtube_dl/extractor/chaturbate.py index e2b828d8a..656e715ae 100644 --- a/youtube_dl/extractor/chaturbate.py +++ b/youtube_dl/extractor/chaturbate.py @@ -7,7 +7,7 @@ from ..utils import ExtractorError class ChaturbateIE(InfoExtractor): - _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?P[^/?#]+)' + _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?:fullvideo/?\?.*?\bb=)?(?P[^/?&#]+)' _TESTS = [{ 'url': 'https://www.chaturbate.com/siswet19/', 'info_dict': { @@ -21,6 +21,9 @@ class ChaturbateIE(InfoExtractor): 'skip_download': True, }, 'skip': 'Room is offline', + }, { + 'url': 'https://chaturbate.com/fullvideo/?b=caylin', + 'only_matching': True, }, { 'url': 'https://en.chaturbate.com/siswet19/', 'only_matching': True, @@ -32,7 +35,8 @@ class ChaturbateIE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage( - url, video_id, headers=self.geo_verification_headers()) + 'https://chaturbate.com/%s/' % video_id, video_id, + headers=self.geo_verification_headers()) m3u8_urls = [] From 0b87beefe60fb6ae52529603fd5826364146dfb7 Mon Sep 17 00:00:00 2001 From: Anh Nhan Nguyen Date: Fri, 4 Oct 2019 14:27:58 +0200 Subject: [PATCH 075/422] [gfycat] Extend _VALID_URL (#22225) --- youtube_dl/extractor/gfycat.py | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/gfycat.py b/youtube_dl/extractor/gfycat.py index bbe3cb283..18a30fe67 100644 --- a/youtube_dl/extractor/gfycat.py +++ b/youtube_dl/extractor/gfycat.py @@ -11,7 +11,7 @@ from ..utils import ( class GfycatIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?gfycat\.com/(?:ru/|ifr/|gifs/detail/)?(?P[^-/?#]+)' + _VALID_URL = r'https?://(?:(?:www|giant|thumbs)\.)?gfycat\.com/(?:ru/|ifr/|gifs/detail/)?(?P[^-/?#\.]+)' _TESTS = [{ 'url': 'http://gfycat.com/DeadlyDecisiveGermanpinscher', 'info_dict': { @@ -53,6 +53,12 @@ class GfycatIE(InfoExtractor): }, { 'url': 'https://gfycat.com/acceptablehappygoluckyharborporpoise-baseball', 'only_matching': True + }, { + 'url': 'https://thumbs.gfycat.com/acceptablehappygoluckyharborporpoise-size_restricted.gif', + 'only_matching': True + }, { + 'url': 'https://giant.gfycat.com/acceptablehappygoluckyharborporpoise.mp4', + 'only_matching': True }] def _real_extract(self, url): From 3a37f2c3be16bb75a12d0617b5bc80ee6cab0f61 Mon Sep 17 00:00:00 2001 From: bitraid Date: Fri, 4 Oct 2019 15:48:20 +0300 Subject: [PATCH 076/422] [wimp] Remove extractor (closes #22088) (#22091) --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/wimp.py | 54 ------------------------------ 2 files changed, 55 deletions(-) delete mode 100644 youtube_dl/extractor/wimp.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 44120cae2..a2d6e5314 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1413,7 +1413,6 @@ from .weibo import ( WeiboMobileIE ) from .weiqitv import WeiqiTVIE -from .wimp import WimpIE from .wistia import WistiaIE from .worldstarhiphop import WorldStarHipHopIE from .wsj import ( diff --git a/youtube_dl/extractor/wimp.py b/youtube_dl/extractor/wimp.py deleted file mode 100644 index ea234e3c5..000000000 --- a/youtube_dl/extractor/wimp.py +++ /dev/null @@ -1,54 +0,0 @@ -from __future__ import unicode_literals - -from .common import InfoExtractor -from .youtube import YoutubeIE - - -class WimpIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?wimp\.com/(?P[^/]+)' - _TESTS = [{ - 'url': 'http://www.wimp.com/maru-is-exhausted/', - 'md5': 'ee21217ffd66d058e8b16be340b74883', - 'info_dict': { - 'id': 'maru-is-exhausted', - 'ext': 'mp4', - 'title': 'Maru is exhausted.', - 'description': 'md5:57e099e857c0a4ea312542b684a869b8', - } - }, { - 'url': 'http://www.wimp.com/clowncar/', - 'md5': '5c31ad862a90dc5b1f023956faec13fe', - 'info_dict': { - 'id': 'cG4CEr2aiSg', - 'ext': 'webm', - 'title': 'Basset hound clown car...incredible!', - 'description': '5 of my Bassets crawled in this dog loo! www.bellinghambassets.com\n\nFor licensing/usage please contact: licensing(at)jukinmediadotcom', - 'upload_date': '20140303', - 'uploader': 'Gretchen Hoey', - 'uploader_id': 'gretchenandjeff1', - }, - 'add_ie': ['Youtube'], - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - youtube_id = self._search_regex( - (r"videoId\s*:\s*[\"']([0-9A-Za-z_-]{11})[\"']", - r'data-id=["\']([0-9A-Za-z_-]{11})'), - webpage, 'video URL', default=None) - if youtube_id: - return self.url_result(youtube_id, YoutubeIE.ie_key()) - - info_dict = self._extract_jwplayer_data( - webpage, video_id, require_title=False) - - info_dict.update({ - 'id': video_id, - 'title': self._og_search_title(webpage), - 'description': self._og_search_description(webpage), - }) - - return info_dict From 05446d483d089d0bc7fa3037900dadc856d3e687 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 4 Oct 2019 20:14:45 +0700 Subject: [PATCH 077/422] [telequebec:squat] Add support for squat.telequebec.tv (closes #18503) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/telequebec.py | 47 ++++++++++++++++++++++++++++++ 2 files changed, 48 insertions(+) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index a2d6e5314..8d3e433c3 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1129,6 +1129,7 @@ from .telegraaf import TelegraafIE from .telemb import TeleMBIE from .telequebec import ( TeleQuebecIE, + TeleQuebecSquatIE, TeleQuebecEmissionIE, TeleQuebecLiveIE, ) diff --git a/youtube_dl/extractor/telequebec.py b/youtube_dl/extractor/telequebec.py index 911385d01..ae9f66787 100644 --- a/youtube_dl/extractor/telequebec.py +++ b/youtube_dl/extractor/telequebec.py @@ -7,6 +7,7 @@ from ..utils import ( int_or_none, smuggle_url, try_get, + unified_timestamp, ) @@ -70,6 +71,52 @@ class TeleQuebecIE(TeleQuebecBaseIE): return info +class TeleQuebecSquatIE(InfoExtractor): + _VALID_URL = r'https://squat\.telequebec\.tv/videos/(?P\d+)' + _TESTS = [{ + 'url': 'https://squat.telequebec.tv/videos/9314', + 'info_dict': { + 'id': 'd59ae78112d542e793d83cc9d3a5b530', + 'ext': 'mp4', + 'title': 'Poupeflekta', + 'description': 'md5:2f0718f8d2f8fece1646ee25fb7bce75', + 'duration': 1351, + 'timestamp': 1569057600, + 'upload_date': '20190921', + 'series': 'Miraculous : Les Aventures de Ladybug et Chat Noir', + 'season': 'Saison 3', + 'season_number': 3, + 'episode_number': 57, + }, + 'params': { + 'skip_download': True, + }, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + video = self._download_json( + 'https://squat.api.telequebec.tv/v1/videos/%s' % video_id, + video_id) + + media_id = video['sourceId'] + + return { + '_type': 'url_transparent', + 'url': 'http://zonevideo.telequebec.tv/media/%s' % media_id, + 'ie_key': TeleQuebecIE.ie_key(), + 'id': media_id, + 'title': video.get('titre'), + 'description': video.get('description'), + 'timestamp': unified_timestamp(video.get('datePublication')), + 'series': video.get('container'), + 'season': video.get('saison'), + 'season_number': int_or_none(video.get('noSaison')), + 'episode_number': int_or_none(video.get('episode')), + } + + class TeleQuebecEmissionIE(TeleQuebecBaseIE): _VALID_URL = r'''(?x) https?:// From 4bf568d36cf516b38e4634e07bd8b4c3d33324f1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 5 Oct 2019 21:43:31 +0700 Subject: [PATCH 078/422] [pornhub:uservideos:upload] Fix extraction (closes #22619) --- youtube_dl/extractor/pornhub.py | 33 ++++++++++----------------------- 1 file changed, 10 insertions(+), 23 deletions(-) diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 11b8cfcf7..ba0ad7da2 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -403,6 +403,15 @@ class PornHubUserIE(PornHubPlaylistBaseIE): class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE): + @staticmethod + def _has_more(webpage): + return re.search( + r'''(?x) + ]+\bclass=["\']page_next| + ]+\brel=["\']next| + ]+\bid=["\']moreDataBtn + ''', webpage) is not None + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) host = mobj.group('host') @@ -411,13 +420,11 @@ class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE): page = int_or_none(self._search_regex( r'\bpage=(\d+)', url, 'page', default=None)) - page_url = self._make_page_url(url) - entries = [] for page_num in (page, ) if page is not None else itertools.count(1): try: webpage = self._download_webpage( - page_url, item_id, 'Downloading page %d' % page_num, + url, item_id, 'Downloading page %d' % page_num, query={'page': page_num}) except ExtractorError as e: if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404: @@ -547,18 +554,6 @@ class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE): if PornHubIE.suitable(url) or PornHubUserIE.suitable(url) or PornHubUserVideosUploadIE.suitable(url) else super(PornHubPagedVideoListIE, cls).suitable(url)) - def _make_page_url(self, url): - return url - - @staticmethod - def _has_more(webpage): - return re.search( - r'''(?x) - ]+\bclass=["\']page_next| - ]+\brel=["\']next| - ]+\bid=["\']moreDataBtn - ''', webpage) is not None - class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE): _VALID_URL = r'(?Phttps?://(?:[^/]+\.)?(?Ppornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P[^/]+)/videos/upload)' @@ -572,11 +567,3 @@ class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE): 'url': 'https://www.pornhub.com/model/zoe_ph/videos/upload', 'only_matching': True, }] - - def _make_page_url(self, url): - mobj = re.match(self._VALID_URL, url) - return '%s/ajax' % mobj.group('url') - - @staticmethod - def _has_more(webpage): - return True From 560d3b7d7c86a0bfff36d59cb977fd3c01b10ad8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 5 Oct 2019 22:04:49 +0700 Subject: [PATCH 079/422] [redtube] Improve metadata extraction (closes #22492, closes #22615) --- youtube_dl/extractor/redtube.py | 28 ++++++++++++++++------------ 1 file changed, 16 insertions(+), 12 deletions(-) diff --git a/youtube_dl/extractor/redtube.py b/youtube_dl/extractor/redtube.py index 10311a81a..5c84028ef 100644 --- a/youtube_dl/extractor/redtube.py +++ b/youtube_dl/extractor/redtube.py @@ -6,6 +6,7 @@ from .common import InfoExtractor from ..utils import ( ExtractorError, int_or_none, + merge_dicts, str_to_int, unified_strdate, url_or_none, @@ -45,11 +46,14 @@ class RedTubeIE(InfoExtractor): if any(s in webpage for s in ['video-deleted-info', '>This video has been removed']): raise ExtractorError('Video %s has been removed' % video_id, expected=True) - title = self._html_search_regex( - (r']+class="(?:video_title_text|videoTitle)[^"]*">(?P(?:(?!\1).)+)</h\1>', - r'(?:videoTitle|title)\s*:\s*(["\'])(?P<title>(?:(?!\1).)+)\1',), - webpage, 'title', group='title', - default=None) or self._og_search_title(webpage) + info = self._search_json_ld(webpage, video_id, default={}) + + if not info.get('title'): + info['title'] = self._html_search_regex( + (r'<h(\d)[^>]+class="(?:video_title_text|videoTitle)[^"]*">(?P<title>(?:(?!\1).)+)</h\1>', + r'(?:videoTitle|title)\s*:\s*(["\'])(?P<title>(?:(?!\1).)+)\1',), + webpage, 'title', group='title', + default=None) or self._og_search_title(webpage) formats = [] sources = self._parse_json( @@ -88,28 +92,28 @@ class RedTubeIE(InfoExtractor): thumbnail = self._og_search_thumbnail(webpage) upload_date = unified_strdate(self._search_regex( - r'<span[^>]+>ADDED ([^<]+)<', - webpage, 'upload date', fatal=False)) + r'<span[^>]+>(?:ADDED|Published on) ([^<]+)<', + webpage, 'upload date', default=None)) duration = int_or_none(self._og_search_property( 'video:duration', webpage, default=None) or self._search_regex( r'videoDuration\s*:\s*(\d+)', webpage, 'duration', default=None)) view_count = str_to_int(self._search_regex( (r'<div[^>]*>Views</div>\s*<div[^>]*>\s*([\d,.]+)', - r'<span[^>]*>VIEWS</span>\s*</td>\s*<td>\s*([\d,.]+)'), - webpage, 'view count', fatal=False)) + r'<span[^>]*>VIEWS</span>\s*</td>\s*<td>\s*([\d,.]+)', + r'<span[^>]+\bclass=["\']video_view_count[^>]*>\s*([\d,.]+)'), + webpage, 'view count', default=None)) # No self-labeling, but they describe themselves as # "Home of Videos Porno" age_limit = 18 - return { + return merge_dicts(info, { 'id': video_id, 'ext': 'mp4', - 'title': title, 'thumbnail': thumbnail, 'upload_date': upload_date, 'duration': duration, 'view_count': view_count, 'age_limit': age_limit, 'formats': formats, - } + }) From d4bb825b83a87813f54d007febd79d2f3dcee7b9 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 9 Oct 2019 11:07:46 +0100 Subject: [PATCH 080/422] [globo] fix format extraction(closes #20319) --- youtube_dl/extractor/globo.py | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/globo.py b/youtube_dl/extractor/globo.py index fb8f7679b..b9c400a57 100644 --- a/youtube_dl/extractor/globo.py +++ b/youtube_dl/extractor/globo.py @@ -96,6 +96,8 @@ class GloboIE(InfoExtractor): video = self._download_json( 'http://api.globovideos.com/videos/%s/playlist' % video_id, video_id)['videos'][0] + if video.get('encrypted') is True: + raise ExtractorError('This video is DRM protected.', expected=True) title = video['title'] @@ -109,8 +111,8 @@ class GloboIE(InfoExtractor): security = self._download_json( 'http://security.video.globo.com/videos/%s/hash' % video_id, video_id, 'Downloading security hash for %s' % resource_id, query={ - 'player': 'flash', - 'version': '17.0.0.132', + 'player': 'desktop', + 'version': '5.19.1', 'resource_id': resource_id, }) @@ -122,19 +124,18 @@ class GloboIE(InfoExtractor): '%s returned error: %s' % (self.IE_NAME, message), expected=True) continue - hash_code = security_hash[:2] - received_time = security_hash[2:12] - received_random = security_hash[12:22] - received_md5 = security_hash[22:] + assert security_hash[:2] in ('04', '14') + received_time = security_hash[3:13] + received_md5 = security_hash[24:] sign_time = compat_str(int(received_time) + 86400) padding = '%010d' % random.randint(1, 10000000000) - md5_data = (received_md5 + sign_time + padding + '0xFF01DD').encode() + md5_data = (received_md5 + sign_time + padding + '0xAC10FD').encode() signed_md5 = base64.urlsafe_b64encode(hashlib.md5(md5_data).digest()).decode().strip('=') - signed_hash = hash_code + received_time + received_random + sign_time + padding + signed_md5 + signed_hash = security_hash[:23] + sign_time + padding + signed_md5 - signed_url = '%s?h=%s&k=%s' % (resource_url, signed_hash, 'flash') + signed_url = '%s?h=%s&k=html5&a=%s&u=%s' % (resource_url, signed_hash, 'F' if video.get('subscriber_only') else 'A', security.get('user') or '') if resource_id.endswith('m3u8') or resource_url.endswith('.m3u8'): formats.extend(self._extract_m3u8_formats( signed_url, resource_id, 'mp4', entry_protocol='m3u8_native', From 1907f06e7b0689840b75810e5ad2683581f83924 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 10 Oct 2019 00:11:41 +0700 Subject: [PATCH 081/422] [kaltura] Fix embed info strip (refs #22658) --- youtube_dl/extractor/kaltura.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/kaltura.py b/youtube_dl/extractor/kaltura.py index 0a733424c..1c486c038 100644 --- a/youtube_dl/extractor/kaltura.py +++ b/youtube_dl/extractor/kaltura.py @@ -151,7 +151,8 @@ class KalturaIE(InfoExtractor): if mobj: embed_info = mobj.groupdict() for k, v in embed_info.items(): - embed_info[k] = v.strip() + if v: + embed_info[k] = v.strip() url = 'kaltura:%(partner_id)s:%(id)s' % embed_info escaped_pid = re.escape(embed_info['partner_id']) service_url = re.search( From 07b50f616e407c8b7b2c183298acbb58e2ddf09b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 10 Oct 2019 00:24:03 +0700 Subject: [PATCH 082/422] [kaltura] Fix service URL extraction (closes #22658) --- youtube_dl/extractor/kaltura.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/kaltura.py b/youtube_dl/extractor/kaltura.py index 1c486c038..2d38b758b 100644 --- a/youtube_dl/extractor/kaltura.py +++ b/youtube_dl/extractor/kaltura.py @@ -155,11 +155,11 @@ class KalturaIE(InfoExtractor): embed_info[k] = v.strip() url = 'kaltura:%(partner_id)s:%(id)s' % embed_info escaped_pid = re.escape(embed_info['partner_id']) - service_url = re.search( - r'<script[^>]+src=["\']((?:https?:)?//.+?)/p/%s/sp/%s00/embedIframeJs' % (escaped_pid, escaped_pid), + service_mobj = re.search( + r'<script[^>]+src=(["\'])(?P<id>(?:https?:)?//(?:(?!\1).)+)/p/%s/sp/%s00/embedIframeJs' % (escaped_pid, escaped_pid), webpage) - if service_url: - url = smuggle_url(url, {'service_url': service_url.group(1)}) + if service_mobj: + url = smuggle_url(url, {'service_url': service_mobj.group('id')}) return url def _kaltura_api_call(self, video_id, actions, service_url=None, *args, **kwargs): From 2765c47a8c4e7154fa0a9be0bb63f3bcba592b10 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 10 Oct 2019 03:40:01 +0700 Subject: [PATCH 083/422] [promptfile] Remove extractor (closes #6239) --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/promptfile.py | 70 ------------------------------ 2 files changed, 71 deletions(-) delete mode 100644 youtube_dl/extractor/promptfile.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 8d3e433c3..f393683da 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -893,7 +893,6 @@ from .puhutv import ( PuhuTVSerieIE, ) from .presstv import PressTVIE -from .promptfile import PromptFileIE from .prosiebensat1 import ProSiebenSat1IE from .puls4 import Puls4IE from .pyvideo import PyvideoIE diff --git a/youtube_dl/extractor/promptfile.py b/youtube_dl/extractor/promptfile.py deleted file mode 100644 index 23ac93d7e..000000000 --- a/youtube_dl/extractor/promptfile.py +++ /dev/null @@ -1,70 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..utils import ( - determine_ext, - ExtractorError, - urlencode_postdata, -) - - -class PromptFileIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?promptfile\.com/l/(?P<id>[0-9A-Z\-]+)' - _TEST = { - 'url': 'http://www.promptfile.com/l/86D1CE8462-576CAAE416', - 'md5': '5a7e285a26e0d66d9a263fae91bc92ce', - 'info_dict': { - 'id': '86D1CE8462-576CAAE416', - 'ext': 'mp4', - 'title': 'oceans.mp4', - 'thumbnail': r're:^https?://.*\.jpg$', - } - } - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - if re.search(r'<div.+id="not_found_msg".+>(?!We are).+</div>[^-]', webpage) is not None: - raise ExtractorError('Video %s does not exist' % video_id, - expected=True) - - chash = self._search_regex( - r'val\("([^"]*)"\s*\+\s*\$\("#chash"\)', webpage, 'chash') - fields = self._hidden_inputs(webpage) - keys = list(fields.keys()) - chash_key = keys[0] if len(keys) == 1 else next( - key for key in keys if key.startswith('cha')) - fields[chash_key] = chash + fields[chash_key] - - webpage = self._download_webpage( - url, video_id, 'Downloading video page', - data=urlencode_postdata(fields), - headers={'Content-type': 'application/x-www-form-urlencoded'}) - - video_url = self._search_regex( - (r'<a[^>]+href=(["\'])(?P<url>(?:(?!\1).)+)\1[^>]*>\s*Download File', - r'<a[^>]+href=(["\'])(?P<url>https?://(?:www\.)?promptfile\.com/file/(?:(?!\1).)+)\1'), - webpage, 'video url', group='url') - title = self._html_search_regex( - r'<span.+title="([^"]+)">', webpage, 'title') - thumbnail = self._html_search_regex( - r'<div id="player_overlay">.*button>.*?<img src="([^"]+)"', - webpage, 'thumbnail', fatal=False, flags=re.DOTALL) - - formats = [{ - 'format_id': 'sd', - 'url': video_url, - 'ext': determine_ext(title), - }] - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': title, - 'thumbnail': thumbnail, - 'formats': formats, - } From c317b6163b294f4cdc2d1dff96e1a63da1bae910 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Thu, 10 Oct 2019 00:01:37 +0100 Subject: [PATCH 084/422] [vessel] remove extractor --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/generic.py | 6 -- youtube_dl/extractor/vessel.py | 157 ----------------------------- 3 files changed, 164 deletions(-) delete mode 100644 youtube_dl/extractor/vessel.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index f393683da..7a1e0dad6 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1282,7 +1282,6 @@ from .varzesh3 import Varzesh3IE from .vbox7 import Vbox7IE from .veehd import VeeHDIE from .veoh import VeohIE -from .vessel import VesselIE from .vesti import VestiIE from .vevo import ( VevoIE, diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index d1725d98b..ec43c5ae4 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -77,7 +77,6 @@ from .instagram import InstagramIE from .liveleak import LiveLeakIE from .threeqsdn import ThreeQSDNIE from .theplatform import ThePlatformIE -from .vessel import VesselIE from .kaltura import KalturaIE from .eagleplatform import EaglePlatformIE from .facebook import FacebookIE @@ -2491,11 +2490,6 @@ class GenericIE(InfoExtractor): if tp_urls: return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform') - # Look for Vessel embeds - vessel_urls = VesselIE._extract_urls(webpage) - if vessel_urls: - return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key()) - # Look for embedded rtl.nl player matches = re.findall( r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"', diff --git a/youtube_dl/extractor/vessel.py b/youtube_dl/extractor/vessel.py deleted file mode 100644 index 31eee0ba7..000000000 --- a/youtube_dl/extractor/vessel.py +++ /dev/null @@ -1,157 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import json -import re - -from .common import InfoExtractor -from ..utils import ( - ExtractorError, - parse_iso8601, - sanitized_Request, -) - - -class VesselIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?vessel\.com/(?:videos|embed)/(?P<id>[0-9a-zA-Z-_]+)' - _API_URL_TEMPLATE = 'https://www.vessel.com/api/view/items/%s' - _LOGIN_URL = 'https://www.vessel.com/api/account/login' - _NETRC_MACHINE = 'vessel' - _TESTS = [{ - 'url': 'https://www.vessel.com/videos/HDN7G5UMs', - 'md5': '455cdf8beb71c6dd797fd2f3818d05c4', - 'info_dict': { - 'id': 'HDN7G5UMs', - 'ext': 'mp4', - 'title': 'Nvidia GeForce GTX Titan X - The Best Video Card on the Market?', - 'thumbnail': r're:^https?://.*\.jpg$', - 'upload_date': '20150317', - 'description': 'Did Nvidia pull out all the stops on the Titan X, or does its performance leave something to be desired?', - 'timestamp': int, - }, - }, { - 'url': 'https://www.vessel.com/embed/G4U7gUJ6a?w=615&h=346', - 'only_matching': True, - }, { - 'url': 'https://www.vessel.com/videos/F01_dsLj1', - 'only_matching': True, - }, { - 'url': 'https://www.vessel.com/videos/RRX-sir-J', - 'only_matching': True, - }] - - @staticmethod - def _extract_urls(webpage): - return [url for _, url in re.findall( - r'<iframe[^>]+src=(["\'])((?:https?:)?//(?:www\.)?vessel\.com/embed/[0-9a-zA-Z-_]+.*?)\1', - webpage)] - - @staticmethod - def make_json_request(url, data): - payload = json.dumps(data).encode('utf-8') - req = sanitized_Request(url, payload) - req.add_header('Content-Type', 'application/json; charset=utf-8') - return req - - @staticmethod - def find_assets(data, asset_type, asset_id=None): - for asset in data.get('assets', []): - if not asset.get('type') == asset_type: - continue - elif asset_id is not None and not asset.get('id') == asset_id: - continue - else: - yield asset - - def _check_access_rights(self, data): - access_info = data.get('__view', {}) - if not access_info.get('allow_access', True): - err_code = access_info.get('error_code') or '' - if err_code == 'ITEM_PAID_ONLY': - raise ExtractorError( - 'This video requires subscription.', expected=True) - else: - raise ExtractorError( - 'Access to this content is restricted. (%s said: %s)' % (self.IE_NAME, err_code), expected=True) - - def _login(self): - username, password = self._get_login_info() - if username is None: - return - self.report_login() - data = { - 'client_id': 'web', - 'type': 'password', - 'user_key': username, - 'password': password, - } - login_request = VesselIE.make_json_request(self._LOGIN_URL, data) - self._download_webpage(login_request, None, False, 'Wrong login info') - - def _real_initialize(self): - self._login() - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - data = self._parse_json(self._search_regex( - r'App\.bootstrapData\((.*?)\);', webpage, 'data'), video_id) - asset_id = data['model']['data']['id'] - - req = VesselIE.make_json_request( - self._API_URL_TEMPLATE % asset_id, {'client': 'web'}) - data = self._download_json(req, video_id) - video_asset_id = data.get('main_video_asset') - - self._check_access_rights(data) - - try: - video_asset = next( - VesselIE.find_assets(data, 'video', asset_id=video_asset_id)) - except StopIteration: - raise ExtractorError('No video assets found') - - formats = [] - for f in video_asset.get('sources', []): - location = f.get('location') - if not location: - continue - name = f.get('name') - if name == 'hls-index': - formats.extend(self._extract_m3u8_formats( - location, video_id, ext='mp4', - entry_protocol='m3u8_native', m3u8_id='m3u8', fatal=False)) - elif name == 'dash-index': - formats.extend(self._extract_mpd_formats( - location, video_id, mpd_id='dash', fatal=False)) - else: - formats.append({ - 'format_id': name, - 'tbr': f.get('bitrate'), - 'height': f.get('height'), - 'width': f.get('width'), - 'url': location, - }) - self._sort_formats(formats) - - thumbnails = [] - for im_asset in VesselIE.find_assets(data, 'image'): - thumbnails.append({ - 'url': im_asset['location'], - 'width': im_asset.get('width', 0), - 'height': im_asset.get('height', 0), - }) - - return { - 'id': video_id, - 'title': data['title'], - 'formats': formats, - 'thumbnails': thumbnails, - 'description': data.get('short_description'), - 'duration': data.get('duration'), - 'comment_count': data.get('comment_count'), - 'like_count': data.get('like_count'), - 'view_count': data.get('view_count'), - 'timestamp': parse_iso8601(data.get('released_at')), - } From 311ee457314359662c975cd29f2ee58ad068db49 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Mon, 14 Oct 2019 18:36:25 +0100 Subject: [PATCH 085/422] [nbc] switch to graphql api(closes #18581)(closes #22693)(closes #22701) --- youtube_dl/extractor/nbc.py | 39 ++++++++++++++++++++++++------------- 1 file changed, 26 insertions(+), 13 deletions(-) diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py index 3282f84ee..10680b202 100644 --- a/youtube_dl/extractor/nbc.py +++ b/youtube_dl/extractor/nbc.py @@ -10,7 +10,6 @@ from .adobepass import AdobePassIE from ..compat import compat_urllib_parse_unquote from ..utils import ( smuggle_url, - try_get, update_url_query, int_or_none, ) @@ -85,27 +84,41 @@ class NBCIE(AdobePassIE): permalink, video_id = re.match(self._VALID_URL, url).groups() permalink = 'http' + compat_urllib_parse_unquote(permalink) response = self._download_json( - 'https://api.nbc.com/v3/videos', video_id, query={ - 'filter[permalink]': permalink, - 'fields[videos]': 'description,entitlement,episodeNumber,guid,keywords,seasonNumber,title,vChipRating', - 'fields[shows]': 'shortTitle', - 'include': 'show.shortTitle', + 'https://friendship.nbc.co/v2/graphql', video_id, query={ + 'query': '''{ + page(name: "%s", platform: web, type: VIDEO, userId: "0") { + data { + ... on VideoPageData { + description + episodeNumber + keywords + locked + mpxAccountId + mpxGuid + rating + seasonNumber + secondaryTitle + seriesShortTitle + } + } + } +}''' % permalink, }) - video_data = response['data'][0]['attributes'] + video_data = response['data']['page']['data'] query = { 'mbr': 'true', 'manifest': 'm3u', } - video_id = video_data['guid'] - title = video_data['title'] - if video_data.get('entitlement') == 'auth': + video_id = video_data['mpxGuid'] + title = video_data['secondaryTitle'] + if video_data.get('locked'): resource = self._get_mvpd_resource( 'nbcentertainment', title, video_id, - video_data.get('vChipRating')) + video_data.get('rating')) query['auth'] = self._extract_mvpd_auth( url, video_id, 'nbcentertainment', resource) theplatform_url = smuggle_url(update_url_query( - 'http://link.theplatform.com/s/NnzsPC/media/guid/2410887629/' + video_id, + 'http://link.theplatform.com/s/NnzsPC/media/guid/%s/%s' % (video_data.get('mpxAccountId') or '2410887629', video_id), query), {'force_smil_url': True}) return { '_type': 'url_transparent', @@ -117,7 +130,7 @@ class NBCIE(AdobePassIE): 'season_number': int_or_none(video_data.get('seasonNumber')), 'episode_number': int_or_none(video_data.get('episodeNumber')), 'episode': title, - 'series': try_get(response, lambda x: x['included'][0]['attributes']['shortTitle']), + 'series': video_data.get('seriesShortTitle'), 'ie_key': 'ThePlatform', } From a1ee23e98fe2ec80b8726829927fcae1267e76b1 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Mon, 14 Oct 2019 18:37:35 +0100 Subject: [PATCH 086/422] [vimeo] fix VHX embed extraction --- youtube_dl/extractor/vimeo.py | 97 ++++------------------------------- 1 file changed, 9 insertions(+), 88 deletions(-) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index ddf375c6c..5dc38e243 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -23,7 +23,6 @@ from ..utils import ( NO_DEFAULT, OnDemandPagedList, parse_filesize, - qualities, RegexNotFoundError, sanitized_Request, smuggle_url, @@ -211,6 +210,7 @@ class VimeoBaseInfoExtractor(InfoExtractor): video_uploader_url = owner.get('url') return { + 'id': video_id, 'title': self._live_title(video_title) if is_live else video_title, 'uploader': owner.get('name'), 'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None, @@ -730,7 +730,6 @@ class VimeoIE(VimeoBaseInfoExtractor): channel_url = 'https://vimeo.com/channels/%s' % channel_id if channel_id else None info_dict = { - 'id': video_id, 'formats': formats, 'timestamp': unified_timestamp(timestamp), 'description': video_description, @@ -1061,7 +1060,6 @@ class VimeoReviewIE(VimeoBaseInfoExtractor): if source_format: info_dict['formats'].append(source_format) self._vimeo_sort_formats(info_dict['formats']) - info_dict['id'] = video_id return info_dict @@ -1115,94 +1113,17 @@ class VimeoLikesIE(VimeoChannelIE): return self._extract_videos(user_id, 'https://vimeo.com/%s/likes' % user_id) -class VHXEmbedIE(InfoExtractor): +class VHXEmbedIE(VimeoBaseInfoExtractor): IE_NAME = 'vhx:embed' _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)' - def _call_api(self, video_id, access_token, path='', query=None): - return self._download_json( - 'https://api.vhx.tv/videos/' + video_id + path, video_id, headers={ - 'Authorization': 'Bearer ' + access_token, - }, query=query) - def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - credentials = self._parse_json(self._search_regex( - r'(?s)credentials\s*:\s*({.+?}),', webpage, - 'config'), video_id, js_to_json) - access_token = credentials['access_token'] - - query = {} - for k, v in credentials.items(): - if k in ('authorization', 'authUserToken', 'ticket') and v and v != 'undefined': - if k == 'authUserToken': - query['auth_user_token'] = v - else: - query[k] = v - files = self._call_api(video_id, access_token, '/files', query) - - formats = [] - for f in files: - href = try_get(f, lambda x: x['_links']['source']['href']) - if not href: - continue - method = f.get('method') - if method == 'hls': - formats.extend(self._extract_m3u8_formats( - href, video_id, 'mp4', 'm3u8_native', - m3u8_id='hls', fatal=False)) - elif method == 'dash': - formats.extend(self._extract_mpd_formats( - href, video_id, mpd_id='dash', fatal=False)) - else: - fmt = { - 'filesize': int_or_none(try_get(f, lambda x: x['size']['bytes'])), - 'format_id': 'http', - 'preference': 1, - 'url': href, - 'vcodec': f.get('codec'), - } - quality = f.get('quality') - if quality: - fmt.update({ - 'format_id': 'http-' + quality, - 'height': int_or_none(self._search_regex(r'(\d+)p', quality, 'height', default=None)), - }) - formats.append(fmt) - self._sort_formats(formats) - - video_data = self._call_api(video_id, access_token) - title = video_data.get('title') or video_data['name'] - - subtitles = {} - for subtitle in try_get(video_data, lambda x: x['tracks']['subtitles'], list) or []: - lang = subtitle.get('srclang') or subtitle.get('label') - for _link in subtitle.get('_links', {}).values(): - href = _link.get('href') - if not href: - continue - subtitles.setdefault(lang, []).append({ - 'url': href, - }) - - q = qualities(['small', 'medium', 'large', 'source']) - thumbnails = [] - for thumbnail_id, thumbnail_url in video_data.get('thumbnail', {}).items(): - thumbnails.append({ - 'id': thumbnail_id, - 'url': thumbnail_url, - 'preference': q(thumbnail_id), - }) - - return { - 'id': video_id, - 'title': title, - 'description': video_data.get('description'), - 'duration': int_or_none(try_get(video_data, lambda x: x['duration']['seconds'])), - 'formats': formats, - 'subtitles': subtitles, - 'thumbnails': thumbnails, - 'timestamp': unified_timestamp(video_data.get('created_at')), - 'view_count': int_or_none(video_data.get('plays_count')), - } + config_url = self._parse_json(self._search_regex( + r'window\.OTTData\s*=\s*({.+})', webpage, + 'ott data'), video_id, js_to_json)['config_url'] + config = self._download_json(config_url, video_id) + info = self._parse_config(config, video_id) + self._vimeo_sort_formats(info['formats']) + return info From 7e05df71b7d8c0e1ea9beafff48275ef3c9e27d2 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Tue, 15 Oct 2019 00:10:22 +0100 Subject: [PATCH 087/422] [nexx] handle result list(closes #22666) --- youtube_dl/extractor/nexx.py | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/nexx.py b/youtube_dl/extractor/nexx.py index 82d526c22..f9aad83c4 100644 --- a/youtube_dl/extractor/nexx.py +++ b/youtube_dl/extractor/nexx.py @@ -295,13 +295,23 @@ class NexxIE(InfoExtractor): video = None + def find_video(result): + if isinstance(result, dict): + return result + elif isinstance(result, list): + vid = int(video_id) + for v in result: + if try_get(v, lambda x: x['general']['ID'], int) == vid: + return v + return None + response = self._download_json( 'https://arc.nexx.cloud/api/video/%s.json' % video_id, video_id, fatal=False) if response and isinstance(response, dict): result = response.get('result') - if result and isinstance(result, dict): - video = result + if result: + video = find_video(result) # not all videos work via arc, e.g. nexx:741:1269984 if not video: @@ -348,7 +358,7 @@ class NexxIE(InfoExtractor): request_token = hashlib.md5( ''.join((op, domain_id, secret)).encode('utf-8')).hexdigest() - video = self._call_api( + result = self._call_api( domain_id, 'videos/%s/%s' % (op, video_id), video_id, data={ 'additionalfields': 'language,channel,actors,studio,licenseby,slug,subtitle,teaser,description', 'addInteractionOptions': '1', @@ -363,6 +373,7 @@ class NexxIE(InfoExtractor): 'X-Request-CID': cid, 'X-Request-Token': request_token, }) + video = find_video(result) general = video['general'] title = general['title'] From 2af01c0293db53dc80c552df3986d0e088b65b76 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Tue, 15 Oct 2019 15:18:51 +0100 Subject: [PATCH 088/422] [bokecc] improve player params extraction(closes #22638) --- youtube_dl/extractor/bokecc.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/bokecc.py b/youtube_dl/extractor/bokecc.py index 86a7f4d7d..6017e8344 100644 --- a/youtube_dl/extractor/bokecc.py +++ b/youtube_dl/extractor/bokecc.py @@ -11,8 +11,8 @@ from ..utils import ExtractorError class BokeCCBaseIE(InfoExtractor): def _extract_bokecc_formats(self, webpage, video_id, format_id=None): player_params_str = self._html_search_regex( - r'<(?:script|embed)[^>]+src="http://p\.bokecc\.com/player\?([^"]+)', - webpage, 'player params') + r'<(?:script|embed)[^>]+src=(?P<q>["\'])(?:https?:)?//p\.bokecc\.com/(?:player|flash/player\.swf)\?(?P<query>.+?)(?P=q)', + webpage, 'player params', group='query') player_params = compat_parse_qs(player_params_str) @@ -36,9 +36,9 @@ class BokeCCIE(BokeCCBaseIE): _VALID_URL = r'https?://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)' _TESTS = [{ - 'url': 'http://union.bokecc.com/playvideo.bo?vid=E44D40C15E65EA30&uid=CD0C5D3C8614B28B', + 'url': 'http://union.bokecc.com/playvideo.bo?vid=E0ABAE9D4F509B189C33DC5901307461&uid=FE644790DE9D154A', 'info_dict': { - 'id': 'CD0C5D3C8614B28B_E44D40C15E65EA30', + 'id': 'FE644790DE9D154A_E0ABAE9D4F509B189C33DC5901307461', 'ext': 'flv', 'title': 'BokeCC Video', }, From 30eb05cb41d95a73f7baff8da9ec1d6a50b08f50 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Tue, 15 Oct 2019 19:54:53 +0100 Subject: [PATCH 089/422] [globo] extract subtitles(closes #22713) --- youtube_dl/extractor/globo.py | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/globo.py b/youtube_dl/extractor/globo.py index b9c400a57..9ad1d95fb 100644 --- a/youtube_dl/extractor/globo.py +++ b/youtube_dl/extractor/globo.py @@ -102,10 +102,18 @@ class GloboIE(InfoExtractor): title = video['title'] formats = [] + subtitles = {} for resource in video['resources']: resource_id = resource.get('_id') resource_url = resource.get('url') - if not resource_id or not resource_url: + resource_type = resource.get('type') + if not resource_url or (resource_type == 'media' and not resource_id) or resource_type not in ('subtitle', 'media'): + continue + + if resource_type == 'subtitle': + subtitles.setdefault(resource.get('language') or 'por', []).append({ + 'url': resource_url, + }) continue security = self._download_json( @@ -165,7 +173,8 @@ class GloboIE(InfoExtractor): 'duration': duration, 'uploader': uploader, 'uploader_id': uploader_id, - 'formats': formats + 'formats': formats, + 'subtitles': subtitles, } From 974311b5aa1a53564a00915b9228af30e2a5b40d Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Tue, 15 Oct 2019 21:01:59 +0100 Subject: [PATCH 090/422] [vimeo] improve album videos id extraction(closes #22599) --- youtube_dl/extractor/vimeo.py | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 5dc38e243..9abd59d98 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -938,7 +938,7 @@ class VimeoAlbumIE(VimeoChannelIE): def _fetch_page(self, album_id, authorizaion, hashed_pass, page): api_page = page + 1 query = { - 'fields': 'link', + 'fields': 'link,uri', 'page': api_page, 'per_page': self._PAGE_SIZE, } @@ -953,7 +953,9 @@ class VimeoAlbumIE(VimeoChannelIE): link = video.get('link') if not link: continue - yield self.url_result(link, VimeoIE.ie_key(), VimeoIE._match_id(link)) + uri = video.get('uri') + video_id = self._search_regex(r'/videos/(\d+)', uri, 'video_id', default=None) if uri else None + yield self.url_result(link, VimeoIE.ie_key(), video_id) def _real_extract(self, url): album_id = self._match_id(url) From 173190f5e3946173daea0539cf0e749cb14acd12 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 16 Oct 2019 03:25:13 +0700 Subject: [PATCH 091/422] [ChangeLog] Actualize [ci skip] --- ChangeLog | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) diff --git a/ChangeLog b/ChangeLog index 80681a9ae..8a59398d9 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,39 @@ +version <unreleased> + +Core +* [extractor/common] Make _is_valid_url more relaxed + +Extractors +* [vimeo] Improve album videos id extraction (#22599) ++ [globo] Extract subtitles (#22713) +* [bokecc] Improve player params extraction (#22638) +* [nexx] Handle result list (#22666) +* [vimeo] Fix VHX embed extraction +* [nbc] Switch to graphql API (#18581, #22693, #22701) +- [vessel] Remove extractor +- [promptfile] Remove extractor (#6239) +* [kaltura] Fix service URL extraction (#22658) +* [kaltura] Fix embed info strip (#22658) +* [globo] Fix format extraction (#20319) +* [redtube] Improve metadata extraction (#22492, #22615) +* [pornhub:uservideos:upload] Fix extraction (#22619) ++ [telequebec:squat] Add support for squat.telequebec.tv (#18503) +- [wimp] Remove extractor (#22088, #22091) ++ [gfycat] Extend URL regular expression (#22225) ++ [chaturbate] Extend URL regular expression (#22309) +* [peertube] Update instances (#22414) ++ [telequebec] Add support for coucou.telequebec.tv (#22482) ++ [xvideos] Extend URL regular expression (#22471) +- [youtube] Remove support for invidious.enkirton.net (#22543) ++ [openload] Add support for oload.monster (#22592) +* [nrktv:seriebase] Fix extraction (#22596) ++ [youtube] Add support for yt.lelux.fi (#22597) +* [orf:tvthek] Make manifest requests non fatal (#22578) +* [teachable] Skip login when already logged in (#22572) +* [viewlift] Improve extraction (#22545) +* [nonktube] Fix extraction (#22544) + + version 2019.09.28 Core From 7815d6b74373feb90d969b5fcde7df11702fa5d0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Wed, 16 Oct 2019 03:26:47 +0700 Subject: [PATCH 092/422] release 2019.10.16 --- .github/ISSUE_TEMPLATE/1_broken_site.md | 6 +++--- .github/ISSUE_TEMPLATE/2_site_support_request.md | 4 ++-- .github/ISSUE_TEMPLATE/3_site_feature_request.md | 4 ++-- .github/ISSUE_TEMPLATE/4_bug_report.md | 6 +++--- .github/ISSUE_TEMPLATE/5_feature_request.md | 4 ++-- ChangeLog | 2 +- docs/supportedsites.md | 4 +--- youtube_dl/version.py | 2 +- 8 files changed, 15 insertions(+), 17 deletions(-) diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.md b/.github/ISSUE_TEMPLATE/1_broken_site.md index 2fea0120e..5cd9f0dc0 100644 --- a/.github/ISSUE_TEMPLATE/1_broken_site.md +++ b/.github/ISSUE_TEMPLATE/1_broken_site.md @@ -18,7 +18,7 @@ title: '' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.09.28. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.16. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape. - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates. @@ -26,7 +26,7 @@ Carefully read and work through this check list in order to prevent the most com --> - [ ] I'm reporting a broken site support -- [ ] I've verified that I'm running youtube-dl version **2019.09.28** +- [ ] I've verified that I'm running youtube-dl version **2019.10.16** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar issues including closed ones @@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.09.28 + [debug] youtube-dl version 2019.10.16 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/2_site_support_request.md b/.github/ISSUE_TEMPLATE/2_site_support_request.md index 6116acc79..6cc34796a 100644 --- a/.github/ISSUE_TEMPLATE/2_site_support_request.md +++ b/.github/ISSUE_TEMPLATE/2_site_support_request.md @@ -19,7 +19,7 @@ labels: 'site-support-request' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.09.28. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.16. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that site you are requesting is not dedicated to copyright infringement, see https://yt-dl.org/copyright-infringement. youtube-dl does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights. - Search the bugtracker for similar site support requests: http://yt-dl.org/search-issues. DO NOT post duplicates. @@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com --> - [ ] I'm reporting a new site support request -- [ ] I've verified that I'm running youtube-dl version **2019.09.28** +- [ ] I've verified that I'm running youtube-dl version **2019.10.16** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that none of provided URLs violate any copyrights - [ ] I've searched the bugtracker for similar site support requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/3_site_feature_request.md b/.github/ISSUE_TEMPLATE/3_site_feature_request.md index 79d1a7f3c..0b7911e79 100644 --- a/.github/ISSUE_TEMPLATE/3_site_feature_request.md +++ b/.github/ISSUE_TEMPLATE/3_site_feature_request.md @@ -18,13 +18,13 @@ title: '' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.09.28. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.16. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Search the bugtracker for similar site feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates. - Finally, put x into all relevant boxes (like this [x]) --> - [ ] I'm reporting a site feature request -- [ ] I've verified that I'm running youtube-dl version **2019.09.28** +- [ ] I've verified that I'm running youtube-dl version **2019.10.16** - [ ] I've searched the bugtracker for similar site feature requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/4_bug_report.md b/.github/ISSUE_TEMPLATE/4_bug_report.md index 9bda3d440..a6f417d38 100644 --- a/.github/ISSUE_TEMPLATE/4_bug_report.md +++ b/.github/ISSUE_TEMPLATE/4_bug_report.md @@ -18,7 +18,7 @@ title: '' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.09.28. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.16. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape. - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates. @@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com --> - [ ] I'm reporting a broken site support issue -- [ ] I've verified that I'm running youtube-dl version **2019.09.28** +- [ ] I've verified that I'm running youtube-dl version **2019.10.16** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar bug reports including closed ones @@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.09.28 + [debug] youtube-dl version 2019.10.16 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/5_feature_request.md b/.github/ISSUE_TEMPLATE/5_feature_request.md index 581344917..3fe753b62 100644 --- a/.github/ISSUE_TEMPLATE/5_feature_request.md +++ b/.github/ISSUE_TEMPLATE/5_feature_request.md @@ -19,13 +19,13 @@ labels: 'request' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.09.28. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.16. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Search the bugtracker for similar feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates. - Finally, put x into all relevant boxes (like this [x]) --> - [ ] I'm reporting a feature request -- [ ] I've verified that I'm running youtube-dl version **2019.09.28** +- [ ] I've verified that I'm running youtube-dl version **2019.10.16** - [ ] I've searched the bugtracker for similar feature requests including closed ones diff --git a/ChangeLog b/ChangeLog index 8a59398d9..dc5c32a1f 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2019.10.16 Core * [extractor/common] Make _is_valid_url more relaxed diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 35275278b..0cbad28ea 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -694,7 +694,6 @@ - **PornoXO** - **PornTube** - **PressTV** - - **PromptFile** - **prosiebensat1**: ProSiebenSat.1 Digital - **puhutv** - **puhutv:serie** @@ -884,6 +883,7 @@ - **TeleQuebec** - **TeleQuebecEmission** - **TeleQuebecLive** + - **TeleQuebecSquat** - **TeleTask** - **Telewebion** - **TennisTV** @@ -991,7 +991,6 @@ - **VeeHD** - **Veoh** - **verystream** - - **Vessel** - **Vesti**: Вести.Ru - **Vevo** - **VevoPlaylist** @@ -1090,7 +1089,6 @@ - **Weibo** - **WeiboMobile** - **WeiqiTV**: WQTV - - **Wimp** - **Wistia** - **wnl**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl - **WorldStarHipHop** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index c3eafb068..53889b7cb 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.09.28' +__version__ = '2019.10.16' From 6d394a66f54216cc2b0b68fadd958eaf455c2778 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 16 Oct 2019 12:03:46 +0100 Subject: [PATCH 093/422] [atresplayer] fix extraction(closes #16277)(closes #16716) --- youtube_dl/extractor/atresplayer.py | 213 +++++++++------------------- 1 file changed, 64 insertions(+), 149 deletions(-) diff --git a/youtube_dl/extractor/atresplayer.py b/youtube_dl/extractor/atresplayer.py index ae1c09427..b96218f6c 100644 --- a/youtube_dl/extractor/atresplayer.py +++ b/youtube_dl/extractor/atresplayer.py @@ -1,202 +1,117 @@ from __future__ import unicode_literals -import time -import hmac -import hashlib import re from .common import InfoExtractor -from ..compat import compat_str +from ..compat import compat_HTTPError from ..utils import ( ExtractorError, - float_or_none, int_or_none, - sanitized_Request, urlencode_postdata, - xpath_text, ) class AtresPlayerIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?atresplayer\.com/television/[^/]+/[^/]+/[^/]+/(?P<id>.+?)_\d+\.html' + _VALID_URL = r'https?://(?:www\.)?atresplayer\.com/[^/]+/[^/]+/[^/]+/[^/]+/(?P<display_id>.+?)_(?P<id>[0-9a-f]{24})' _NETRC_MACHINE = 'atresplayer' _TESTS = [ { - 'url': 'http://www.atresplayer.com/television/programas/el-club-de-la-comedia/temporada-4/capitulo-10-especial-solidario-nochebuena_2014122100174.html', - 'md5': 'efd56753cda1bb64df52a3074f62e38a', + 'url': 'https://www.atresplayer.com/antena3/series/pequenas-coincidencias/temporada-1/capitulo-7-asuntos-pendientes_5d4aa2c57ed1a88fc715a615/', 'info_dict': { - 'id': 'capitulo-10-especial-solidario-nochebuena', + 'id': '5d4aa2c57ed1a88fc715a615', 'ext': 'mp4', - 'title': 'Especial Solidario de Nochebuena', - 'description': 'md5:e2d52ff12214fa937107d21064075bf1', - 'duration': 5527.6, - 'thumbnail': r're:^https?://.*\.jpg$', + 'title': 'Capítulo 7: Asuntos pendientes', + 'description': 'md5:7634cdcb4d50d5381bedf93efb537fbc', + 'duration': 3413, + }, + 'params': { + 'format': 'bestvideo', }, 'skip': 'This video is only available for registered users' }, { - 'url': 'http://www.atresplayer.com/television/especial/videoencuentros/temporada-1/capitulo-112-david-bustamante_2014121600375.html', - 'md5': '6e52cbb513c405e403dbacb7aacf8747', - 'info_dict': { - 'id': 'capitulo-112-david-bustamante', - 'ext': 'flv', - 'title': 'David Bustamante', - 'description': 'md5:f33f1c0a05be57f6708d4dd83a3b81c6', - 'duration': 1439.0, - 'thumbnail': r're:^https?://.*\.jpg$', - }, + 'url': 'https://www.atresplayer.com/lasexta/programas/el-club-de-la-comedia/temporada-4/capitulo-10-especial-solidario-nochebuena_5ad08edf986b2855ed47adc4/', + 'only_matching': True, }, { - 'url': 'http://www.atresplayer.com/television/series/el-secreto-de-puente-viejo/el-chico-de-los-tres-lunares/capitulo-977-29-12-14_2014122400174.html', + 'url': 'https://www.atresplayer.com/antena3/series/el-secreto-de-puente-viejo/el-chico-de-los-tres-lunares/capitulo-977-29-12-14_5ad51046986b2886722ccdea/', 'only_matching': True, }, ] - - _USER_AGENT = 'Dalvik/1.6.0 (Linux; U; Android 4.3; GT-I9300 Build/JSS15J' - _MAGIC = 'QWtMLXs414Yo+c#_+Q#K@NN)' - _TIMESTAMP_SHIFT = 30000 - - _TIME_API_URL = 'http://servicios.atresplayer.com/api/admin/time.json' - _URL_VIDEO_TEMPLATE = 'https://servicios.atresplayer.com/api/urlVideo/{1}/{0}/{1}|{2}|{3}.json' - _PLAYER_URL_TEMPLATE = 'https://servicios.atresplayer.com/episode/getplayer.json?episodePk=%s' - _EPISODE_URL_TEMPLATE = 'http://www.atresplayer.com/episodexml/%s' - - _LOGIN_URL = 'https://servicios.atresplayer.com/j_spring_security_check' - - _ERRORS = { - 'UNPUBLISHED': 'We\'re sorry, but this video is not yet available.', - 'DELETED': 'This video has expired and is no longer available for online streaming.', - 'GEOUNPUBLISHED': 'We\'re sorry, but this video is not available in your region due to right restrictions.', - # 'PREMIUM': 'PREMIUM', - } + _API_BASE = 'https://api.atresplayer.com/' def _real_initialize(self): self._login() + def _handle_error(self, e, code): + if isinstance(e.cause, compat_HTTPError) and e.cause.code == code: + error = self._parse_json(e.cause.read(), None) + if error.get('error') == 'required_registered': + self.raise_login_required() + raise ExtractorError(error['error_description'], expected=True) + raise + def _login(self): username, password = self._get_login_info() if username is None: return - login_form = { - 'j_username': username, - 'j_password': password, - } + self._request_webpage( + self._API_BASE + 'login', None, 'Downloading login page') - request = sanitized_Request( - self._LOGIN_URL, urlencode_postdata(login_form)) - request.add_header('Content-Type', 'application/x-www-form-urlencoded') - response = self._download_webpage( - request, None, 'Logging in') + try: + target_url = self._download_json( + 'https://account.atresmedia.com/api/login', None, + 'Logging in', headers={ + 'Content-Type': 'application/x-www-form-urlencoded' + }, data=urlencode_postdata({ + 'username': username, + 'password': password, + }))['targetUrl'] + except ExtractorError as e: + self._handle_error(e, 400) - error = self._html_search_regex( - r'(?s)<ul[^>]+class="[^"]*\blist_error\b[^"]*">(.+?)</ul>', - response, 'error', default=None) - if error: - raise ExtractorError( - 'Unable to login: %s' % error, expected=True) + self._request_webpage(target_url, None, 'Following Target URL') def _real_extract(self, url): - video_id = self._match_id(url) + display_id, video_id = re.match(self._VALID_URL, url).groups() - webpage = self._download_webpage(url, video_id) + try: + episode = self._download_json( + self._API_BASE + 'client/v1/player/episode/' + video_id, video_id) + except ExtractorError as e: + self._handle_error(e, 403) - episode_id = self._search_regex( - r'episode="([^"]+)"', webpage, 'episode id') - - request = sanitized_Request( - self._PLAYER_URL_TEMPLATE % episode_id, - headers={'User-Agent': self._USER_AGENT}) - player = self._download_json(request, episode_id, 'Downloading player JSON') - - episode_type = player.get('typeOfEpisode') - error_message = self._ERRORS.get(episode_type) - if error_message: - raise ExtractorError( - '%s returned error: %s' % (self.IE_NAME, error_message), expected=True) + title = episode['titulo'] formats = [] - video_url = player.get('urlVideo') - if video_url: - format_info = { - 'url': video_url, - 'format_id': 'http', - } - mobj = re.search(r'(?P<bitrate>\d+)K_(?P<width>\d+)x(?P<height>\d+)', video_url) - if mobj: - format_info.update({ - 'width': int_or_none(mobj.group('width')), - 'height': int_or_none(mobj.group('height')), - 'tbr': int_or_none(mobj.group('bitrate')), - }) - formats.append(format_info) - - timestamp = int_or_none(self._download_webpage( - self._TIME_API_URL, - video_id, 'Downloading timestamp', fatal=False), 1000, time.time()) - timestamp_shifted = compat_str(timestamp + self._TIMESTAMP_SHIFT) - token = hmac.new( - self._MAGIC.encode('ascii'), - (episode_id + timestamp_shifted).encode('utf-8'), hashlib.md5 - ).hexdigest() - - request = sanitized_Request( - self._URL_VIDEO_TEMPLATE.format('windows', episode_id, timestamp_shifted, token), - headers={'User-Agent': self._USER_AGENT}) - - fmt_json = self._download_json( - request, video_id, 'Downloading windows video JSON') - - result = fmt_json.get('resultDes') - if result.lower() != 'ok': - raise ExtractorError( - '%s returned error: %s' % (self.IE_NAME, result), expected=True) - - for format_id, video_url in fmt_json['resultObject'].items(): - if format_id == 'token' or not video_url.startswith('http'): + for source in episode.get('sources', []): + src = source.get('src') + if not src: continue - if 'geodeswowsmpra3player' in video_url: - # f4m_path = video_url.split('smil:', 1)[-1].split('free_', 1)[0] - # f4m_url = 'http://drg.antena3.com/{0}hds/es/sd.f4m'.format(f4m_path) - # this videos are protected by DRM, the f4m downloader doesn't support them - continue - video_url_hd = video_url.replace('free_es', 'es') - formats.extend(self._extract_f4m_formats( - video_url_hd[:-9] + '/manifest.f4m', video_id, f4m_id='hds', - fatal=False)) - formats.extend(self._extract_mpd_formats( - video_url_hd[:-9] + '/manifest.mpd', video_id, mpd_id='dash', - fatal=False)) + src_type = source.get('type') + if src_type == 'application/vnd.apple.mpegurl': + formats.extend(self._extract_m3u8_formats( + src, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) + elif src_type == 'application/dash+xml': + formats.extend(self._extract_mpd_formats( + src, video_id, mpd_id='dash', fatal=False)) self._sort_formats(formats) - path_data = player.get('pathData') - - episode = self._download_xml( - self._EPISODE_URL_TEMPLATE % path_data, video_id, - 'Downloading episode XML') - - duration = float_or_none(xpath_text( - episode, './media/asset/info/technical/contentDuration', 'duration')) - - art = episode.find('./media/asset/info/art') - title = xpath_text(art, './name', 'title') - description = xpath_text(art, './description', 'description') - thumbnail = xpath_text(episode, './media/asset/files/background', 'thumbnail') - - subtitles = {} - subtitle_url = xpath_text(episode, './media/asset/files/subtitle', 'subtitle') - if subtitle_url: - subtitles['es'] = [{ - 'ext': 'srt', - 'url': subtitle_url, - }] + heartbeat = episode.get('heartbeat') or {} + omniture = episode.get('omniture') or {} + get_meta = lambda x: heartbeat.get(x) or omniture.get(x) return { + 'display_id': display_id, 'id': video_id, 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'duration': duration, + 'description': episode.get('descripcion'), + 'thumbnail': episode.get('imgPoster'), + 'duration': int_or_none(episode.get('duration')), 'formats': formats, - 'subtitles': subtitles, + 'channel': get_meta('channel'), + 'season': get_meta('season'), + 'episode_number': int_or_none(get_meta('episodeNumber')), } From e29e96a9f5bc390789d176d509f592e208aa30d8 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 16 Oct 2019 15:06:48 +0100 Subject: [PATCH 094/422] [dumpert] fix extraction(closes #22428)(closes #22564) --- youtube_dl/extractor/dumpert.py | 83 +++++++++++++++++++-------------- 1 file changed, 47 insertions(+), 36 deletions(-) diff --git a/youtube_dl/extractor/dumpert.py b/youtube_dl/extractor/dumpert.py index be2e3d378..d9d9afdec 100644 --- a/youtube_dl/extractor/dumpert.py +++ b/youtube_dl/extractor/dumpert.py @@ -1,20 +1,17 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..compat import compat_b64decode from ..utils import ( + int_or_none, qualities, - sanitized_Request, ) class DumpertIE(InfoExtractor): - _VALID_URL = r'(?P<protocol>https?)://(?:www\.)?dumpert\.nl/(?:mediabase|embed)/(?P<id>[0-9]+/[0-9a-zA-Z]+)' + _VALID_URL = r'(?P<protocol>https?)://(?:(?:www|legacy)\.)?dumpert\.nl/(?:mediabase|embed|item)/(?P<id>[0-9]+[/_][0-9a-zA-Z]+)' _TESTS = [{ - 'url': 'http://www.dumpert.nl/mediabase/6646981/951bc60f/', + 'url': 'https://www.dumpert.nl/item/6646981_951bc60f', 'md5': '1b9318d7d5054e7dcb9dc7654f21d643', 'info_dict': { 'id': '6646981/951bc60f', @@ -24,46 +21,60 @@ class DumpertIE(InfoExtractor): 'thumbnail': r're:^https?://.*\.jpg$', } }, { - 'url': 'http://www.dumpert.nl/embed/6675421/dc440fe7/', + 'url': 'https://www.dumpert.nl/embed/6675421_dc440fe7', + 'only_matching': True, + }, { + 'url': 'http://legacy.dumpert.nl/mediabase/6646981/951bc60f', + 'only_matching': True, + }, { + 'url': 'http://legacy.dumpert.nl/embed/6675421/dc440fe7', 'only_matching': True, }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - protocol = mobj.group('protocol') - - url = '%s://www.dumpert.nl/mediabase/%s' % (protocol, video_id) - req = sanitized_Request(url) - req.add_header('Cookie', 'nsfw=1; cpc=10') - webpage = self._download_webpage(req, video_id) - - files_base64 = self._search_regex( - r'data-files="([^"]+)"', webpage, 'data files') - - files = self._parse_json( - compat_b64decode(files_base64).decode('utf-8'), - video_id) + video_id = self._match_id(url).replace('_', '/') + item = self._download_json( + 'http://api-live.dumpert.nl/mobile_api/json/info/' + video_id.replace('/', '_'), + video_id)['items'][0] + title = item['title'] + media = next(m for m in item['media'] if m.get('mediatype') == 'VIDEO') quality = qualities(['flv', 'mobile', 'tablet', '720p']) - - formats = [{ - 'url': video_url, - 'format_id': format_id, - 'quality': quality(format_id), - } for format_id, video_url in files.items() if format_id != 'still'] + formats = [] + for variant in media.get('variants', []): + uri = variant.get('uri') + if not uri: + continue + version = variant.get('version') + formats.append({ + 'url': uri, + 'format_id': version, + 'quality': quality(version), + }) self._sort_formats(formats) - title = self._html_search_meta( - 'title', webpage) or self._og_search_title(webpage) - description = self._html_search_meta( - 'description', webpage) or self._og_search_description(webpage) - thumbnail = files.get('still') or self._og_search_thumbnail(webpage) + thumbnails = [] + stills = item.get('stills') or {} + for t in ('thumb', 'still'): + for s in ('', '-medium', '-large'): + still_id = t + s + still_url = stills.get(still_id) + if not still_url: + continue + thumbnails.append({ + 'id': still_id, + 'url': still_url, + }) + + stats = item.get('stats') or {} return { 'id': video_id, 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'formats': formats + 'description': item.get('description'), + 'thumbnails': thumbnails, + 'formats': formats, + 'duration': int_or_none(media.get('duration')), + 'like_count': int_or_none(stats.get('kudos_total')), + 'view_count': int_or_none(stats.get('views_total')), } From 2b115b9460502944d6088cf42810c440495128a3 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 16 Oct 2019 15:41:58 +0100 Subject: [PATCH 095/422] [servingsys] Remove extractor(closes #22639) --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/servingsys.py | 72 ------------------------------ 2 files changed, 73 deletions(-) delete mode 100644 youtube_dl/extractor/servingsys.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 7a1e0dad6..53d527440 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -995,7 +995,6 @@ from .scrippsnetworks import ScrippsNetworksWatchIE from .seeker import SeekerIE from .senateisvp import SenateISVPIE from .sendtonews import SendtoNewsIE -from .servingsys import ServingSysIE from .servus import ServusIE from .sevenplus import SevenPlusIE from .sexu import SexuIE diff --git a/youtube_dl/extractor/servingsys.py b/youtube_dl/extractor/servingsys.py deleted file mode 100644 index c013d678f..000000000 --- a/youtube_dl/extractor/servingsys.py +++ /dev/null @@ -1,72 +0,0 @@ -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..utils import ( - int_or_none, -) - - -class ServingSysIE(InfoExtractor): - _VALID_URL = r'https?://(?:[^.]+\.)?serving-sys\.com/BurstingPipe/adServer\.bs\?.*?&pli=(?P<id>[0-9]+)' - - _TEST = { - 'url': 'http://bs.serving-sys.com/BurstingPipe/adServer.bs?cn=is&c=23&pl=VAST&pli=5349193&PluID=0&pos=7135&ord=[timestamp]&cim=1?', - 'info_dict': { - 'id': '5349193', - 'title': 'AdAPPter_Hyundai_demo', - }, - 'playlist': [{ - 'md5': 'baed851342df6846eb8677a60a011a0f', - 'info_dict': { - 'id': '29955898', - 'ext': 'flv', - 'title': 'AdAPPter_Hyundai_demo (1)', - 'duration': 74, - 'tbr': 1378, - 'width': 640, - 'height': 400, - }, - }, { - 'md5': '979b4da2655c4bc2d81aeb915a8c5014', - 'info_dict': { - 'id': '29907998', - 'ext': 'flv', - 'title': 'AdAPPter_Hyundai_demo (2)', - 'duration': 34, - 'width': 854, - 'height': 480, - 'tbr': 516, - }, - }], - 'params': { - 'playlistend': 2, - }, - '_skip': 'Blocked in the US [sic]', - } - - def _real_extract(self, url): - pl_id = self._match_id(url) - vast_doc = self._download_xml(url, pl_id) - - title = vast_doc.find('.//AdTitle').text - media = vast_doc.find('.//MediaFile').text - info_url = self._search_regex(r'&adData=([^&]+)&', media, 'info URL') - - doc = self._download_xml(info_url, pl_id, 'Downloading video info') - entries = [{ - '_type': 'video', - 'id': a.attrib['id'], - 'title': '%s (%s)' % (title, a.attrib['assetID']), - 'url': a.attrib['URL'], - 'duration': int_or_none(a.attrib.get('length')), - 'tbr': int_or_none(a.attrib.get('bitrate')), - 'height': int_or_none(a.attrib.get('height')), - 'width': int_or_none(a.attrib.get('width')), - } for a in doc.findall('.//AdditionalAssets/asset')] - - return { - '_type': 'playlist', - 'id': pl_id, - 'title': title, - 'entries': entries, - } From d07866f13efac39bf3f0b331870a15e0f5e98057 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 16 Oct 2019 15:45:45 +0100 Subject: [PATCH 096/422] [mit] Remove support for video.mit.edu(closes #22403) --- youtube_dl/extractor/extractors.py | 2 +- youtube_dl/extractor/mit.py | 24 ------------------------ 2 files changed, 1 insertion(+), 25 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 53d527440..ea47b99f6 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -644,7 +644,7 @@ from .minhateca import MinhatecaIE from .ministrygrid import MinistryGridIE from .minoto import MinotoIE from .miomio import MioMioIE -from .mit import TechTVMITIE, MITIE, OCWMITIE +from .mit import TechTVMITIE, OCWMITIE from .mitele import MiTeleIE from .mixcloud import ( MixcloudIE, diff --git a/youtube_dl/extractor/mit.py b/youtube_dl/extractor/mit.py index 1aea78d11..e1506a745 100644 --- a/youtube_dl/extractor/mit.py +++ b/youtube_dl/extractor/mit.py @@ -65,30 +65,6 @@ class TechTVMITIE(InfoExtractor): } -class MITIE(TechTVMITIE): - IE_NAME = 'video.mit.edu' - _VALID_URL = r'https?://video\.mit\.edu/watch/(?P<title>[^/]+)' - - _TEST = { - 'url': 'http://video.mit.edu/watch/the-government-is-profiling-you-13222/', - 'md5': '7db01d5ccc1895fc5010e9c9e13648da', - 'info_dict': { - 'id': '21783', - 'ext': 'mp4', - 'title': 'The Government is Profiling You', - 'description': 'md5:ad5795fe1e1623b73620dbfd47df9afd', - }, - } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - page_title = mobj.group('title') - webpage = self._download_webpage(url, page_title) - embed_url = self._search_regex( - r'<iframe .*?src="(.+?)"', webpage, 'embed url') - return self.url_result(embed_url) - - class OCWMITIE(InfoExtractor): IE_NAME = 'ocw.mit.edu' _VALID_URL = r'^https?://ocw\.mit\.edu/courses/(?P<topic>[a-z0-9\-]+)' From bc48773ed4c068adfe67078714814035660e5ca4 Mon Sep 17 00:00:00 2001 From: MobiDotS <msaad615@gmail.com> Date: Wed, 16 Oct 2019 10:13:35 -0500 Subject: [PATCH 097/422] [twitch] update VOD URL matching (closes #22395) (#22727) --- youtube_dl/extractor/twitch.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py index 0500e33a6..ca7676fe2 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -248,7 +248,7 @@ class TwitchVodIE(TwitchItemBaseIE): https?:// (?: (?:(?:www|go|m)\.)?twitch\.tv/(?:[^/]+/v(?:ideo)?|videos)/| - player\.twitch\.tv/\?.*?\bvideo=v + player\.twitch\.tv/\?.*?\bvideo=v? ) (?P<id>\d+) ''' @@ -306,6 +306,9 @@ class TwitchVodIE(TwitchItemBaseIE): }, { 'url': 'https://www.twitch.tv/northernlion/video/291940395', 'only_matching': True, + }, { + 'url': 'https://player.twitch.tv/?video=480452374', + 'only_matching': True, }] def _real_extract(self, url): From 000115759485797be719c71716c1ac35f003ba6c Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 16 Oct 2019 23:57:40 +0100 Subject: [PATCH 098/422] [atresplayer] Add coding cookie --- youtube_dl/extractor/atresplayer.py | 1 + 1 file changed, 1 insertion(+) diff --git a/youtube_dl/extractor/atresplayer.py b/youtube_dl/extractor/atresplayer.py index b96218f6c..c2cec9845 100644 --- a/youtube_dl/extractor/atresplayer.py +++ b/youtube_dl/extractor/atresplayer.py @@ -1,3 +1,4 @@ +# coding: utf-8 from __future__ import unicode_literals import re From 86f63633c8e7c62ce245d1352d4d381efb614466 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Thu, 17 Oct 2019 13:20:16 +0100 Subject: [PATCH 099/422] [audioboom] improve metadata extraction --- youtube_dl/extractor/audioboom.py | 34 +++++++++++++++++-------------- 1 file changed, 19 insertions(+), 15 deletions(-) diff --git a/youtube_dl/extractor/audioboom.py b/youtube_dl/extractor/audioboom.py index 393f381c6..c51837b40 100644 --- a/youtube_dl/extractor/audioboom.py +++ b/youtube_dl/extractor/audioboom.py @@ -2,22 +2,25 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import float_or_none +from ..utils import ( + clean_html, + float_or_none, +) class AudioBoomIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?audioboom\.com/(?:boos|posts)/(?P<id>[0-9]+)' _TESTS = [{ - 'url': 'https://audioboom.com/boos/4279833-3-09-2016-czaban-hour-3?t=0', - 'md5': '63a8d73a055c6ed0f1e51921a10a5a76', + 'url': 'https://audioboom.com/posts/7398103-asim-chaudhry', + 'md5': '7b00192e593ff227e6a315486979a42d', 'info_dict': { - 'id': '4279833', + 'id': '7398103', 'ext': 'mp3', - 'title': '3/09/2016 Czaban Hour 3', - 'description': 'Guest: Nate Davis - NFL free agency, Guest: Stan Gans', - 'duration': 2245.72, - 'uploader': 'SB Nation A.M.', - 'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channel/steveczabanyahoosportsradio', + 'title': 'Asim Chaudhry', + 'description': 'md5:2f3fef17dacc2595b5362e1d7d3602fc', + 'duration': 4000.99, + 'uploader': 'Sue Perkins: An hour or so with...', + 'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channel/perkins', } }, { 'url': 'https://audioboom.com/posts/4279833-3-09-2016-czaban-hour-3?t=0', @@ -32,8 +35,8 @@ class AudioBoomIE(InfoExtractor): clip = None clip_store = self._parse_json( - self._search_regex( - r'data-new-clip-store=(["\'])(?P<json>{.*?"clipId"\s*:\s*%s.*?})\1' % video_id, + self._html_search_regex( + r'data-new-clip-store=(["\'])(?P<json>{.+?})\1', webpage, 'clip store', default='{}', group='json'), video_id, fatal=False) if clip_store: @@ -47,14 +50,15 @@ class AudioBoomIE(InfoExtractor): audio_url = from_clip('clipURLPriorToLoading') or self._og_search_property( 'audio', webpage, 'audio url') - title = from_clip('title') or self._og_search_title(webpage) - description = from_clip('description') or self._og_search_description(webpage) + title = from_clip('title') or self._html_search_meta( + ['og:title', 'og:audio:title', 'audio_title'], webpage) + description = from_clip('description') or clean_html(from_clip('formattedDescription')) or self._og_search_description(webpage) duration = float_or_none(from_clip('duration') or self._html_search_meta( 'weibo:audio:duration', webpage)) - uploader = from_clip('author') or self._og_search_property( - 'audio:artist', webpage, 'uploader', fatal=False) + uploader = from_clip('author') or self._html_search_meta( + ['og:audio:artist', 'twitter:audio:artist_name', 'audio_artist'], webpage, 'uploader') uploader_url = from_clip('author_url') or self._html_search_meta( 'audioboo:channel', webpage, 'uploader url') From 755541a4c8ac3dd4e8b9abd0c7df95182a1f3fd4 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Thu, 17 Oct 2019 13:21:44 +0100 Subject: [PATCH 100/422] [mangomolo] fix video format extraction and add support for player URLs --- youtube_dl/extractor/generic.py | 8 ++++++-- youtube_dl/extractor/mangomolo.py | 17 +++++++++++------ 2 files changed, 17 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index ec43c5ae4..5ed952b29 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -2962,10 +2962,14 @@ class GenericIE(InfoExtractor): # Look for Mangomolo embeds mobj = re.search( - r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/ + r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?// + (?: + admin\.mangomolo\.com/analytics/index\.php/customers/embed| + player\.mangomolo\.com/v1 + )/ (?: video\?.*?\bid=(?P<video_id>\d+)| - index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+) + (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+) ).+?)\1''', webpage) if mobj is not None: info = { diff --git a/youtube_dl/extractor/mangomolo.py b/youtube_dl/extractor/mangomolo.py index 482175a34..acee370e9 100644 --- a/youtube_dl/extractor/mangomolo.py +++ b/youtube_dl/extractor/mangomolo.py @@ -10,18 +10,21 @@ from ..utils import int_or_none class MangomoloBaseIE(InfoExtractor): + _BASE_REGEX = r'https?://(?:admin\.mangomolo\.com/analytics/index\.php/customers/embed/|player\.mangomolo\.com/v1/)' + def _get_real_id(self, page_id): return page_id def _real_extract(self, url): page_id = self._get_real_id(self._match_id(url)) - webpage = self._download_webpage(url, page_id) + webpage = self._download_webpage( + 'https://player.mangomolo.com/v1/%s?%s' % (self._TYPE, url.split('?')[1]), page_id) hidden_inputs = self._hidden_inputs(webpage) m3u8_entry_protocol = 'm3u8' if self._IS_LIVE else 'm3u8_native' format_url = self._html_search_regex( [ - r'file\s*:\s*"(https?://[^"]+?/playlist\.m3u8)', + r'(?:file|src)\s*:\s*"(https?://[^"]+?/playlist\.m3u8)', r'<a[^>]+href="(rtsp://[^"]+)"' ], webpage, 'format url') formats = self._extract_wowza_formats( @@ -39,14 +42,16 @@ class MangomoloBaseIE(InfoExtractor): class MangomoloVideoIE(MangomoloBaseIE): - IE_NAME = 'mangomolo:video' - _VALID_URL = r'https?://admin\.mangomolo\.com/analytics/index\.php/customers/embed/video\?.*?\bid=(?P<id>\d+)' + _TYPE = 'video' + IE_NAME = 'mangomolo:' + _TYPE + _VALID_URL = MangomoloBaseIE._BASE_REGEX + r'video\?.*?\bid=(?P<id>\d+)' _IS_LIVE = False class MangomoloLiveIE(MangomoloBaseIE): - IE_NAME = 'mangomolo:live' - _VALID_URL = r'https?://admin\.mangomolo\.com/analytics/index\.php/customers/embed/index\?.*?\bchannelid=(?P<id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)' + _TYPE = 'live' + IE_NAME = 'mangomolo:' + _TYPE + _VALID_URL = MangomoloBaseIE._BASE_REGEX + r'(live|index)\?.*?\bchannelid=(?P<id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)' _IS_LIVE = True def _get_real_id(self, page_id): From 59296bae7ec6d15b0df37dce34bdd96381c0e743 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Thu, 17 Oct 2019 13:26:45 +0100 Subject: [PATCH 101/422] [xfileshare] clean extractor - update the list of domains - add support for aa-encoded video data - improve jwplayer format extraction - add support for Clappr sources closes #17032 closes #17906 closes #18237 closes #18239 --- youtube_dl/extractor/xfileshare.py | 192 +++++++++++++---------------- 1 file changed, 86 insertions(+), 106 deletions(-) diff --git a/youtube_dl/extractor/xfileshare.py b/youtube_dl/extractor/xfileshare.py index b38c7a7b3..48ef07ed1 100644 --- a/youtube_dl/extractor/xfileshare.py +++ b/youtube_dl/extractor/xfileshare.py @@ -4,37 +4,64 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_chr from ..utils import ( decode_packed_codes, determine_ext, ExtractorError, int_or_none, - NO_DEFAULT, + js_to_json, urlencode_postdata, ) +# based on openload_decode from 2bfeee69b976fe049761dd3012e30b637ee05a58 +def aa_decode(aa_code): + symbol_table = [ + ('7', '((ﾟｰﾟ) + (o^_^o))'), + ('6', '((o^_^o) +(o^_^o))'), + ('5', '((ﾟｰﾟ) + (ﾟΘﾟ))'), + ('2', '((o^_^o) - (ﾟΘﾟ))'), + ('4', '(ﾟｰﾟ)'), + ('3', '(o^_^o)'), + ('1', '(ﾟΘﾟ)'), + ('0', '(c^_^o)'), + ] + delim = '(ﾟДﾟ)[ﾟεﾟ]+' + ret = '' + for aa_char in aa_code.split(delim): + for val, pat in symbol_table: + aa_char = aa_char.replace(pat, val) + aa_char = aa_char.replace('+ ', '') + m = re.match(r'^\d+', aa_char) + if m: + ret += compat_chr(int(m.group(0), 8)) + else: + m = re.match(r'^u([\da-f]+)', aa_char) + if m: + ret += compat_chr(int(m.group(1), 16)) + return ret + + class XFileShareIE(InfoExtractor): _SITES = ( - (r'daclips\.(?:in|com)', 'DaClips'), - (r'filehoot\.com', 'FileHoot'), - (r'gorillavid\.(?:in|com)', 'GorillaVid'), - (r'movpod\.in', 'MovPod'), - (r'powerwatch\.pw', 'PowerWatch'), - (r'rapidvideo\.ws', 'Rapidvideo.ws'), + (r'clipwatching\.com', 'ClipWatching'), + (r'gounlimited\.to', 'GoUnlimited'), + (r'govid\.me', 'GoVid'), + (r'holavid\.com', 'HolaVid'), + (r'streamty\.com', 'Streamty'), (r'thevideobee\.to', 'TheVideoBee'), - (r'vidto\.(?:me|se)', 'Vidto'), - (r'streamin\.to', 'Streamin.To'), - (r'xvidstage\.com', 'XVIDSTAGE'), - (r'vidabc\.com', 'Vid ABC'), + (r'uqload\.com', 'Uqload'), (r'vidbom\.com', 'VidBom'), (r'vidlo\.us', 'vidlo'), - (r'rapidvideo\.(?:cool|org)', 'RapidVideo.TV'), - (r'fastvideo\.me', 'FastVideo.me'), + (r'vidlocker\.xyz', 'VidLocker'), + (r'vidshare\.tv', 'VidShare'), + (r'vup\.to', 'VUp'), + (r'xvideosharing\.com', 'XVideoSharing'), ) IE_DESC = 'XFileShare based sites: %s' % ', '.join(list(zip(*_SITES))[1]) - _VALID_URL = (r'https?://(?P<host>(?:www\.)?(?:%s))/(?:embed-)?(?P<id>[0-9a-zA-Z]+)' + _VALID_URL = (r'https?://(?:www\.)?(?P<host>%s)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)' % '|'.join(site for site in list(zip(*_SITES))[0])) _FILE_NOT_FOUND_REGEXES = ( @@ -43,82 +70,14 @@ class XFileShareIE(InfoExtractor): ) _TESTS = [{ - 'url': 'http://gorillavid.in/06y9juieqpmi', - 'md5': '5ae4a3580620380619678ee4875893ba', + 'url': 'http://xvideosharing.com/fq65f94nd2ve', + 'md5': '4181f63957e8fe90ac836fa58dc3c8a6', 'info_dict': { - 'id': '06y9juieqpmi', + 'id': 'fq65f94nd2ve', 'ext': 'mp4', - 'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ', + 'title': 'sample', 'thumbnail': r're:http://.*\.jpg', }, - }, { - 'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html', - 'only_matching': True, - }, { - 'url': 'http://daclips.in/3rso4kdn6f9m', - 'md5': '1ad8fd39bb976eeb66004d3a4895f106', - 'info_dict': { - 'id': '3rso4kdn6f9m', - 'ext': 'mp4', - 'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc', - 'thumbnail': r're:http://.*\.jpg', - } - }, { - 'url': 'http://movpod.in/0wguyyxi1yca', - 'only_matching': True, - }, { - 'url': 'http://filehoot.com/3ivfabn7573c.html', - 'info_dict': { - 'id': '3ivfabn7573c', - 'ext': 'mp4', - 'title': 'youtube-dl test video \'äBaW_jenozKc.mp4.mp4', - 'thumbnail': r're:http://.*\.jpg', - }, - 'skip': 'Video removed', - }, { - 'url': 'http://vidto.me/ku5glz52nqe1.html', - 'info_dict': { - 'id': 'ku5glz52nqe1', - 'ext': 'mp4', - 'title': 'test' - } - }, { - 'url': 'http://powerwatch.pw/duecjibvicbu', - 'info_dict': { - 'id': 'duecjibvicbu', - 'ext': 'mp4', - 'title': 'Big Buck Bunny trailer', - }, - }, { - 'url': 'http://xvidstage.com/e0qcnl03co6z', - 'info_dict': { - 'id': 'e0qcnl03co6z', - 'ext': 'mp4', - 'title': 'Chucky Prank 2015.mp4', - }, - }, { - # removed by administrator - 'url': 'http://xvidstage.com/amfy7atlkx25', - 'only_matching': True, - }, { - 'url': 'http://vidabc.com/i8ybqscrphfv', - 'info_dict': { - 'id': 'i8ybqscrphfv', - 'ext': 'mp4', - 'title': 're:Beauty and the Beast 2017', - }, - 'params': { - 'skip_download': True, - }, - }, { - 'url': 'http://www.rapidvideo.cool/b667kprndr8w', - 'only_matching': True, - }, { - 'url': 'http://www.fastvideo.me/k8604r8nk8sn/FAST_FURIOUS_8_-_Trailer_italiano_ufficiale.mp4.html', - 'only_matching': True, - }, { - 'url': 'http://vidto.se/1tx1pf6t12cg.html', - 'only_matching': True, }] @staticmethod @@ -131,10 +90,9 @@ class XFileShareIE(InfoExtractor): webpage)] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + host, video_id = re.match(self._VALID_URL, url).groups() - url = 'http://%s/%s' % (mobj.group('host'), video_id) + url = 'https://%s/' % host + ('embed-%s.html' % video_id if host in ('govid.me', 'vidlo.us') else video_id) webpage = self._download_webpage(url, video_id) if any(re.search(p, webpage) for p in self._FILE_NOT_FOUND_REGEXES): @@ -142,7 +100,7 @@ class XFileShareIE(InfoExtractor): fields = self._hidden_inputs(webpage) - if fields['op'] == 'download1': + if fields.get('op') == 'download1': countdown = int_or_none(self._search_regex( r'<span id="countdown_str">(?:[Ww]ait)?\s*<span id="cxc">(\d+)</span>\s*(?:seconds?)?</span>', webpage, 'countdown', default=None)) @@ -160,13 +118,37 @@ class XFileShareIE(InfoExtractor): (r'style="z-index: [0-9]+;">([^<]+)</span>', r'<td nowrap>([^<]+)</td>', r'h4-fine[^>]*>([^<]+)<', - r'>Watch (.+) ', + r'>Watch (.+)[ <]', r'<h2 class="video-page-head">([^<]+)</h2>', - r'<h2 style="[^"]*color:#403f3d[^"]*"[^>]*>([^<]+)<'), # streamin.to + r'<h2 style="[^"]*color:#403f3d[^"]*"[^>]*>([^<]+)<', # streamin.to + r'title\s*:\s*"([^"]+)"'), # govid.me webpage, 'title', default=None) or self._og_search_title( webpage, default=None) or video_id).strip() - def extract_formats(default=NO_DEFAULT): + for regex, func in ( + (r'(eval\(function\(p,a,c,k,e,d\){.+)', decode_packed_codes), + (r'(ﾟ.+)', aa_decode)): + obf_code = self._search_regex(regex, webpage, 'obfuscated code', default=None) + if obf_code: + webpage = webpage.replace(obf_code, func(obf_code)) + + formats = [] + + jwplayer_data = self._search_regex( + [ + r'jwplayer\("[^"]+"\)\.load\(\[({.+?})\]\);', + r'jwplayer\("[^"]+"\)\.setup\(({.+?})\);', + ], webpage, + 'jwplayer data', default=None) + if jwplayer_data: + jwplayer_data = self._parse_json( + jwplayer_data.replace(r"\'", "'"), video_id, js_to_json) + if jwplayer_data: + formats = self._parse_jwplayer_data( + jwplayer_data, video_id, False, + m3u8_id='hls', mpd_id='dash')['formats'] + + if not formats: urls = [] for regex in ( r'(?:file|src)\s*:\s*(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1', @@ -177,6 +159,12 @@ class XFileShareIE(InfoExtractor): video_url = mobj.group('url') if video_url not in urls: urls.append(video_url) + + sources = self._search_regex( + r'sources\s*:\s*(\[(?!{)[^\]]+\])', webpage, 'sources', default=None) + if sources: + urls.extend(self._parse_json(sources, video_id)) + formats = [] for video_url in urls: if determine_ext(video_url) == 'm3u8': @@ -189,21 +177,13 @@ class XFileShareIE(InfoExtractor): 'url': video_url, 'format_id': 'sd', }) - if not formats and default is not NO_DEFAULT: - return default - self._sort_formats(formats) - return formats - - formats = extract_formats(default=None) - - if not formats: - webpage = decode_packed_codes(self._search_regex( - r"(}\('(.+)',(\d+),(\d+),'[^']*\b(?:file|embed)\b[^']*'\.split\('\|'\))", - webpage, 'packed code')) - formats = extract_formats() + self._sort_formats(formats) thumbnail = self._search_regex( - r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', default=None) + [ + r'<video[^>]+poster="([^"]+)"', + r'(?:image|poster)\s*:\s*["\'](http[^"\']+)["\'],', + ], webpage, 'thumbnail', default=None) return { 'id': video_id, From 34e3885bc9e3aecab104b96eabce03854ac8f7a2 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Thu, 17 Oct 2019 15:55:44 +0100 Subject: [PATCH 102/422] [viewster->contv] remove viewster extractor and add support for contv.com --- youtube_dl/extractor/contv.py | 118 ++++++++++++++++ youtube_dl/extractor/extractors.py | 2 +- youtube_dl/extractor/viewster.py | 217 ----------------------------- 3 files changed, 119 insertions(+), 218 deletions(-) create mode 100644 youtube_dl/extractor/contv.py delete mode 100644 youtube_dl/extractor/viewster.py diff --git a/youtube_dl/extractor/contv.py b/youtube_dl/extractor/contv.py new file mode 100644 index 000000000..84b462d40 --- /dev/null +++ b/youtube_dl/extractor/contv.py @@ -0,0 +1,118 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + float_or_none, + int_or_none, +) + + +class CONtvIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?contv\.com/details-movie/(?P<id>[^/]+)' + _TESTS = [{ + 'url': 'https://www.contv.com/details-movie/CEG10022949/days-of-thrills-&-laughter', + 'info_dict': { + 'id': 'CEG10022949', + 'ext': 'mp4', + 'title': 'Days Of Thrills & Laughter', + 'description': 'md5:5d6b3d0b1829bb93eb72898c734802eb', + 'upload_date': '20180703', + 'timestamp': 1530634789.61, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + 'url': 'https://www.contv.com/details-movie/CLIP-show_fotld_bts/fight-of-the-living-dead:-behind-the-scenes-bites', + 'info_dict': { + 'id': 'CLIP-show_fotld_bts', + 'title': 'Fight of the Living Dead: Behind the Scenes Bites', + }, + 'playlist_mincount': 7, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + details = self._download_json( + 'http://metax.contv.live.junctiontv.net/metax/2.5/details/' + video_id, + video_id, query={'device': 'web'}) + + if details.get('type') == 'episodic': + seasons = self._download_json( + 'http://metax.contv.live.junctiontv.net/metax/2.5/seriesfeed/json/' + video_id, + video_id) + entries = [] + for season in seasons: + for episode in season.get('episodes', []): + episode_id = episode.get('id') + if not episode_id: + continue + entries.append(self.url_result( + 'https://www.contv.com/details-movie/' + episode_id, + CONtvIE.ie_key(), episode_id)) + return self.playlist_result(entries, video_id, details.get('title')) + + m_details = details['details'] + title = details['title'] + + formats = [] + + media_hls_url = m_details.get('media_hls_url') + if media_hls_url: + formats.extend(self._extract_m3u8_formats( + media_hls_url, video_id, 'mp4', + m3u8_id='hls', fatal=False)) + + media_mp4_url = m_details.get('media_mp4_url') + if media_mp4_url: + formats.append({ + 'format_id': 'http', + 'url': media_mp4_url, + }) + + self._sort_formats(formats) + + subtitles = {} + captions = m_details.get('captions') or {} + for caption_url in captions.values(): + subtitles.setdefault('en', []).append({ + 'url': caption_url + }) + + thumbnails = [] + for image in m_details.get('images', []): + image_url = image.get('url') + if not image_url: + continue + thumbnails.append({ + 'url': image_url, + 'width': int_or_none(image.get('width')), + 'height': int_or_none(image.get('height')), + }) + + description = None + for p in ('large_', 'medium_', 'small_', ''): + d = m_details.get(p + 'description') + if d: + description = d + break + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnails': thumbnails, + 'description': description, + 'timestamp': float_or_none(details.get('metax_added_on'), 1000), + 'subtitles': subtitles, + 'duration': float_or_none(m_details.get('duration'), 1000), + 'view_count': int_or_none(details.get('num_watched')), + 'like_count': int_or_none(details.get('num_fav')), + 'categories': details.get('category'), + 'tags': details.get('tags'), + 'season_number': int_or_none(details.get('season')), + 'episode_number': int_or_none(details.get('episode')), + 'release_year': int_or_none(details.get('pub_year')), + } diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index ea47b99f6..1db21529f 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -231,6 +231,7 @@ from .commonprotocols import ( RtmpIE, ) from .condenast import CondeNastIE +from .contv import CONtvIE from .corus import CorusIE from .cracked import CrackedIE from .crackle import CrackleIE @@ -1322,7 +1323,6 @@ from .viewlift import ( ViewLiftIE, ViewLiftEmbedIE, ) -from .viewster import ViewsterIE from .viidea import ViideaIE from .vimeo import ( VimeoIE, diff --git a/youtube_dl/extractor/viewster.py b/youtube_dl/extractor/viewster.py deleted file mode 100644 index 6e318479c..000000000 --- a/youtube_dl/extractor/viewster.py +++ /dev/null @@ -1,217 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..compat import ( - compat_HTTPError, - compat_urllib_parse_unquote, -) -from ..utils import ( - determine_ext, - ExtractorError, - int_or_none, - parse_iso8601, - sanitized_Request, - HEADRequest, - url_basename, -) - - -class ViewsterIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?viewster\.com/(?:serie|movie)/(?P<id>\d+-\d+-\d+)' - _TESTS = [{ - # movie, Type=Movie - 'url': 'http://www.viewster.com/movie/1140-11855-000/the-listening-project/', - 'md5': 'e642d1b27fcf3a4ffa79f194f5adde36', - 'info_dict': { - 'id': '1140-11855-000', - 'ext': 'mp4', - 'title': 'The listening Project', - 'description': 'md5:bac720244afd1a8ea279864e67baa071', - 'timestamp': 1214870400, - 'upload_date': '20080701', - 'duration': 4680, - }, - }, { - # series episode, Type=Episode - 'url': 'http://www.viewster.com/serie/1284-19427-001/the-world-and-a-wall/', - 'md5': '9243079a8531809efe1b089db102c069', - 'info_dict': { - 'id': '1284-19427-001', - 'ext': 'mp4', - 'title': 'The World and a Wall', - 'description': 'md5:24814cf74d3453fdf5bfef9716d073e3', - 'timestamp': 1428192000, - 'upload_date': '20150405', - 'duration': 1500, - }, - }, { - # serie, Type=Serie - 'url': 'http://www.viewster.com/serie/1303-19426-000/', - 'info_dict': { - 'id': '1303-19426-000', - 'title': 'Is It Wrong to Try to Pick up Girls in a Dungeon?', - 'description': 'md5:eeda9bef25b0d524b3a29a97804c2f11', - }, - 'playlist_count': 13, - }, { - # unfinished serie, no Type - 'url': 'http://www.viewster.com/serie/1284-19427-000/baby-steps-season-2/', - 'info_dict': { - 'id': '1284-19427-000', - 'title': 'Baby Steps—Season 2', - 'description': 'md5:e7097a8fc97151e25f085c9eb7a1cdb1', - }, - 'playlist_mincount': 16, - }, { - # geo restricted series - 'url': 'https://www.viewster.com/serie/1280-18794-002/', - 'only_matching': True, - }, { - # geo restricted video - 'url': 'https://www.viewster.com/serie/1280-18794-002/what-is-extraterritoriality-lawo/', - 'only_matching': True, - }] - - _ACCEPT_HEADER = 'application/json, text/javascript, */*; q=0.01' - - def _download_json(self, url, video_id, note='Downloading JSON metadata', fatal=True, query={}): - request = sanitized_Request(url) - request.add_header('Accept', self._ACCEPT_HEADER) - request.add_header('Auth-token', self._AUTH_TOKEN) - return super(ViewsterIE, self)._download_json(request, video_id, note, fatal=fatal, query=query) - - def _real_extract(self, url): - video_id = self._match_id(url) - # Get 'api_token' cookie - self._request_webpage( - HEADRequest('http://www.viewster.com/'), - video_id, headers=self.geo_verification_headers()) - cookies = self._get_cookies('http://www.viewster.com/') - self._AUTH_TOKEN = compat_urllib_parse_unquote(cookies['api_token'].value) - - info = self._download_json( - 'https://public-api.viewster.com/search/%s' % video_id, - video_id, 'Downloading entry JSON') - - entry_id = info.get('Id') or info['id'] - - # unfinished serie has no Type - if info.get('Type') in ('Serie', None): - try: - episodes = self._download_json( - 'https://public-api.viewster.com/series/%s/episodes' % entry_id, - video_id, 'Downloading series JSON') - except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404: - self.raise_geo_restricted() - else: - raise - entries = [ - self.url_result( - 'http://www.viewster.com/movie/%s' % episode['OriginId'], 'Viewster') - for episode in episodes] - title = (info.get('Title') or info['Synopsis']['Title']).strip() - description = info.get('Synopsis', {}).get('Detailed') - return self.playlist_result(entries, video_id, title, description) - - formats = [] - for language_set in info.get('LanguageSets', []): - manifest_url = None - m3u8_formats = [] - audio = language_set.get('Audio') or '' - subtitle = language_set.get('Subtitle') or '' - base_format_id = audio - if subtitle: - base_format_id += '-%s' % subtitle - - def concat(suffix, sep='-'): - return (base_format_id + '%s%s' % (sep, suffix)) if base_format_id else suffix - - medias = self._download_json( - 'https://public-api.viewster.com/movies/%s/videos' % entry_id, - video_id, fatal=False, query={ - 'mediaTypes': ['application/f4m+xml', 'application/x-mpegURL', 'video/mp4'], - 'language': audio, - 'subtitle': subtitle, - }) - if not medias: - continue - for media in medias: - video_url = media.get('Uri') - if not video_url: - continue - ext = determine_ext(video_url) - if ext == 'f4m': - manifest_url = video_url - video_url += '&' if '?' in video_url else '?' - video_url += 'hdcore=3.2.0&plugin=flowplayer-3.2.0.1' - formats.extend(self._extract_f4m_formats( - video_url, video_id, f4m_id=concat('hds'))) - elif ext == 'm3u8': - manifest_url = video_url - m3u8_formats = self._extract_m3u8_formats( - video_url, video_id, 'mp4', m3u8_id=concat('hls'), - fatal=False) # m3u8 sometimes fail - if m3u8_formats: - formats.extend(m3u8_formats) - else: - qualities_basename = self._search_regex( - r'/([^/]+)\.csmil/', - manifest_url, 'qualities basename', default=None) - if not qualities_basename: - continue - QUALITIES_RE = r'((,\d+k)+,?)' - qualities = self._search_regex( - QUALITIES_RE, qualities_basename, - 'qualities', default=None) - if not qualities: - continue - qualities = list(map(lambda q: int(q[:-1]), qualities.strip(',').split(','))) - qualities.sort() - http_template = re.sub(QUALITIES_RE, r'%dk', qualities_basename) - http_url_basename = url_basename(video_url) - if m3u8_formats: - self._sort_formats(m3u8_formats) - m3u8_formats = list(filter( - lambda f: f.get('vcodec') != 'none', m3u8_formats)) - if len(qualities) == len(m3u8_formats): - for q, m3u8_format in zip(qualities, m3u8_formats): - f = m3u8_format.copy() - f.update({ - 'url': video_url.replace(http_url_basename, http_template % q), - 'format_id': f['format_id'].replace('hls', 'http'), - 'protocol': 'http', - }) - formats.append(f) - else: - for q in qualities: - formats.append({ - 'url': video_url.replace(http_url_basename, http_template % q), - 'ext': 'mp4', - 'format_id': 'http-%d' % q, - 'tbr': q, - }) - - if not formats and not info.get('VODSettings'): - self.raise_geo_restricted() - - self._sort_formats(formats) - - synopsis = info.get('Synopsis') or {} - # Prefer title outside synopsis since it's less messy - title = (info.get('Title') or synopsis['Title']).strip() - description = synopsis.get('Detailed') or (info.get('Synopsis') or {}).get('Short') - duration = int_or_none(info.get('Duration')) - timestamp = parse_iso8601(info.get('ReleaseDate')) - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'timestamp': timestamp, - 'duration': duration, - 'formats': formats, - } From 824fa51165d92ceee01589bf995ebbf009df328c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 18 Oct 2019 04:03:53 +0700 Subject: [PATCH 103/422] [utils] Improve subtitles_filename (closes #22753) --- test/test_utils.py | 6 ++++++ youtube_dl/YoutubeDL.py | 2 +- youtube_dl/postprocessor/ffmpeg.py | 8 ++++---- youtube_dl/utils.py | 4 ++-- 4 files changed, 13 insertions(+), 7 deletions(-) diff --git a/test/test_utils.py b/test/test_utils.py index 659c6ece5..3920542bb 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -74,6 +74,7 @@ from youtube_dl.utils import ( str_to_int, strip_jsonp, strip_or_none, + subtitles_filename, timeconvert, unescapeHTML, unified_strdate, @@ -261,6 +262,11 @@ class TestUtil(unittest.TestCase): self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp') self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp') + def test_subtitles_filename(self): + self.assertEqual(subtitles_filename('abc.ext', 'en', 'vtt'), 'abc.en.vtt') + self.assertEqual(subtitles_filename('abc.ext', 'en', 'vtt', 'ext'), 'abc.en.vtt') + self.assertEqual(subtitles_filename('abc.unexpected_ext', 'en', 'vtt', 'ext'), 'abc.unexpected_ext.en.vtt') + def test_remove_start(self): self.assertEqual(remove_start(None, 'A - '), None) self.assertEqual(remove_start('A - B', 'A - '), 'B') diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index c3d1407f9..f5cb46308 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -1814,7 +1814,7 @@ class YoutubeDL(object): ie = self.get_info_extractor(info_dict['extractor_key']) for sub_lang, sub_info in subtitles.items(): sub_format = sub_info['ext'] - sub_filename = subtitles_filename(filename, sub_lang, sub_format) + sub_filename = subtitles_filename(filename, sub_lang, sub_format, info_dict.get('ext')) if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(sub_filename)): self.to_screen('[info] Video subtitle %s.%s is already present' % (sub_lang, sub_format)) else: diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index 70416c25e..fd3f921a8 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -393,7 +393,7 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor): sub_ext = sub_info['ext'] if ext != 'webm' or ext == 'webm' and sub_ext == 'vtt': sub_langs.append(lang) - sub_filenames.append(subtitles_filename(filename, lang, sub_ext)) + sub_filenames.append(subtitles_filename(filename, lang, sub_ext, ext)) else: if not webm_vtt_warn and ext == 'webm' and sub_ext != 'vtt': webm_vtt_warn = True @@ -606,9 +606,9 @@ class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor): self._downloader.to_screen( '[ffmpeg] Subtitle file for %s is already in the requested format' % new_ext) continue - old_file = subtitles_filename(filename, lang, ext) + old_file = subtitles_filename(filename, lang, ext, info.get('ext')) sub_filenames.append(old_file) - new_file = subtitles_filename(filename, lang, new_ext) + new_file = subtitles_filename(filename, lang, new_ext, info.get('ext')) if ext in ('dfxp', 'ttml', 'tt'): self._downloader.report_warning( @@ -616,7 +616,7 @@ class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor): 'which results in style information loss') dfxp_file = old_file - srt_file = subtitles_filename(filename, lang, 'srt') + srt_file = subtitles_filename(filename, lang, 'srt', info.get('ext')) with open(dfxp_file, 'rb') as f: srt_data = dfxp2srt(f.read()) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 798757241..53117ea90 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -2906,8 +2906,8 @@ def determine_ext(url, default_ext='unknown_video'): return default_ext -def subtitles_filename(filename, sub_lang, sub_format): - return filename.rsplit('.', 1)[0] + '.' + sub_lang + '.' + sub_format +def subtitles_filename(filename, sub_lang, sub_format, expected_real_ext=None): + return replace_extension(filename, sub_lang + '.' + sub_format, expected_real_ext) def date_from_str(date_str): From 2297c0d7d977921dca865e6c9cbc7ee5282ba8ef Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 19 Oct 2019 23:56:36 +0700 Subject: [PATCH 104/422] [facebook] Bypass download rate limits (closes #21018) --- youtube_dl/extractor/facebook.py | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index a3dcdca3e..a56f85c21 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -405,6 +405,11 @@ class FacebookIE(InfoExtractor): if not formats: raise ExtractorError('Cannot find video formats') + # Downloads with browser's User-Agent are rate limited. Working around + # with non-browser User-Agent. + for f in formats: + f.setdefault('http_headers', {})['User-Agent'] = 'facebookexternalhit/1.1' + self._sort_formats(formats) video_title = self._html_search_regex( From b4818e3c7a718428d3366c34da8e21e2f416f5e0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 22 Oct 2019 00:02:22 +0700 Subject: [PATCH 105/422] [ChangeLog] Actualize [ci skip] --- ChangeLog | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/ChangeLog b/ChangeLog index dc5c32a1f..045349b05 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,26 @@ +version <unreleased> + +Core +* [utils] Improve subtitles_filename (#22753) + +Extractors +* [facebook] Bypass download rate limits (#21018) ++ [contv] Add support for contv.com +- [viewster] Remove extractor +* [xfileshare] Improve extractor (#17032, #17906, #18237, #18239) + * Update the list of domains + + Add support for aa-encoded video data + * Improve jwplayer format extraction + + Add support for Clappr sources +* [mangomolo] Fix video format extraction and add support for player URLs +* [audioboom] Improve metadata extraction +* [twitch] Update VOD URL matching (#22395, #22727) +- [mit] Remove support for video.mit.edu (#22403) +- [servingsys] Remove extractor (#22639) +* [dumpert] Fix extraction (#22428, #22564) +* [atresplayer] Fix extraction (#16277, #16716) + + version 2019.10.16 Core From 820215f0e34813089d559fed24a398d9e91810e0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 22 Oct 2019 00:09:02 +0700 Subject: [PATCH 106/422] release 2019.10.22 --- .github/ISSUE_TEMPLATE/1_broken_site.md | 6 +++--- .github/ISSUE_TEMPLATE/2_site_support_request.md | 4 ++-- .github/ISSUE_TEMPLATE/3_site_feature_request.md | 4 ++-- .github/ISSUE_TEMPLATE/4_bug_report.md | 6 +++--- .github/ISSUE_TEMPLATE/5_feature_request.md | 4 ++-- ChangeLog | 2 +- docs/supportedsites.md | 6 ++---- youtube_dl/version.py | 2 +- 8 files changed, 16 insertions(+), 18 deletions(-) diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.md b/.github/ISSUE_TEMPLATE/1_broken_site.md index 5cd9f0dc0..f1afe704c 100644 --- a/.github/ISSUE_TEMPLATE/1_broken_site.md +++ b/.github/ISSUE_TEMPLATE/1_broken_site.md @@ -18,7 +18,7 @@ title: '' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.16. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.22. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape. - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates. @@ -26,7 +26,7 @@ Carefully read and work through this check list in order to prevent the most com --> - [ ] I'm reporting a broken site support -- [ ] I've verified that I'm running youtube-dl version **2019.10.16** +- [ ] I've verified that I'm running youtube-dl version **2019.10.22** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar issues including closed ones @@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.10.16 + [debug] youtube-dl version 2019.10.22 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/2_site_support_request.md b/.github/ISSUE_TEMPLATE/2_site_support_request.md index 6cc34796a..a4dc9b005 100644 --- a/.github/ISSUE_TEMPLATE/2_site_support_request.md +++ b/.github/ISSUE_TEMPLATE/2_site_support_request.md @@ -19,7 +19,7 @@ labels: 'site-support-request' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.16. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.22. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that site you are requesting is not dedicated to copyright infringement, see https://yt-dl.org/copyright-infringement. youtube-dl does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights. - Search the bugtracker for similar site support requests: http://yt-dl.org/search-issues. DO NOT post duplicates. @@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com --> - [ ] I'm reporting a new site support request -- [ ] I've verified that I'm running youtube-dl version **2019.10.16** +- [ ] I've verified that I'm running youtube-dl version **2019.10.22** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that none of provided URLs violate any copyrights - [ ] I've searched the bugtracker for similar site support requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/3_site_feature_request.md b/.github/ISSUE_TEMPLATE/3_site_feature_request.md index 0b7911e79..5bf86adce 100644 --- a/.github/ISSUE_TEMPLATE/3_site_feature_request.md +++ b/.github/ISSUE_TEMPLATE/3_site_feature_request.md @@ -18,13 +18,13 @@ title: '' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.16. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.22. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Search the bugtracker for similar site feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates. - Finally, put x into all relevant boxes (like this [x]) --> - [ ] I'm reporting a site feature request -- [ ] I've verified that I'm running youtube-dl version **2019.10.16** +- [ ] I've verified that I'm running youtube-dl version **2019.10.22** - [ ] I've searched the bugtracker for similar site feature requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/4_bug_report.md b/.github/ISSUE_TEMPLATE/4_bug_report.md index a6f417d38..7aa5534e5 100644 --- a/.github/ISSUE_TEMPLATE/4_bug_report.md +++ b/.github/ISSUE_TEMPLATE/4_bug_report.md @@ -18,7 +18,7 @@ title: '' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.16. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.22. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape. - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates. @@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com --> - [ ] I'm reporting a broken site support issue -- [ ] I've verified that I'm running youtube-dl version **2019.10.16** +- [ ] I've verified that I'm running youtube-dl version **2019.10.22** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar bug reports including closed ones @@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.10.16 + [debug] youtube-dl version 2019.10.22 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/5_feature_request.md b/.github/ISSUE_TEMPLATE/5_feature_request.md index 3fe753b62..5d3645e3d 100644 --- a/.github/ISSUE_TEMPLATE/5_feature_request.md +++ b/.github/ISSUE_TEMPLATE/5_feature_request.md @@ -19,13 +19,13 @@ labels: 'request' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.16. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.22. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Search the bugtracker for similar feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates. - Finally, put x into all relevant boxes (like this [x]) --> - [ ] I'm reporting a feature request -- [ ] I've verified that I'm running youtube-dl version **2019.10.16** +- [ ] I've verified that I'm running youtube-dl version **2019.10.22** - [ ] I've searched the bugtracker for similar feature requests including closed ones diff --git a/ChangeLog b/ChangeLog index 045349b05..64233b03b 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2019.10.22 Core * [utils] Improve subtitles_filename (#22753) diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 0cbad28ea..a1b0edeeb 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -183,6 +183,7 @@ - **ComedyCentralShortname** - **ComedyCentralTV** - **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED + - **CONtv** - **Corus** - **Coub** - **Cracked** @@ -784,7 +785,6 @@ - **Seeker** - **SenateISVP** - **SendtoNews** - - **ServingSys** - **Servus** - **Sexu** - **SeznamZpravy** @@ -1005,7 +1005,6 @@ - **Viddler** - **Videa** - **video.google:search**: Google Video search - - **video.mit.edu** - **VideoDetective** - **videofy.me** - **videomore** @@ -1023,7 +1022,6 @@ - **vier:videos** - **ViewLift** - **ViewLiftEmbed** - - **Viewster** - **Viidea** - **viki** - **viki:channel** @@ -1097,7 +1095,7 @@ - **WWE** - **XBef** - **XboxClips** - - **XFileShare**: XFileShare based sites: DaClips, FileHoot, GorillaVid, MovPod, PowerWatch, Rapidvideo.ws, TheVideoBee, Vidto, Streamin.To, XVIDSTAGE, Vid ABC, VidBom, vidlo, RapidVideo.TV, FastVideo.me + - **XFileShare**: XFileShare based sites: ClipWatching, GoUnlimited, GoVid, HolaVid, Streamty, TheVideoBee, Uqload, VidBom, vidlo, VidLocker, VidShare, VUp, XVideoSharing - **XHamster** - **XHamsterEmbed** - **XHamsterUser** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 53889b7cb..39b355b9e 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.10.16' +__version__ = '2019.10.22' From 0c2d10d225f61ac1fb534d8ed1788250401465b2 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Tue, 22 Oct 2019 17:49:50 +0100 Subject: [PATCH 107/422] [globo] handle alternative hash signing method --- youtube_dl/extractor/globo.py | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/globo.py b/youtube_dl/extractor/globo.py index 9ad1d95fb..60d842d3a 100644 --- a/youtube_dl/extractor/globo.py +++ b/youtube_dl/extractor/globo.py @@ -132,18 +132,24 @@ class GloboIE(InfoExtractor): '%s returned error: %s' % (self.IE_NAME, message), expected=True) continue - assert security_hash[:2] in ('04', '14') - received_time = security_hash[3:13] - received_md5 = security_hash[24:] - - sign_time = compat_str(int(received_time) + 86400) + hash_code = security_hash[:2] padding = '%010d' % random.randint(1, 10000000000) + if hash_code in ('04', '14'): + received_time = security_hash[3:13] + received_md5 = security_hash[24:] + hash_prefix = security_hash[:23] + elif hash_code in ('02', '12', '03', '13'): + received_time = security_hash[2:12] + received_md5 = security_hash[22:] + padding += '1' + hash_prefix = '05' + security_hash[:22] - md5_data = (received_md5 + sign_time + padding + '0xAC10FD').encode() + padded_sign_time = compat_str(int(received_time) + 86400) + padding + md5_data = (received_md5 + padded_sign_time + '0xAC10FD').encode() signed_md5 = base64.urlsafe_b64encode(hashlib.md5(md5_data).digest()).decode().strip('=') - signed_hash = security_hash[:23] + sign_time + padding + signed_md5 - + signed_hash = hash_prefix + padded_sign_time + signed_md5 signed_url = '%s?h=%s&k=html5&a=%s&u=%s' % (resource_url, signed_hash, 'F' if video.get('subscriber_only') else 'A', security.get('user') or '') + if resource_id.endswith('m3u8') or resource_url.endswith('.m3u8'): formats.extend(self._extract_m3u8_formats( signed_url, resource_id, 'mp4', entry_protocol='m3u8_native', From 07154c793065bca816793186590d8d6461e07478 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Tue, 22 Oct 2019 17:53:47 +0100 Subject: [PATCH 108/422] [facebook] extract subtitles(closes #22777) --- youtube_dl/extractor/ceskatelevize.py | 2 ++ youtube_dl/extractor/facebook.py | 5 +++++ 2 files changed, 7 insertions(+) diff --git a/youtube_dl/extractor/ceskatelevize.py b/youtube_dl/extractor/ceskatelevize.py index 1ec58f7d8..7cb4efb74 100644 --- a/youtube_dl/extractor/ceskatelevize.py +++ b/youtube_dl/extractor/ceskatelevize.py @@ -147,6 +147,8 @@ class CeskaTelevizeIE(InfoExtractor): is_live = item.get('type') == 'LIVE' formats = [] for format_id, stream_url in item.get('streamUrls', {}).items(): + if 'drmOnly=true' in stream_url: + continue if 'playerType=flash' in stream_url: stream_formats = self._extract_m3u8_formats( stream_url, playlist_id, 'mp4', 'm3u8_native', diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index a56f85c21..c723726b7 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -379,6 +379,7 @@ class FacebookIE(InfoExtractor): if not video_data: raise ExtractorError('Cannot parse data') + subtitles = {} formats = [] for f in video_data: format_id = f['stream_type'] @@ -402,6 +403,9 @@ class FacebookIE(InfoExtractor): if dash_manifest: formats.extend(self._parse_mpd_formats( compat_etree_fromstring(compat_urllib_parse_unquote_plus(dash_manifest)))) + subtitles_src = f[0].get('subtitles_src') + if subtitles_src: + subtitles.setdefault('en', []).append({'url': subtitles_src}) if not formats: raise ExtractorError('Cannot find video formats') @@ -447,6 +451,7 @@ class FacebookIE(InfoExtractor): 'timestamp': timestamp, 'thumbnail': thumbnail, 'view_count': view_count, + 'subtitles': subtitles, } return webpage, info_dict From 162bcc68dc73706699b559fffdd8bed3db6643b9 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Thu, 24 Oct 2019 12:53:33 +0100 Subject: [PATCH 109/422] [puhutv] improve extraction - fix subtitles extraction - transform HLS URLs to http URLs - improve metadata extraction --- youtube_dl/extractor/puhutv.py | 90 ++++++++++++++++++---------------- 1 file changed, 49 insertions(+), 41 deletions(-) diff --git a/youtube_dl/extractor/puhutv.py b/youtube_dl/extractor/puhutv.py index 5465e8ab7..fb704a3c4 100644 --- a/youtube_dl/extractor/puhutv.py +++ b/youtube_dl/extractor/puhutv.py @@ -25,21 +25,21 @@ class PuhuTVIE(InfoExtractor): _TESTS = [{ # film 'url': 'https://puhutv.com/sut-kardesler-izle', - 'md5': 'fbd8f2d8e7681f8bcd51b592475a6ae7', + 'md5': 'a347470371d56e1585d1b2c8dab01c96', 'info_dict': { 'id': '5085', 'display_id': 'sut-kardesler', 'ext': 'mp4', 'title': 'Süt Kardeşler', - 'description': 'md5:405fd024df916ca16731114eb18e511a', + 'description': 'md5:ca09da25b7e57cbb5a9280d6e48d17aa', 'thumbnail': r're:^https?://.*\.jpg$', 'duration': 4832.44, 'creator': 'Arzu Film', - 'timestamp': 1469778212, - 'upload_date': '20160729', + 'timestamp': 1561062602, + 'upload_date': '20190620', 'release_year': 1976, 'view_count': int, - 'tags': ['Aile', 'Komedi', 'Klasikler'], + 'tags': list, }, }, { # episode, geo restricted, bypassable with --geo-verification-proxy @@ -64,9 +64,10 @@ class PuhuTVIE(InfoExtractor): display_id)['data'] video_id = compat_str(info['id']) - title = info.get('name') or info['title']['name'] + show = info.get('title') or {} + title = info.get('name') or show['name'] if info.get('display_name'): - title = '%s %s' % (title, info.get('display_name')) + title = '%s %s' % (title, info['display_name']) try: videos = self._download_json( @@ -78,17 +79,36 @@ class PuhuTVIE(InfoExtractor): self.raise_geo_restricted() raise + urls = [] formats = [] + + def add_http_from_hls(m3u8_f): + http_url = m3u8_f['url'].replace('/hls/', '/mp4/').replace('/chunklist.m3u8', '.mp4') + if http_url != m3u8_f['url']: + f = m3u8_f.copy() + f.update({ + 'format_id': f['format_id'].replace('hls', 'http'), + 'protocol': 'http', + 'url': http_url, + }) + formats.append(f) + for video in videos['data']['videos']: media_url = url_or_none(video.get('url')) - if not media_url: + if not media_url or media_url in urls: continue + urls.append(media_url) + playlist = video.get('is_playlist') - if video.get('stream_type') == 'hls' and playlist is True: - formats.extend(self._extract_m3u8_formats( + if (video.get('stream_type') == 'hls' and playlist is True) or 'playlist.m3u8' in media_url: + m3u8_formats = self._extract_m3u8_formats( media_url, video_id, 'mp4', entry_protocol='m3u8_native', - m3u8_id='hls', fatal=False)) + m3u8_id='hls', fatal=False) + for m3u8_f in m3u8_formats: + formats.append(m3u8_f) + add_http_from_hls(m3u8_f) continue + quality = int_or_none(video.get('quality')) f = { 'url': media_url, @@ -96,34 +116,29 @@ class PuhuTVIE(InfoExtractor): 'height': quality } video_format = video.get('video_format') - if video_format == 'hls' and playlist is False: + is_hls = (video_format == 'hls' or '/hls/' in media_url or '/chunklist.m3u8' in media_url) and playlist is False + if is_hls: format_id = 'hls' f['protocol'] = 'm3u8_native' elif video_format == 'mp4': format_id = 'http' - else: continue if quality: format_id += '-%sp' % quality f['format_id'] = format_id formats.append(f) + if is_hls: + add_http_from_hls(f) self._sort_formats(formats) - description = try_get( - info, lambda x: x['title']['description'], - compat_str) or info.get('description') - timestamp = unified_timestamp(info.get('created_at')) creator = try_get( - info, lambda x: x['title']['producer']['name'], compat_str) + show, lambda x: x['producer']['name'], compat_str) - duration = float_or_none( - try_get(info, lambda x: x['content']['duration_in_ms'], int), - scale=1000) - view_count = try_get(info, lambda x: x['content']['watch_count'], int) + content = info.get('content') or {} images = try_get( - info, lambda x: x['content']['images']['wide'], dict) or {} + content, lambda x: x['images']['wide'], dict) or {} thumbnails = [] for image_id, image_url in images.items(): if not isinstance(image_url, compat_str): @@ -137,14 +152,8 @@ class PuhuTVIE(InfoExtractor): }) thumbnails.append(t) - release_year = try_get(info, lambda x: x['title']['released_at'], int) - - season_number = int_or_none(info.get('season_number')) - season_id = str_or_none(info.get('season_id')) - episode_number = int_or_none(info.get('episode_number')) - tags = [] - for genre in try_get(info, lambda x: x['title']['genres'], list) or []: + for genre in show.get('genres') or []: if not isinstance(genre, dict): continue genre_name = genre.get('name') @@ -152,12 +161,11 @@ class PuhuTVIE(InfoExtractor): tags.append(genre_name) subtitles = {} - for subtitle in try_get( - info, lambda x: x['content']['subtitles'], list) or []: + for subtitle in content.get('subtitles') or []: if not isinstance(subtitle, dict): continue lang = subtitle.get('language') - sub_url = url_or_none(subtitle.get('url')) + sub_url = url_or_none(subtitle.get('url') or subtitle.get('file')) if not lang or not isinstance(lang, compat_str) or not sub_url: continue subtitles[self._SUBTITLE_LANGS.get(lang, lang)] = [{ @@ -168,15 +176,15 @@ class PuhuTVIE(InfoExtractor): 'id': video_id, 'display_id': display_id, 'title': title, - 'description': description, - 'season_id': season_id, - 'season_number': season_number, - 'episode_number': episode_number, - 'release_year': release_year, - 'timestamp': timestamp, + 'description': info.get('description') or show.get('description'), + 'season_id': str_or_none(info.get('season_id')), + 'season_number': int_or_none(info.get('season_number')), + 'episode_number': int_or_none(info.get('episode_number')), + 'release_year': int_or_none(show.get('released_at')), + 'timestamp': unified_timestamp(info.get('created_at')), 'creator': creator, - 'view_count': view_count, - 'duration': duration, + 'view_count': int_or_none(content.get('watch_count')), + 'duration': float_or_none(content.get('duration_in_ms'), 1000), 'tags': tags, 'subtitles': subtitles, 'thumbnails': thumbnails, From 416c3ca7f53dab76b9e5ec46a0c0335698252c2d Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Fri, 25 Oct 2019 19:27:28 +0100 Subject: [PATCH 110/422] [odnoklassniki] add support for Schemeless embed extraction --- youtube_dl/extractor/generic.py | 7 ++++--- youtube_dl/extractor/odnoklassniki.py | 9 +++++++++ 2 files changed, 13 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 5ed952b29..f66cae0eb 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -118,6 +118,7 @@ from .foxnews import FoxNewsIE from .viqeo import ViqeoIE from .expressen import ExpressenIE from .zype import ZypeIE +from .odnoklassniki import OdnoklassnikiIE class GenericIE(InfoExtractor): @@ -2627,9 +2628,9 @@ class GenericIE(InfoExtractor): return self.url_result(mobj.group('url'), 'VK') # Look for embedded Odnoklassniki player - mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage) - if mobj is not None: - return self.url_result(mobj.group('url'), 'Odnoklassniki') + odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage) + if odnoklassniki_url: + return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key()) # Look for embedded ivi player mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage) diff --git a/youtube_dl/extractor/odnoklassniki.py b/youtube_dl/extractor/odnoklassniki.py index 114b93c07..7ed9fac55 100644 --- a/youtube_dl/extractor/odnoklassniki.py +++ b/youtube_dl/extractor/odnoklassniki.py @@ -1,6 +1,8 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..compat import ( compat_etree_fromstring, @@ -121,6 +123,13 @@ class OdnoklassnikiIE(InfoExtractor): 'only_matching': True, }] + @staticmethod + def _extract_url(webpage): + mobj = re.search( + r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage) + if mobj: + return mobj.group('url') + def _real_extract(self, url): start_time = int_or_none(compat_parse_qs( compat_urllib_parse_urlparse(url).query).get('fromTime', [None])[0]) From 3c989818e7dc7706da069312bbdd040165a97517 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Fri, 25 Oct 2019 19:35:07 +0100 Subject: [PATCH 111/422] [vk] improve extraction - add support for Odnoklassniki embeds - update tests - extract more video from user lists(closes #4470) - fix wall post audio extraction(closes #18332) - improve error detection(closes #22568) --- youtube_dl/extractor/vk.py | 329 +++++++++++++++++++------------------ 1 file changed, 173 insertions(+), 156 deletions(-) diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index 8b6dc0e24..c289fcad3 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -12,7 +12,6 @@ from ..utils import ( get_element_by_class, int_or_none, orderedSet, - remove_start, str_or_none, str_to_int, unescapeHTML, @@ -21,6 +20,7 @@ from ..utils import ( urlencode_postdata, ) from .dailymotion import DailymotionIE +from .odnoklassniki import OdnoklassnikiIE from .pladform import PladformIE from .vimeo import VimeoIE from .youtube import YoutubeIE @@ -60,6 +60,18 @@ class VKBaseIE(InfoExtractor): def _real_initialize(self): self._login() + def _download_payload(self, path, video_id, data, fatal=True): + data['al'] = 1 + code, payload = self._download_json( + 'https://vk.com/%s.php' % path, video_id, + data=urlencode_postdata(data), fatal=fatal, + headers={'X-Requested-With': 'XMLHttpRequest'})['payload'] + if code == '3': + self.raise_login_required() + elif code == '8': + raise ExtractorError(clean_html(payload[0][1:-1]), expected=True) + return payload + class VKIE(VKBaseIE): IE_NAME = 'vk' @@ -96,7 +108,6 @@ class VKIE(VKBaseIE): }, { 'url': 'http://vk.com/video205387401_165548505', - 'md5': '6c0aeb2e90396ba97035b9cbde548700', 'info_dict': { 'id': '205387401_165548505', 'ext': 'mp4', @@ -110,18 +121,18 @@ class VKIE(VKBaseIE): }, { 'note': 'Embedded video', - 'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1', - 'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a', + 'url': 'https://vk.com/video_ext.php?oid=-77521&id=162222515&hash=87b046504ccd8bfa', + 'md5': '7babad3b85ea2e91948005b1b8b0cb84', 'info_dict': { - 'id': '32194266_162925554', + 'id': '-77521_162222515', 'ext': 'mp4', - 'uploader': 'Vladimir Gavrin', - 'title': 'Lin Dan', - 'duration': 101, - 'upload_date': '20120730', - 'view_count': int, + 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*', + 'title': 'ProtivoGunz - Хуёвая песня', + 'duration': 195, + 'upload_date': '20120212', + 'timestamp': 1329049880, + 'uploader_id': '-77521', }, - 'skip': 'This video has been removed from public access.', }, { # VIDEO NOW REMOVED @@ -138,18 +149,19 @@ class VKIE(VKBaseIE): 'upload_date': '20121218', 'view_count': int, }, - 'skip': 'Requires vk account credentials', + 'skip': 'Removed', }, { 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d', - 'md5': '4d7a5ef8cf114dfa09577e57b2993202', 'info_dict': { 'id': '-43215063_168067957', 'ext': 'mp4', - 'uploader': 'Киномания - лучшее из мира кино', + 'uploader': 'Bro Mazter', 'title': ' ', 'duration': 7291, 'upload_date': '20140328', + 'uploader_id': '223413403', + 'timestamp': 1396018030, }, 'skip': 'Requires vk account credentials', }, @@ -165,7 +177,7 @@ class VKIE(VKBaseIE): 'upload_date': '20140626', 'view_count': int, }, - 'skip': 'Only works from Russia', + 'skip': 'Removed', }, { # video (removed?) only available with list id @@ -247,6 +259,9 @@ class VKIE(VKBaseIE): 'uploader_id': '-387766', 'timestamp': 1475137527, }, + 'params': { + 'skip_download': True, + }, }, { # live stream, hls and rtmp links, most likely already finished live @@ -288,80 +303,94 @@ class VKIE(VKBaseIE): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('videoid') + mv_data = {} if video_id: - info_url = 'https://vk.com/al_video.php?act=show_inline&al=1&video=' + video_id + data = { + 'act': 'show_inline', + 'video': video_id, + } # Some videos (removed?) can only be downloaded with list id specified list_id = mobj.group('list_id') if list_id: - info_url += '&list=%s' % list_id + data['list'] = list_id + + payload = self._download_payload('al_video', video_id, data) + info_page = payload[1] + opts = payload[-1] + mv_data = opts.get('mvData') or {} + player = opts.get('player') or {} else: - info_url = 'http://vk.com/video_ext.php?' + mobj.group('embed_query') video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id')) - info_page = self._download_webpage(info_url, video_id) + info_page = self._download_webpage( + 'http://vk.com/video_ext.php?' + mobj.group('embed_query'), video_id) - error_message = self._html_search_regex( - [r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>', - r'(?s)<div[^>]+id="video_ext_msg"[^>]*>(.+?)</div>'], - info_page, 'error message', default=None) - if error_message: - raise ExtractorError(error_message, expected=True) + error_message = self._html_search_regex( + [r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>', + r'(?s)<div[^>]+id="video_ext_msg"[^>]*>(.+?)</div>'], + info_page, 'error message', default=None) + if error_message: + raise ExtractorError(error_message, expected=True) - if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page): - raise ExtractorError( - 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.', - expected=True) + if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page): + raise ExtractorError( + 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.', + expected=True) - ERROR_COPYRIGHT = 'Video %s has been removed from public access due to rightholder complaint.' + ERROR_COPYRIGHT = 'Video %s has been removed from public access due to rightholder complaint.' - ERRORS = { - r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<': - ERROR_COPYRIGHT, + ERRORS = { + r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<': + ERROR_COPYRIGHT, - r'>The video .*? was removed from public access by request of the copyright holder.<': - ERROR_COPYRIGHT, + r'>The video .*? was removed from public access by request of the copyright holder.<': + ERROR_COPYRIGHT, - r'<!>Please log in or <': - 'Video %s is only available for registered users, ' - 'use --username and --password options to provide account credentials.', + r'<!>Please log in or <': + 'Video %s is only available for registered users, ' + 'use --username and --password options to provide account credentials.', - r'<!>Unknown error': - 'Video %s does not exist.', + r'<!>Unknown error': + 'Video %s does not exist.', - r'<!>Видео временно недоступно': - 'Video %s is temporarily unavailable.', + r'<!>Видео временно недоступно': + 'Video %s is temporarily unavailable.', - r'<!>Access denied': - 'Access denied to video %s.', + r'<!>Access denied': + 'Access denied to video %s.', - r'<!>Видеозапись недоступна, так как её автор был заблокирован.': - 'Video %s is no longer available, because its author has been blocked.', + r'<!>Видеозапись недоступна, так как её автор был заблокирован.': + 'Video %s is no longer available, because its author has been blocked.', - r'<!>This video is no longer available, because its author has been blocked.': - 'Video %s is no longer available, because its author has been blocked.', + r'<!>This video is no longer available, because its author has been blocked.': + 'Video %s is no longer available, because its author has been blocked.', - r'<!>This video is no longer available, because it has been deleted.': - 'Video %s is no longer available, because it has been deleted.', + r'<!>This video is no longer available, because it has been deleted.': + 'Video %s is no longer available, because it has been deleted.', - r'<!>The video .+? is not available in your region.': - 'Video %s is not available in your region.', - } + r'<!>The video .+? is not available in your region.': + 'Video %s is not available in your region.', + } - for error_re, error_msg in ERRORS.items(): - if re.search(error_re, info_page): - raise ExtractorError(error_msg % video_id, expected=True) + for error_re, error_msg in ERRORS.items(): + if re.search(error_re, info_page): + raise ExtractorError(error_msg % video_id, expected=True) + + player = self._parse_json(self._search_regex( + r'var\s+playerParams\s*=\s*({.+?})\s*;\s*\n', + info_page, 'player params'), video_id) youtube_url = YoutubeIE._extract_url(info_page) if youtube_url: - return self.url_result(youtube_url, ie=YoutubeIE.ie_key()) + return self.url_result(youtube_url, YoutubeIE.ie_key()) vimeo_url = VimeoIE._extract_url(url, info_page) if vimeo_url is not None: - return self.url_result(vimeo_url) + return self.url_result(vimeo_url, VimeoIE.ie_key()) pladform_url = PladformIE._extract_url(info_page) if pladform_url: - return self.url_result(pladform_url) + return self.url_result(pladform_url, PladformIE.ie_key()) m_rutube = re.search( r'\ssrc="((?:https?:)?//rutube\.ru\\?/(?:video|play)\\?/embed(?:.*?))\\?"', info_page) @@ -374,6 +403,10 @@ class VKIE(VKBaseIE): if dailymotion_urls: return self.url_result(dailymotion_urls[0], DailymotionIE.ie_key()) + odnoklassniki_url = OdnoklassnikiIE._extract_url(info_page) + if odnoklassniki_url: + return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key()) + m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page) if m_opts: m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1)) @@ -383,38 +416,7 @@ class VKIE(VKBaseIE): opts_url = 'http:' + opts_url return self.url_result(opts_url) - # vars does not look to be served anymore since 24.10.2016 - data = self._parse_json( - self._search_regex( - r'var\s+vars\s*=\s*({.+?});', info_page, 'vars', default='{}'), - video_id, fatal=False) - - # <!json> is served instead - if not data: - data = self._parse_json( - self._search_regex( - [r'<!json>\s*({.+?})\s*<!>', r'<!json>\s*({.+})'], - info_page, 'json', default='{}'), - video_id) - if data: - data = data['player']['params'][0] - - if not data: - data = self._parse_json( - self._search_regex( - r'var\s+playerParams\s*=\s*({.+?})\s*;\s*\n', info_page, - 'player params', default='{}'), - video_id) - if data: - data = data['params'][0] - - # <!--{...} - if not data: - data = self._parse_json( - self._search_regex( - r'<!--\s*({.+})', info_page, 'payload'), - video_id)['payload'][-1][-1]['player']['params'][0] - + data = player['params'][0] title = unescapeHTML(data['md_title']) # 2 = live @@ -463,12 +465,12 @@ class VKIE(VKBaseIE): 'title': title, 'thumbnail': data.get('jpg'), 'uploader': data.get('md_author'), - 'uploader_id': str_or_none(data.get('author_id')), - 'duration': data.get('duration'), + 'uploader_id': str_or_none(data.get('author_id') or mv_data.get('authorId')), + 'duration': int_or_none(data.get('duration') or mv_data.get('duration')), 'timestamp': timestamp, 'view_count': view_count, - 'like_count': int_or_none(data.get('liked')), - 'dislike_count': int_or_none(data.get('nolikes')), + 'like_count': int_or_none(mv_data.get('likes')), + 'comment_count': int_or_none(mv_data.get('commcount')), 'is_live': is_live, } @@ -482,7 +484,6 @@ class VKUserVideosIE(VKBaseIE): 'url': 'http://vk.com/videos205387401', 'info_dict': { 'id': '205387401', - 'title': "Tom Cruise's Videos", }, 'playlist_mincount': 4, }, { @@ -498,22 +499,25 @@ class VKUserVideosIE(VKBaseIE): 'url': 'http://new.vk.com/videos205387401', 'only_matching': True, }] + _VIDEO = collections.namedtuple( + 'Video', ['owner_id', 'id', 'thumb', 'title', 'flags', 'duration', 'hash', 'moder_acts', 'owner', 'date', 'views', 'platform', 'blocked', 'music_video_meta']) def _real_extract(self, url): page_id = self._match_id(url) - webpage = self._download_webpage(url, page_id) + l = self._download_payload('al_video', page_id, { + 'act': 'load_videos_silent', + 'oid': page_id, + })[0]['']['list'] - entries = [ - self.url_result( - 'http://vk.com/video' + video_id, 'VK', video_id=video_id) - for video_id in orderedSet(re.findall(r'href="/video(-?[0-9_]+)"', webpage))] + entries = [] + for video in l: + v = self._VIDEO._make(video) + video_id = '%d_%d' % (v.owner_id, v.id) + entries.append(self.url_result( + 'http://vk.com/video' + video_id, 'VK', video_id=video_id)) - title = unescapeHTML(self._search_regex( - r'<title>\s*([^<]+?)\s+\|\s+\d+\s+videos', - webpage, 'title', default=page_id)) - - return self.playlist_result(entries, page_id, title) + return self.playlist_result(entries, page_id) class VKWallPostIE(VKBaseIE): @@ -523,15 +527,15 @@ class VKWallPostIE(VKBaseIE): # public page URL, audio playlist 'url': 'https://vk.com/bs.official?w=wall-23538238_35', 'info_dict': { - 'id': '23538238_35', - 'title': 'Black Shadow - Wall post 23538238_35', + 'id': '-23538238_35', + 'title': 'Black Shadow - Wall post -23538238_35', 'description': 'md5:3f84b9c4f9ef499731cf1ced9998cc0c', }, 'playlist': [{ 'md5': '5ba93864ec5b85f7ce19a9af4af080f6', 'info_dict': { 'id': '135220665_111806521', - 'ext': 'mp3', + 'ext': 'mp4', 'title': 'Black Shadow - Слепое Верование', 'duration': 370, 'uploader': 'Black Shadow', @@ -542,18 +546,16 @@ class VKWallPostIE(VKBaseIE): 'md5': '4cc7e804579122b17ea95af7834c9233', 'info_dict': { 'id': '135220665_111802303', - 'ext': 'mp3', + 'ext': 'mp4', 'title': 'Black Shadow - Война - Негасимое Бездны Пламя!', 'duration': 423, 'uploader': 'Black Shadow', 'artist': 'Black Shadow', 'track': 'Война - Негасимое Бездны Пламя!', }, - 'params': { - 'skip_download': True, - }, }], 'params': { + 'skip_download': True, 'usenetrc': True, }, 'skip': 'Requires vk account credentials', @@ -562,7 +564,7 @@ class VKWallPostIE(VKBaseIE): 'url': 'https://vk.com/wall85155021_6319', 'info_dict': { 'id': '85155021_6319', - 'title': 'Sergey Gorbunov - Wall post 85155021_6319', + 'title': 'Сергей Горбунов - Wall post 85155021_6319', }, 'playlist_count': 1, 'params': { @@ -578,58 +580,73 @@ class VKWallPostIE(VKBaseIE): 'url': 'https://m.vk.com/wall-23538238_35', 'only_matching': True, }] + _BASE64_CHARS = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMN0PQRSTUVWXYZO123456789+/=' + _AUDIO = collections.namedtuple( + 'Audio', ['id', 'owner_id', 'url', 'title', 'performer', 'duration', 'album_id', 'unk', 'author_link', 'lyrics', 'flags', 'context', 'extra', 'hashes', 'cover_url', 'ads', 'subtitle', 'main_artists', 'feat_artists', 'album', 'track_code', 'restriction', 'album_part', 'new_stats', 'access_key']) + + def _decode(self, enc): + dec = '' + e = n = 0 + for c in enc: + r = self._BASE64_CHARS.index(c) + cond = n % 4 + e = 64 * e + r if cond else r + n += 1 + if cond: + dec += chr(255 & e >> (-2 * n & 6)) + return dec + + def _unmask_url(self, mask_url, vk_id): + if 'audio_api_unavailable' in mask_url: + extra = mask_url.split('?extra=')[1].split('#') + func, base = self._decode(extra[1]).split(chr(11)) + assert (func == 'i') + mask_url = list(self._decode(extra[0])) + url_len = len(mask_url) + indexes = [None] * url_len + index = int(base) ^ vk_id + for n in range(url_len - 1, -1, -1): + index = (url_len * (n + 1) ^ index + n) % url_len + indexes[n] = index + for n in range(1, url_len): + c = mask_url[n] + index = indexes[url_len - 1 - n] + mask_url[n] = mask_url[index] + mask_url[index] = c + mask_url = ''.join(mask_url) + return mask_url def _real_extract(self, url): post_id = self._match_id(url) - wall_url = 'https://vk.com/wall%s' % post_id - - post_id = remove_start(post_id, '-') - - webpage = self._download_webpage(wall_url, post_id) - - error = self._html_search_regex( - r'>Error</div>\s*<div[^>]+class=["\']body["\'][^>]*>([^<]+)', - webpage, 'error', default=None) - if error: - raise ExtractorError('VK said: %s' % error, expected=True) + webpage = self._download_payload('wkview', post_id, { + 'act': 'show', + 'w': 'wall' + post_id, + })[1] description = clean_html(get_element_by_class('wall_post_text', webpage)) uploader = clean_html(get_element_by_class('author', webpage)) - thumbnail = self._og_search_thumbnail(webpage) entries = [] - audio_ids = re.findall(r'data-full-id=["\'](\d+_\d+)', webpage) - if audio_ids: - al_audio = self._download_webpage( - 'https://vk.com/al_audio.php', post_id, - note='Downloading audio info', fatal=False, - data=urlencode_postdata({ - 'act': 'reload_audio', - 'al': '1', - 'ids': ','.join(audio_ids) - })) - if al_audio: - Audio = collections.namedtuple( - 'Audio', ['id', 'user_id', 'url', 'track', 'artist', 'duration']) - audios = self._parse_json( - self._search_regex( - r'<!json>(.+?)<!>', al_audio, 'audios', default='[]'), - post_id, fatal=False, transform_source=unescapeHTML) - if isinstance(audios, list): - for audio in audios: - a = Audio._make(audio[:6]) - entries.append({ - 'id': '%s_%s' % (a.user_id, a.id), - 'url': a.url, - 'title': '%s - %s' % (a.artist, a.track) if a.artist and a.track else a.id, - 'thumbnail': thumbnail, - 'duration': a.duration, - 'uploader': uploader, - 'artist': a.artist, - 'track': a.track, - }) + for audio in re.findall(r'data-audio="([^"]+)', webpage): + audio = self._parse_json(unescapeHTML(audio), post_id) + a = self._AUDIO._make(audio) + if not a.url: + continue + title = unescapeHTML(a.title) + entries.append({ + 'id': '%s_%s' % (a.owner_id, a.id), + 'url': self._unmask_url(a.url, a.ads['vk_id']), + 'title': '%s - %s' % (a.performer, title) if a.performer else title, + 'thumbnail': a.cover_url.split(',') if a.cover_url else None, + 'duration': a.duration, + 'uploader': uploader, + 'artist': a.performer, + 'track': title, + 'ext': 'mp4', + 'protocol': 'm3u8', + }) for video in re.finditer( r'<a[^>]+href=(["\'])(?P<url>/video(?:-?[\d_]+).*?)\1', webpage): From 42cd0824b3975e6ce500d8cecd60e1fc077a758b Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sat, 26 Oct 2019 00:06:05 +0100 Subject: [PATCH 112/422] [vk] remove assert statement --- youtube_dl/extractor/vk.py | 1 - 1 file changed, 1 deletion(-) diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index c289fcad3..4c8ca4f41 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -600,7 +600,6 @@ class VKWallPostIE(VKBaseIE): if 'audio_api_unavailable' in mask_url: extra = mask_url.split('?extra=')[1].split('#') func, base = self._decode(extra[1]).split(chr(11)) - assert (func == 'i') mask_url = list(self._decode(extra[0])) url_len = len(mask_url) indexes = [None] * url_len From 235dbb434bfa724718c37d8af0a61baf93b775be Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sat, 26 Oct 2019 14:57:42 +0100 Subject: [PATCH 113/422] [discoverynetworks] add support for dplay.co.uk --- youtube_dl/extractor/discoverynetworks.py | 63 +++++++---------------- 1 file changed, 19 insertions(+), 44 deletions(-) diff --git a/youtube_dl/extractor/discoverynetworks.py b/youtube_dl/extractor/discoverynetworks.py index fba1ef221..607a54948 100644 --- a/youtube_dl/extractor/discoverynetworks.py +++ b/youtube_dl/extractor/discoverynetworks.py @@ -3,63 +3,38 @@ from __future__ import unicode_literals import re -from .brightcove import BrightcoveLegacyIE from .dplay import DPlayIE -from ..compat import ( - compat_parse_qs, - compat_urlparse, -) -from ..utils import smuggle_url class DiscoveryNetworksDeIE(DPlayIE): - _VALID_URL = r'''(?x)https?://(?:www\.)?(?P<site>discovery|tlc|animalplanet|dmax)\.de/ - (?: - .*\#(?P<id>\d+)| - (?:[^/]+/)*videos/(?P<display_id>[^/?#]+)| - programme/(?P<programme>[^/]+)/video/(?P<alternate_id>[^/]+) - )''' + _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:tlc|dmax)\.de|dplay\.co\.uk)/(?:programme|show)/(?P<programme>[^/]+)/video/(?P<alternate_id>[^/]+)' _TESTS = [{ - 'url': 'http://www.tlc.de/sendungen/breaking-amish/videos/#3235167922001', + 'url': 'https://www.tlc.de/programme/breaking-amish/video/die-welt-da-drauen/DCB331270001100', 'info_dict': { - 'id': '3235167922001', + 'id': '78867', 'ext': 'mp4', - 'title': 'Breaking Amish: Die Welt da draußen', - 'description': ( - 'Vier Amische und eine Mennonitin wagen in New York' - ' den Sprung in ein komplett anderes Leben. Begleitet sie auf' - ' ihrem spannenden Weg.'), - 'timestamp': 1396598084, - 'upload_date': '20140404', - 'uploader_id': '1659832546', + 'title': 'Die Welt da draußen', + 'description': 'md5:61033c12b73286e409d99a41742ef608', + 'timestamp': 1554069600, + 'upload_date': '20190331', + }, + 'params': { + 'format': 'bestvideo', + 'skip_download': True, }, }, { - 'url': 'http://www.dmax.de/programme/storage-hunters-uk/videos/storage-hunters-uk-episode-6/', + 'url': 'https://www.dmax.de/programme/dmax-highlights/video/tuning-star-sidney-hoffmann-exklusiv-bei-dmax/191023082312316', 'only_matching': True, }, { - 'url': 'http://www.discovery.de/#5332316765001', + 'url': 'https://www.dplay.co.uk/show/ghost-adventures/video/hotel-leger-103620/EHD_280313B', 'only_matching': True, }] - BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1659832546/default_default/index.html?videoId=%s' def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - alternate_id = mobj.group('alternate_id') - if alternate_id: - self._initialize_geo_bypass({ - 'countries': ['DE'], - }) - return self._get_disco_api_info( - url, '%s/%s' % (mobj.group('programme'), alternate_id), - 'sonic-eu1-prod.disco-api.com', mobj.group('site') + 'de') - brightcove_id = mobj.group('id') - if not brightcove_id: - title = mobj.group('title') - webpage = self._download_webpage(url, title) - brightcove_legacy_url = BrightcoveLegacyIE._extract_brightcove_url(webpage) - brightcove_id = compat_parse_qs(compat_urlparse.urlparse( - brightcove_legacy_url).query)['@videoPlayer'][0] - return self.url_result(smuggle_url( - self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, {'geo_countries': ['DE']}), - 'BrightcoveNew', brightcove_id) + domain, programme, alternate_id = re.match(self._VALID_URL, url).groups() + country = 'GB' if domain == 'dplay.co.uk' else 'DE' + realm = 'questuk' if country == 'GB' else domain.replace('.', '') + return self._get_disco_api_info( + url, '%s/%s' % (programme, alternate_id), + 'sonic-eu1-prod.disco-api.com', realm, country) From 0b98f3a7517601b7d2aabc789997016b9c3c24f2 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sat, 26 Oct 2019 14:58:29 +0100 Subject: [PATCH 114/422] [dplay] improve extraction - add support for dplay.fi, dplay.jp and es.dplay.com(closes #16969) - fix it.dplay.com extraction(closes #22826) - update tests - extract creator, tags and thumbnails - handle playback API call errors --- youtube_dl/extractor/dplay.py | 397 ++++++++++------------------- youtube_dl/extractor/extractors.py | 5 +- 2 files changed, 133 insertions(+), 269 deletions(-) diff --git a/youtube_dl/extractor/dplay.py b/youtube_dl/extractor/dplay.py index ebf59512c..d9c3d59cd 100644 --- a/youtube_dl/extractor/dplay.py +++ b/youtube_dl/extractor/dplay.py @@ -1,74 +1,68 @@ # coding: utf-8 from __future__ import unicode_literals -import json import re -import time from .common import InfoExtractor -from ..compat import ( - compat_HTTPError, - compat_str, - compat_urlparse, -) +from ..compat import compat_HTTPError from ..utils import ( determine_ext, ExtractorError, float_or_none, int_or_none, - remove_end, - try_get, - unified_strdate, unified_timestamp, - update_url_query, - urljoin, - USER_AGENTS, ) class DPlayIE(InfoExtractor): - _VALID_URL = r'https?://(?P<domain>www\.(?P<host>dplay\.(?P<country>dk|se|no)))/(?:video(?:er|s)/)?(?P<id>[^/]+/[^/?#]+)' + _VALID_URL = r'''(?x)https?:// + (?P<domain> + (?:www\.)?(?P<host>dplay\.(?P<country>dk|fi|jp|se|no))| + (?P<subdomain_country>es|it)\.dplay\.com + )/[^/]+/(?P<id>[^/]+/[^/?#]+)''' _TESTS = [{ # non geo restricted, via secure api, unsigned download hls URL - 'url': 'http://www.dplay.se/nugammalt-77-handelser-som-format-sverige/season-1-svensken-lar-sig-njuta-av-livet/', + 'url': 'https://www.dplay.se/videos/nugammalt-77-handelser-som-format-sverige/nugammalt-77-handelser-som-format-sverige-101', 'info_dict': { - 'id': '3172', - 'display_id': 'nugammalt-77-handelser-som-format-sverige/season-1-svensken-lar-sig-njuta-av-livet', + 'id': '13628', + 'display_id': 'nugammalt-77-handelser-som-format-sverige/nugammalt-77-handelser-som-format-sverige-101', 'ext': 'mp4', 'title': 'Svensken lär sig njuta av livet', 'description': 'md5:d3819c9bccffd0fe458ca42451dd50d8', - 'duration': 2650, - 'timestamp': 1365454320, + 'duration': 2649.856, + 'timestamp': 1365453720, 'upload_date': '20130408', - 'creator': 'Kanal 5 (Home)', + 'creator': 'Kanal 5', 'series': 'Nugammalt - 77 händelser som format Sverige', 'season_number': 1, 'episode_number': 1, - 'age_limit': 0, + }, + 'params': { + 'format': 'bestvideo', + 'skip_download': True, }, }, { # geo restricted, via secure api, unsigned download hls URL - 'url': 'http://www.dplay.dk/mig-og-min-mor/season-6-episode-12/', + 'url': 'http://www.dplay.dk/videoer/ted-bundy-mind-of-a-monster/ted-bundy-mind-of-a-monster', 'info_dict': { - 'id': '70816', - 'display_id': 'mig-og-min-mor/season-6-episode-12', + 'id': '104465', + 'display_id': 'ted-bundy-mind-of-a-monster/ted-bundy-mind-of-a-monster', 'ext': 'mp4', - 'title': 'Episode 12', - 'description': 'md5:9c86e51a93f8a4401fc9641ef9894c90', - 'duration': 2563, - 'timestamp': 1429696800, - 'upload_date': '20150422', - 'creator': 'Kanal 4 (Home)', - 'series': 'Mig og min mor', - 'season_number': 6, - 'episode_number': 12, - 'age_limit': 0, + 'title': 'Ted Bundy: Mind Of A Monster', + 'description': 'md5:8b780f6f18de4dae631668b8a9637995', + 'duration': 5290.027, + 'timestamp': 1570694400, + 'upload_date': '20191010', + 'creator': 'ID - Investigation Discovery', + 'series': 'Ted Bundy: Mind Of A Monster', + 'season_number': 1, + 'episode_number': 1, + }, + 'params': { + 'format': 'bestvideo', + 'skip_download': True, }, - }, { - # geo restricted, via direct unsigned hls URL - 'url': 'http://www.dplay.no/pga-tour/season-1-hoydepunkter-18-21-februar/', - 'only_matching': True, }, { # disco-api 'url': 'https://www.dplay.no/videoer/i-kongens-klr/sesong-1-episode-7', @@ -89,19 +83,59 @@ class DPlayIE(InfoExtractor): 'format': 'bestvideo', 'skip_download': True, }, + 'skip': 'Available for Premium users', }, { - - 'url': 'https://www.dplay.dk/videoer/singleliv/season-5-episode-3', + 'url': 'http://it.dplay.com/nove/biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij/', + 'md5': '2b808ffb00fc47b884a172ca5d13053c', + 'info_dict': { + 'id': '6918', + 'display_id': 'biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij', + 'ext': 'mp4', + 'title': 'Luigi Di Maio: la psicosi di Stanislawskij', + 'description': 'md5:3c7a4303aef85868f867a26f5cc14813', + 'thumbnail': r're:^https?://.*\.jpe?g', + 'upload_date': '20160524', + 'timestamp': 1464076800, + 'series': 'Biografie imbarazzanti', + 'season_number': 1, + 'episode': 'Episode 1', + 'episode_number': 1, + }, + }, { + 'url': 'https://es.dplay.com/dmax/la-fiebre-del-oro/temporada-8-episodio-1/', + 'info_dict': { + 'id': '21652', + 'display_id': 'la-fiebre-del-oro/temporada-8-episodio-1', + 'ext': 'mp4', + 'title': 'Episodio 1', + 'description': 'md5:b9dcff2071086e003737485210675f69', + 'thumbnail': r're:^https?://.*\.png', + 'upload_date': '20180709', + 'timestamp': 1531173540, + 'series': 'La fiebre del oro', + 'season_number': 8, + 'episode': 'Episode 1', + 'episode_number': 1, + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://www.dplay.fi/videot/shifting-gears-with-aaron-kaufman/episode-16', 'only_matching': True, }, { - 'url': 'https://www.dplay.se/videos/sofias-anglar/sofias-anglar-1001', + 'url': 'https://www.dplay.jp/video/gold-rush/24086', 'only_matching': True, }] - def _get_disco_api_info(self, url, display_id, disco_host, realm): - disco_base = 'https://' + disco_host + def _get_disco_api_info(self, url, display_id, disco_host, realm, country): + geo_countries = [country.upper()] + self._initialize_geo_bypass({ + 'countries': geo_countries, + }) + disco_base = 'https://%s/' % disco_host token = self._download_json( - '%s/token' % disco_base, display_id, 'Downloading token', + disco_base + 'token', display_id, 'Downloading token', query={ 'realm': realm, })['data']['attributes']['token'] @@ -110,17 +144,30 @@ class DPlayIE(InfoExtractor): 'Authorization': 'Bearer ' + token, } video = self._download_json( - '%s/content/videos/%s' % (disco_base, display_id), display_id, + disco_base + 'content/videos/' + display_id, display_id, headers=headers, query={ - 'include': 'show' + 'include': 'images,primaryChannel,show,tags' }) video_id = video['data']['id'] info = video['data']['attributes'] - title = info['name'] + title = info['name'].strip() formats = [] - for format_id, format_dict in self._download_json( - '%s/playback/videoPlaybackInfo/%s' % (disco_base, video_id), - display_id, headers=headers)['data']['attributes']['streaming'].items(): + try: + streaming = self._download_json( + disco_base + 'playback/videoPlaybackInfo/' + video_id, + display_id, headers=headers)['data']['attributes']['streaming'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + info = self._parse_json(e.cause.read().decode('utf-8'), display_id) + error = info['errors'][0] + error_code = error.get('code') + if error_code == 'access.denied.geoblocked': + self.raise_geo_restricted(countries=geo_countries) + elif error_code == 'access.denied.missingpackage': + self.raise_login_required() + raise ExtractorError(info['errors'][0]['detail'], expected=True) + raise + for format_id, format_dict in streaming.items(): if not isinstance(format_dict, dict): continue format_url = format_dict.get('url') @@ -142,235 +189,55 @@ class DPlayIE(InfoExtractor): }) self._sort_formats(formats) - series = None - try: - included = video.get('included') - if isinstance(included, list): - show = next(e for e in included if e.get('type') == 'show') - series = try_get( - show, lambda x: x['attributes']['name'], compat_str) - except StopIteration: - pass + creator = series = None + tags = [] + thumbnails = [] + included = video.get('included') or [] + if isinstance(included, list): + for e in included: + attributes = e.get('attributes') + if not attributes: + continue + e_type = e.get('type') + if e_type == 'channel': + creator = attributes.get('name') + elif e_type == 'image': + src = attributes.get('src') + if src: + thumbnails.append({ + 'url': src, + 'width': int_or_none(attributes.get('width')), + 'height': int_or_none(attributes.get('height')), + }) + if e_type == 'show': + series = attributes.get('name') + elif e_type == 'tag': + name = attributes.get('name') + if name: + tags.append(name) return { 'id': video_id, 'display_id': display_id, 'title': title, 'description': info.get('description'), - 'duration': float_or_none( - info.get('videoDuration'), scale=1000), + 'duration': float_or_none(info.get('videoDuration'), 1000), 'timestamp': unified_timestamp(info.get('publishStart')), 'series': series, 'season_number': int_or_none(info.get('seasonNumber')), 'episode_number': int_or_none(info.get('episodeNumber')), 'age_limit': int_or_none(info.get('minimum_age')), + 'creator': creator, + 'tags': tags, + 'thumbnails': thumbnails, 'formats': formats, } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) display_id = mobj.group('id') - domain = mobj.group('domain') - - self._initialize_geo_bypass({ - 'countries': [mobj.group('country').upper()], - }) - - webpage = self._download_webpage(url, display_id) - - video_id = self._search_regex( - r'data-video-id=["\'](\d+)', webpage, 'video id', default=None) - - if not video_id: - host = mobj.group('host') - return self._get_disco_api_info( - url, display_id, 'disco-api.' + host, host.replace('.', '')) - - info = self._download_json( - 'http://%s/api/v2/ajax/videos?video_id=%s' % (domain, video_id), - video_id)['data'][0] - - title = info['title'] - - PROTOCOLS = ('hls', 'hds') - formats = [] - - def extract_formats(protocol, manifest_url): - if protocol == 'hls': - m3u8_formats = self._extract_m3u8_formats( - manifest_url, video_id, ext='mp4', - entry_protocol='m3u8_native', m3u8_id=protocol, fatal=False) - # Sometimes final URLs inside m3u8 are unsigned, let's fix this - # ourselves. Also fragments' URLs are only served signed for - # Safari user agent. - query = compat_urlparse.parse_qs(compat_urlparse.urlparse(manifest_url).query) - for m3u8_format in m3u8_formats: - m3u8_format.update({ - 'url': update_url_query(m3u8_format['url'], query), - 'http_headers': { - 'User-Agent': USER_AGENTS['Safari'], - }, - }) - formats.extend(m3u8_formats) - elif protocol == 'hds': - formats.extend(self._extract_f4m_formats( - manifest_url + '&hdcore=3.8.0&plugin=flowplayer-3.8.0.0', - video_id, f4m_id=protocol, fatal=False)) - - domain_tld = domain.split('.')[-1] - if domain_tld in ('se', 'dk', 'no'): - for protocol in PROTOCOLS: - # Providing dsc-geo allows to bypass geo restriction in some cases - self._set_cookie( - 'secure.dplay.%s' % domain_tld, 'dsc-geo', - json.dumps({ - 'countryCode': domain_tld.upper(), - 'expiry': (time.time() + 20 * 60) * 1000, - })) - stream = self._download_json( - 'https://secure.dplay.%s/secure/api/v2/user/authorization/stream/%s?stream_type=%s' - % (domain_tld, video_id, protocol), video_id, - 'Downloading %s stream JSON' % protocol, fatal=False) - if stream and stream.get(protocol): - extract_formats(protocol, stream[protocol]) - - # The last resort is to try direct unsigned hls/hds URLs from info dictionary. - # Sometimes this does work even when secure API with dsc-geo has failed (e.g. - # http://www.dplay.no/pga-tour/season-1-hoydepunkter-18-21-februar/). - if not formats: - for protocol in PROTOCOLS: - if info.get(protocol): - extract_formats(protocol, info[protocol]) - - self._sort_formats(formats) - - subtitles = {} - for lang in ('se', 'sv', 'da', 'nl', 'no'): - for format_id in ('web_vtt', 'vtt', 'srt'): - subtitle_url = info.get('subtitles_%s_%s' % (lang, format_id)) - if subtitle_url: - subtitles.setdefault(lang, []).append({'url': subtitle_url}) - - return { - 'id': video_id, - 'display_id': display_id, - 'title': title, - 'description': info.get('video_metadata_longDescription'), - 'duration': int_or_none(info.get('video_metadata_length'), scale=1000), - 'timestamp': int_or_none(info.get('video_publish_date')), - 'creator': info.get('video_metadata_homeChannel'), - 'series': info.get('video_metadata_show'), - 'season_number': int_or_none(info.get('season')), - 'episode_number': int_or_none(info.get('episode')), - 'age_limit': int_or_none(info.get('minimum_age')), - 'formats': formats, - 'subtitles': subtitles, - } - - -class DPlayItIE(InfoExtractor): - _VALID_URL = r'https?://it\.dplay\.com/[^/]+/[^/]+/(?P<id>[^/?#]+)' - _GEO_COUNTRIES = ['IT'] - _TEST = { - 'url': 'http://it.dplay.com/nove/biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij/', - 'md5': '2b808ffb00fc47b884a172ca5d13053c', - 'info_dict': { - 'id': '6918', - 'display_id': 'luigi-di-maio-la-psicosi-di-stanislawskij', - 'ext': 'mp4', - 'title': 'Biografie imbarazzanti: Luigi Di Maio: la psicosi di Stanislawskij', - 'description': 'md5:3c7a4303aef85868f867a26f5cc14813', - 'thumbnail': r're:^https?://.*\.jpe?g', - 'upload_date': '20160524', - 'series': 'Biografie imbarazzanti', - 'season_number': 1, - 'episode': 'Luigi Di Maio: la psicosi di Stanislawskij', - 'episode_number': 1, - }, - } - - def _real_extract(self, url): - display_id = self._match_id(url) - - webpage = self._download_webpage(url, display_id) - - title = remove_end(self._og_search_title(webpage), ' | Dplay') - - video_id = None - - info = self._search_regex( - r'playback_json\s*:\s*JSON\.parse\s*\(\s*("(?:\\.|[^"\\])+?")', - webpage, 'playback JSON', default=None) - if info: - for _ in range(2): - info = self._parse_json(info, display_id, fatal=False) - if not info: - break - else: - video_id = try_get(info, lambda x: x['data']['id']) - - if not info: - info_url = self._search_regex( - (r'playback_json_url\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', - r'url\s*[:=]\s*["\'](?P<url>(?:https?:)?//[^/]+/playback/videoPlaybackInfo/\d+)'), - webpage, 'info url', group='url') - - info_url = urljoin(url, info_url) - video_id = info_url.rpartition('/')[-1] - - try: - info = self._download_json( - info_url, display_id, headers={ - 'Authorization': 'Bearer %s' % self._get_cookies(url).get( - 'dplayit_token').value, - 'Referer': url, - }) - if isinstance(info, compat_str): - info = self._parse_json(info, display_id) - except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 403): - info = self._parse_json(e.cause.read().decode('utf-8'), display_id) - error = info['errors'][0] - if error.get('code') == 'access.denied.geoblocked': - self.raise_geo_restricted( - msg=error.get('detail'), countries=self._GEO_COUNTRIES) - raise ExtractorError(info['errors'][0]['detail'], expected=True) - raise - - hls_url = info['data']['attributes']['streaming']['hls']['url'] - - formats = self._extract_m3u8_formats( - hls_url, display_id, ext='mp4', entry_protocol='m3u8_native', - m3u8_id='hls') - self._sort_formats(formats) - - series = self._html_search_regex( - r'(?s)<h1[^>]+class=["\'].*?\bshow_title\b.*?["\'][^>]*>(.+?)</h1>', - webpage, 'series', fatal=False) - episode = self._search_regex( - r'<p[^>]+class=["\'].*?\bdesc_ep\b.*?["\'][^>]*>\s*<br/>\s*<b>([^<]+)', - webpage, 'episode', fatal=False) - - mobj = re.search( - r'(?s)<span[^>]+class=["\']dates["\'][^>]*>.+?\bS\.(?P<season_number>\d+)\s+E\.(?P<episode_number>\d+)\s*-\s*(?P<upload_date>\d{2}/\d{2}/\d{4})', - webpage) - if mobj: - season_number = int(mobj.group('season_number')) - episode_number = int(mobj.group('episode_number')) - upload_date = unified_strdate(mobj.group('upload_date')) - else: - season_number = episode_number = upload_date = None - - return { - 'id': compat_str(video_id or display_id), - 'display_id': display_id, - 'title': title, - 'description': self._og_search_description(webpage), - 'thumbnail': self._og_search_thumbnail(webpage), - 'series': series, - 'season_number': season_number, - 'episode': episode, - 'episode_number': episode_number, - 'upload_date': upload_date, - 'formats': formats, - } + domain = mobj.group('domain').lstrip('www.') + country = mobj.group('country') or mobj.group('subdomain_country') + host = 'disco-api.' + domain if domain.startswith('dplay.') else 'eu2-prod.disco-api.com' + return self._get_disco_api_info( + url, display_id, host, 'dplay' + country, country) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 1db21529f..a8fe0de1a 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -277,10 +277,7 @@ from .douyutv import ( DouyuShowIE, DouyuTVIE, ) -from .dplay import ( - DPlayIE, - DPlayItIE, -) +from .dplay import DPlayIE from .dreisat import DreiSatIE from .drbonanza import DRBonanzaIE from .drtuber import DrTuberIE From 548c395716b1d5aa215e526fcb052a03926c1573 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 27 Oct 2019 17:52:46 +0100 Subject: [PATCH 115/422] [soundcloud] improve extraction - improve format extraction(closes #22123) - extract uploader_id and uploader_url(closes #21916) - extract all known thumbnails(closes #19071)(closes #20659) - fix extration for private playlists(closes #20976) - add support for playlist embeds(#20976) - skip preview formats(closes #22806) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/generic.py | 6 +- youtube_dl/extractor/soundcloud.py | 497 ++++++++++++++--------------- 3 files changed, 248 insertions(+), 256 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index a8fe0de1a..388c1ebe6 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1033,6 +1033,7 @@ from .snotr import SnotrIE from .sohu import SohuIE from .sonyliv import SonyLIVIE from .soundcloud import ( + SoundcloudEmbedIE, SoundcloudIE, SoundcloudSetIE, SoundcloudUserIE, diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index f66cae0eb..1c0780e98 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -80,7 +80,7 @@ from .theplatform import ThePlatformIE from .kaltura import KalturaIE from .eagleplatform import EaglePlatformIE from .facebook import FacebookIE -from .soundcloud import SoundcloudIE +from .soundcloud import SoundcloudEmbedIE from .tunein import TuneInBaseIE from .vbox7 import Vbox7IE from .dbtv import DBTVIE @@ -2749,9 +2749,9 @@ class GenericIE(InfoExtractor): return self.url_result(myvi_url) # Look for embedded soundcloud player - soundcloud_urls = SoundcloudIE._extract_urls(webpage) + soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage) if soundcloud_urls: - return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key()) + return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML) # Look for tunein player tunein_urls = TuneInBaseIE._extract_urls(webpage) diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 05538f3d6..875b9d887 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -11,14 +11,13 @@ from .common import ( from ..compat import ( compat_str, compat_urlparse, - compat_urllib_parse_urlencode, ) from ..utils import ( ExtractorError, float_or_none, + HEADRequest, int_or_none, KNOWN_EXTENSIONS, - merge_dicts, mimetype2ext, str_or_none, try_get, @@ -28,6 +27,20 @@ from ..utils import ( ) +class SoundcloudEmbedIE(InfoExtractor): + _VALID_URL = r'https?://(?:w|player|p)\.soundcloud\.com/player/?.*?url=(?P<id>.*)' + + @staticmethod + def _extract_urls(webpage): + return [m.group('url') for m in re.finditer( + r'<iframe[^>]+src=(["\'])(?P<url>(?:https?://)?(?:w\.)?soundcloud\.com/player.+?)\1', + webpage)] + + def _real_extract(self, url): + return self.url_result(compat_urlparse.parse_qs( + compat_urlparse.urlparse(url).query)['url'][0]) + + class SoundcloudIE(InfoExtractor): """Information extractor for soundcloud.com To access the media, the uid of the song and a stream token @@ -44,9 +57,8 @@ class SoundcloudIE(InfoExtractor): (?!(?:tracks|albums|sets(?:/.+?)?|reposts|likes|spotlight)/?(?:$|[?#])) (?P<title>[\w\d-]+)/? (?P<token>[^?]+?)?(?:[?].*)?$) - |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+) + |(?:api(?:-v2)?\.soundcloud\.com/tracks/(?P<track_id>\d+) (?:/?\?secret_token=(?P<secret_token>[^&]+))?) - |(?P<player>(?:w|player|p.)\.soundcloud\.com/player/?.*?url=.*) ) ''' IE_NAME = 'soundcloud' @@ -60,6 +72,7 @@ class SoundcloudIE(InfoExtractor): 'title': 'Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1', 'description': 'No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o\'d', 'uploader': 'E.T. ExTerrestrial Music', + 'uploader_id': '1571244', 'timestamp': 1349920598, 'upload_date': '20121011', 'duration': 143.216, @@ -79,6 +92,7 @@ class SoundcloudIE(InfoExtractor): 'title': 'Goldrushed', 'description': 'From Stockholm Sweden\r\nPovel / Magnus / Filip / David\r\nwww.theroyalconcept.com', 'uploader': 'The Royal Concept', + 'uploader_id': '9615865', 'timestamp': 1337635207, 'upload_date': '20120521', 'duration': 30, @@ -92,6 +106,7 @@ class SoundcloudIE(InfoExtractor): # rtmp 'skip_download': True, }, + 'skip': 'Preview', }, # private link { @@ -103,6 +118,7 @@ class SoundcloudIE(InfoExtractor): 'title': 'Youtube - Dl Test Video \'\' Ä↭', 'description': 'test chars: \"\'/\\ä↭', 'uploader': 'jaimeMF', + 'uploader_id': '69767071', 'timestamp': 1386604920, 'upload_date': '20131209', 'duration': 9.927, @@ -123,6 +139,7 @@ class SoundcloudIE(InfoExtractor): 'title': 'Youtube - Dl Test Video \'\' Ä↭', 'description': 'test chars: \"\'/\\ä↭', 'uploader': 'jaimeMF', + 'uploader_id': '69767071', 'timestamp': 1386604920, 'upload_date': '20131209', 'duration': 9.927, @@ -143,6 +160,7 @@ class SoundcloudIE(InfoExtractor): 'title': 'Bus Brakes', 'description': 'md5:0053ca6396e8d2fd7b7e1595ef12ab66', 'uploader': 'oddsamples', + 'uploader_id': '73680509', 'timestamp': 1389232924, 'upload_date': '20140109', 'duration': 17.346, @@ -163,6 +181,7 @@ class SoundcloudIE(InfoExtractor): 'title': 'Uplifting Only 238 [No Talking] (incl. Alex Feed Guestmix) (Aug 31, 2017) [wav]', 'description': 'md5:fa20ee0fca76a3d6df8c7e57f3715366', 'uploader': 'Ori Uplift Music', + 'uploader_id': '12563093', 'timestamp': 1504206263, 'upload_date': '20170831', 'duration': 7449.096, @@ -183,6 +202,7 @@ class SoundcloudIE(InfoExtractor): 'title': 'Sideways (Prod. Mad Real)', 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', 'uploader': 'garyvee', + 'uploader_id': '2366352', 'timestamp': 1488152409, 'upload_date': '20170226', 'duration': 207.012, @@ -207,6 +227,7 @@ class SoundcloudIE(InfoExtractor): 'title': 'Mezzo Valzer', 'description': 'md5:4138d582f81866a530317bae316e8b61', 'uploader': 'Giovanni Sarani', + 'uploader_id': '3352531', 'timestamp': 1551394171, 'upload_date': '20190228', 'duration': 180.157, @@ -221,114 +242,81 @@ class SoundcloudIE(InfoExtractor): } ] + _API_BASE = 'https://api.soundcloud.com/' + _API_V2_BASE = 'https://api-v2.soundcloud.com/' + _BASE_URL = 'https://soundcloud.com/' _CLIENT_ID = 'BeGVhOrGmfboy1LtiHTQF6Ejpt9ULJCI' + _IMAGE_REPL_RE = r'-([0-9a-z]+)\.jpg' - @staticmethod - def _extract_urls(webpage): - return [m.group('url') for m in re.finditer( - r'<iframe[^>]+src=(["\'])(?P<url>(?:https?://)?(?:w\.)?soundcloud\.com/player.+?)\1', - webpage)] + _ARTWORK_MAP = { + 'mini': 16, + 'tiny': 20, + 'small': 32, + 'badge': 47, + 't67x67': 67, + 'large': 100, + 't300x300': 300, + 'crop': 400, + 't500x500': 500, + 'original': 0, + } @classmethod def _resolv_url(cls, url): - return 'https://api.soundcloud.com/resolve.json?url=' + url + '&client_id=' + cls._CLIENT_ID + return SoundcloudIE._API_V2_BASE + 'resolve?url=' + url + '&client_id=' + cls._CLIENT_ID - def _extract_info_dict(self, info, full_title=None, quiet=False, secret_token=None): + def _extract_info_dict(self, info, full_title=None, secret_token=None, version=2): track_id = compat_str(info['id']) title = info['title'] - name = full_title or track_id - if quiet: - self.report_extraction(name) - thumbnail = info.get('artwork_url') or info.get('user', {}).get('avatar_url') - if isinstance(thumbnail, compat_str): - thumbnail = thumbnail.replace('-large', '-t500x500') - username = try_get(info, lambda x: x['user']['username'], compat_str) - - def extract_count(key): - return int_or_none(info.get('%s_count' % key)) - - like_count = extract_count('favoritings') - if like_count is None: - like_count = extract_count('likes') - - result = { - 'id': track_id, - 'uploader': username, - 'timestamp': unified_timestamp(info.get('created_at')), - 'title': title, - 'description': info.get('description'), - 'thumbnail': thumbnail, - 'duration': float_or_none(info.get('duration'), 1000), - 'webpage_url': info.get('permalink_url'), - 'license': info.get('license'), - 'view_count': extract_count('playback'), - 'like_count': like_count, - 'comment_count': extract_count('comment'), - 'repost_count': extract_count('reposts'), - 'genre': info.get('genre'), - } + track_base_url = self._API_BASE + 'tracks/%s' % track_id format_urls = set() formats = [] query = {'client_id': self._CLIENT_ID} - if secret_token is not None: + if secret_token: query['secret_token'] = secret_token - if info.get('downloadable', False): - # We can build a direct link to the song + + if info.get('downloadable'): format_url = update_url_query( - 'https://api.soundcloud.com/tracks/%s/download' % track_id, query) + info.get('download_url') or track_base_url + '/download', query) format_urls.add(format_url) + if version == 2: + v1_info = self._download_json( + track_base_url, track_id, query=query, fatal=False) or {} + else: + v1_info = info formats.append({ 'format_id': 'download', - 'ext': info.get('original_format', 'mp3'), + 'ext': v1_info.get('original_format') or 'mp3', + 'filesize': int_or_none(v1_info.get('original_content_size')), 'url': format_url, - 'vcodec': 'none', 'preference': 10, }) - # Old API, does not work for some tracks (e.g. - # https://soundcloud.com/giovannisarani/mezzo-valzer) - format_dict = self._download_json( - 'https://api.soundcloud.com/i1/tracks/%s/streams' % track_id, - track_id, 'Downloading track url', query=query, fatal=False) + def invalid_url(url): + return not url or url in format_urls or re.search(r'/(?:preview|playlist)/0/30/', url) - if format_dict: - for key, stream_url in format_dict.items(): - if stream_url in format_urls: - continue - format_urls.add(stream_url) - ext, abr = 'mp3', None - mobj = re.search(r'_([^_]+)_(\d+)_url', key) - if mobj: - ext, abr = mobj.groups() - abr = int(abr) - if key.startswith('http'): - stream_formats = [{ - 'format_id': key, - 'ext': ext, - 'url': stream_url, - }] - elif key.startswith('rtmp'): - # The url doesn't have an rtmp app, we have to extract the playpath - url, path = stream_url.split('mp3:', 1) - stream_formats = [{ - 'format_id': key, - 'url': url, - 'play_path': 'mp3:' + path, - 'ext': 'flv', - }] - elif key.startswith('hls'): - stream_formats = self._extract_m3u8_formats( - stream_url, track_id, ext, entry_protocol='m3u8_native', - m3u8_id=key, fatal=False) - else: - continue - - if abr: - for f in stream_formats: - f['abr'] = abr - - formats.extend(stream_formats) + def add_format(f, protocol): + mobj = re.search(r'\.(?P<abr>\d+)\.(?P<ext>[0-9a-z]{3,4})(?=[/?])', stream_url) + if mobj: + for k, v in mobj.groupdict().items(): + if not f.get(k): + f[k] = v + format_id_list = [] + if protocol: + format_id_list.append(protocol) + for k in ('ext', 'abr'): + v = f.get(k) + if v: + format_id_list.append(v) + abr = f.get('abr') + if abr: + f['abr'] = int(abr) + f.update({ + 'format_id': '_'.join(format_id_list), + 'protocol': 'm3u8_native' if protocol == 'hls' else 'http', + }) + formats.append(f) # New API transcodings = try_get( @@ -337,129 +325,165 @@ class SoundcloudIE(InfoExtractor): if not isinstance(t, dict): continue format_url = url_or_none(t.get('url')) - if not format_url: + if not format_url or t.get('snipped') or '/preview/' in format_url: continue stream = self._download_json( - update_url_query(format_url, query), track_id, fatal=False) + format_url, track_id, query=query, fatal=False) if not isinstance(stream, dict): continue stream_url = url_or_none(stream.get('url')) - if not stream_url: - continue - if stream_url in format_urls: + if invalid_url(stream_url): continue format_urls.add(stream_url) - protocol = try_get(t, lambda x: x['format']['protocol'], compat_str) + stream_format = t.get('format') or {} + protocol = stream_format.get('protocol') if protocol != 'hls' and '/hls' in format_url: protocol = 'hls' ext = None preset = str_or_none(t.get('preset')) if preset: ext = preset.split('_')[0] - if ext not in KNOWN_EXTENSIONS: - mimetype = try_get( - t, lambda x: x['format']['mime_type'], compat_str) - ext = mimetype2ext(mimetype) or 'mp3' - format_id_list = [] - if protocol: - format_id_list.append(protocol) - format_id_list.append(ext) - format_id = '_'.join(format_id_list) - formats.append({ + if ext not in KNOWN_EXTENSIONS: + ext = mimetype2ext(stream_format.get('mime_type')) + add_format({ 'url': stream_url, - 'format_id': format_id, 'ext': ext, - 'protocol': 'm3u8_native' if protocol == 'hls' else 'http', - }) + }, 'http' if protocol == 'progressive' else protocol) + + if not formats: + # Old API, does not work for some tracks (e.g. + # https://soundcloud.com/giovannisarani/mezzo-valzer) + # and might serve preview URLs (e.g. + # http://www.soundcloud.com/snbrn/ele) + format_dict = self._download_json( + track_base_url + '/streams', track_id, + 'Downloading track url', query=query, fatal=False) or {} + + for key, stream_url in format_dict.items(): + if invalid_url(stream_url): + continue + format_urls.add(stream_url) + mobj = re.search(r'(http|hls)_([^_]+)_(\d+)_url', key) + if mobj: + protocol, ext, abr = mobj.groups() + add_format({ + 'abr': abr, + 'ext': ext, + 'url': stream_url, + }, protocol) if not formats: # We fallback to the stream_url in the original info, this # cannot be always used, sometimes it can give an HTTP 404 error - formats.append({ - 'format_id': 'fallback', - 'url': update_url_query(info['stream_url'], query), - 'ext': 'mp3', - }) - self._check_formats(formats, track_id) + urlh = self._request_webpage( + HEADRequest(info.get('stream_url') or track_base_url + '/stream'), + track_id, query=query, fatal=False) + if urlh: + stream_url = urlh.geturl() + if not invalid_url(stream_url): + add_format({'url': stream_url}, 'http') for f in formats: f['vcodec'] = 'none' self._sort_formats(formats) - result['formats'] = formats - return result + user = info.get('user') or {} + + thumbnails = [] + artwork_url = info.get('artwork_url') + thumbnail = artwork_url or user.get('avatar_url') + if isinstance(thumbnail, compat_str): + if re.search(self._IMAGE_REPL_RE, thumbnail): + for image_id, size in self._ARTWORK_MAP.items(): + i = { + 'id': image_id, + 'url': re.sub(self._IMAGE_REPL_RE, '-%s.jpg' % image_id, thumbnail), + } + if image_id == 'tiny' and not artwork_url: + size = 18 + elif image_id == 'original': + i['preference'] = 10 + if size: + i.update({ + 'width': size, + 'height': size, + }) + thumbnails.append(i) + else: + thumbnails = [{'url': thumbnail}] + + def extract_count(key): + return int_or_none(info.get('%s_count' % key)) + + return { + 'id': track_id, + 'uploader': user.get('username'), + 'uploader_id': str_or_none(user.get('id')) or user.get('permalink'), + 'uploader_url': user.get('permalink_url'), + 'timestamp': unified_timestamp(info.get('created_at')), + 'title': title, + 'description': info.get('description'), + 'thumbnails': thumbnails, + 'duration': float_or_none(info.get('duration'), 1000), + 'webpage_url': info.get('permalink_url'), + 'license': info.get('license'), + 'view_count': extract_count('playback'), + 'like_count': extract_count('favoritings') or extract_count('likes'), + 'comment_count': extract_count('comment'), + 'repost_count': extract_count('reposts'), + 'genre': info.get('genre'), + 'formats': formats + } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE) - if mobj is None: - raise ExtractorError('Invalid URL: %s' % url) + mobj = re.match(self._VALID_URL, url) track_id = mobj.group('track_id') - new_info = {} - if track_id is not None: - info_json_url = 'https://api.soundcloud.com/tracks/' + track_id + '.json?client_id=' + self._CLIENT_ID + query = { + 'client_id': self._CLIENT_ID, + } + if track_id: + info_json_url = self._API_V2_BASE + 'tracks/' + track_id full_title = track_id token = mobj.group('secret_token') if token: - info_json_url += '&secret_token=' + token - elif mobj.group('player'): - query = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) - real_url = query['url'][0] - # If the token is in the query of the original url we have to - # manually add it - if 'secret_token' in query: - real_url += '?secret_token=' + query['secret_token'][0] - return self.url_result(real_url) + query['secret_token'] = token else: - # extract uploader (which is in the url) - uploader = mobj.group('uploader') - # extract simple title (uploader + slug of song title) - slug_title = mobj.group('title') + full_title = resolve_title = '%s/%s' % mobj.group('uploader', 'title') token = mobj.group('token') - full_title = resolve_title = '%s/%s' % (uploader, slug_title) if token: resolve_title += '/%s' % token + info_json_url = self._resolv_url(self._BASE_URL + resolve_title) - webpage = self._download_webpage(url, full_title, fatal=False) - if webpage: - entries = self._parse_json( - self._search_regex( - r'var\s+c\s*=\s*(\[.+?\])\s*,\s*o\s*=Date\b', webpage, - 'data', default='[]'), full_title, fatal=False) - if entries: - for e in entries: - if not isinstance(e, dict): - continue - if e.get('id') != 67: - continue - data = try_get(e, lambda x: x['data'][0], dict) - if data: - new_info = data - break - info_json_url = self._resolv_url( - 'https://soundcloud.com/%s' % resolve_title) - - # Contains some additional info missing from new_info + version = 2 info = self._download_json( - info_json_url, full_title, 'Downloading info JSON') + info_json_url, full_title, 'Downloading info JSON', query=query, fatal=False) + if not info: + info = self._download_json( + info_json_url.replace(self._API_V2_BASE, self._API_BASE), + full_title, 'Downloading info JSON', query=query) + version = 1 - return self._extract_info_dict( - merge_dicts(info, new_info), full_title, secret_token=token) + return self._extract_info_dict(info, full_title, token, version) class SoundcloudPlaylistBaseIE(SoundcloudIE): - @staticmethod - def _extract_id(e): - return compat_str(e['id']) if e.get('id') else None - - def _extract_track_entries(self, tracks): - return [ - self.url_result( - track['permalink_url'], SoundcloudIE.ie_key(), - video_id=self._extract_id(track)) - for track in tracks if track.get('permalink_url')] + def _extract_track_entries(self, tracks, token=None): + entries = [] + for track in tracks: + track_id = str_or_none(track.get('id')) + url = track.get('permalink_url') + if not url: + if not track_id: + continue + url = self._API_V2_BASE + 'tracks/' + track_id + if token: + url += '?secret_token=' + token + entries.append(self.url_result( + url, SoundcloudIE.ie_key(), track_id)) + return entries class SoundcloudSetIE(SoundcloudPlaylistBaseIE): @@ -480,41 +504,28 @@ class SoundcloudSetIE(SoundcloudPlaylistBaseIE): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - # extract uploader (which is in the url) - uploader = mobj.group('uploader') - # extract simple title (uploader + slug of song title) - slug_title = mobj.group('slug_title') - full_title = '%s/sets/%s' % (uploader, slug_title) - url = 'https://soundcloud.com/%s/sets/%s' % (uploader, slug_title) - + full_title = '%s/sets/%s' % mobj.group('uploader', 'slug_title') token = mobj.group('token') if token: full_title += '/' + token - url += '/' + token - resolv_url = self._resolv_url(url) - info = self._download_json(resolv_url, full_title) + info = self._download_json(self._resolv_url( + self._BASE_URL + full_title), full_title) if 'errors' in info: msgs = (compat_str(err['error_message']) for err in info['errors']) raise ExtractorError('unable to download video webpage: %s' % ','.join(msgs)) - entries = self._extract_track_entries(info['tracks']) + entries = self._extract_track_entries(info['tracks'], token) - return { - '_type': 'playlist', - 'entries': entries, - 'id': '%s' % info['id'], - 'title': info['title'], - } + return self.playlist_result( + entries, str_or_none(info.get('id')), info.get('title')) class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE): - _API_V2_BASE = 'https://api-v2.soundcloud.com' - def _extract_playlist(self, base_url, playlist_id, playlist_title): COMMON_QUERY = { - 'limit': 50, + 'limit': 2000000000, 'client_id': self._CLIENT_ID, 'linked_partitioning': '1', } @@ -522,12 +533,13 @@ class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE): query = COMMON_QUERY.copy() query['offset'] = 0 - next_href = base_url + '?' + compat_urllib_parse_urlencode(query) + next_href = base_url entries = [] for i in itertools.count(): response = self._download_json( - next_href, playlist_id, 'Downloading track page %s' % (i + 1)) + next_href, playlist_id, + 'Downloading track page %s' % (i + 1), query=query) collection = response['collection'] @@ -546,9 +558,8 @@ class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE): continue return self.url_result( permalink_url, - ie=SoundcloudIE.ie_key() if SoundcloudIE.suitable(permalink_url) else None, - video_id=self._extract_id(cand), - video_title=cand.get('title')) + SoundcloudIE.ie_key() if SoundcloudIE.suitable(permalink_url) else None, + str_or_none(cand.get('id')), cand.get('title')) for e in collection: entry = resolve_entry((e, e.get('track'), e.get('playlist'))) @@ -559,11 +570,10 @@ class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE): if not next_href: break - parsed_next_href = compat_urlparse.urlparse(response['next_href']) - qs = compat_urlparse.parse_qs(parsed_next_href.query) - qs.update(COMMON_QUERY) - next_href = compat_urlparse.urlunparse( - parsed_next_href._replace(query=compat_urllib_parse_urlencode(qs, True))) + next_href = response['next_href'] + parsed_next_href = compat_urlparse.urlparse(next_href) + query = compat_urlparse.parse_qs(parsed_next_href.query) + query.update(COMMON_QUERY) return { '_type': 'playlist', @@ -609,7 +619,7 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE): 'url': 'https://soundcloud.com/jcv246/sets', 'info_dict': { 'id': '12982173', - 'title': 'Jordi / cv (Playlists)', + 'title': 'Jordi / cv (Sets)', }, 'playlist_mincount': 2, }, { @@ -636,39 +646,29 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE): }] _BASE_URL_MAP = { - 'all': '%s/stream/users/%%s' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, - 'tracks': '%s/users/%%s/tracks' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, - 'albums': '%s/users/%%s/albums' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, - 'sets': '%s/users/%%s/playlists' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, - 'reposts': '%s/stream/users/%%s/reposts' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, - 'likes': '%s/users/%%s/likes' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, - 'spotlight': '%s/users/%%s/spotlight' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, - } - - _TITLE_MAP = { - 'all': 'All', - 'tracks': 'Tracks', - 'albums': 'Albums', - 'sets': 'Playlists', - 'reposts': 'Reposts', - 'likes': 'Likes', - 'spotlight': 'Spotlight', + 'all': 'stream/users/%s', + 'tracks': 'users/%s/tracks', + 'albums': 'users/%s/albums', + 'sets': 'users/%s/playlists', + 'reposts': 'stream/users/%s/reposts', + 'likes': 'users/%s/likes', + 'spotlight': 'users/%s/spotlight', } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) uploader = mobj.group('user') - url = 'https://soundcloud.com/%s/' % uploader - resolv_url = self._resolv_url(url) user = self._download_json( - resolv_url, uploader, 'Downloading user info') + self._resolv_url(self._BASE_URL + uploader), + uploader, 'Downloading user info') resource = mobj.group('rsrc') or 'all' return self._extract_playlist( - self._BASE_URL_MAP[resource] % user['id'], compat_str(user['id']), - '%s (%s)' % (user['username'], self._TITLE_MAP[resource])) + self._API_V2_BASE + self._BASE_URL_MAP[resource] % user['id'], + str_or_none(user.get('id')), + '%s (%s)' % (user['username'], resource.capitalize())) class SoundcloudTrackStationIE(SoundcloudPagedPlaylistBaseIE): @@ -678,7 +678,7 @@ class SoundcloudTrackStationIE(SoundcloudPagedPlaylistBaseIE): 'url': 'https://soundcloud.com/stations/track/officialsundial/your-text', 'info_dict': { 'id': '286017854', - 'title': 'Track station: your-text', + 'title': 'Track station: your text', }, 'playlist_mincount': 47, }] @@ -686,19 +686,17 @@ class SoundcloudTrackStationIE(SoundcloudPagedPlaylistBaseIE): def _real_extract(self, url): track_name = self._match_id(url) - webpage = self._download_webpage(url, track_name) - + track = self._download_json(self._resolv_url(url), track_name) track_id = self._search_regex( - r'soundcloud:track-stations:(\d+)', webpage, 'track id') + r'soundcloud:track-stations:(\d+)', track['id'], 'track id') return self._extract_playlist( - '%s/stations/soundcloud:track-stations:%s/tracks' - % (self._API_V2_BASE, track_id), - track_id, 'Track station: %s' % track_name) + self._API_V2_BASE + 'stations/%s/tracks' % track['id'], + track_id, 'Track station: %s' % track['title']) class SoundcloudPlaylistIE(SoundcloudPlaylistBaseIE): - _VALID_URL = r'https?://api\.soundcloud\.com/playlists/(?P<id>[0-9]+)(?:/?\?secret_token=(?P<token>[^&]+?))?$' + _VALID_URL = r'https?://api(?:-v2)?\.soundcloud\.com/playlists/(?P<id>[0-9]+)(?:/?\?secret_token=(?P<token>[^&]+?))?$' IE_NAME = 'soundcloud:playlist' _TESTS = [{ 'url': 'https://api.soundcloud.com/playlists/4110309', @@ -713,29 +711,22 @@ class SoundcloudPlaylistIE(SoundcloudPlaylistBaseIE): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) playlist_id = mobj.group('id') - base_url = '%s//api.soundcloud.com/playlists/%s.json?' % (self.http_scheme(), playlist_id) - data_dict = { + query = { 'client_id': self._CLIENT_ID, } token = mobj.group('token') - if token: - data_dict['secret_token'] = token + query['secret_token'] = token - data = compat_urllib_parse_urlencode(data_dict) data = self._download_json( - base_url + data, playlist_id, 'Downloading playlist') + self._API_V2_BASE + 'playlists/' + playlist_id, + playlist_id, 'Downloading playlist', query=query) - entries = self._extract_track_entries(data['tracks']) + entries = self._extract_track_entries(data['tracks'], token) - return { - '_type': 'playlist', - 'id': playlist_id, - 'title': data.get('title'), - 'description': data.get('description'), - 'entries': entries, - } + return self.playlist_result( + entries, playlist_id, data.get('title'), data.get('description')) class SoundcloudSearchIE(SearchInfoExtractor, SoundcloudIE): @@ -753,18 +744,18 @@ class SoundcloudSearchIE(SearchInfoExtractor, SoundcloudIE): _SEARCH_KEY = 'scsearch' _MAX_RESULTS_PER_PAGE = 200 _DEFAULT_RESULTS_PER_PAGE = 50 - _API_V2_BASE = 'https://api-v2.soundcloud.com' def _get_collection(self, endpoint, collection_id, **query): limit = min( query.get('limit', self._DEFAULT_RESULTS_PER_PAGE), self._MAX_RESULTS_PER_PAGE) - query['limit'] = limit - query['client_id'] = self._CLIENT_ID - query['linked_partitioning'] = '1' - query['offset'] = 0 - data = compat_urllib_parse_urlencode(query) - next_url = '{0}{1}?{2}'.format(self._API_V2_BASE, endpoint, data) + query.update({ + 'limit': limit, + 'client_id': self._CLIENT_ID, + 'linked_partitioning': 1, + 'offset': 0, + }) + next_url = update_url_query(self._API_V2_BASE + endpoint, query) collected_results = 0 @@ -791,5 +782,5 @@ class SoundcloudSearchIE(SearchInfoExtractor, SoundcloudIE): break def _get_n_results(self, query, n): - tracks = self._get_collection('/search/tracks', query, limit=n, q=query) + tracks = self._get_collection('search/tracks', query, limit=n, q=query) return self.playlist_result(tracks, playlist_title=query) From dd90451f0f4867480c5ed8cb3588b30312204e3f Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 27 Oct 2019 22:02:46 +0100 Subject: [PATCH 116/422] [tenplay] Add new extractor(closes #21446) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/tenplay.py | 55 ++++++++++++++++++++++++++++++ 2 files changed, 56 insertions(+) create mode 100644 youtube_dl/extractor/tenplay.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 388c1ebe6..339a141a5 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1133,6 +1133,7 @@ from .telequebec import ( from .teletask import TeleTaskIE from .telewebion import TelewebionIE from .tennistv import TennisTVIE +from .tenplay import TenPlayIE from .testurl import TestURLIE from .tf1 import TF1IE from .tfo import TFOIE diff --git a/youtube_dl/extractor/tenplay.py b/youtube_dl/extractor/tenplay.py new file mode 100644 index 000000000..dff44a4e2 --- /dev/null +++ b/youtube_dl/extractor/tenplay.py @@ -0,0 +1,55 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + parse_age_limit, + parse_iso8601, + smuggle_url, +) + + +class TenPlayIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?10play\.com\.au/[^/]+/episodes/[^/]+/[^/]+/(?P<id>tpv\d{6}[a-z]{5})' + _TEST = { + 'url': 'https://10play.com.au/masterchef/episodes/season-1/masterchef-s1-ep-1/tpv190718kwzga', + 'info_dict': { + 'id': '6060533435001', + 'ext': 'mp4', + 'title': 'MasterChef - S1 Ep. 1', + 'description': 'md5:4fe7b78e28af8f2d900cd20d900ef95c', + 'age_limit': 10, + 'timestamp': 1240828200, + 'upload_date': '20090427', + 'uploader_id': '2199827728001', + }, + 'params': { + 'format': 'bestvideo', + 'skip_download': True, + } + } + BRIGHTCOVE_URL_TEMPLATE = 'https://players.brightcove.net/2199827728001/cN6vRtRQt_default/index.html?videoId=%s' + + def _real_extract(self, url): + content_id = self._match_id(url) + data = self._download_json( + 'https://10play.com.au/api/video/' + content_id, content_id) + video = data.get('video') or {} + metadata = data.get('metaData') or {} + brightcove_id = video.get('videoId') or metadata['showContentVideoId'] + brightcove_url = smuggle_url( + self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, + {'geo_countries': ['AU']}) + + return { + '_type': 'url_transparent', + 'url': brightcove_url, + 'id': content_id, + 'title': video.get('title') or metadata.get('pageContentName') or metadata.get('showContentName'), + 'description': video.get('description'), + 'age_limit': parse_age_limit(video.get('showRatingClassification') or metadata.get('showProgramClassification')), + 'series': metadata.get('showName'), + 'season': metadata.get('showContentSeason'), + 'timestamp': parse_iso8601(metadata.get('contentPublishDate') or metadata.get('pageContentPublishDate')), + 'ie_key': 'BrightcoveNew', + } From 71fa0b04f9099090f43f6747632a9bdc3a4b1015 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Mon, 28 Oct 2019 13:30:30 +0100 Subject: [PATCH 117/422] [makertv] remove extractor --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/makertv.py | 32 ------------------------------ 2 files changed, 33 deletions(-) delete mode 100644 youtube_dl/extractor/makertv.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 339a141a5..4229518fd 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -604,7 +604,6 @@ from .mailru import ( MailRuMusicIE, MailRuMusicSearchIE, ) -from .makertv import MakerTVIE from .malltv import MallTVIE from .mangomolo import ( MangomoloVideoIE, diff --git a/youtube_dl/extractor/makertv.py b/youtube_dl/extractor/makertv.py deleted file mode 100644 index 8eda69cfc..000000000 --- a/youtube_dl/extractor/makertv.py +++ /dev/null @@ -1,32 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor - - -class MakerTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:(?:www\.)?maker\.tv/(?:[^/]+/)*video|makerplayer\.com/embed/maker)/(?P<id>[a-zA-Z0-9]{12})' - _TEST = { - 'url': 'http://www.maker.tv/video/Fh3QgymL9gsc', - 'md5': 'ca237a53a8eb20b6dc5bd60564d4ab3e', - 'info_dict': { - 'id': 'Fh3QgymL9gsc', - 'ext': 'mp4', - 'title': 'Maze Runner: The Scorch Trials Official Movie Review', - 'description': 'md5:11ff3362d7ef1d679fdb649f6413975a', - 'upload_date': '20150918', - 'timestamp': 1442549540, - } - } - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - jwplatform_id = self._search_regex(r'jw_?id="([^"]+)"', webpage, 'jwplatform id') - - return { - '_type': 'url_transparent', - 'id': video_id, - 'url': 'jwplatform:%s' % jwplatform_id, - 'ie_key': 'JWPlatform', - } From 80c2126e80bc41f7b66d325c4c67c61887c58fb0 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Mon, 28 Oct 2019 13:32:35 +0100 Subject: [PATCH 118/422] [thesun] fix extraction(closes #16966) --- youtube_dl/extractor/thesun.py | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/thesun.py b/youtube_dl/extractor/thesun.py index 22d003776..15d4a6932 100644 --- a/youtube_dl/extractor/thesun.py +++ b/youtube_dl/extractor/thesun.py @@ -3,7 +3,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from .ooyala import OoyalaIE +from ..utils import extract_attributes class TheSunIE(InfoExtractor): @@ -16,6 +16,7 @@ class TheSunIE(InfoExtractor): }, 'playlist_count': 2, } + BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' def _real_extract(self, url): article_id = self._match_id(url) @@ -23,10 +24,15 @@ class TheSunIE(InfoExtractor): webpage = self._download_webpage(url, article_id) entries = [] - for ooyala_id in re.findall( - r'<[^>]+\b(?:id\s*=\s*"thesun-ooyala-player-|data-content-id\s*=\s*")([^"]+)', + for video in re.findall( + r'<video[^>]+data-video-id-pending=[^>]+>', webpage): - entries.append(OoyalaIE._build_url_result(ooyala_id)) + attrs = extract_attributes(video) + video_id = attrs['data-video-id-pending'] + account_id = attrs.get('data-account', '5067014667001') + entries.append(self.url_result( + self.BRIGHTCOVE_URL_TEMPLATE % (account_id, video_id), + 'BrightcoveNew', video_id)) return self.playlist_result( entries, article_id, self._og_search_title(webpage, fatal=False)) From 0f9d53566a5956854af77173c0e910ed7454aadf Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Mon, 28 Oct 2019 15:17:06 +0100 Subject: [PATCH 119/422] [la7] update Kaltura service URL(closes #22358) --- youtube_dl/extractor/la7.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/la7.py b/youtube_dl/extractor/la7.py index 6373268c4..c3b4ffa7e 100644 --- a/youtube_dl/extractor/la7.py +++ b/youtube_dl/extractor/la7.py @@ -20,7 +20,7 @@ class LA7IE(InfoExtractor): 'url': 'http://www.la7.it/crozza/video/inccool8-02-10-2015-163722', 'md5': '8b613ffc0c4bf9b9e377169fc19c214c', 'info_dict': { - 'id': 'inccool8-02-10-2015-163722', + 'id': '0_42j6wd36', 'ext': 'mp4', 'title': 'Inc.Cool8', 'description': 'Benvenuti nell\'incredibile mondo della INC. COOL. 8. dove “INC.” sta per “Incorporated” “COOL” sta per “fashion” ed Eight sta per il gesto atletico', @@ -57,7 +57,7 @@ class LA7IE(InfoExtractor): return { '_type': 'url_transparent', 'url': smuggle_url('kaltura:103:%s' % player_data['vid'], { - 'service_url': 'http://kdam.iltrovatore.it', + 'service_url': 'http://nkdam.iltrovatore.it', }), 'id': video_id, 'title': player_data['title'], From 3e252cca0e81aef55b0288f86991bb566878a9fc Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Mon, 28 Oct 2019 17:39:01 +0100 Subject: [PATCH 120/422] [macgamestore] remove extractor Covered by generic extractor --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/macgamestore.py | 42 ---------------------------- 2 files changed, 43 deletions(-) delete mode 100644 youtube_dl/extractor/macgamestore.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 4229518fd..1807744be 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -598,7 +598,6 @@ from .lynda import ( LyndaCourseIE ) from .m6 import M6IE -from .macgamestore import MacGameStoreIE from .mailru import ( MailRuIE, MailRuMusicIE, diff --git a/youtube_dl/extractor/macgamestore.py b/youtube_dl/extractor/macgamestore.py deleted file mode 100644 index 43db9929c..000000000 --- a/youtube_dl/extractor/macgamestore.py +++ /dev/null @@ -1,42 +0,0 @@ -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..utils import ExtractorError - - -class MacGameStoreIE(InfoExtractor): - IE_NAME = 'macgamestore' - IE_DESC = 'MacGameStore trailers' - _VALID_URL = r'https?://(?:www\.)?macgamestore\.com/mediaviewer\.php\?trailer=(?P<id>\d+)' - - _TEST = { - 'url': 'http://www.macgamestore.com/mediaviewer.php?trailer=2450', - 'md5': '8649b8ea684b6666b4c5be736ecddc61', - 'info_dict': { - 'id': '2450', - 'ext': 'm4v', - 'title': 'Crow', - } - } - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage( - url, video_id, 'Downloading trailer page') - - if '>Missing Media<' in webpage: - raise ExtractorError( - 'Trailer %s does not exist' % video_id, expected=True) - - video_title = self._html_search_regex( - r'<title>MacGameStore: (.*?) Trailer', webpage, 'title') - - video_url = self._html_search_regex( - r'(?s)', - webpage, 'video URL') - - return { - 'id': video_id, - 'url': video_url, - 'title': video_title - } From 831b732da1d0796a1927af8767d76af780cc90f0 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 28 Oct 2019 17:41:17 +0100 Subject: [PATCH 121/422] [learnr] remove extractor --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/learnr.py | 33 ------------------------------ 2 files changed, 34 deletions(-) delete mode 100644 youtube_dl/extractor/learnr.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 1807744be..9f3a5f8a5 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -546,7 +546,6 @@ from .lcp import ( LcpPlayIE, LcpIE, ) -from .learnr import LearnrIE from .lecture2go import Lecture2GoIE from .lecturio import ( LecturioIE, diff --git a/youtube_dl/extractor/learnr.py b/youtube_dl/extractor/learnr.py deleted file mode 100644 index 1435e090e..000000000 --- a/youtube_dl/extractor/learnr.py +++ /dev/null @@ -1,33 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor - - -class LearnrIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?learnr\.pro/view/video/(?P[0-9]+)' - _TEST = { - 'url': 'http://www.learnr.pro/view/video/51624-web-development-tutorial-for-beginners-1-how-to-build-webpages-with-html-css-javascript', - 'md5': '3719fdf0a68397f49899e82c308a89de', - 'info_dict': { - 'id': '51624', - 'ext': 'mp4', - 'title': 'Web Development Tutorial for Beginners (#1) - How to build webpages with HTML, CSS, Javascript', - 'description': 'md5:b36dbfa92350176cdf12b4d388485503', - 'uploader': 'LearnCode.academy', - 'uploader_id': 'learncodeacademy', - 'upload_date': '20131021', - }, - 'add_ie': ['Youtube'], - } - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - return { - '_type': 'url_transparent', - 'url': self._search_regex( - r"videoId\s*:\s*'([^']+)'", webpage, 'youtube id'), - 'id': video_id, - } From b3c2fa6dad607da6455a13d232461d4380e4b53c Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 28 Oct 2019 17:42:33 +0100 Subject: [PATCH 122/422] [tutv] remove extractor --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/tutv.py | 36 ------------------------------ 2 files changed, 37 deletions(-) delete mode 100644 youtube_dl/extractor/tutv.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 9f3a5f8a5..39282b785 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1183,7 +1183,6 @@ from .tunein import ( ) from .tunepk import TunePkIE from .turbo import TurboIE -from .tutv import TutvIE from .tv2 import ( TV2IE, TV2ArticleIE, diff --git a/youtube_dl/extractor/tutv.py b/youtube_dl/extractor/tutv.py deleted file mode 100644 index 362318b24..000000000 --- a/youtube_dl/extractor/tutv.py +++ /dev/null @@ -1,36 +0,0 @@ -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..compat import ( - compat_b64decode, - compat_parse_qs, -) - - -class TutvIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?tu\.tv/videos/(?P[^/?]+)' - _TEST = { - 'url': 'http://tu.tv/videos/robots-futbolistas', - 'md5': '0cd9e28ad270488911b0d2a72323395d', - 'info_dict': { - 'id': '2973058', - 'ext': 'mp4', - 'title': 'Robots futbolistas', - }, - } - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - internal_id = self._search_regex(r'codVideo=([0-9]+)', webpage, 'internal video ID') - - data_content = self._download_webpage( - 'http://tu.tv/flvurl.php?codVideo=%s' % internal_id, video_id, 'Downloading video info') - video_url = compat_b64decode(compat_parse_qs(data_content)['kpt'][0]).decode('utf-8') - - return { - 'id': internal_id, - 'url': video_url, - 'title': self._og_search_title(webpage), - } From 702984eca955f61811078c33337faf9eebeb48c8 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 28 Oct 2019 17:49:05 +0100 Subject: [PATCH 123/422] [hark] remove extractor --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/hark.py | 33 ------------------------------ 2 files changed, 34 deletions(-) delete mode 100644 youtube_dl/extractor/hark.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 39282b785..114ede8b9 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -428,7 +428,6 @@ from .googlesearch import GoogleSearchIE from .goshgay import GoshgayIE from .gputechconf import GPUTechConfIE from .groupon import GrouponIE -from .hark import HarkIE from .hbo import HBOIE from .hearthisat import HearThisAtIE from .heise import HeiseIE diff --git a/youtube_dl/extractor/hark.py b/youtube_dl/extractor/hark.py deleted file mode 100644 index 342a6130e..000000000 --- a/youtube_dl/extractor/hark.py +++ /dev/null @@ -1,33 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor - - -class HarkIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?hark\.com/clips/(?P.+?)-.+' - _TEST = { - 'url': 'http://www.hark.com/clips/mmbzyhkgny-obama-beyond-the-afghan-theater-we-only-target-al-qaeda-on-may-23-2013', - 'md5': '6783a58491b47b92c7c1af5a77d4cbee', - 'info_dict': { - 'id': 'mmbzyhkgny', - 'ext': 'mp3', - 'title': 'Obama: \'Beyond The Afghan Theater, We Only Target Al Qaeda\' on May 23, 2013', - 'description': 'President Barack Obama addressed the nation live on May 23, 2013 in a speech aimed at addressing counter-terrorism policies including the use of drone strikes, detainees at Guantanamo Bay prison facility, and American citizens who are terrorists.', - 'duration': 11, - } - } - - def _real_extract(self, url): - video_id = self._match_id(url) - data = self._download_json( - 'http://www.hark.com/clips/%s.json' % video_id, video_id) - - return { - 'id': video_id, - 'url': data['url'], - 'title': data['name'], - 'description': data.get('description'), - 'thumbnail': data.get('image_original'), - 'duration': data.get('duration'), - } From 895e5c03db310ee97d585360ef8e6ae117e4cbd6 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 28 Oct 2019 19:31:20 +0100 Subject: [PATCH 124/422] [nbcnews] fix extraction closes #12569 closes #12576 closes #21703 closes #21923 --- youtube_dl/extractor/nbc.py | 86 +++++++++++++++++++++++++++---------- 1 file changed, 63 insertions(+), 23 deletions(-) diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py index 10680b202..5bc39d002 100644 --- a/youtube_dl/extractor/nbc.py +++ b/youtube_dl/extractor/nbc.py @@ -9,9 +9,13 @@ from .theplatform import ThePlatformIE from .adobepass import AdobePassIE from ..compat import compat_urllib_parse_unquote from ..utils import ( - smuggle_url, - update_url_query, int_or_none, + js_to_json, + parse_duration, + smuggle_url, + try_get, + unified_timestamp, + update_url_query, ) @@ -285,13 +289,12 @@ class NBCNewsIE(ThePlatformIE): _TESTS = [ { 'url': 'http://www.nbcnews.com/watch/nbcnews-com/how-twitter-reacted-to-the-snowden-interview-269389891880', - 'md5': 'af1adfa51312291a017720403826bb64', + 'md5': 'cf4bc9e6ce0130f00f545d80ecedd4bf', 'info_dict': { 'id': '269389891880', 'ext': 'mp4', 'title': 'How Twitter Reacted To The Snowden Interview', 'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64', - 'uploader': 'NBCU-NEWS', 'timestamp': 1401363060, 'upload_date': '20140529', }, @@ -309,28 +312,26 @@ class NBCNewsIE(ThePlatformIE): }, { 'url': 'http://www.nbcnews.com/nightly-news/video/nightly-news-with-brian-williams-full-broadcast-february-4-394064451844', - 'md5': '73135a2e0ef819107bbb55a5a9b2a802', + 'md5': '8eb831eca25bfa7d25ddd83e85946548', 'info_dict': { 'id': '394064451844', 'ext': 'mp4', 'title': 'Nightly News with Brian Williams Full Broadcast (February 4)', 'description': 'md5:1c10c1eccbe84a26e5debb4381e2d3c5', 'timestamp': 1423104900, - 'uploader': 'NBCU-NEWS', 'upload_date': '20150205', }, }, { 'url': 'http://www.nbcnews.com/business/autos/volkswagen-11-million-vehicles-could-have-suspect-software-emissions-scandal-n431456', - 'md5': 'a49e173825e5fcd15c13fc297fced39d', + 'md5': '4a8c4cec9e1ded51060bdda36ff0a5c0', 'info_dict': { - 'id': '529953347624', + 'id': 'n431456', 'ext': 'mp4', - 'title': 'Volkswagen U.S. Chief:\xa0 We Have Totally Screwed Up', - 'description': 'md5:c8be487b2d80ff0594c005add88d8351', + 'title': "Volkswagen U.S. Chief: We 'Totally Screwed Up'", + 'description': 'md5:d22d1281a24f22ea0880741bb4dd6301', 'upload_date': '20150922', 'timestamp': 1442917800, - 'uploader': 'NBCU-NEWS', }, }, { @@ -343,7 +344,6 @@ class NBCNewsIE(ThePlatformIE): 'description': 'md5:74752b7358afb99939c5f8bb2d1d04b1', 'upload_date': '20160420', 'timestamp': 1461152093, - 'uploader': 'NBCU-NEWS', }, }, { @@ -357,7 +357,6 @@ class NBCNewsIE(ThePlatformIE): 'thumbnail': r're:^https?://.*\.jpg$', 'timestamp': 1406937606, 'upload_date': '20140802', - 'uploader': 'NBCU-NEWS', }, }, { @@ -373,20 +372,61 @@ class NBCNewsIE(ThePlatformIE): def _real_extract(self, url): video_id = self._match_id(url) - if not video_id.isdigit(): - webpage = self._download_webpage(url, video_id) + webpage = self._download_webpage(url, video_id) - data = self._parse_json(self._search_regex( - r'window\.__data\s*=\s*({.+});', webpage, - 'bootstrap json'), video_id) - video_id = data['article']['content'][0]['primaryMedia']['video']['mpxMetadata']['id'] + data = self._parse_json(self._search_regex( + r'window\.__data\s*=\s*({.+});', webpage, + 'bootstrap json'), video_id, js_to_json) + video_data = try_get(data, lambda x: x['video']['current'], dict) + if not video_data: + video_data = data['article']['content'][0]['primaryMedia']['video'] + title = video_data['headline']['primary'] + + formats = [] + for va in video_data.get('videoAssets', []): + public_url = va.get('publicUrl') + if not public_url: + continue + if '://link.theplatform.com/' in public_url: + public_url = update_url_query(public_url, {'format': 'redirect'}) + format_id = va.get('format') + if format_id == 'M3U': + formats.extend(self._extract_m3u8_formats( + public_url, video_id, 'mp4', 'm3u8_native', + m3u8_id=format_id, fatal=False)) + continue + tbr = int_or_none(va.get('bitrate'), 1000) + if tbr: + format_id += '-%d' % tbr + formats.append({ + 'format_id': format_id, + 'url': public_url, + 'width': int_or_none(va.get('width')), + 'height': int_or_none(va.get('height')), + 'tbr': tbr, + 'ext': 'mp4', + }) + self._sort_formats(formats) + + subtitles = {} + closed_captioning = video_data.get('closedCaptioning') + if closed_captioning: + for cc_url in closed_captioning.values(): + if not cc_url: + continue + subtitles.setdefault('en', []).append({ + 'url': cc_url, + }) return { - '_type': 'url_transparent', 'id': video_id, - # http://feed.theplatform.com/f/2E2eJC/nbcnews also works - 'url': update_url_query('http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews', {'byId': video_id}), - 'ie_key': 'ThePlatformFeed', + 'title': title, + 'description': try_get(video_data, lambda x: x['description']['primary']), + 'thumbnail': try_get(video_data, lambda x: x['primaryImage']['url']['primary']), + 'duration': parse_duration(video_data.get('duration')), + 'timestamp': unified_timestamp(video_data.get('datePublished')), + 'formats': formats, + 'subtitles': subtitles, } From 83e49259bfd4e0b54a4b53c30742109555087e3a Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 28 Oct 2019 19:45:42 +0100 Subject: [PATCH 125/422] [internetvideoarchive] fix extraction --- youtube_dl/extractor/internetvideoarchive.py | 92 ++++++-------------- 1 file changed, 28 insertions(+), 64 deletions(-) diff --git a/youtube_dl/extractor/internetvideoarchive.py b/youtube_dl/extractor/internetvideoarchive.py index 76cc5ec3e..59b0a90c3 100644 --- a/youtube_dl/extractor/internetvideoarchive.py +++ b/youtube_dl/extractor/internetvideoarchive.py @@ -1,15 +1,13 @@ from __future__ import unicode_literals +import json +import re + from .common import InfoExtractor from ..compat import ( compat_parse_qs, compat_urlparse, ) -from ..utils import ( - determine_ext, - int_or_none, - xpath_text, -) class InternetVideoArchiveIE(InfoExtractor): @@ -20,7 +18,7 @@ class InternetVideoArchiveIE(InfoExtractor): 'info_dict': { 'id': '194487', 'ext': 'mp4', - 'title': 'KICK-ASS 2', + 'title': 'Kick-Ass 2', 'description': 'md5:c189d5b7280400630a1d3dd17eaa8d8a', }, 'params': { @@ -33,68 +31,34 @@ class InternetVideoArchiveIE(InfoExtractor): def _build_json_url(query): return 'http://video.internetvideoarchive.net/player/6/configuration.ashx?' + query - @staticmethod - def _build_xml_url(query): - return 'http://video.internetvideoarchive.net/flash/players/flashconfiguration.aspx?' + query - def _real_extract(self, url): - query = compat_urlparse.urlparse(url).query - query_dic = compat_parse_qs(query) - video_id = query_dic['publishedid'][0] - - if '/player/' in url: - configuration = self._download_json(url, video_id) - - # There are multiple videos in the playlist whlie only the first one - # matches the video played in browsers - video_info = configuration['playlist'][0] - title = video_info['title'] - - formats = [] - for source in video_info['sources']: - file_url = source['file'] - if determine_ext(file_url) == 'm3u8': - m3u8_formats = self._extract_m3u8_formats( - file_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False) - if m3u8_formats: - formats.extend(m3u8_formats) - file_url = m3u8_formats[0]['url'] - formats.extend(self._extract_f4m_formats( - file_url.replace('.m3u8', '.f4m'), - video_id, f4m_id='hds', fatal=False)) - formats.extend(self._extract_mpd_formats( - file_url.replace('.m3u8', '.mpd'), - video_id, mpd_id='dash', fatal=False)) - else: - a_format = { - 'url': file_url, - } - - if source.get('label') and source['label'][-4:] == ' kbs': - tbr = int_or_none(source['label'][:-4]) - a_format.update({ - 'tbr': tbr, - 'format_id': 'http-%d' % tbr, - }) - formats.append(a_format) - - self._sort_formats(formats) - - description = video_info.get('description') - thumbnail = video_info.get('image') - else: - configuration = self._download_xml(url, video_id) - formats = [{ - 'url': xpath_text(configuration, './file', 'file URL', fatal=True), - }] - thumbnail = xpath_text(configuration, './image', 'thumbnail') - title = 'InternetVideoArchive video %s' % video_id - description = None + query = compat_parse_qs(compat_urlparse.urlparse(url).query) + video_id = query['publishedid'][0] + data = self._download_json( + 'https://video.internetvideoarchive.net/videojs7/videojs7.ivasettings.ashx', + video_id, data=json.dumps({ + 'customerid': query['customerid'][0], + 'publishedid': video_id, + }).encode()) + title = data['Title'] + formats = self._extract_m3u8_formats( + data['VideoUrl'], video_id, 'mp4', + 'm3u8_native', m3u8_id='hls', fatal=False) + file_url = formats[0]['url'] + if '.ism/' in file_url: + replace_url = lambda x: re.sub(r'\.ism/[^?]+', '.ism/' + x, file_url) + formats.extend(self._extract_f4m_formats( + replace_url('.f4m'), video_id, f4m_id='hds', fatal=False)) + formats.extend(self._extract_mpd_formats( + replace_url('.mpd'), video_id, mpd_id='dash', fatal=False)) + formats.extend(self._extract_ism_formats( + replace_url('Manifest'), video_id, ism_id='mss', fatal=False)) + self._sort_formats(formats) return { 'id': video_id, 'title': title, 'formats': formats, - 'thumbnail': thumbnail, - 'description': description, + 'thumbnail': data.get('PosterUrl'), + 'description': data.get('Description'), } From 0086726e8674e9edec0682e7a84275c3c25ce646 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 28 Oct 2019 19:48:34 +0100 Subject: [PATCH 126/422] [videodetective] fix extraction --- youtube_dl/extractor/videodetective.py | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/videodetective.py b/youtube_dl/extractor/videodetective.py index a19411a05..fe70db713 100644 --- a/youtube_dl/extractor/videodetective.py +++ b/youtube_dl/extractor/videodetective.py @@ -1,7 +1,6 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import compat_urlparse from .internetvideoarchive import InternetVideoArchiveIE @@ -13,7 +12,7 @@ class VideoDetectiveIE(InfoExtractor): 'info_dict': { 'id': '194487', 'ext': 'mp4', - 'title': 'KICK-ASS 2', + 'title': 'Kick-Ass 2', 'description': 'md5:c189d5b7280400630a1d3dd17eaa8d8a', }, 'params': { @@ -24,7 +23,7 @@ class VideoDetectiveIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - og_video = self._og_search_video_url(webpage) - query = compat_urlparse.urlparse(og_video).query - return self.url_result(InternetVideoArchiveIE._build_json_url(query), ie=InternetVideoArchiveIE.ie_key()) + query = 'customerid=69249&publishedid=' + video_id + return self.url_result( + InternetVideoArchiveIE._build_json_url(query), + ie=InternetVideoArchiveIE.ie_key()) From cfabc505984acb3830aeac7759d913bb885d64b6 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 28 Oct 2019 22:55:01 +0100 Subject: [PATCH 127/422] [mtv] fix extraction for mtv.de (closes #22113) --- youtube_dl/extractor/mtv.py | 51 ++++++++++++++----------------------- 1 file changed, 19 insertions(+), 32 deletions(-) diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py index 7a3b57abd..7e95ca18e 100644 --- a/youtube_dl/extractor/mtv.py +++ b/youtube_dl/extractor/mtv.py @@ -425,14 +425,14 @@ class MTVVideoIE(MTVServicesInfoExtractor): class MTVDEIE(MTVServicesInfoExtractor): IE_NAME = 'mtv.de' - _VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:artists|shows|news)/(?:[^/]+/)*(?P\d+)-[^/#?]+/*(?:[#?].*)?$' + _VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:musik/videoclips|folgen|news)/(?P[0-9a-z]+)' _TESTS = [{ - 'url': 'http://www.mtv.de/artists/10571-cro/videos/61131-traum', + 'url': 'http://www.mtv.de/musik/videoclips/2gpnv7/Traum', 'info_dict': { - 'id': 'music_video-a50bc5f0b3aa4b3190aa', - 'ext': 'flv', - 'title': 'MusicVideo_cro-traum', - 'description': 'Cro - Traum', + 'id': 'd5d472bc-f5b7-11e5-bffd-a4badb20dab5', + 'ext': 'mp4', + 'title': 'Traum', + 'description': 'Traum', }, 'params': { # rtmp download @@ -441,11 +441,12 @@ class MTVDEIE(MTVServicesInfoExtractor): 'skip': 'Blocked at Travis CI', }, { # mediagen URL without query (e.g. http://videos.mtvnn.com/mediagen/e865da714c166d18d6f80893195fcb97) - 'url': 'http://www.mtv.de/shows/933-teen-mom-2/staffeln/5353/folgen/63565-enthullungen', + 'url': 'http://www.mtv.de/folgen/6b1ylu/teen-mom-2-enthuellungen-S5-F1', 'info_dict': { - 'id': 'local_playlist-f5ae778b9832cc837189', - 'ext': 'flv', - 'title': 'Episode_teen-mom-2_shows_season-5_episode-1_full-episode_part1', + 'id': '1e5a878b-31c5-11e7-a442-0e40cf2fc285', + 'ext': 'mp4', + 'title': 'Teen Mom 2', + 'description': 'md5:dc65e357ef7e1085ed53e9e9d83146a7', }, 'params': { # rtmp download @@ -453,7 +454,7 @@ class MTVDEIE(MTVServicesInfoExtractor): }, 'skip': 'Blocked at Travis CI', }, { - 'url': 'http://www.mtv.de/news/77491-mtv-movies-spotlight-pixels-teil-3', + 'url': 'http://www.mtv.de/news/glolix/77491-mtv-movies-spotlight--pixels--teil-3', 'info_dict': { 'id': 'local_playlist-4e760566473c4c8c5344', 'ext': 'mp4', @@ -466,25 +467,11 @@ class MTVDEIE(MTVServicesInfoExtractor): }, 'skip': 'Das Video kann zur Zeit nicht abgespielt werden.', }] + _GEO_COUNTRIES = ['DE'] + _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed' - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - playlist = self._parse_json( - self._search_regex( - r'window\.pagePlaylist\s*=\s*(\[.+?\]);\n', webpage, 'page playlist'), - video_id) - - def _mrss_url(item): - return item['mrss'] + item.get('mrssvars', '') - - # news pages contain single video in playlist with different id - if len(playlist) == 1: - return self._get_videos_info_from_url(_mrss_url(playlist[0]), video_id) - - for item in playlist: - item_id = item.get('id') - if item_id and compat_str(item_id) == video_id: - return self._get_videos_info_from_url(_mrss_url(item), video_id) + def _get_feed_query(self, uri): + return { + 'arcEp': 'mtv.de', + 'mgid': uri, + } From 3cdcebf5470a56df7d52e6f8acbcde5b4b9f0241 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 28 Oct 2019 23:31:14 +0100 Subject: [PATCH 128/422] [mtv] add support for mtvjapan.com --- youtube_dl/extractor/mtv.py | 37 +++++++++++++++++-------------------- 1 file changed, 17 insertions(+), 20 deletions(-) diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py index 7e95ca18e..fedd5f46b 100644 --- a/youtube_dl/extractor/mtv.py +++ b/youtube_dl/extractor/mtv.py @@ -1,3 +1,4 @@ +# coding: utf-8 from __future__ import unicode_literals import re @@ -349,33 +350,29 @@ class MTVIE(MTVServicesInfoExtractor): }] -class MTV81IE(InfoExtractor): - IE_NAME = 'mtv81' - _VALID_URL = r'https?://(?:www\.)?mtv81\.com/videos/(?P[^/?#.]+)' +class MTVJapanIE(MTVServicesInfoExtractor): + IE_NAME = 'mtvjapan' + _VALID_URL = r'https?://(?:www\.)?mtvjapan\.com/videos/(?P[0-9a-z]+)' _TEST = { - 'url': 'http://www.mtv81.com/videos/artist-to-watch/the-godfather-of-japanese-hip-hop-segment-1/', - 'md5': '1edbcdf1e7628e414a8c5dcebca3d32b', + 'url': 'http://www.mtvjapan.com/videos/prayht/fresh-info-cadillac-escalade', 'info_dict': { - 'id': '5e14040d-18a4-47c4-a582-43ff602de88e', + 'id': 'bc01da03-6fe5-4284-8880-f291f4e368f5', 'ext': 'mp4', - 'title': 'Unlocking The Truth|July 18, 2016|1|101|Trailer', - 'description': '"Unlocking the Truth" premieres August 17th at 11/10c.', - 'timestamp': 1468846800, - 'upload_date': '20160718', + 'title': '【Fresh Info】Cadillac ESCALADE Sport Edition', + }, + 'params': { + 'skip_download': True, }, } + _GEO_COUNTRIES = ['JP'] + _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed' - def _extract_mgid(self, webpage): - return self._search_regex( - r'getTheVideo\((["\'])(?Pmgid:.+?)\1', webpage, - 'mgid', group='id') - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - mgid = self._extract_mgid(webpage) - return self.url_result('http://media.mtvnservices.com/embed/%s' % mgid) + def _get_feed_query(self, uri): + return { + 'arcEp': 'mtvjapan.com', + 'mgid': uri, + } class MTVVideoIE(MTVServicesInfoExtractor): From 01358b9fc198cafb619a03ed5ad7865a74805611 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 28 Oct 2019 23:34:31 +0100 Subject: [PATCH 129/422] [extractors] add import for MTVJapanIE --- youtube_dl/extractor/extractors.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 114ede8b9..c10bcbcc1 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -666,7 +666,7 @@ from .mtv import ( MTVVideoIE, MTVServicesEmbeddedIE, MTVDEIE, - MTV81IE, + MTVJapanIE, ) from .muenchentv import MuenchenTVIE from .musicplayon import MusicPlayOnIE From dd90a21c28cb1ec592e5961a5f67556edfb3ce87 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 29 Oct 2019 05:49:36 +0700 Subject: [PATCH 130/422] [go] Add support for abc.com and freeform.com (closes #22823, closes #22864) --- youtube_dl/extractor/go.py | 44 ++++++++++++++++++++++++++++++++------ 1 file changed, 38 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/go.py b/youtube_dl/extractor/go.py index 03e48f4ea..107059023 100644 --- a/youtube_dl/extractor/go.py +++ b/youtube_dl/extractor/go.py @@ -40,8 +40,8 @@ class GoIE(AdobePassIE): 'resource_id': 'Disney', } } - _VALID_URL = r'https?://(?:(?:(?P%s)\.)?go|(?Pdisneynow))\.com/(?:(?:[^/]+/)*(?Pvdka\w+)|(?:[^/]+/)*(?P[^/?#]+))'\ - % '|'.join(list(_SITE_INFO.keys()) + ['disneynow']) + _VALID_URL = r'https?://(?:(?:(?P%s)\.)?go|(?Pabc|freeform|disneynow))\.com/(?:(?:[^/]+/)*(?Pvdka\w+)|(?:[^/]+/)*(?P[^/?#]+))'\ + % '|'.join(list(_SITE_INFO.keys())) _TESTS = [{ 'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643', 'info_dict': { @@ -54,6 +54,7 @@ class GoIE(AdobePassIE): # m3u8 download 'skip_download': True, }, + 'skip': 'This content is no longer available.', }, { 'url': 'http://watchdisneyxd.go.com/doraemon', 'info_dict': { @@ -61,6 +62,34 @@ class GoIE(AdobePassIE): 'id': 'SH55574025', }, 'playlist_mincount': 51, + }, { + 'url': 'http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood', + 'info_dict': { + 'id': 'VDKA3609139', + 'ext': 'mp4', + 'title': 'This Guilty Blood', + 'description': 'md5:f18e79ad1c613798d95fdabfe96cd292', + 'age_limit': 14, + }, + 'params': { + 'geo_bypass_ip_block': '3.244.239.0/24', + # m3u8 download + 'skip_download': True, + }, + }, { + 'url': 'https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet', + 'info_dict': { + 'id': 'VDKA13435179', + 'ext': 'mp4', + 'title': 'The Bet', + 'description': 'md5:c66de8ba2e92c6c5c113c3ade84ab404', + 'age_limit': 14, + }, + 'params': { + 'geo_bypass_ip_block': '3.244.239.0/24', + # m3u8 download + 'skip_download': True, + }, }, { 'url': 'http://abc.go.com/shows/the-catch/episode-guide/season-01/10-the-wedding', 'only_matching': True, @@ -95,10 +124,13 @@ class GoIE(AdobePassIE): if not video_id or not site_info: webpage = self._download_webpage(url, display_id or video_id) video_id = self._search_regex( - # There may be inner quotes, e.g. data-video-id="'VDKA3609139'" - # from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood - r'data-video-id=["\']*(VDKA\w+)', webpage, 'video id', - default=video_id) + ( + # There may be inner quotes, e.g. data-video-id="'VDKA3609139'" + # from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood + r'data-video-id=["\']*(VDKA\w+)', + # https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet + r'\b(?:video)?id["\']\s*:\s*["\'](VDKA\w+)' + ), webpage, 'video id', default=video_id) if not site_info: brand = self._search_regex( (r'data-brand=\s*["\']\s*(\d+)', From aef9f87ea4dcfe483c5b776f1c37310766ad818d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 29 Oct 2019 05:52:15 +0700 Subject: [PATCH 131/422] [go] Improve and beautify _VALID_URL --- youtube_dl/extractor/go.py | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/go.py b/youtube_dl/extractor/go.py index 107059023..03cfba91f 100644 --- a/youtube_dl/extractor/go.py +++ b/youtube_dl/extractor/go.py @@ -40,8 +40,17 @@ class GoIE(AdobePassIE): 'resource_id': 'Disney', } } - _VALID_URL = r'https?://(?:(?:(?P%s)\.)?go|(?Pabc|freeform|disneynow))\.com/(?:(?:[^/]+/)*(?Pvdka\w+)|(?:[^/]+/)*(?P[^/?#]+))'\ - % '|'.join(list(_SITE_INFO.keys())) + _VALID_URL = r'''(?x) + https?:// + (?: + (?:(?P%s)\.)?go| + (?Pabc|freeform|disneynow) + )\.com/ + (?: + (?:[^/]+/)*(?P[Vv][Dd][Kk][Aa]\w+)| + (?:[^/]+/)*(?P[^/?\#]+) + ) + ''' % '|'.join(list(_SITE_INFO.keys())) _TESTS = [{ 'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643', 'info_dict': { From 0d7392e68b7ebb7215651da0784e859d7bdff826 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 29 Oct 2019 05:54:32 +0700 Subject: [PATCH 132/422] [ChangeLog] Actualize [ci skip] --- ChangeLog | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) diff --git a/ChangeLog b/ChangeLog index 64233b03b..b664368a1 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,48 @@ +version + +Extractors ++ [go] Add support for abc.com and freeform.com (#22823, #22864) ++ [mtv] Add support for mtvjapan.com +* [mtv] Fix extraction for mtv.de (#22113) +* [videodetective] Fix extraction +* [internetvideoarchive] Fix extraction +* [nbcnews] Fix extraction (#12569, #12576, #21703, #21923) +- [hark] Remove extractor +- [tutv] Remove extractor +- [learnr] Remove extractor +- [macgamestore] Remove extractor +* [la7] Update Kaltura service URL (#22358) +* [thesun] Fix extraction (#16966) +- [makertv] Remove extractor ++ [tenplay] Add support for 10play.com.au (#21446) +* [soundcloud] Improve extraction + * Improve format extraction (#22123) + + Extract uploader_id and uploader_url (#21916) + + Extract all known thumbnails (#19071, #20659) + * Fix extration for private playlists (#20976) + + Add support for playlist embeds (#20976) + * Skip preview formats (#22806) +* [dplay] Improve extraction + + Add support for dplay.fi, dplay.jp and es.dplay.com (#16969) + * Fix it.dplay.com extraction (#22826) + + Extract creator, tags and thumbnails + * Handle playback API call errors ++ [discoverynetworks] Add support for dplay.co.uk +* [vk] Improve extraction + + Add support for Odnoklassniki embeds + + Extract more videos from user lists (#4470) + + Fix wall post audio extraction (#18332) + * Improve error detection (#22568) ++ [odnoklassniki] Add support for embeds +* [puhutv] Improve extraction + * Fix subtitles extraction + * Transform HLS URLs to HTTP URLs + * Improve metadata extraction +* [ceskatelevize] Skip DRM media ++ [facebook] Extract subtitles (#22777) +* [globo] Handle alternative hash signing method + + version 2019.10.22 Core From 53896ca5be9a629c2cbaceb3fe43c707bb217437 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 29 Oct 2019 06:10:20 +0700 Subject: [PATCH 133/422] [utils] Actualize major IPv4 address blocks per country --- youtube_dl/utils.py | 71 +++++++++++++++++++++++---------------------- 1 file changed, 37 insertions(+), 34 deletions(-) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 53117ea90..aed988b88 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -4979,7 +4979,7 @@ class ISO3166Utils(object): class GeoUtils(object): # Major IPv4 address blocks per country _country_ip_map = { - 'AD': '85.94.160.0/19', + 'AD': '46.172.224.0/19', 'AE': '94.200.0.0/13', 'AF': '149.54.0.0/17', 'AG': '209.59.64.0/18', @@ -4987,28 +4987,30 @@ class GeoUtils(object): 'AL': '46.99.0.0/16', 'AM': '46.70.0.0/15', 'AO': '105.168.0.0/13', - 'AP': '159.117.192.0/21', + 'AP': '182.50.184.0/21', + 'AQ': '23.154.160.0/24', 'AR': '181.0.0.0/12', 'AS': '202.70.112.0/20', - 'AT': '84.112.0.0/13', + 'AT': '77.116.0.0/14', 'AU': '1.128.0.0/11', 'AW': '181.41.0.0/18', - 'AZ': '5.191.0.0/16', + 'AX': '185.217.4.0/22', + 'AZ': '5.197.0.0/16', 'BA': '31.176.128.0/17', 'BB': '65.48.128.0/17', 'BD': '114.130.0.0/16', 'BE': '57.0.0.0/8', - 'BF': '129.45.128.0/17', + 'BF': '102.178.0.0/15', 'BG': '95.42.0.0/15', 'BH': '37.131.0.0/17', 'BI': '154.117.192.0/18', 'BJ': '137.255.0.0/16', - 'BL': '192.131.134.0/24', + 'BL': '185.212.72.0/23', 'BM': '196.12.64.0/18', 'BN': '156.31.0.0/16', 'BO': '161.56.0.0/16', 'BQ': '161.0.80.0/20', - 'BR': '152.240.0.0/12', + 'BR': '191.128.0.0/12', 'BS': '24.51.64.0/18', 'BT': '119.2.96.0/19', 'BW': '168.167.0.0/16', @@ -5016,20 +5018,20 @@ class GeoUtils(object): 'BZ': '179.42.192.0/18', 'CA': '99.224.0.0/11', 'CD': '41.243.0.0/16', - 'CF': '196.32.200.0/21', - 'CG': '197.214.128.0/17', + 'CF': '197.242.176.0/21', + 'CG': '160.113.0.0/16', 'CH': '85.0.0.0/13', - 'CI': '154.232.0.0/14', + 'CI': '102.136.0.0/14', 'CK': '202.65.32.0/19', 'CL': '152.172.0.0/14', - 'CM': '165.210.0.0/15', + 'CM': '102.244.0.0/14', 'CN': '36.128.0.0/10', 'CO': '181.240.0.0/12', 'CR': '201.192.0.0/12', 'CU': '152.206.0.0/15', 'CV': '165.90.96.0/19', 'CW': '190.88.128.0/17', - 'CY': '46.198.0.0/15', + 'CY': '31.153.0.0/16', 'CZ': '88.100.0.0/14', 'DE': '53.0.0.0/8', 'DJ': '197.241.0.0/17', @@ -5046,6 +5048,7 @@ class GeoUtils(object): 'EU': '2.16.0.0/13', 'FI': '91.152.0.0/13', 'FJ': '144.120.0.0/16', + 'FK': '80.73.208.0/21', 'FM': '119.252.112.0/20', 'FO': '88.85.32.0/19', 'FR': '90.0.0.0/9', @@ -5055,8 +5058,8 @@ class GeoUtils(object): 'GE': '31.146.0.0/16', 'GF': '161.22.64.0/18', 'GG': '62.68.160.0/19', - 'GH': '45.208.0.0/14', - 'GI': '85.115.128.0/19', + 'GH': '154.160.0.0/12', + 'GI': '95.164.0.0/16', 'GL': '88.83.0.0/19', 'GM': '160.182.0.0/15', 'GN': '197.149.192.0/18', @@ -5085,13 +5088,13 @@ class GeoUtils(object): 'JE': '87.244.64.0/18', 'JM': '72.27.0.0/17', 'JO': '176.29.0.0/16', - 'JP': '126.0.0.0/8', + 'JP': '133.0.0.0/8', 'KE': '105.48.0.0/12', 'KG': '158.181.128.0/17', 'KH': '36.37.128.0/17', 'KI': '103.25.140.0/22', 'KM': '197.255.224.0/20', - 'KN': '198.32.32.0/19', + 'KN': '198.167.192.0/19', 'KP': '175.45.176.0/22', 'KR': '175.192.0.0/10', 'KW': '37.36.0.0/14', @@ -5099,10 +5102,10 @@ class GeoUtils(object): 'KZ': '2.72.0.0/13', 'LA': '115.84.64.0/18', 'LB': '178.135.0.0/16', - 'LC': '192.147.231.0/24', + 'LC': '24.92.144.0/20', 'LI': '82.117.0.0/19', 'LK': '112.134.0.0/15', - 'LR': '41.86.0.0/19', + 'LR': '102.183.0.0/16', 'LS': '129.232.0.0/17', 'LT': '78.56.0.0/13', 'LU': '188.42.0.0/16', @@ -5127,7 +5130,7 @@ class GeoUtils(object): 'MT': '46.11.0.0/16', 'MU': '105.16.0.0/12', 'MV': '27.114.128.0/18', - 'MW': '105.234.0.0/16', + 'MW': '102.70.0.0/15', 'MX': '187.192.0.0/11', 'MY': '175.136.0.0/13', 'MZ': '197.218.0.0/15', @@ -5158,23 +5161,23 @@ class GeoUtils(object): 'PW': '202.124.224.0/20', 'PY': '181.120.0.0/14', 'QA': '37.210.0.0/15', - 'RE': '139.26.0.0/16', + 'RE': '102.35.0.0/16', 'RO': '79.112.0.0/13', - 'RS': '178.220.0.0/14', + 'RS': '93.86.0.0/15', 'RU': '5.136.0.0/13', - 'RW': '105.178.0.0/15', + 'RW': '41.186.0.0/16', 'SA': '188.48.0.0/13', 'SB': '202.1.160.0/19', 'SC': '154.192.0.0/11', - 'SD': '154.96.0.0/13', + 'SD': '102.120.0.0/13', 'SE': '78.64.0.0/12', - 'SG': '152.56.0.0/14', + 'SG': '8.128.0.0/10', 'SI': '188.196.0.0/14', 'SK': '78.98.0.0/15', - 'SL': '197.215.0.0/17', + 'SL': '102.143.0.0/17', 'SM': '89.186.32.0/19', 'SN': '41.82.0.0/15', - 'SO': '197.220.64.0/19', + 'SO': '154.115.192.0/18', 'SR': '186.179.128.0/17', 'SS': '105.235.208.0/21', 'ST': '197.159.160.0/19', @@ -5197,15 +5200,15 @@ class GeoUtils(object): 'TV': '202.2.96.0/19', 'TW': '120.96.0.0/11', 'TZ': '156.156.0.0/14', - 'UA': '93.72.0.0/13', - 'UG': '154.224.0.0/13', - 'US': '3.0.0.0/8', + 'UA': '37.52.0.0/14', + 'UG': '102.80.0.0/13', + 'US': '6.0.0.0/8', 'UY': '167.56.0.0/13', - 'UZ': '82.215.64.0/18', + 'UZ': '84.54.64.0/18', 'VA': '212.77.0.0/19', - 'VC': '24.92.144.0/20', + 'VC': '207.191.240.0/21', 'VE': '186.88.0.0/13', - 'VG': '172.103.64.0/18', + 'VG': '66.81.192.0/20', 'VI': '146.226.0.0/16', 'VN': '14.160.0.0/11', 'VU': '202.80.32.0/20', @@ -5214,8 +5217,8 @@ class GeoUtils(object): 'YE': '134.35.0.0/16', 'YT': '41.242.116.0/22', 'ZA': '41.0.0.0/11', - 'ZM': '165.56.0.0/13', - 'ZW': '41.85.192.0/19', + 'ZM': '102.144.0.0/13', + 'ZW': '102.177.192.0/18', } @classmethod From cae0bbc53831eed38c4af3755de43e223c503270 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 29 Oct 2019 06:11:09 +0700 Subject: [PATCH 134/422] [ChangeLog] Actualize [ci skip] --- ChangeLog | 3 +++ 1 file changed, 3 insertions(+) diff --git a/ChangeLog b/ChangeLog index b664368a1..2957b7ced 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,5 +1,8 @@ version +Core +* [utils] Actualize major IPv4 address blocks per country + Extractors + [go] Add support for abc.com and freeform.com (#22823, #22864) + [mtv] Add support for mtvjapan.com From c4bd9cb7bb57c6e4bbc04fb054dfea14d4ecb171 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 29 Oct 2019 06:12:33 +0700 Subject: [PATCH 135/422] release 2019.10.29 --- .github/ISSUE_TEMPLATE/1_broken_site.md | 6 +++--- .github/ISSUE_TEMPLATE/2_site_support_request.md | 4 ++-- .github/ISSUE_TEMPLATE/3_site_feature_request.md | 4 ++-- .github/ISSUE_TEMPLATE/4_bug_report.md | 6 +++--- .github/ISSUE_TEMPLATE/5_feature_request.md | 4 ++-- ChangeLog | 2 +- docs/supportedsites.md | 10 +++------- youtube_dl/version.py | 2 +- 8 files changed, 17 insertions(+), 21 deletions(-) diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.md b/.github/ISSUE_TEMPLATE/1_broken_site.md index f1afe704c..f82502bd1 100644 --- a/.github/ISSUE_TEMPLATE/1_broken_site.md +++ b/.github/ISSUE_TEMPLATE/1_broken_site.md @@ -18,7 +18,7 @@ title: '' - [ ] I'm reporting a broken site support -- [ ] I've verified that I'm running youtube-dl version **2019.10.22** +- [ ] I've verified that I'm running youtube-dl version **2019.10.29** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar issues including closed ones @@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.10.22 + [debug] youtube-dl version 2019.10.29 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/2_site_support_request.md b/.github/ISSUE_TEMPLATE/2_site_support_request.md index a4dc9b005..5ef983d43 100644 --- a/.github/ISSUE_TEMPLATE/2_site_support_request.md +++ b/.github/ISSUE_TEMPLATE/2_site_support_request.md @@ -19,7 +19,7 @@ labels: 'site-support-request' - [ ] I'm reporting a new site support request -- [ ] I've verified that I'm running youtube-dl version **2019.10.22** +- [ ] I've verified that I'm running youtube-dl version **2019.10.29** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that none of provided URLs violate any copyrights - [ ] I've searched the bugtracker for similar site support requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/3_site_feature_request.md b/.github/ISSUE_TEMPLATE/3_site_feature_request.md index 5bf86adce..8f05aa79f 100644 --- a/.github/ISSUE_TEMPLATE/3_site_feature_request.md +++ b/.github/ISSUE_TEMPLATE/3_site_feature_request.md @@ -18,13 +18,13 @@ title: '' - [ ] I'm reporting a site feature request -- [ ] I've verified that I'm running youtube-dl version **2019.10.22** +- [ ] I've verified that I'm running youtube-dl version **2019.10.29** - [ ] I've searched the bugtracker for similar site feature requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/4_bug_report.md b/.github/ISSUE_TEMPLATE/4_bug_report.md index 7aa5534e5..e90900d8d 100644 --- a/.github/ISSUE_TEMPLATE/4_bug_report.md +++ b/.github/ISSUE_TEMPLATE/4_bug_report.md @@ -18,7 +18,7 @@ title: '' - [ ] I'm reporting a broken site support issue -- [ ] I've verified that I'm running youtube-dl version **2019.10.22** +- [ ] I've verified that I'm running youtube-dl version **2019.10.29** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar bug reports including closed ones @@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.10.22 + [debug] youtube-dl version 2019.10.29 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/5_feature_request.md b/.github/ISSUE_TEMPLATE/5_feature_request.md index 5d3645e3d..7021d7397 100644 --- a/.github/ISSUE_TEMPLATE/5_feature_request.md +++ b/.github/ISSUE_TEMPLATE/5_feature_request.md @@ -19,13 +19,13 @@ labels: 'request' - [ ] I'm reporting a feature request -- [ ] I've verified that I'm running youtube-dl version **2019.10.22** +- [ ] I've verified that I'm running youtube-dl version **2019.10.29** - [ ] I've searched the bugtracker for similar feature requests including closed ones diff --git a/ChangeLog b/ChangeLog index 2957b7ced..fcab1102c 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version +version 2019.10.29 Core * [utils] Actualize major IPv4 address blocks per country diff --git a/docs/supportedsites.md b/docs/supportedsites.md index a1b0edeeb..af905db5a 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -232,7 +232,6 @@ - **DouyuShow** - **DouyuTV**: 斗鱼 - **DPlay** - - **DPlayIt** - **DRBonanza** - **Dropbox** - **DrTuber** @@ -339,7 +338,6 @@ - **Goshgay** - **GPUTechConf** - **Groupon** - - **Hark** - **hbo** - **HearThisAt** - **Heise** @@ -432,7 +430,6 @@ - **Lcp** - **LcpPlay** - **Le**: 乐视网 - - **Learnr** - **Lecture2Go** - **Lecturio** - **LecturioCourse** @@ -466,11 +463,9 @@ - **lynda**: lynda.com videos - **lynda:course**: lynda.com online courses - **m6** - - **macgamestore**: MacGameStore trailers - **mailru**: Видео@Mail.Ru - **mailru:music**: Музыка@Mail.Ru - **mailru:music:search**: Музыка@Mail.Ru - - **MakerTV** - **MallTV** - **mangomolo:live** - **mangomolo:video** @@ -526,8 +521,8 @@ - **mtg**: MTG services - **mtv** - **mtv.de** - - **mtv81** - **mtv:video** + - **mtvjapan** - **mtvservices:embedded** - **MuenchenTV**: münchen.tv - **MusicPlayOn** @@ -815,6 +810,7 @@ - **soundcloud:set** - **soundcloud:trackstation** - **soundcloud:user** + - **SoundcloudEmbed** - **soundgasm** - **soundgasm:profile** - **southpark.cc.com** @@ -887,6 +883,7 @@ - **TeleTask** - **Telewebion** - **TennisTV** + - **TenPlay** - **TF1** - **TFO** - **TheIntercept** @@ -925,7 +922,6 @@ - **tunein:topic** - **TunePk** - **Turbo** - - **Tutv** - **tv.dfb.de** - **TV2** - **tv2.hu** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 39b355b9e..924f26ca8 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.10.22' +__version__ = '2019.10.29' From 7455832f311843663b416968b9e5a0a0c6134d8d Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Tue, 29 Oct 2019 09:43:17 +0100 Subject: [PATCH 136/422] [fox9] fix extraction --- youtube_dl/extractor/extractors.py | 5 +++- youtube_dl/extractor/fox9.py | 43 +++++++++++++++--------------- 2 files changed, 25 insertions(+), 23 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index c10bcbcc1..15f96fb8f 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -367,7 +367,10 @@ from .fourtube import ( FuxIE, ) from .fox import FOXIE -from .fox9 import FOX9IE +from .fox9 import ( + FOX9IE, + FOX9NewsIE, +) from .foxgay import FoxgayIE from .foxnews import ( FoxNewsIE, diff --git a/youtube_dl/extractor/fox9.py b/youtube_dl/extractor/fox9.py index 17dfffa7b..91f8f7b8a 100644 --- a/youtube_dl/extractor/fox9.py +++ b/youtube_dl/extractor/fox9.py @@ -1,13 +1,23 @@ # coding: utf-8 from __future__ import unicode_literals -from .anvato import AnvatoIE +from .common import InfoExtractor -class FOX9IE(AnvatoIE): - _VALID_URL = r'https?://(?:www\.)?fox9\.com/(?:[^/]+/)+(?P\d+)-story' - _TESTS = [{ - 'url': 'http://www.fox9.com/news/215123287-story', +class FOX9IE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?fox9\.com/video/(?P\d+)' + + def _real_extract(self, url): + video_id = self._match_id(url) + return self.url_result( + 'anvato:anvato_epfox_app_web_prod_b3373168e12f423f41504f207000188daf88251b:' + video_id, + 'Anvato', video_id) + + +class FOX9NewsIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?fox9\.com/news/(?P[^/?&#]+)' + _TEST = { + 'url': 'https://www.fox9.com/news/black-bear-in-tree-draws-crowd-in-downtown-duluth-minnesota', 'md5': 'd6e1b2572c3bab8a849c9103615dd243', 'info_dict': { 'id': '314473', @@ -21,22 +31,11 @@ class FOX9IE(AnvatoIE): 'categories': ['News', 'Sports'], 'tags': ['news', 'video'], }, - }, { - 'url': 'http://www.fox9.com/news/investigators/214070684-story', - 'only_matching': True, - }] + } def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - video_id = self._parse_json( - self._search_regex( - r"this\.videosJson\s*=\s*'(\[.+?\])';", - webpage, 'anvato playlist'), - video_id)[0]['video'] - - return self._get_anvato_videos( - 'anvato_epfox_app_web_prod_b3373168e12f423f41504f207000188daf88251b', - video_id) + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + anvato_id = self._search_regex( + r'anvatoId\s*:\s*[\'"](\d+)', webpage, 'anvato id') + return self.url_result('https://www.fox9.com/video/' + anvato_id, 'FOX9') From 8989349e6dcaa98204f77fb9f1e15a86eecb823d Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Tue, 29 Oct 2019 09:44:07 +0100 Subject: [PATCH 137/422] [onet] improve extraction - add support for onet100.vod.pl domain - extract m3u8 formats - correct audio only format info --- youtube_dl/extractor/onet.py | 54 ++++++++++++++++++++++++------------ 1 file changed, 36 insertions(+), 18 deletions(-) diff --git a/youtube_dl/extractor/onet.py b/youtube_dl/extractor/onet.py index 58da1bc27..e55b2ac89 100644 --- a/youtube_dl/extractor/onet.py +++ b/youtube_dl/extractor/onet.py @@ -20,6 +20,8 @@ from ..utils import ( class OnetBaseIE(InfoExtractor): + _URL_BASE_RE = r'https?://(?:(?:www\.)?onet\.tv|onet100\.vod\.pl)/[a-z]/' + def _search_mvp_id(self, webpage): return self._search_regex( r'id=(["\'])mvp:(?P.+?)\1', webpage, 'mvp id', group='id') @@ -45,7 +47,7 @@ class OnetBaseIE(InfoExtractor): video = response['result'].get('0') formats = [] - for _, formats_dict in video['formats'].items(): + for format_type, formats_dict in video['formats'].items(): if not isinstance(formats_dict, dict): continue for format_id, format_list in formats_dict.items(): @@ -56,21 +58,31 @@ class OnetBaseIE(InfoExtractor): if not video_url: continue ext = determine_ext(video_url) - if format_id == 'ism': + if format_id.startswith('ism'): formats.extend(self._extract_ism_formats( video_url, video_id, 'mss', fatal=False)) elif ext == 'mpd': formats.extend(self._extract_mpd_formats( video_url, video_id, mpd_id='dash', fatal=False)) + elif format_id.startswith('hls'): + formats.extend(self._extract_m3u8_formats( + video_url, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) else: - formats.append({ + http_f = { 'url': video_url, 'format_id': format_id, - 'height': int_or_none(f.get('vertical_resolution')), - 'width': int_or_none(f.get('horizontal_resolution')), 'abr': float_or_none(f.get('audio_bitrate')), - 'vbr': float_or_none(f.get('video_bitrate')), - }) + } + if format_type == 'audio': + http_f['vcodec'] = 'none' + else: + http_f.update({ + 'height': int_or_none(f.get('vertical_resolution')), + 'width': int_or_none(f.get('horizontal_resolution')), + 'vbr': float_or_none(f.get('video_bitrate')), + }) + formats.append(http_f) self._sort_formats(formats) meta = video.get('meta', {}) @@ -105,12 +117,12 @@ class OnetMVPIE(OnetBaseIE): class OnetIE(OnetBaseIE): - _VALID_URL = r'https?://(?:www\.)?onet\.tv/[a-z]/[a-z]+/(?P[0-9a-z-]+)/(?P[0-9a-z]+)' + _VALID_URL = OnetBaseIE._URL_BASE_RE + r'[a-z]+/(?P[0-9a-z-]+)/(?P[0-9a-z]+)' IE_NAME = 'onet.tv' - _TEST = { + _TESTS = [{ 'url': 'http://onet.tv/k/openerfestival/open-er-festival-2016-najdziwniejsze-wymagania-gwiazd/qbpyqc', - 'md5': 'e3ffbf47590032ac3f27249204173d50', + 'md5': '436102770fb095c75b8bb0392d3da9ff', 'info_dict': { 'id': 'qbpyqc', 'display_id': 'open-er-festival-2016-najdziwniejsze-wymagania-gwiazd', @@ -120,7 +132,10 @@ class OnetIE(OnetBaseIE): 'upload_date': '20160705', 'timestamp': 1467721580, }, - } + }, { + 'url': 'https://onet100.vod.pl/k/openerfestival/open-er-festival-2016-najdziwniejsze-wymagania-gwiazd/qbpyqc', + 'only_matching': True, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -140,18 +155,21 @@ class OnetIE(OnetBaseIE): class OnetChannelIE(OnetBaseIE): - _VALID_URL = r'https?://(?:www\.)?onet\.tv/[a-z]/(?P[a-z]+)(?:[?#]|$)' + _VALID_URL = OnetBaseIE._URL_BASE_RE + r'(?P[a-z]+)(?:[?#]|$)' IE_NAME = 'onet.tv:channel' - _TEST = { + _TESTS = [{ 'url': 'http://onet.tv/k/openerfestival', 'info_dict': { 'id': 'openerfestival', - 'title': 'Open\'er Festival Live', - 'description': 'Dziękujemy, że oglądaliście transmisje. Zobaczcie nasze relacje i wywiady z artystami.', + 'title': "Open'er Festival", + 'description': "Tak było na Open'er Festival 2016! Oglądaj nasze reportaże i wywiady z artystami.", }, - 'playlist_mincount': 46, - } + 'playlist_mincount': 35, + }, { + 'url': 'https://onet100.vod.pl/k/openerfestival', + 'only_matching': True, + }] def _real_extract(self, url): channel_id = self._match_id(url) @@ -173,7 +191,7 @@ class OnetChannelIE(OnetBaseIE): 'Downloading channel %s - add --no-playlist to just download video %s' % ( channel_id, video_name)) matches = re.findall( - r']+href=[\'"](https?://(?:www\.)?onet\.tv/[a-z]/[a-z]+/[0-9a-z-]+/[0-9a-z]+)', + r']+href=[\'"](%s[a-z]+/[0-9a-z-]+/[0-9a-z]+)' % self._URL_BASE_RE, webpage) entries = [ self.url_result(video_link, OnetIE.ie_key()) From c56b2ac43ca27b32fb4f7b230d851a61b5fc7cbd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 30 Oct 2019 02:21:03 +0700 Subject: [PATCH 138/422] [tv2dk] Add extractor --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/tv2dk.py | 82 ++++++++++++++++++++++++++++++ 2 files changed, 83 insertions(+) create mode 100644 youtube_dl/extractor/tv2dk.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 15f96fb8f..5d20ba863 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1189,6 +1189,7 @@ from .tv2 import ( TV2IE, TV2ArticleIE, ) +from .tv2dk import TV2DKIE from .tv2hu import TV2HuIE from .tv4 import TV4IE from .tv5mondeplus import TV5MondePlusIE diff --git a/youtube_dl/extractor/tv2dk.py b/youtube_dl/extractor/tv2dk.py new file mode 100644 index 000000000..eb39424df --- /dev/null +++ b/youtube_dl/extractor/tv2dk.py @@ -0,0 +1,82 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import extract_attributes + + +class TV2DKIE(InfoExtractor): + _VALID_URL = r'''(?x) + https?:// + (?:www\.)? + (?: + tvsyd| + tv2ostjylland| + tvmidtvest| + tv2fyn| + tv2east| + tv2lorry| + tv2nord + )\.dk/ + (:[^/]+/)* + (?P[^/?\#&]+) + ''' + _TESTS = [{ + 'url': 'https://www.tvsyd.dk/nyheder/28-10-2019/1930/1930-28-okt-2019?autoplay=1#player', + 'info_dict': { + 'id': '0_52jmwa0p', + 'ext': 'mp4', + 'title': '19:30 - 28. okt. 2019', + 'timestamp': 1572290248, + 'upload_date': '20191028', + 'uploader_id': 'tvsyd', + 'duration': 1347, + 'view_count': int, + }, + 'params': { + 'skip_download': True, + }, + 'add_ie': ['Kaltura'], + }, { + 'url': 'https://www.tv2ostjylland.dk/artikel/minister-gaar-ind-i-sag-om-diabetes-teknologi', + 'only_matching': True, + }, { + 'url': 'https://www.tv2ostjylland.dk/nyheder/28-10-2019/22/2200-nyhederne-mandag-d-28-oktober-2019?autoplay=1#player', + 'only_matching': True, + }, { + 'url': 'https://www.tvmidtvest.dk/nyheder/27-10-2019/1930/1930-27-okt-2019', + 'only_matching': True, + }, { + 'url': 'https://www.tv2fyn.dk/artikel/fyn-kan-faa-landets-foerste-fabrik-til-groent-jetbraendstof', + 'only_matching': True, + }, { + 'url': 'https://www.tv2east.dk/artikel/gods-faar-indleveret-tonsvis-af-aebler-100-kilo-aebler-gaar-til-en-aeblebrandy', + 'only_matching': True, + }, { + 'url': 'https://www.tv2lorry.dk/koebenhavn/rasmus-paludan-evakueret-til-egen-demonstration#player', + 'only_matching': True, + }, { + 'url': 'https://www.tv2nord.dk/artikel/dybt-uacceptabelt', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + entries = [] + for video_el in re.findall(r'(?s)<[^>]+\bdata-entryid\s*=[^>]*>', webpage): + video = extract_attributes(video_el) + kaltura_id = video.get('data-entryid') + if not kaltura_id: + continue + partner_id = video.get('data-partnerid') + if not partner_id: + continue + entries.append(self.url_result( + 'kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura', + video_id=kaltura_id)) + return self.playlist_result(entries) From 9a621ddc3a42769f107f8bd0d67b2c7073ea8256 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 30 Oct 2019 02:21:52 +0700 Subject: [PATCH 139/422] [tv2] Fix and improve extraction (closes #22787) --- youtube_dl/extractor/tv2.py | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/tv2.py b/youtube_dl/extractor/tv2.py index d5071e8a5..1b6590767 100644 --- a/youtube_dl/extractor/tv2.py +++ b/youtube_dl/extractor/tv2.py @@ -11,6 +11,7 @@ from ..utils import ( js_to_json, parse_iso8601, remove_end, + try_get, ) @@ -44,7 +45,14 @@ class TV2IE(InfoExtractor): data = self._download_json( 'http://sumo.tv2.no/api/web/asset/%s/play.json?protocol=%s&videoFormat=SMIL+ISMUSP' % (video_id, protocol), video_id, 'Downloading play JSON')['playback'] - for item in data['items']['item']: + items = try_get(data, lambda x: x['items']['item']) + if not items: + continue + if not isinstance(items, list): + items = [items] + for item in items: + if not isinstance(item, dict): + continue video_url = item.get('url') if not video_url or video_url in format_urls: continue From 45f4a433894556301204b704caca7d6a14286287 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 30 Oct 2019 23:07:35 +0100 Subject: [PATCH 140/422] [yahoo] improve extraction - add support for live streams(closes #3597)(closes #3779)(closes #22178) - bypass cookie consent page for european domains(closes #16948)(closes #22576) - add generic support for embeds(closes #20332) --- youtube_dl/extractor/yahoo.py | 672 +++++++++++++--------------------- 1 file changed, 264 insertions(+), 408 deletions(-) diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index e5ebdd180..ee68096d0 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -3,453 +3,309 @@ from __future__ import unicode_literals import hashlib import itertools -import json import re from .common import InfoExtractor, SearchInfoExtractor from ..compat import ( compat_str, compat_urllib_parse, - compat_urlparse, ) from ..utils import ( clean_html, - determine_ext, - ExtractorError, - extract_attributes, int_or_none, mimetype2ext, + parse_iso8601, smuggle_url, try_get, - unescapeHTML, url_or_none, ) -from .brightcove import ( - BrightcoveLegacyIE, - BrightcoveNewIE, -) -from .nbc import NBCSportsVPlayerIE +from .brightcove import BrightcoveNewIE class YahooIE(InfoExtractor): IE_DESC = 'Yahoo screen and movies' - _VALID_URL = r'(?Phttps?://(?:(?P[a-zA-Z]{2})\.)?[\da-zA-Z_-]+\.yahoo\.com)/(?:[^/]+/)*(?:(?P.+)?-)?(?P[0-9]+)(?:-[a-z]+)?(?:\.html)?' - _TESTS = [ - { - 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html', - 'info_dict': { - 'id': '2d25e626-2378-391f-ada0-ddaf1417e588', - 'ext': 'mp4', - 'title': 'Julian Smith & Travis Legg Watch Julian Smith', - 'description': 'Julian and Travis watch Julian Smith', - 'duration': 6863, - }, + _VALID_URL = r'(?Phttps?://(?:(?P[a-zA-Z]{2}(?:-[a-zA-Z]{2})?|malaysia)\.)?(?:[\da-zA-Z_-]+\.)?yahoo\.com/(?:[^/]+/)*(?P[^?&#]*-[0-9]+)\.html)' + _TESTS = [{ + 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html', + 'info_dict': { + 'id': '2d25e626-2378-391f-ada0-ddaf1417e588', + 'ext': 'mp4', + 'title': 'Julian Smith & Travis Legg Watch Julian Smith', + 'description': 'Julian and Travis watch Julian Smith', + 'duration': 6863, + 'timestamp': 1369812016, + 'upload_date': '20130529', }, - { - 'url': 'http://screen.yahoo.com/wired/codefellas-s1-ep12-cougar-lies-103000935.html', - 'md5': '251af144a19ebc4a033e8ba91ac726bb', - 'info_dict': { - 'id': 'd1dedf8c-d58c-38c3-8963-e899929ae0a9', - 'ext': 'mp4', - 'title': 'Codefellas - The Cougar Lies with Spanish Moss', - 'description': 'md5:66b627ab0a282b26352136ca96ce73c1', - 'duration': 151, - }, - 'skip': 'HTTP Error 404', + }, { + 'url': 'https://screen.yahoo.com/community/community-sizzle-reel-203225340.html?format=embed', + 'md5': '7993e572fac98e044588d0b5260f4352', + 'info_dict': { + 'id': '4fe78544-8d48-39d8-97cd-13f205d9fcdb', + 'ext': 'mp4', + 'title': "Yahoo Saves 'Community'", + 'description': 'md5:4d4145af2fd3de00cbb6c1d664105053', + 'duration': 170, + 'timestamp': 1406838636, + 'upload_date': '20140731', }, - { - 'url': 'https://screen.yahoo.com/community/community-sizzle-reel-203225340.html?format=embed', - 'md5': '7993e572fac98e044588d0b5260f4352', - 'info_dict': { - 'id': '4fe78544-8d48-39d8-97cd-13f205d9fcdb', - 'ext': 'mp4', - 'title': "Yahoo Saves 'Community'", - 'description': 'md5:4d4145af2fd3de00cbb6c1d664105053', - 'duration': 170, - } - }, - { - 'url': 'https://tw.news.yahoo.com/%E6%95%A2%E5%95%8F%E5%B8%82%E9%95%B7%20%E9%BB%83%E7%A7%80%E9%9C%9C%E6%89%B9%E8%B3%B4%E6%B8%85%E5%BE%B7%20%E9%9D%9E%E5%B8%B8%E9%AB%98%E5%82%B2-034024051.html', - 'md5': '45c024bad51e63e9b6f6fad7a43a8c23', - 'info_dict': { - 'id': 'cac903b3-fcf4-3c14-b632-643ab541712f', - 'ext': 'mp4', - 'title': '敢問市長／黃秀霜批賴清德「非常高傲」', - 'description': '直言台南沒捷運 交通居五都之末', - 'duration': 396, - }, - }, - { - 'url': 'https://uk.screen.yahoo.com/editor-picks/cute-raccoon-freed-drain-using-091756545.html', - 'md5': '71298482f7c64cbb7fa064e4553ff1c1', - 'info_dict': { - 'id': 'b3affa53-2e14-3590-852b-0e0db6cd1a58', - 'ext': 'webm', - 'title': 'Cute Raccoon Freed From Drain\u00a0Using Angle Grinder', - 'description': 'md5:f66c890e1490f4910a9953c941dee944', - 'duration': 97, - } - }, - { - 'url': 'https://ca.sports.yahoo.com/video/program-makes-hockey-more-affordable-013127711.html', - 'md5': '57e06440778b1828a6079d2f744212c4', - 'info_dict': { - 'id': 'c9fa2a36-0d4d-3937-b8f6-cc0fb1881e73', - 'ext': 'mp4', - 'title': 'Program that makes hockey more affordable not offered in Manitoba', - 'description': 'md5:c54a609f4c078d92b74ffb9bf1f496f4', - 'duration': 121, - }, - 'skip': 'Video gone', - }, { - 'url': 'https://ca.finance.yahoo.com/news/hackers-sony-more-trouble-well-154609075.html', - 'info_dict': { - 'id': '154609075', - }, - 'playlist': [{ - 'md5': '000887d0dc609bc3a47c974151a40fb8', - 'info_dict': { - 'id': 'e624c4bc-3389-34de-9dfc-025f74943409', - 'ext': 'mp4', - 'title': '\'The Interview\' TV Spot: War', - 'description': 'The Interview', - 'duration': 30, - }, - }, { - 'md5': '81bc74faf10750fe36e4542f9a184c66', - 'info_dict': { - 'id': '1fc8ada0-718e-3abe-a450-bf31f246d1a9', - 'ext': 'mp4', - 'title': '\'The Interview\' TV Spot: Guys', - 'description': 'The Interview', - 'duration': 30, - }, - }], - }, { - 'url': 'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html', - 'md5': '88e209b417f173d86186bef6e4d1f160', - 'info_dict': { - 'id': 'f885cf7f-43d4-3450-9fac-46ac30ece521', - 'ext': 'mp4', - 'title': 'China Moses Is Crazy About the Blues', - 'description': 'md5:9900ab8cd5808175c7b3fe55b979bed0', - 'duration': 128, - } - }, { - 'url': 'https://in.lifestyle.yahoo.com/video/connect-dots-dark-side-virgo-090247395.html', - 'md5': 'd9a083ccf1379127bf25699d67e4791b', - 'info_dict': { - 'id': '52aeeaa3-b3d1-30d8-9ef8-5d0cf05efb7c', - 'ext': 'mp4', - 'title': 'Connect the Dots: Dark Side of Virgo', - 'description': 'md5:1428185051cfd1949807ad4ff6d3686a', - 'duration': 201, - }, - 'skip': 'Domain name in.lifestyle.yahoo.com gone', - }, { - 'url': 'https://www.yahoo.com/movies/v/true-story-trailer-173000497.html', - 'md5': '989396ae73d20c6f057746fb226aa215', - 'info_dict': { - 'id': '071c4013-ce30-3a93-a5b2-e0413cd4a9d1', - 'ext': 'mp4', - 'title': '\'True Story\' Trailer', - 'description': 'True Story', - 'duration': 150, - }, - }, { - 'url': 'https://gma.yahoo.com/pizza-delivery-man-surprised-huge-tip-college-kids-195200785.html', - 'only_matching': True, - }, { - 'note': 'NBC Sports embeds', - 'url': 'http://sports.yahoo.com/blogs/ncaab-the-dagger/tyler-kalinoski-s-buzzer-beater-caps-davidson-s-comeback-win-185609842.html?guid=nbc_cbk_davidsonbuzzerbeater_150313', - 'info_dict': { - 'id': '9CsDKds0kvHI', - 'ext': 'flv', - 'description': 'md5:df390f70a9ba7c95ff1daace988f0d8d', - 'title': 'Tyler Kalinoski hits buzzer-beater to lift Davidson', - 'upload_date': '20150313', - 'uploader': 'NBCU-SPORTS', - 'timestamp': 1426270238, - } - }, { - 'url': 'https://tw.news.yahoo.com/-100120367.html', - 'only_matching': True, - }, { - # Query result is embedded in webpage, but explicit request to video API fails with geo restriction - 'url': 'https://screen.yahoo.com/community/communitary-community-episode-1-ladders-154501237.html', - 'md5': '4fbafb9c9b6f07aa8f870629f6671b35', - 'info_dict': { - 'id': '1f32853c-a271-3eef-8cb6-f6d6872cb504', - 'ext': 'mp4', - 'title': 'Communitary - Community Episode 1: Ladders', - 'description': 'md5:8fc39608213295748e1e289807838c97', - 'duration': 1646, - }, - }, { - # it uses an alias to get the video_id - 'url': 'https://www.yahoo.com/movies/the-stars-of-daddys-home-have-very-different-212843197.html', - 'info_dict': { - 'id': '40eda9c8-8e5f-3552-8745-830f67d0c737', - 'ext': 'mp4', - 'title': 'Will Ferrell & Mark Wahlberg Are Pro-Spanking', - 'description': 'While they play feuding fathers in \'Daddy\'s Home,\' star Will Ferrell & Mark Wahlberg share their true feelings on parenthood.', - }, - }, - { - # config['models']['applet_model']['data']['sapi'] has no query - 'url': 'https://www.yahoo.com/music/livenation/event/galactic-2016', - 'md5': 'dac0c72d502bc5facda80c9e6d5c98db', - 'info_dict': { - 'id': 'a6015640-e9e5-3efb-bb60-05589a183919', - 'ext': 'mp4', - 'description': 'Galactic', - 'title': 'Dolla Diva (feat. Maggie Koerner)', - }, - 'skip': 'redirect to https://www.yahoo.com/music', - }, - { - # yahoo://article/ - 'url': 'https://www.yahoo.com/movies/video/true-story-trailer-173000497.html', - 'info_dict': { - 'id': '071c4013-ce30-3a93-a5b2-e0413cd4a9d1', - 'ext': 'mp4', - 'title': "'True Story' Trailer", - 'description': 'True Story', - }, - 'params': { - 'skip_download': True, - }, - }, - { - # ytwnews://cavideo/ - 'url': 'https://tw.video.yahoo.com/movie-tw/單車天使-中文版預-092316541.html', - 'info_dict': { - 'id': 'ba133ff2-0793-3510-b636-59dfe9ff6cff', - 'ext': 'mp4', - 'title': '單車天使 - 中文版預', - 'description': '中文版預', - }, - 'params': { - 'skip_download': True, - }, - }, - { - # custom brightcove - 'url': 'https://au.tv.yahoo.com/plus7/sunrise/-/watch/37083565/clown-entertainers-say-it-is-hurting-their-business/', - 'info_dict': { - 'id': '5575377707001', - 'ext': 'mp4', - 'title': "Clown entertainers say 'It' is hurting their business", - 'description': 'Stephen King s horror film has much to answer for. Jelby and Mr Loopy the Clowns join us.', - 'timestamp': 1505341164, - 'upload_date': '20170913', - 'uploader_id': '2376984109001', - }, - 'params': { - 'skip_download': True, - }, - }, - { - # custom brightcove, geo-restricted to Australia, bypassable - 'url': 'https://au.tv.yahoo.com/plus7/sunrise/-/watch/37263964/sunrise-episode-wed-27-sep/', - 'only_matching': True, + }, { + 'url': 'https://uk.screen.yahoo.com/editor-picks/cute-raccoon-freed-drain-using-091756545.html', + 'md5': '0b51660361f0e27c9789e7037ef76f4b', + 'info_dict': { + 'id': 'b3affa53-2e14-3590-852b-0e0db6cd1a58', + 'ext': 'mp4', + 'title': 'Cute Raccoon Freed From Drain\u00a0Using Angle Grinder', + 'description': 'md5:f66c890e1490f4910a9953c941dee944', + 'duration': 97, + 'timestamp': 1414489862, + 'upload_date': '20141028', } - ] + }, { + 'url': 'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html', + 'md5': '88e209b417f173d86186bef6e4d1f160', + 'info_dict': { + 'id': 'f885cf7f-43d4-3450-9fac-46ac30ece521', + 'ext': 'mp4', + 'title': 'China Moses Is Crazy About the Blues', + 'description': 'md5:9900ab8cd5808175c7b3fe55b979bed0', + 'duration': 128, + 'timestamp': 1385722202, + 'upload_date': '20131129', + } + }, { + 'url': 'https://www.yahoo.com/movies/v/true-story-trailer-173000497.html', + 'md5': '2a9752f74cb898af5d1083ea9f661b58', + 'info_dict': { + 'id': '071c4013-ce30-3a93-a5b2-e0413cd4a9d1', + 'ext': 'mp4', + 'title': '\'True Story\' Trailer', + 'description': 'True Story', + 'duration': 150, + 'timestamp': 1418919206, + 'upload_date': '20141218', + }, + }, { + 'url': 'https://gma.yahoo.com/pizza-delivery-man-surprised-huge-tip-college-kids-195200785.html', + 'only_matching': True, + }, { + 'note': 'NBC Sports embeds', + 'url': 'http://sports.yahoo.com/blogs/ncaab-the-dagger/tyler-kalinoski-s-buzzer-beater-caps-davidson-s-comeback-win-185609842.html?guid=nbc_cbk_davidsonbuzzerbeater_150313', + 'info_dict': { + 'id': '9CsDKds0kvHI', + 'ext': 'flv', + 'description': 'md5:df390f70a9ba7c95ff1daace988f0d8d', + 'title': 'Tyler Kalinoski hits buzzer-beater to lift Davidson', + 'upload_date': '20150313', + 'uploader': 'NBCU-SPORTS', + 'timestamp': 1426270238, + }, + }, { + 'url': 'https://tw.news.yahoo.com/-100120367.html', + 'only_matching': True, + }, { + # Query result is embedded in webpage, but explicit request to video API fails with geo restriction + 'url': 'https://screen.yahoo.com/community/communitary-community-episode-1-ladders-154501237.html', + 'md5': '4fbafb9c9b6f07aa8f870629f6671b35', + 'info_dict': { + 'id': '1f32853c-a271-3eef-8cb6-f6d6872cb504', + 'ext': 'mp4', + 'title': 'Communitary - Community Episode 1: Ladders', + 'description': 'md5:8fc39608213295748e1e289807838c97', + 'duration': 1646, + 'timestamp': 1440436550, + 'upload_date': '20150824', + 'series': 'Communitary', + 'season_number': 6, + 'episode_number': 1, + }, + }, { + # ytwnews://cavideo/ + 'url': 'https://tw.video.yahoo.com/movie-tw/單車天使-中文版預-092316541.html', + 'info_dict': { + 'id': 'ba133ff2-0793-3510-b636-59dfe9ff6cff', + 'ext': 'mp4', + 'title': '單車天使 - 中文版預', + 'description': '中文版預', + 'timestamp': 1476696196, + 'upload_date': '20161017', + }, + 'params': { + 'skip_download': True, + }, + }, { + # Contains both a Yahoo hosted video and multiple Youtube embeds + 'url': 'https://www.yahoo.com/entertainment/gwen-stefani-reveals-the-pop-hit-she-passed-on-assigns-it-to-her-voice-contestant-instead-033045672.html', + 'info_dict': { + 'id': '46c5d95a-528f-3d03-b732-732fcadd51de', + 'title': 'Gwen Stefani reveals the pop hit she passed on, assigns it to her \'Voice\' contestant instead', + 'description': 'Gwen decided not to record this hit herself, but she decided it was the perfect fit for Kyndall Inskeep.', + }, + 'playlist': [{ + 'info_dict': { + 'id': '966d4262-4fd1-3aaa-b45b-049ca6e38ba6', + 'ext': 'mp4', + 'title': 'Gwen Stefani reveals she turned down one of Sia\'s best songs', + 'description': 'On "The Voice" Tuesday, Gwen Stefani told Taylor Swift which Sia hit was almost hers.', + 'timestamp': 1572406500, + 'upload_date': '20191030', + }, + }, { + 'info_dict': { + 'id': '352CFDOQrKg', + 'ext': 'mp4', + 'title': 'Kyndal Inskeep "Performs the Hell Out of" Sia\'s "Elastic Heart" - The Voice Knockouts 2019', + 'description': 'md5:35b61e94c2ae214bc965ff4245f80d11', + 'uploader': 'The Voice', + 'uploader_id': 'NBCTheVoice', + 'upload_date': '20191029', + }, + }], + 'params': { + 'playlistend': 2, + }, + }, { + 'url': 'https://malaysia.news.yahoo.com/video/bystanders-help-ontario-policeman-bust-190932818.html', + 'only_matching': True, + }, { + 'url': 'https://es-us.noticias.yahoo.com/es-la-puerta-irrompible-que-110539379.html', + 'only_matching': True, + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - page_id = mobj.group('id') - display_id = mobj.group('display_id') or page_id - host = mobj.group('host') - webpage, urlh = self._download_webpage_handle(url, display_id) - if 'err=404' in urlh.geturl(): - raise ExtractorError('Video gone', expected=True) - - # Look for iframed media first - entries = [] - iframe_urls = re.findall(r']+src="(/video/.+?-\d+\.html\?format=embed.*?)"', webpage) - for idx, iframe_url in enumerate(iframe_urls): - entries.append(self.url_result(host + iframe_url, 'Yahoo')) - if entries: - return self.playlist_result(entries, page_id) - - # Look for NBCSports iframes - nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage) - if nbc_sports_url: - return self.url_result(nbc_sports_url, NBCSportsVPlayerIE.ie_key()) - - # Look for Brightcove Legacy Studio embeds - bc_url = BrightcoveLegacyIE._extract_brightcove_url(webpage) - if bc_url: - return self.url_result(bc_url, BrightcoveLegacyIE.ie_key()) - - def brightcove_url_result(bc_url): - return self.url_result( - smuggle_url(bc_url, {'geo_countries': [mobj.group('country')]}), - BrightcoveNewIE.ie_key()) - - # Look for Brightcove New Studio embeds - bc_url = BrightcoveNewIE._extract_url(self, webpage) - if bc_url: - return brightcove_url_result(bc_url) - - brightcove_iframe = self._search_regex( - r'(]+data-video-id=["\']\d+[^>]+>)', webpage, - 'brightcove iframe', default=None) - if brightcove_iframe: - attr = extract_attributes(brightcove_iframe) - src = attr.get('src') - if src: - parsed_src = compat_urlparse.urlparse(src) - qs = compat_urlparse.parse_qs(parsed_src.query) - account_id = qs.get('accountId', ['2376984109001'])[0] - brightcove_id = attr.get('data-video-id') or qs.get('videoId', [None])[0] - if account_id and brightcove_id: - return brightcove_url_result( - 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' - % (account_id, brightcove_id)) - - # Query result is often embedded in webpage as JSON. Sometimes explicit requests - # to video API results in a failure with geo restriction reason therefore using - # embedded query result when present sounds reasonable. - config_json = self._search_regex( - r'window\.Af\.bootstrap\[[^\]]+\]\s*=\s*({.*?"applet_type"\s*:\s*"td-applet-videoplayer".*?});(?:|$)', - webpage, 'videoplayer applet', default=None) - if config_json: - config = self._parse_json(config_json, display_id, fatal=False) - if config: - sapi = config.get('models', {}).get('applet_model', {}).get('data', {}).get('sapi') - if sapi and 'query' in sapi: - info = self._extract_info(display_id, sapi, webpage) - self._sort_formats(info['formats']) - return info - - items_json = self._search_regex( - r'mediaItems: ({.*?})$', webpage, 'items', flags=re.MULTILINE, - default=None) - if items_json is None: - alias = self._search_regex( - r'"aliases":{"video":"(.*?)"', webpage, 'alias', default=None) - if alias is not None: - alias_info = self._download_json( - 'https://www.yahoo.com/_td/api/resource/VideoService.videos;video_aliases=["%s"]' % alias, - display_id, 'Downloading alias info') - video_id = alias_info[0]['id'] - else: - CONTENT_ID_REGEXES = [ - r'YUI\.namespace\("Media"\)\.CONTENT_ID\s*=\s*"([^"]+)"', - r'root\.App\.Cache\.context\.videoCache\.curVideo = \{"([^"]+)"', - r'"first_videoid"\s*:\s*"([^"]+)"', - r'%s[^}]*"ccm_id"\s*:\s*"([^"]+)"' % re.escape(page_id), - r']data-uuid=["\']([^"\']+)', - r']+yahoo://article/view\?.*\buuid=([^&"\']+)', - r']+["\']ytwnews://cavideo/(?:[^/]+/)+([\da-fA-F-]+)[&"\']', - ] - video_id = self._search_regex( - CONTENT_ID_REGEXES, webpage, 'content ID') + url, country, display_id = re.match(self._VALID_URL, url).groups() + if not country: + country = 'us' else: - items = json.loads(items_json) - info = items['mediaItems']['query']['results']['mediaObj'][0] - # The 'meta' field is not always in the video webpage, we request it - # from another page - video_id = info['id'] - return self._get_info(video_id, display_id, webpage) + country = country.split('-')[0] + api_base = 'https://%s.yahoo.com/_td/api/resource/' % country - def _extract_info(self, display_id, query, webpage): - info = query['query']['results']['mediaObj'][0] - meta = info.get('meta') - video_id = info.get('id') + for i, uuid in enumerate(['url=' + url, 'ymedia-alias=' + display_id]): + content = self._download_json( + api_base + 'content;getDetailView=true;uuids=["%s"]' % uuid, + display_id, 'Downloading content JSON metadata', fatal=i == 1) + if content: + item = content['items'][0] + break - if not meta: - msg = info['status'].get('msg') - if msg: - raise ExtractorError( - '%s returned error: %s' % (self.IE_NAME, msg), expected=True) - raise ExtractorError('Unable to extract media object meta') + if item.get('type') != 'video': + entries = [] + cover = item.get('cover') or {} + if cover.get('type') == 'yvideo': + cover_url = cover.get('url') + if cover_url: + entries.append(self.url_result( + cover_url, 'Yahoo', cover.get('uuid'))) + + for e in item.get('body', []): + if e.get('type') == 'videoIframe': + iframe_url = e.get('url') + if not iframe_url: + continue + entries.append(self.url_result(iframe_url)) + + return self.playlist_result( + entries, item.get('uuid'), + item.get('title'), item.get('summary')) + + video_id = item['uuid'] + video = self._download_json( + api_base + 'VideoService.videos;view=full;video_ids=["%s"]' % video_id, + video_id, 'Downloading video JSON metadata')[0] + title = video['title'] + + if country == 'malaysia': + country = 'my' + + is_live = video.get('live_state') == 'live' + fmts = ('m3u8',) if is_live else ('web', 'mp4') + + urls = [] formats = [] - for s in info['streams']: - tbr = int_or_none(s.get('bitrate')) - format_info = { - 'width': int_or_none(s.get('width')), - 'height': int_or_none(s.get('height')), - 'tbr': tbr, - } - - host = s['host'] - path = s['path'] - if host.startswith('rtmp'): - fmt = 'rtmp' - format_info.update({ - 'url': host, - 'play_path': path, - 'ext': 'flv', - }) - else: - if s.get('format') == 'm3u8_playlist': - fmt = 'hls' - format_info.update({ - 'protocol': 'm3u8_native', - 'ext': 'mp4', - }) - else: - fmt = format_info['ext'] = determine_ext(path) - format_url = compat_urlparse.urljoin(host, path) - format_info['url'] = format_url - format_info['format_id'] = fmt + ('-%d' % tbr if tbr else '') - formats.append(format_info) - - closed_captions = self._html_search_regex( - r'"closedcaptions":(\[[^\]]+\])', webpage, 'closed captions', - default='[]') - - cc_json = self._parse_json(closed_captions, video_id, fatal=False) subtitles = {} - if cc_json: - for closed_caption in cc_json: - lang = closed_caption['lang'] - if lang not in subtitles: - subtitles[lang] = [] - subtitles[lang].append({ - 'url': closed_caption['url'], - 'ext': mimetype2ext(closed_caption['content_type']), + for fmt in fmts: + media_obj = self._download_json( + 'https://video-api.yql.yahoo.com/v1/video/sapi/streams/' + video_id, + video_id, 'Downloading %s JSON metadata' % fmt, + headers=self.geo_verification_headers(), query={ + 'format': fmt, + 'region': country.upper(), + })['query']['results']['mediaObj'][0] + msg = media_obj.get('status', {}).get('msg') + + for s in media_obj.get('streams', []): + host = s.get('host') + path = s.get('path') + if not host or not path: + continue + s_url = host + path + if s.get('format') == 'm3u8': + formats.extend(self._extract_m3u8_formats( + s_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) + continue + tbr = int_or_none(s.get('bitrate')) + formats.append({ + 'url': s_url, + 'format_id': fmt + ('-%d' % tbr if tbr else ''), + 'width': int_or_none(s.get('width')), + 'height': int_or_none(s.get('height')), + 'tbr': tbr, + 'fps': int_or_none(s.get('framerate')), }) + for cc in media_obj.get('closedcaptions', []): + cc_url = cc.get('url') + if not cc_url or cc_url in urls: + continue + urls.append(cc_url) + subtitles.setdefault(cc.get('lang') or 'en-US', []).append({ + 'url': cc_url, + 'ext': mimetype2ext(cc.get('content_type')), + }) + + streaming_url = video.get('streaming_url') + if streaming_url and not is_live: + formats.extend(self._extract_m3u8_formats( + streaming_url, video_id, 'mp4', + 'm3u8_native', m3u8_id='hls', fatal=False)) + + if not formats and msg == 'geo restricted': + self.raise_geo_restricted() + + self._sort_formats(formats) + + thumbnails = [] + for thumb in video.get('thumbnails', []): + thumb_url = thumb.get('url') + if not thumb_url: + continue + thumbnails.append({ + 'id': thumb.get('tag'), + 'url': thumb.get('url'), + 'width': int_or_none(thumb.get('width')), + 'height': int_or_none(thumb.get('height')), + }) + + series_info = video.get('series_info') or {} + return { 'id': video_id, - 'display_id': display_id, - 'title': unescapeHTML(meta['title']), + 'title': self._live_title(title) if is_live else title, 'formats': formats, - 'description': clean_html(meta['description']), - 'thumbnail': meta['thumbnail'] if meta.get('thumbnail') else self._og_search_thumbnail(webpage), - 'duration': int_or_none(meta.get('duration')), + 'display_id': display_id, + 'thumbnails': thumbnails, + 'description': clean_html(video.get('description')), + 'timestamp': parse_iso8601(video.get('publish_time')), 'subtitles': subtitles, + 'duration': int_or_none(video.get('duration')), + 'view_count': int_or_none(video.get('view_count')), + 'is_live': is_live, + 'series': video.get('show_name'), + 'season_number': int_or_none(series_info.get('season_number')), + 'episode_number': int_or_none(series_info.get('episode_number')), } - def _get_info(self, video_id, display_id, webpage): - region = self._search_regex( - r'\\?"region\\?"\s*:\s*\\?"([^"]+?)\\?"', - webpage, 'region', fatal=False, default='US').upper() - formats = [] - info = {} - for fmt in ('webm', 'mp4'): - query_result = self._download_json( - 'https://video.media.yql.yahoo.com/v1/video/sapi/streams/' + video_id, - display_id, 'Downloading %s video info' % fmt, query={ - 'protocol': 'http', - 'region': region, - 'format': fmt, - }) - info = self._extract_info(display_id, query_result, webpage) - formats.extend(info['formats']) - formats.extend(self._extract_m3u8_formats( - 'http://video.media.yql.yahoo.com/v1/hls/%s?region=%s' % (video_id, region), - video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) - self._sort_formats(formats) - info['formats'] = formats - return info - class YahooSearchIE(SearchInfoExtractor): IE_DESC = 'Yahoo screen search' From 8040a0d35e11f7b2bf6d698175ab0b12424d696f Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 30 Oct 2019 23:52:09 +0100 Subject: [PATCH 141/422] [yahoo] fix typo --- youtube_dl/extractor/yahoo.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index ee68096d0..6c6bd76e8 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -51,10 +51,10 @@ class YahooIE(InfoExtractor): }, }, { 'url': 'https://uk.screen.yahoo.com/editor-picks/cute-raccoon-freed-drain-using-091756545.html', - 'md5': '0b51660361f0e27c9789e7037ef76f4b', + 'md5': '71298482f7c64cbb7fa064e4553ff1c1', 'info_dict': { 'id': 'b3affa53-2e14-3590-852b-0e0db6cd1a58', - 'ext': 'mp4', + 'ext': 'webm', 'title': 'Cute Raccoon Freed From Drain\u00a0Using Angle Grinder', 'description': 'md5:f66c890e1490f4910a9953c941dee944', 'duration': 97, @@ -164,6 +164,7 @@ class YahooIE(InfoExtractor): 'params': { 'playlistend': 2, }, + 'expected_warnings': ['HTTP Error 404'], }, { 'url': 'https://malaysia.news.yahoo.com/video/bystanders-help-ontario-policeman-bust-190932818.html', 'only_matching': True, @@ -219,7 +220,7 @@ class YahooIE(InfoExtractor): country = 'my' is_live = video.get('live_state') == 'live' - fmts = ('m3u8',) if is_live else ('web', 'mp4') + fmts = ('m3u8',) if is_live else ('webm', 'mp4') urls = [] formats = [] From 237513e801671a51cc45d6a2fe5e7df69517958e Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Thu, 31 Oct 2019 07:38:53 +0100 Subject: [PATCH 142/422] [yahoo] restore support for cbs suffixed URLs --- test/test_all_urls.py | 6 ------ youtube_dl/extractor/yahoo.py | 5 ++++- 2 files changed, 4 insertions(+), 7 deletions(-) diff --git a/test/test_all_urls.py b/test/test_all_urls.py index 465ce0050..81056a999 100644 --- a/test/test_all_urls.py +++ b/test/test_all_urls.py @@ -123,12 +123,6 @@ class TestAllURLsMatching(unittest.TestCase): self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['pbs']) self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['pbs']) - def test_yahoo_https(self): - # https://github.com/ytdl-org/youtube-dl/issues/2701 - self.assertMatch( - 'https://screen.yahoo.com/smartwatches-latest-wearable-gadgets-163745379-cbs.html', - ['Yahoo']) - def test_no_duplicated_ie_names(self): name_accu = collections.defaultdict(list) for ie in self.ies: diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index 6c6bd76e8..f041cf5de 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -25,7 +25,7 @@ from .brightcove import BrightcoveNewIE class YahooIE(InfoExtractor): IE_DESC = 'Yahoo screen and movies' - _VALID_URL = r'(?Phttps?://(?:(?P[a-zA-Z]{2}(?:-[a-zA-Z]{2})?|malaysia)\.)?(?:[\da-zA-Z_-]+\.)?yahoo\.com/(?:[^/]+/)*(?P[^?&#]*-[0-9]+)\.html)' + _VALID_URL = r'(?Phttps?://(?:(?P[a-zA-Z]{2}(?:-[a-zA-Z]{2})?|malaysia)\.)?(?:[\da-zA-Z_-]+\.)?yahoo\.com/(?:[^/]+/)*(?P[^?&#]*-[0-9]+)(?:-[a-z]+)?\.html)' _TESTS = [{ 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html', 'info_dict': { @@ -171,6 +171,9 @@ class YahooIE(InfoExtractor): }, { 'url': 'https://es-us.noticias.yahoo.com/es-la-puerta-irrompible-que-110539379.html', 'only_matching': True, + }, { + 'url': 'https://www.yahoo.com/entertainment/v/longtime-cbs-news-60-minutes-032036500-cbs.html', + 'only_matching': True, }] def _real_extract(self, url): From 3cf70bf1590ce364dc223197ba804cb70e704760 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Thu, 31 Oct 2019 07:44:21 +0100 Subject: [PATCH 143/422] [yahoo] make cbs URL suffix part of the media alias --- youtube_dl/extractor/yahoo.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index f041cf5de..b9a9e88a0 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -25,7 +25,7 @@ from .brightcove import BrightcoveNewIE class YahooIE(InfoExtractor): IE_DESC = 'Yahoo screen and movies' - _VALID_URL = r'(?Phttps?://(?:(?P[a-zA-Z]{2}(?:-[a-zA-Z]{2})?|malaysia)\.)?(?:[\da-zA-Z_-]+\.)?yahoo\.com/(?:[^/]+/)*(?P[^?&#]*-[0-9]+)(?:-[a-z]+)?\.html)' + _VALID_URL = r'(?Phttps?://(?:(?P[a-zA-Z]{2}(?:-[a-zA-Z]{2})?|malaysia)\.)?(?:[\da-zA-Z_-]+\.)?yahoo\.com/(?:[^/]+/)*(?P[^?&#]*-[0-9]+(?:-[a-z]+)?)\.html)' _TESTS = [{ 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html', 'info_dict': { From e993f1a0959fc04507b1cb2efeb610ae628d6d98 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Thu, 31 Oct 2019 08:13:10 +0100 Subject: [PATCH 144/422] [mixcloud] fix cloudcast data extraction(closes #22821) --- youtube_dl/extractor/mixcloud.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index bf5353ef9..e5f631506 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -86,9 +86,10 @@ class MixcloudIE(InfoExtractor): r'', webpage, 'play info'), 'play info') for item in full_info_json: - item_data = try_get( - item, lambda x: x['cloudcast']['data']['cloudcastLookup'], - dict) + item_data = try_get(item, [ + lambda x: x['cloudcast']['data']['cloudcastLookup'], + lambda x: x['cloudcastLookup']['data']['cloudcastLookup'], + ], dict) if try_get(item_data, lambda x: x['streamInfo']['url']): info_json = item_data break From 274bf5e4c58bceed4ff8c283d77457bf1cb76d3e Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Fri, 1 Nov 2019 11:37:41 +0100 Subject: [PATCH 145/422] [kakao] improve extraction - support embed URLs - support Kakao Legacy vid based embed URLs - only extract fields used for extraction - strip description and extract tags --- youtube_dl/extractor/kakao.py | 45 +++++++++++++++++++---------------- 1 file changed, 24 insertions(+), 21 deletions(-) diff --git a/youtube_dl/extractor/kakao.py b/youtube_dl/extractor/kakao.py index 7fa140b0c..96f918b75 100644 --- a/youtube_dl/extractor/kakao.py +++ b/youtube_dl/extractor/kakao.py @@ -6,14 +6,15 @@ from .common import InfoExtractor from ..compat import compat_str from ..utils import ( int_or_none, + strip_or_none, unified_timestamp, update_url_query, ) class KakaoIE(InfoExtractor): - _VALID_URL = r'https?://tv\.kakao\.com/channel/(?P\d+)/cliplink/(?P\d+)' - _API_BASE = 'http://tv.kakao.com/api/v1/ft/cliplinks' + _VALID_URL = r'https?://(?:play-)?tv\.kakao\.com/(?:channel/\d+|embed/player)/cliplink/(?P\d+|[^?#&]+@my)' + _API_BASE_TMPL = 'http://tv.kakao.com/api/v1/ft/cliplinks/%s/' _TESTS = [{ 'url': 'http://tv.kakao.com/channel/2671005/cliplink/301965083', @@ -36,7 +37,7 @@ class KakaoIE(InfoExtractor): 'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\r\n\r\n[쇼! 음악중심] 20160611, 507회', 'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)', 'uploader_id': 2653210, - 'uploader': '쇼 음악중심', + 'uploader': '쇼! 음악중심', 'timestamp': 1485684628, 'upload_date': '20170129', } @@ -44,6 +45,8 @@ class KakaoIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) + display_id = video_id.rstrip('@my') + api_base = self._API_BASE_TMPL % video_id player_header = { 'Referer': update_url_query( @@ -55,20 +58,22 @@ class KakaoIE(InfoExtractor): }) } - QUERY_COMMON = { + query = { 'player': 'monet_html5', 'referer': url, 'uuid': '', 'service': 'kakao_tv', 'section': '', 'dteType': 'PC', + 'fields': ','.join([ + '-*', 'tid', 'clipLink', 'displayTitle', 'clip', 'title', + 'description', 'channelId', 'createTime', 'duration', 'playCount', + 'likeCount', 'commentCount', 'tagList', 'channel', 'name', + 'clipChapterThumbnailList', 'thumbnailUrl', 'timeInSec', 'isDefault']) } - query = QUERY_COMMON.copy() - query['fields'] = 'clipLink,clip,channel,hasPlusFriend,-service,-tagList' impress = self._download_json( - '%s/%s/impress' % (self._API_BASE, video_id), - video_id, 'Downloading video info', + api_base + 'impress', display_id, 'Downloading video info', query=query, headers=player_header) clip_link = impress['clipLink'] @@ -78,30 +83,27 @@ class KakaoIE(InfoExtractor): tid = impress.get('tid', '') - query = QUERY_COMMON.copy() query.update({ + 'fields': '-*,outputList,profile,width,height,label,filesize', 'tid': tid, 'profile': 'HIGH', }) raw = self._download_json( - '%s/%s/raw' % (self._API_BASE, video_id), - video_id, 'Downloading video formats info', + api_base + 'raw', display_id, 'Downloading video formats info', query=query, headers=player_header) formats = [] for fmt in raw.get('outputList', []): try: profile_name = fmt['profile'] + query.update({ + 'profile': profile_name, + 'fields': '-*,url', + }) fmt_url_json = self._download_json( - '%s/%s/raw/videolocation' % (self._API_BASE, video_id), - video_id, + api_base + 'raw/videolocation', display_id, 'Downloading video URL for profile %s' % profile_name, - query={ - 'service': 'kakao_tv', - 'section': '', - 'tid': tid, - 'profile': profile_name - }, headers=player_header, fatal=False) + query=query, headers=player_header, fatal=False) if fmt_url_json is None: continue @@ -134,9 +136,9 @@ class KakaoIE(InfoExtractor): }) return { - 'id': video_id, + 'id': display_id, 'title': title, - 'description': clip.get('description'), + 'description': strip_or_none(clip.get('description')), 'uploader': clip_link.get('channel', {}).get('name'), 'uploader_id': clip_link.get('channelId'), 'thumbnails': thumbs, @@ -146,4 +148,5 @@ class KakaoIE(InfoExtractor): 'like_count': int_or_none(clip.get('likeCount')), 'comment_count': int_or_none(clip.get('commentCount')), 'formats': formats, + 'tags': clip.get('tagList'), } From d439989215fcb1672bc2ac18d4fb6206e12c387a Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Fri, 1 Nov 2019 11:43:18 +0100 Subject: [PATCH 146/422] [daum] fix VOD and Clip extracton(closes #15015) --- youtube_dl/extractor/daum.py | 106 +++++++++++------------------------ 1 file changed, 32 insertions(+), 74 deletions(-) diff --git a/youtube_dl/extractor/daum.py b/youtube_dl/extractor/daum.py index 76f021892..137095577 100644 --- a/youtube_dl/extractor/daum.py +++ b/youtube_dl/extractor/daum.py @@ -2,25 +2,21 @@ from __future__ import unicode_literals -import re import itertools from .common import InfoExtractor from ..compat import ( compat_parse_qs, compat_urllib_parse_unquote, - compat_urllib_parse_urlencode, compat_urlparse, ) -from ..utils import ( - int_or_none, - str_to_int, - xpath_text, - unescapeHTML, -) -class DaumIE(InfoExtractor): +class DaumBaseIE(InfoExtractor): + _KAKAO_EMBED_BASE = 'http://tv.kakao.com/embed/player/cliplink/' + + +class DaumIE(DaumBaseIE): _VALID_URL = r'https?://(?:(?:m\.)?tvpot\.daum\.net/v/|videofarm\.daum\.net/controller/player/VodPlayer\.swf\?vid=)(?P[^?#&]+)' IE_NAME = 'daum.net' @@ -36,6 +32,9 @@ class DaumIE(InfoExtractor): 'duration': 2117, 'view_count': int, 'comment_count': int, + 'uploader_id': 186139, + 'uploader': '콘간지', + 'timestamp': 1387310323, }, }, { 'url': 'http://m.tvpot.daum.net/v/65139429', @@ -44,11 +43,14 @@ class DaumIE(InfoExtractor): 'ext': 'mp4', 'title': '1297회, \'아빠 아들로 태어나길 잘 했어\' 민수, 감동의 눈물[아빠 어디가] 20150118', 'description': 'md5:79794514261164ff27e36a21ad229fc5', - 'upload_date': '20150604', + 'upload_date': '20150118', 'thumbnail': r're:^https?://.*\.(?:jpg|png)', 'duration': 154, 'view_count': int, 'comment_count': int, + 'uploader': 'MBC 예능', + 'uploader_id': 132251, + 'timestamp': 1421604228, }, }, { 'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24', @@ -59,12 +61,15 @@ class DaumIE(InfoExtractor): 'id': 'vwIpVpCQsT8$', 'ext': 'flv', 'title': '01-Korean War ( Trouble on the horizon )', - 'description': '\nKorean War 01\nTrouble on the horizon\n전쟁의 먹구름', + 'description': 'Korean War 01\r\nTrouble on the horizon\r\n전쟁의 먹구름', 'upload_date': '20080223', 'thumbnail': r're:^https?://.*\.(?:jpg|png)', 'duration': 249, 'view_count': int, 'comment_count': int, + 'uploader': '까칠한 墮落始祖 황비홍님의', + 'uploader_id': 560824, + 'timestamp': 1203770745, }, }, { # Requires dte_type=WEB (#9972) @@ -73,60 +78,24 @@ class DaumIE(InfoExtractor): 'info_dict': { 'id': 's3794Uf1NZeZ1qMpGpeqeRU', 'ext': 'mp4', - 'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny) [쇼! 음악중심] 508회 20160611', - 'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\n\n[쇼! 음악중심] 20160611, 507회', - 'upload_date': '20160611', + 'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)', + 'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\r\n\r\n[쇼! 음악중심] 20160611, 507회', + 'upload_date': '20170129', + 'uploader': '쇼! 음악중심', + 'uploader_id': 2653210, + 'timestamp': 1485684628, }, }] def _real_extract(self, url): video_id = compat_urllib_parse_unquote(self._match_id(url)) - movie_data = self._download_json( - 'http://videofarm.daum.net/controller/api/closed/v1_2/IntegratedMovieData.json', - video_id, 'Downloading video formats info', query={'vid': video_id, 'dte_type': 'WEB'}) - - # For urls like http://m.tvpot.daum.net/v/65139429, where the video_id is really a clipid - if not movie_data.get('output_list', {}).get('output_list') and re.match(r'^\d+$', video_id): - return self.url_result('http://tvpot.daum.net/clip/ClipView.do?clipid=%s' % video_id) - - info = self._download_xml( - 'http://tvpot.daum.net/clip/ClipInfoXml.do', video_id, - 'Downloading video info', query={'vid': video_id}) - - formats = [] - for format_el in movie_data['output_list']['output_list']: - profile = format_el['profile'] - format_query = compat_urllib_parse_urlencode({ - 'vid': video_id, - 'profile': profile, - }) - url_doc = self._download_xml( - 'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query, - video_id, note='Downloading video data for %s format' % profile) - format_url = url_doc.find('result/url').text - formats.append({ - 'url': format_url, - 'format_id': profile, - 'width': int_or_none(format_el.get('width')), - 'height': int_or_none(format_el.get('height')), - 'filesize': int_or_none(format_el.get('filesize')), - }) - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': info.find('TITLE').text, - 'formats': formats, - 'thumbnail': xpath_text(info, 'THUMB_URL'), - 'description': xpath_text(info, 'CONTENTS'), - 'duration': int_or_none(xpath_text(info, 'DURATION')), - 'upload_date': info.find('REGDTTM').text[:8], - 'view_count': str_to_int(xpath_text(info, 'PLAY_CNT')), - 'comment_count': str_to_int(xpath_text(info, 'COMMENT_CNT')), - } + if not video_id.isdigit(): + video_id += '@my' + return self.url_result( + self._KAKAO_EMBED_BASE + video_id, 'Kakao', video_id) -class DaumClipIE(InfoExtractor): +class DaumClipIE(DaumBaseIE): _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:clip/ClipView.(?:do|tv)|mypot/View.do)\?.*?clipid=(?P\d+)' IE_NAME = 'daum.net:clip' _URL_TEMPLATE = 'http://tvpot.daum.net/clip/ClipView.do?clipid=%s' @@ -142,6 +111,9 @@ class DaumClipIE(InfoExtractor): 'thumbnail': r're:^https?://.*\.(?:jpg|png)', 'duration': 3868, 'view_count': int, + 'uploader': 'GOMeXP', + 'uploader_id': 6667, + 'timestamp': 1377911092, }, }, { 'url': 'http://m.tvpot.daum.net/clip/ClipView.tv?clipid=54999425', @@ -154,22 +126,8 @@ class DaumClipIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - clip_info = self._download_json( - 'http://tvpot.daum.net/mypot/json/GetClipInfo.do?clipid=%s' % video_id, - video_id, 'Downloading clip info')['clip_bean'] - - return { - '_type': 'url_transparent', - 'id': video_id, - 'url': 'http://tvpot.daum.net/v/%s' % clip_info['vid'], - 'title': unescapeHTML(clip_info['title']), - 'thumbnail': clip_info.get('thumb_url'), - 'description': clip_info.get('contents'), - 'duration': int_or_none(clip_info.get('duration')), - 'upload_date': clip_info.get('up_date')[:8], - 'view_count': int_or_none(clip_info.get('play_count')), - 'ie_key': 'Daum', - } + return self.url_result( + self._KAKAO_EMBED_BASE + video_id, 'Kakao', video_id) class DaumListIE(InfoExtractor): From e987ce4bda476a387937e4af5b46f4a412a67830 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Fri, 1 Nov 2019 12:40:41 +0100 Subject: [PATCH 147/422] [kakao] remove raw request and extract format total bitrate --- youtube_dl/extractor/kakao.py | 21 ++++++++------------- 1 file changed, 8 insertions(+), 13 deletions(-) diff --git a/youtube_dl/extractor/kakao.py b/youtube_dl/extractor/kakao.py index 96f918b75..32935bb28 100644 --- a/youtube_dl/extractor/kakao.py +++ b/youtube_dl/extractor/kakao.py @@ -69,7 +69,8 @@ class KakaoIE(InfoExtractor): '-*', 'tid', 'clipLink', 'displayTitle', 'clip', 'title', 'description', 'channelId', 'createTime', 'duration', 'playCount', 'likeCount', 'commentCount', 'tagList', 'channel', 'name', - 'clipChapterThumbnailList', 'thumbnailUrl', 'timeInSec', 'isDefault']) + 'clipChapterThumbnailList', 'thumbnailUrl', 'timeInSec', 'isDefault', + 'videoOutputList', 'width', 'height', 'kbps', 'profile', 'label']) } impress = self._download_json( @@ -81,21 +82,14 @@ class KakaoIE(InfoExtractor): title = clip.get('title') or clip_link.get('displayTitle') - tid = impress.get('tid', '') - - query.update({ - 'fields': '-*,outputList,profile,width,height,label,filesize', - 'tid': tid, - 'profile': 'HIGH', - }) - raw = self._download_json( - api_base + 'raw', display_id, 'Downloading video formats info', - query=query, headers=player_header) + query['tid'] = impress.get('tid', '') formats = [] - for fmt in raw.get('outputList', []): + for fmt in clip.get('videoOutputList', []): try: profile_name = fmt['profile'] + if profile_name == 'AUDIO': + continue query.update({ 'profile': profile_name, 'fields': '-*,url', @@ -115,7 +109,8 @@ class KakaoIE(InfoExtractor): 'width': int_or_none(fmt.get('width')), 'height': int_or_none(fmt.get('height')), 'format_note': fmt.get('label'), - 'filesize': int_or_none(fmt.get('filesize')) + 'filesize': int_or_none(fmt.get('filesize')), + 'tbr': int_or_none(fmt.get('kbps')), }) except KeyError: pass From 20cc7c082b82e82050a4e1f1bb815fee51f6c1c2 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Fri, 1 Nov 2019 16:36:35 +0100 Subject: [PATCH 148/422] [go90] remove extractor --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/go90.py | 149 ----------------------------- 2 files changed, 150 deletions(-) delete mode 100644 youtube_dl/extractor/go90.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 5d20ba863..e9b59ce52 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -422,7 +422,6 @@ from .globo import ( GloboArticleIE, ) from .go import GoIE -from .go90 import Go90IE from .godtube import GodTubeIE from .golem import GolemIE from .googledrive import GoogleDriveIE diff --git a/youtube_dl/extractor/go90.py b/youtube_dl/extractor/go90.py deleted file mode 100644 index c3ea717bc..000000000 --- a/youtube_dl/extractor/go90.py +++ /dev/null @@ -1,149 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..compat import compat_HTTPError -from ..utils import ( - determine_ext, - ExtractorError, - int_or_none, - parse_age_limit, - parse_iso8601, -) - - -class Go90IE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?go90\.com/(?:videos|embed)/(?P[0-9a-zA-Z]+)' - _TESTS = [{ - 'url': 'https://www.go90.com/videos/84BUqjLpf9D', - 'md5': 'efa7670dbbbf21a7b07b360652b24a32', - 'info_dict': { - 'id': '84BUqjLpf9D', - 'ext': 'mp4', - 'title': 'Daily VICE - Inside The Utah Coalition Against Pornography Convention', - 'description': 'VICE\'s Karley Sciortino meets with activists who discuss the state\'s strong anti-porn stance. Then, VICE Sports explains NFL contracts.', - 'timestamp': 1491868800, - 'upload_date': '20170411', - 'age_limit': 14, - } - }, { - 'url': 'https://www.go90.com/embed/261MflWkD3N', - 'only_matching': True, - }] - _GEO_BYPASS = False - - def _real_extract(self, url): - video_id = self._match_id(url) - - try: - headers = self.geo_verification_headers() - headers.update({ - 'Content-Type': 'application/json; charset=utf-8', - }) - video_data = self._download_json( - 'https://www.go90.com/api/view/items/' + video_id, video_id, - headers=headers, data=b'{"client":"web","device_type":"pc"}') - except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400: - message = self._parse_json(e.cause.read().decode(), None)['error']['message'] - if 'region unavailable' in message: - self.raise_geo_restricted(countries=['US']) - raise ExtractorError(message, expected=True) - raise - - if video_data.get('requires_drm'): - raise ExtractorError('This video is DRM protected.', expected=True) - main_video_asset = video_data['main_video_asset'] - - episode_number = int_or_none(video_data.get('episode_number')) - series = None - season = None - season_id = None - season_number = None - for metadata in video_data.get('__children', {}).get('Item', {}).values(): - if metadata.get('type') == 'show': - series = metadata.get('title') - elif metadata.get('type') == 'season': - season = metadata.get('title') - season_id = metadata.get('id') - season_number = int_or_none(metadata.get('season_number')) - - title = episode = video_data.get('title') or series - if series and series != title: - title = '%s - %s' % (series, title) - - thumbnails = [] - formats = [] - subtitles = {} - for asset in video_data.get('assets'): - if asset.get('id') == main_video_asset: - for source in asset.get('sources', []): - source_location = source.get('location') - if not source_location: - continue - source_type = source.get('type') - if source_type == 'hls': - m3u8_formats = self._extract_m3u8_formats( - source_location, video_id, 'mp4', - 'm3u8_native', m3u8_id='hls', fatal=False) - for f in m3u8_formats: - mobj = re.search(r'/hls-(\d+)-(\d+)K', f['url']) - if mobj: - height, tbr = mobj.groups() - height = int_or_none(height) - f.update({ - 'height': f.get('height') or height, - 'width': f.get('width') or int_or_none(height / 9.0 * 16.0 if height else None), - 'tbr': f.get('tbr') or int_or_none(tbr), - }) - formats.extend(m3u8_formats) - elif source_type == 'dash': - formats.extend(self._extract_mpd_formats( - source_location, video_id, mpd_id='dash', fatal=False)) - else: - formats.append({ - 'format_id': source.get('name'), - 'url': source_location, - 'width': int_or_none(source.get('width')), - 'height': int_or_none(source.get('height')), - 'tbr': int_or_none(source.get('bitrate')), - }) - - for caption in asset.get('caption_metadata', []): - caption_url = caption.get('source_url') - if not caption_url: - continue - subtitles.setdefault(caption.get('language', 'en'), []).append({ - 'url': caption_url, - 'ext': determine_ext(caption_url, 'vtt'), - }) - elif asset.get('type') == 'image': - asset_location = asset.get('location') - if not asset_location: - continue - thumbnails.append({ - 'url': asset_location, - 'width': int_or_none(asset.get('width')), - 'height': int_or_none(asset.get('height')), - }) - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': title, - 'formats': formats, - 'thumbnails': thumbnails, - 'description': video_data.get('short_description'), - 'like_count': int_or_none(video_data.get('like_count')), - 'timestamp': parse_iso8601(video_data.get('released_at')), - 'series': series, - 'episode': episode, - 'season': season, - 'season_id': season_id, - 'season_number': season_number, - 'episode_number': episode_number, - 'subtitles': subtitles, - 'age_limit': parse_age_limit(video_data.get('rating')), - } From 152f22920d73bb0dc24fa357d5904a8dd97a5bf6 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Fri, 1 Nov 2019 17:44:34 +0100 Subject: [PATCH 149/422] [wistia] reduce embed extraction false positives and support inline embeds(closes #22931) --- youtube_dl/extractor/wistia.py | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/wistia.py b/youtube_dl/extractor/wistia.py index fa142b974..0fbc888ec 100644 --- a/youtube_dl/extractor/wistia.py +++ b/youtube_dl/extractor/wistia.py @@ -12,7 +12,7 @@ from ..utils import ( class WistiaIE(InfoExtractor): - _VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/)(?P[a-z0-9]+)' + _VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/)(?P[a-z0-9]{10})' _API_URL = 'http://fast.wistia.com/embed/medias/%s.json' _IFRAME_URL = 'http://fast.wistia.net/embed/iframe/%s' @@ -43,25 +43,26 @@ class WistiaIE(InfoExtractor): 'only_matching': True, }] + # https://wistia.com/support/embed-and-share/video-on-your-website @staticmethod def _extract_url(webpage): match = re.search( - r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/iframe/.+?)\1', webpage) + r'<(?:meta[^>]+?content|(?:iframe|script)[^>]+?src)=["\'](?P(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/[a-z0-9]{10})', webpage) if match: return unescapeHTML(match.group('url')) - match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P[^"\']+)', webpage) - if match: - return 'wistia:%s' % match.group('id') - match = re.search( r'''(?sx) ]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*? - ]+class=(["']).*?\bwistia_async_(?P[a-z0-9]+)\b.*?\2 + ]+class=(["']).*?\bwistia_async_(?P[a-z0-9]{10})\b.*?\2 ''', webpage) if match: return 'wistia:%s' % match.group('id') + match = re.search(r'(?:data-wistia-?id=["\']|Wistia\.embed\(["\']|id=["\']wistia_)(?P[a-z0-9]{10})', webpage) + if match: + return 'wistia:%s' % match.group('id') + def _real_extract(self, url): video_id = self._match_id(url) From 4c95fcf9e8fa2ed113698d13df55df4aaecd8433 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Fri, 1 Nov 2019 21:16:47 +0100 Subject: [PATCH 150/422] [bambuser] remove extractor https://web.archive.org/web/20190808014227/https://go.bambuser.com/shutdown-announcement --- youtube_dl/extractor/bambuser.py | 142 ----------------------------- youtube_dl/extractor/extractors.py | 1 - 2 files changed, 143 deletions(-) delete mode 100644 youtube_dl/extractor/bambuser.py diff --git a/youtube_dl/extractor/bambuser.py b/youtube_dl/extractor/bambuser.py deleted file mode 100644 index 4400ff9c1..000000000 --- a/youtube_dl/extractor/bambuser.py +++ /dev/null @@ -1,142 +0,0 @@ -from __future__ import unicode_literals - -import re -import itertools - -from .common import InfoExtractor -from ..compat import compat_str -from ..utils import ( - ExtractorError, - float_or_none, - int_or_none, - sanitized_Request, - urlencode_postdata, -) - - -class BambuserIE(InfoExtractor): - IE_NAME = 'bambuser' - _VALID_URL = r'https?://bambuser\.com/v/(?P\d+)' - _API_KEY = '005f64509e19a868399060af746a00aa' - _LOGIN_URL = 'https://bambuser.com/user' - _NETRC_MACHINE = 'bambuser' - - _TEST = { - 'url': 'http://bambuser.com/v/4050584', - # MD5 seems to be flaky, see https://travis-ci.org/ytdl-org/youtube-dl/jobs/14051016#L388 - # 'md5': 'fba8f7693e48fd4e8641b3fd5539a641', - 'info_dict': { - 'id': '4050584', - 'ext': 'flv', - 'title': 'Education engineering days - lightning talks', - 'duration': 3741, - 'uploader': 'pixelversity', - 'uploader_id': '344706', - 'timestamp': 1382976692, - 'upload_date': '20131028', - 'view_count': int, - }, - 'params': { - # It doesn't respect the 'Range' header, it would download the whole video - # caused the travis builds to fail: https://travis-ci.org/ytdl-org/youtube-dl/jobs/14493845#L59 - 'skip_download': True, - }, - } - - def _login(self): - username, password = self._get_login_info() - if username is None: - return - - login_form = { - 'form_id': 'user_login', - 'op': 'Log in', - 'name': username, - 'pass': password, - } - - request = sanitized_Request( - self._LOGIN_URL, urlencode_postdata(login_form)) - request.add_header('Referer', self._LOGIN_URL) - response = self._download_webpage( - request, None, 'Logging in') - - login_error = self._html_search_regex( - r'(?s)
    (.+?)
    ', - response, 'login error', default=None) - if login_error: - raise ExtractorError( - 'Unable to login: %s' % login_error, expected=True) - - def _real_initialize(self): - self._login() - - def _real_extract(self, url): - video_id = self._match_id(url) - - info = self._download_json( - 'http://player-c.api.bambuser.com/getVideo.json?api_key=%s&vid=%s' - % (self._API_KEY, video_id), video_id) - - error = info.get('error') - if error: - raise ExtractorError( - '%s returned error: %s' % (self.IE_NAME, error), expected=True) - - result = info['result'] - - return { - 'id': video_id, - 'title': result['title'], - 'url': result['url'], - 'thumbnail': result.get('preview'), - 'duration': int_or_none(result.get('length')), - 'uploader': result.get('username'), - 'uploader_id': compat_str(result.get('owner', {}).get('uid')), - 'timestamp': int_or_none(result.get('created')), - 'fps': float_or_none(result.get('framerate')), - 'view_count': int_or_none(result.get('views_total')), - 'comment_count': int_or_none(result.get('comment_count')), - } - - -class BambuserChannelIE(InfoExtractor): - IE_NAME = 'bambuser:channel' - _VALID_URL = r'https?://bambuser\.com/channel/(?P.*?)(?:/|#|\?|$)' - # The maximum number we can get with each request - _STEP = 50 - _TEST = { - 'url': 'http://bambuser.com/channel/pixelversity', - 'info_dict': { - 'title': 'pixelversity', - }, - 'playlist_mincount': 60, - } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - user = mobj.group('user') - urls = [] - last_id = '' - for i in itertools.count(1): - req_url = ( - 'http://bambuser.com/xhr-api/index.php?username={user}' - '&sort=created&access_mode=0%2C1%2C2&limit={count}' - '&method=broadcast&format=json&vid_older_than={last}' - ).format(user=user, count=self._STEP, last=last_id) - req = sanitized_Request(req_url) - # Without setting this header, we wouldn't get any result - req.add_header('Referer', 'http://bambuser.com/channel/%s' % user) - data = self._download_json( - req, user, 'Downloading page %d' % i) - results = data['result'] - if not results: - break - last_id = results[-1]['vid'] - urls.extend(self.url_result(v['page'], 'Bambuser') for v in results) - - return { - '_type': 'playlist', - 'title': user, - 'entries': urls, - } diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index e9b59ce52..af3fff601 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -80,7 +80,6 @@ from .awaan import ( ) from .azmedien import AZMedienIE from .baidu import BaiduVideoIE -from .bambuser import BambuserIE, BambuserChannelIE from .bandcamp import BandcampIE, BandcampAlbumIE, BandcampWeeklyIE from .bbc import ( BBCCoUkIE, From 836bfcb54e4d1664815ebffb753a9dc7c9c7d72c Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sat, 2 Nov 2019 11:08:51 +0100 Subject: [PATCH 151/422] [flipagram] remove extractor --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/flipagram.py | 115 ----------------------------- 2 files changed, 116 deletions(-) delete mode 100644 youtube_dl/extractor/flipagram.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index af3fff601..33fb461a0 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -355,7 +355,6 @@ from .firsttv import FirstTVIE from .fivemin import FiveMinIE from .fivetv import FiveTVIE from .flickr import FlickrIE -from .flipagram import FlipagramIE from .folketinget import FolketingetIE from .footyroom import FootyRoomIE from .formula1 import Formula1IE diff --git a/youtube_dl/extractor/flipagram.py b/youtube_dl/extractor/flipagram.py deleted file mode 100644 index b7be40f1b..000000000 --- a/youtube_dl/extractor/flipagram.py +++ /dev/null @@ -1,115 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..compat import compat_str -from ..utils import ( - int_or_none, - float_or_none, - try_get, - unified_timestamp, -) - - -class FlipagramIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?flipagram\.com/f/(?P[^/?#&]+)' - _TEST = { - 'url': 'https://flipagram.com/f/nyvTSJMKId', - 'md5': '888dcf08b7ea671381f00fab74692755', - 'info_dict': { - 'id': 'nyvTSJMKId', - 'ext': 'mp4', - 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction', - 'description': 'md5:d55e32edc55261cae96a41fa85ff630e', - 'duration': 35.571, - 'timestamp': 1461244995, - 'upload_date': '20160421', - 'uploader': 'kitty juria', - 'uploader_id': 'sjuria101', - 'creator': 'kitty juria', - 'view_count': int, - 'like_count': int, - 'repost_count': int, - 'comment_count': int, - 'comments': list, - 'formats': 'mincount:2', - }, - } - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - video_data = self._parse_json( - self._search_regex( - r'window\.reactH2O\s*=\s*({.+});', webpage, 'video data'), - video_id) - - flipagram = video_data['flipagram'] - video = flipagram['video'] - - json_ld = self._search_json_ld(webpage, video_id, default={}) - title = json_ld.get('title') or flipagram['captionText'] - description = json_ld.get('description') or flipagram.get('captionText') - - formats = [{ - 'url': video['url'], - 'width': int_or_none(video.get('width')), - 'height': int_or_none(video.get('height')), - 'filesize': int_or_none(video_data.get('size')), - }] - - preview_url = try_get( - flipagram, lambda x: x['music']['track']['previewUrl'], compat_str) - if preview_url: - formats.append({ - 'url': preview_url, - 'ext': 'm4a', - 'vcodec': 'none', - }) - - self._sort_formats(formats) - - counts = flipagram.get('counts', {}) - user = flipagram.get('user', {}) - video_data = flipagram.get('video', {}) - - thumbnails = [{ - 'url': self._proto_relative_url(cover['url']), - 'width': int_or_none(cover.get('width')), - 'height': int_or_none(cover.get('height')), - 'filesize': int_or_none(cover.get('size')), - } for cover in flipagram.get('covers', []) if cover.get('url')] - - # Note that this only retrieves comments that are initially loaded. - # For videos with large amounts of comments, most won't be retrieved. - comments = [] - for comment in video_data.get('comments', {}).get(video_id, {}).get('items', []): - text = comment.get('comment') - if not text or not isinstance(text, list): - continue - comments.append({ - 'author': comment.get('user', {}).get('name'), - 'author_id': comment.get('user', {}).get('username'), - 'id': comment.get('id'), - 'text': text[0], - 'timestamp': unified_timestamp(comment.get('created')), - }) - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'duration': float_or_none(flipagram.get('duration'), 1000), - 'thumbnails': thumbnails, - 'timestamp': unified_timestamp(flipagram.get('iso8601Created')), - 'uploader': user.get('name'), - 'uploader_id': user.get('username'), - 'creator': user.get('name'), - 'view_count': int_or_none(counts.get('plays')), - 'like_count': int_or_none(counts.get('likes')), - 'repost_count': int_or_none(counts.get('reflips')), - 'comment_count': int_or_none(counts.get('comments')), - 'comments': comments, - 'formats': formats, - } From 79b35e7c15f4a285525b5ec52035ff0f8fc6150d Mon Sep 17 00:00:00 2001 From: geditorit <52565706+geditorit@users.noreply.github.com> Date: Sat, 2 Nov 2019 18:32:49 +0700 Subject: [PATCH 152/422] [gameone] Remove extractor (#21778) --- youtube_dl/extractor/extractors.py | 4 - youtube_dl/extractor/gameone.py | 134 ----------------------------- 2 files changed, 138 deletions(-) delete mode 100644 youtube_dl/extractor/gameone.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 33fb461a0..dce08e077 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -401,10 +401,6 @@ from .fusion import FusionIE from .fxnetworks import FXNetworksIE from .gaia import GaiaIE from .gameinformer import GameInformerIE -from .gameone import ( - GameOneIE, - GameOnePlaylistIE, -) from .gamespot import GameSpotIE from .gamestar import GameStarIE from .gaskrank import GaskrankIE diff --git a/youtube_dl/extractor/gameone.py b/youtube_dl/extractor/gameone.py deleted file mode 100644 index a07d69841..000000000 --- a/youtube_dl/extractor/gameone.py +++ /dev/null @@ -1,134 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..utils import ( - xpath_with_ns, - parse_iso8601, - float_or_none, - int_or_none, -) - -NAMESPACE_MAP = { - 'media': 'http://search.yahoo.com/mrss/', -} - -# URL prefix to download the mp4 files directly instead of streaming via rtmp -# Credits go to XBox-Maniac -# http://board.jdownloader.org/showpost.php?p=185835&postcount=31 -RAW_MP4_URL = 'http://cdn.riptide-mtvn.com/' - - -class GameOneIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?gameone\.de/tv/(?P\d+)' - _TESTS = [ - { - 'url': 'http://www.gameone.de/tv/288', - 'md5': '136656b7fb4c9cb4a8e2d500651c499b', - 'info_dict': { - 'id': '288', - 'ext': 'mp4', - 'title': 'Game One - Folge 288', - 'duration': 1238, - 'thumbnail': 'http://s3.gameone.de/gameone/assets/video_metas/teaser_images/000/643/636/big/640x360.jpg', - 'description': 'FIFA-Pressepokal 2014, Star Citizen, Kingdom Come: Deliverance, Project Cars, Schöner Trants Nerdquiz Folge 2 Runde 1', - 'age_limit': 16, - 'upload_date': '20140513', - 'timestamp': 1399980122, - } - }, - { - 'url': 'http://gameone.de/tv/220', - 'md5': '5227ca74c4ae6b5f74c0510a7c48839e', - 'info_dict': { - 'id': '220', - 'ext': 'mp4', - 'upload_date': '20120918', - 'description': 'Jet Set Radio HD, Tekken Tag Tournament 2, Source Filmmaker', - 'timestamp': 1347971451, - 'title': 'Game One - Folge 220', - 'duration': 896.62, - 'age_limit': 16, - } - } - - ] - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - og_video = self._og_search_video_url(webpage, secure=False) - description = self._html_search_meta('description', webpage) - age_limit = int( - self._search_regex( - r'age=(\d+)', - self._html_search_meta( - 'age-de-meta-label', - webpage), - 'age_limit', - '0')) - mrss_url = self._search_regex(r'mrss=([^&]+)', og_video, 'mrss') - - mrss = self._download_xml(mrss_url, video_id, 'Downloading mrss') - title = mrss.find('.//item/title').text - thumbnail = mrss.find('.//item/image').get('url') - timestamp = parse_iso8601(mrss.find('.//pubDate').text, delimiter=' ') - content = mrss.find(xpath_with_ns('.//media:content', NAMESPACE_MAP)) - content_url = content.get('url') - - content = self._download_xml( - content_url, - video_id, - 'Downloading media:content') - rendition_items = content.findall('.//rendition') - duration = float_or_none(rendition_items[0].get('duration')) - formats = [ - { - 'url': re.sub(r'.*/(r2)', RAW_MP4_URL + r'\1', r.find('./src').text), - 'width': int_or_none(r.get('width')), - 'height': int_or_none(r.get('height')), - 'tbr': int_or_none(r.get('bitrate')), - } - for r in rendition_items - ] - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': title, - 'thumbnail': thumbnail, - 'duration': duration, - 'formats': formats, - 'description': description, - 'age_limit': age_limit, - 'timestamp': timestamp, - } - - -class GameOnePlaylistIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?gameone\.de(?:/tv)?/?$' - IE_NAME = 'gameone:playlist' - _TEST = { - 'url': 'http://www.gameone.de/tv', - 'info_dict': { - 'title': 'GameOne', - }, - 'playlist_mincount': 294, - } - - def _real_extract(self, url): - webpage = self._download_webpage('http://www.gameone.de/tv', 'TV') - max_id = max(map(int, re.findall(r' Date: Sat, 2 Nov 2019 13:09:44 +0100 Subject: [PATCH 153/422] [keek] remove extractor --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/keek.py | 39 ------------------------------ 2 files changed, 40 deletions(-) delete mode 100644 youtube_dl/extractor/keek.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index dce08e077..08facf8d3 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -515,7 +515,6 @@ from .ketnet import KetnetIE from .khanacademy import KhanAcademyIE from .kickstarter import KickStarterIE from .kinopoisk import KinoPoiskIE -from .keek import KeekIE from .konserthusetplay import KonserthusetPlayIE from .kontrtube import KontrTubeIE from .krasview import KrasViewIE diff --git a/youtube_dl/extractor/keek.py b/youtube_dl/extractor/keek.py deleted file mode 100644 index 94a03d277..000000000 --- a/youtube_dl/extractor/keek.py +++ /dev/null @@ -1,39 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor - - -class KeekIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?keek\.com/keek/(?P\w+)' - IE_NAME = 'keek' - _TEST = { - 'url': 'https://www.keek.com/keek/NODfbab', - 'md5': '9b0636f8c0f7614afa4ea5e4c6e57e83', - 'info_dict': { - 'id': 'NODfbab', - 'ext': 'mp4', - 'title': 'md5:35d42050a3ece241d5ddd7fdcc6fd896', - 'uploader': 'ytdl', - 'uploader_id': 'eGT5bab', - }, - } - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - return { - 'id': video_id, - 'url': self._og_search_video_url(webpage), - 'ext': 'mp4', - 'title': self._og_search_description(webpage).strip(), - 'thumbnail': self._og_search_thumbnail(webpage), - 'uploader': self._search_regex( - r'data-username=(["\'])(?P.+?)\1', webpage, - 'uploader', fatal=False, group='uploader'), - 'uploader_id': self._search_regex( - r'data-user-id=(["\'])(?P.+?)\1', webpage, - 'uploader id', fatal=False, group='uploader_id'), - } From 5e36b63486794750aca0ee6b9b83f27abf6332dc Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sat, 2 Nov 2019 13:25:39 +0100 Subject: [PATCH 154/422] [iconosquare] remove extractor --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/iconosquare.py | 85 ----------------------------- 2 files changed, 86 deletions(-) delete mode 100644 youtube_dl/extractor/iconosquare.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 08facf8d3..dd5f68ca3 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -455,7 +455,6 @@ from .hungama import ( HungamaSongIE, ) from .hypem import HypemIE -from .iconosquare import IconosquareIE from .ign import ( IGNIE, OneUPIE, diff --git a/youtube_dl/extractor/iconosquare.py b/youtube_dl/extractor/iconosquare.py deleted file mode 100644 index a39f422e9..000000000 --- a/youtube_dl/extractor/iconosquare.py +++ /dev/null @@ -1,85 +0,0 @@ -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..utils import ( - int_or_none, - get_element_by_id, - remove_end, -) - - -class IconosquareIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?:iconosquare\.com|statigr\.am)/p/(?P[^/]+)' - _TEST = { - 'url': 'http://statigr.am/p/522207370455279102_24101272', - 'md5': '6eb93b882a3ded7c378ee1d6884b1814', - 'info_dict': { - 'id': '522207370455279102_24101272', - 'ext': 'mp4', - 'title': 'Instagram photo by @aguynamedpatrick (Patrick Janelle)', - 'description': 'md5:644406a9ec27457ed7aa7a9ebcd4ce3d', - 'timestamp': 1376471991, - 'upload_date': '20130814', - 'uploader': 'aguynamedpatrick', - 'uploader_id': '24101272', - 'comment_count': int, - 'like_count': int, - }, - } - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - media = self._parse_json( - get_element_by_id('mediaJson', webpage), - video_id) - - formats = [{ - 'url': f['url'], - 'format_id': format_id, - 'width': int_or_none(f.get('width')), - 'height': int_or_none(f.get('height')) - } for format_id, f in media['videos'].items()] - self._sort_formats(formats) - - title = remove_end(self._og_search_title(webpage), ' - via Iconosquare') - - timestamp = int_or_none(media.get('created_time') or media.get('caption', {}).get('created_time')) - description = media.get('caption', {}).get('text') - - uploader = media.get('user', {}).get('username') - uploader_id = media.get('user', {}).get('id') - - comment_count = int_or_none(media.get('comments', {}).get('count')) - like_count = int_or_none(media.get('likes', {}).get('count')) - - thumbnails = [{ - 'url': t['url'], - 'id': thumbnail_id, - 'width': int_or_none(t.get('width')), - 'height': int_or_none(t.get('height')) - } for thumbnail_id, t in media.get('images', {}).items()] - - comments = [{ - 'id': comment.get('id'), - 'text': comment['text'], - 'timestamp': int_or_none(comment.get('created_time')), - 'author': comment.get('from', {}).get('full_name'), - 'author_id': comment.get('from', {}).get('username'), - } for comment in media.get('comments', {}).get('data', []) if 'text' in comment] - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'thumbnails': thumbnails, - 'timestamp': timestamp, - 'uploader': uploader, - 'uploader_id': uploader_id, - 'comment_count': comment_count, - 'like_count': like_count, - 'formats': formats, - 'comments': comments, - } From e54924c46fac6a9745868424dc14011da2572178 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sat, 2 Nov 2019 18:13:31 +0100 Subject: [PATCH 155/422] [stv] fix extraction(closes #22928) --- youtube_dl/extractor/stv.py | 89 +++++++++++++------------------------ 1 file changed, 31 insertions(+), 58 deletions(-) diff --git a/youtube_dl/extractor/stv.py b/youtube_dl/extractor/stv.py index ccb074cd4..bae8b71f4 100644 --- a/youtube_dl/extractor/stv.py +++ b/youtube_dl/extractor/stv.py @@ -4,15 +4,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_parse_qs, - compat_urllib_parse_urlparse -) from ..utils import ( - extract_attributes, + compat_str, float_or_none, int_or_none, - str_or_none, ) @@ -20,20 +15,20 @@ class STVPlayerIE(InfoExtractor): IE_NAME = 'stv:player' _VALID_URL = r'https?://player\.stv\.tv/(?Pepisode|video)/(?P[a-z0-9]{4})' _TEST = { - 'url': 'https://player.stv.tv/video/7srz/victoria/interview-with-the-cast-ahead-of-new-victoria/', - 'md5': '2ad867d4afd641fa14187596e0fbc91b', + 'url': 'https://player.stv.tv/video/4gwd/emmerdale/60-seconds-on-set-with-laura-norton/', + 'md5': '5adf9439c31d554f8be0707c7abe7e0a', 'info_dict': { - 'id': '6016487034001', + 'id': '5333973339001', 'ext': 'mp4', - 'upload_date': '20190321', - 'title': 'Interview with the cast ahead of new Victoria', - 'description': 'Nell Hudson and Lily Travers tell us what to expect in the new season of Victoria.', - 'timestamp': 1553179628, + 'upload_date': '20170301', + 'title': '60 seconds on set with Laura Norton', + 'description': "How many questions can Laura - a.k.a Kerry Wyatt - answer in 60 seconds? Let\'s find out!", + 'timestamp': 1488388054, 'uploader_id': '1486976045', }, 'skip': 'this resource is unavailable outside of the UK', } - _PUBLISHER_ID = '1486976045' + BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1486976045/default_default/index.html?videoId=%s' _PTYPE_MAP = { 'episode': 'episodes', 'video': 'shortform', @@ -41,54 +36,32 @@ class STVPlayerIE(InfoExtractor): def _real_extract(self, url): ptype, video_id = re.match(self._VALID_URL, url).groups() - webpage = self._download_webpage(url, video_id) + resp = self._download_json( + 'https://player.api.stv.tv/v1/%s/%s' % (self._PTYPE_MAP[ptype], video_id), + video_id) - qs = compat_parse_qs(compat_urllib_parse_urlparse(self._search_regex( - r'itemprop="embedURL"[^>]+href="([^"]+)', - webpage, 'embed URL', default=None)).query) - publisher_id = qs.get('publisherID', [None])[0] or self._PUBLISHER_ID + result = resp['results'] + video = result['video'] + video_id = compat_str(video['id']) - player_attr = extract_attributes(self._search_regex( - r'(<[^>]+class="bcplayer"[^>]+>)', webpage, 'player', default=None)) or {} + subtitles = {} + _subtitles = result.get('_subtitles') or {} + for ext, sub_url in _subtitles.items(): + subtitles.setdefault('en', []).append({ + 'ext': 'vtt' if ext == 'webvtt' else ext, + 'url': sub_url, + }) - info = {} - duration = ref_id = series = video_id = None - api_ref_id = player_attr.get('data-player-api-refid') - if api_ref_id: - resp = self._download_json( - 'https://player.api.stv.tv/v1/%s/%s' % (self._PTYPE_MAP[ptype], api_ref_id), - api_ref_id, fatal=False) - if resp: - result = resp.get('results') or {} - video = result.get('video') or {} - video_id = str_or_none(video.get('id')) - ref_id = video.get('guid') - duration = video.get('length') - programme = result.get('programme') or {} - series = programme.get('name') or programme.get('shortName') - subtitles = {} - _subtitles = result.get('_subtitles') or {} - for ext, sub_url in _subtitles.items(): - subtitles.setdefault('en', []).append({ - 'ext': 'vtt' if ext == 'webvtt' else ext, - 'url': sub_url, - }) - info.update({ - 'description': result.get('summary'), - 'subtitles': subtitles, - 'view_count': int_or_none(result.get('views')), - }) - if not video_id: - video_id = qs.get('videoId', [None])[0] or self._search_regex( - r' Date: Sat, 2 Nov 2019 22:33:51 +0100 Subject: [PATCH 156/422] [bellmedia] add support for marilyn.ca videos(#22193) --- youtube_dl/extractor/bellmedia.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/bellmedia.py b/youtube_dl/extractor/bellmedia.py index f36a2452d..485173774 100644 --- a/youtube_dl/extractor/bellmedia.py +++ b/youtube_dl/extractor/bellmedia.py @@ -22,7 +22,8 @@ class BellMediaIE(InfoExtractor): bravo| mtv| space| - etalk + etalk| + marilyn )\.ca| much\.com )/.*?(?:\bvid(?:eoid)?=|-vid|~|%7E|/(?:episode)?)(?P[0-9]{6,})''' @@ -70,6 +71,7 @@ class BellMediaIE(InfoExtractor): 'animalplanet': 'aniplan', 'etalk': 'ctv', 'bnnbloomberg': 'bnn', + 'marilyn': 'ctv_marilyn', } def _real_extract(self, url): From 564275e26fc963fb920236e37c6c19e8e2b046f0 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sun, 3 Nov 2019 22:04:03 +0100 Subject: [PATCH 157/422] [telegraaf] fix extraction --- youtube_dl/extractor/telegraaf.py | 75 ++++++++++++++++++------------- 1 file changed, 43 insertions(+), 32 deletions(-) diff --git a/youtube_dl/extractor/telegraaf.py b/youtube_dl/extractor/telegraaf.py index 0f576c1ab..2dc020537 100644 --- a/youtube_dl/extractor/telegraaf.py +++ b/youtube_dl/extractor/telegraaf.py @@ -4,21 +4,25 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( determine_ext, - remove_end, + int_or_none, + parse_iso8601, + try_get, ) class TelegraafIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?telegraaf\.nl/tv/(?:[^/]+/)+(?P\d+)/[^/]+\.html' + _VALID_URL = r'https?://(?:www\.)?telegraaf\.nl/video/(?P\d+)' _TEST = { - 'url': 'http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html', + 'url': 'https://www.telegraaf.nl/video/734366489/historisch-scheepswrak-slaat-na-100-jaar-los', 'info_dict': { - 'id': '24353229', + 'id': 'gaMItuoSeUg2', 'ext': 'mp4', - 'title': 'Tikibad ontruimd wegens brand', - 'description': 'md5:05ca046ff47b931f9b04855015e163a4', - 'thumbnail': r're:^https?://.*\.jpg$', - 'duration': 33, + 'title': 'Historisch scheepswrak slaat na 100 jaar los', + 'description': 'md5:6f53b7c4f55596722ac24d6c0ec00cfb', + 'thumbnail': r're:^https?://.*\.jpg', + 'duration': 55, + 'timestamp': 1572805527, + 'upload_date': '20191103', }, 'params': { # m3u8 download @@ -27,23 +31,30 @@ class TelegraafIE(InfoExtractor): } def _real_extract(self, url): - video_id = self._match_id(url) + article_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + video_id = self._download_json( + 'https://www.telegraaf.nl/graphql', article_id, query={ + 'query': '''{ + article(uid: %s) { + videos { + videoId + } + } +}''' % article_id, + })['data']['article']['videos'][0]['videoId'] - player_url = self._html_search_regex( - r']+src="([^"]+")', webpage, 'player URL') - player_page = self._download_webpage( - player_url, video_id, note='Download player webpage') - playlist_url = self._search_regex( - r'playlist\s*:\s*"([^"]+)"', player_page, 'playlist URL') - playlist_data = self._download_json(playlist_url, video_id) + item = self._download_json( + 'https://content.tmgvideo.nl/playlist/item=%s/playlist.json' % video_id, + video_id)['items'][0] + title = item['title'] - item = playlist_data['items'][0] formats = [] - locations = item['locations'] + locations = item.get('locations') or {} for location in locations.get('adaptive', []): - manifest_url = location['src'] + manifest_url = location.get('src') + if not manifest_url: + continue ext = determine_ext(manifest_url) if ext == 'm3u8': formats.extend(self._extract_m3u8_formats( @@ -54,25 +65,25 @@ class TelegraafIE(InfoExtractor): else: self.report_warning('Unknown adaptive format %s' % ext) for location in locations.get('progressive', []): + src = try_get(location, lambda x: x['sources'][0]['src']) + if not src: + continue + label = location.get('label') formats.append({ - 'url': location['sources'][0]['src'], - 'width': location.get('width'), - 'height': location.get('height'), - 'format_id': 'http-%s' % location['label'], + 'url': src, + 'width': int_or_none(location.get('width')), + 'height': int_or_none(location.get('height')), + 'format_id': 'http' + ('-%s' % label if label else ''), }) self._sort_formats(formats) - title = remove_end(self._og_search_title(webpage), ' - VIDEO') - description = self._og_search_description(webpage) - duration = item.get('duration') - thumbnail = item.get('poster') - return { 'id': video_id, 'title': title, - 'description': description, + 'description': item.get('description'), 'formats': formats, - 'duration': duration, - 'thumbnail': thumbnail, + 'duration': int_or_none(item.get('duration')), + 'thumbnail': item.get('poster'), + 'timestamp': parse_iso8601(item.get('datecreated'), ' '), } From a6e6673e825f6225c3a316b164ddca03fd20b5d2 Mon Sep 17 00:00:00 2001 From: Manu Cornet Date: Sun, 3 Nov 2019 21:23:27 +0000 Subject: [PATCH 158/422] [README.md] Also read permission to the binary in how to update section (#22903) --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index c39b13616..01f975958 100644 --- a/README.md +++ b/README.md @@ -752,8 +752,8 @@ As a last resort, you can also uninstall the version installed by your package m Afterwards, simply follow [our manual installation instructions](https://ytdl-org.github.io/youtube-dl/download.html): ``` -sudo wget https://yt-dl.org/latest/youtube-dl -O /usr/local/bin/youtube-dl -sudo chmod a+x /usr/local/bin/youtube-dl +sudo wget https://yt-dl.org/downloads/latest/youtube-dl -O /usr/local/bin/youtube-dl +sudo chmod a+rx /usr/local/bin/youtube-dl hash -r ``` From ef382405c6dc79d2b7e3f81a527232941e2c0b2d Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 4 Nov 2019 02:01:01 +0100 Subject: [PATCH 159/422] [mediaset] extract unprotected M3U and MPD manifests(closes #17204) --- youtube_dl/extractor/mediaset.py | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/mediaset.py b/youtube_dl/extractor/mediaset.py index df3748798..fcbc064ff 100644 --- a/youtube_dl/extractor/mediaset.py +++ b/youtube_dl/extractor/mediaset.py @@ -62,7 +62,6 @@ class MediasetIE(ThePlatformBaseIE): 'uploader': 'Canale 5', 'uploader_id': 'C5', }, - 'expected_warnings': ['HTTP Error 403: Forbidden'], }, { # clip 'url': 'https://www.mediasetplay.mediaset.it/video/gogglebox/un-grande-classico-della-commedia-sexy_FAFU000000661680', @@ -109,6 +108,11 @@ class MediasetIE(ThePlatformBaseIE): entries.append(embed_url) return entries + def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None, transform_rtmp_url=None): + for video in smil.findall(self._xpath_ns('.//video', namespace)): + video.attrib['src'] = re.sub(r'(https?://vod05)t(-mediaset-it\.akamaized\.net/.+?.mpd)\?.+', r'\1\2', video.attrib['src']) + return super()._parse_smil_formats(smil, smil_url, video_id, namespace, f4m_params, transform_rtmp_url) + def _real_extract(self, url): guid = self._match_id(url) tp_path = 'PR1GhC/media/guid/2702976343/' + guid @@ -118,14 +122,15 @@ class MediasetIE(ThePlatformBaseIE): subtitles = {} first_e = None for asset_type in ('SD', 'HD'): - for f in ('MPEG4', 'MPEG-DASH', 'M3U', 'ISM'): + # TODO: fixup ISM+none manifest URLs + for f in ('MPEG4', 'MPEG-DASH+none', 'M3U+none'): try: tp_formats, tp_subtitles = self._extract_theplatform_smil( update_url_query('http://link.theplatform.%s/s/%s' % (self._TP_TLD, tp_path), { 'mbr': 'true', 'formats': f, 'assetTypes': asset_type, - }), guid, 'Downloading %s %s SMIL data' % (f, asset_type)) + }), guid, 'Downloading %s %s SMIL data' % (f.split('+')[0], asset_type)) except ExtractorError as e: if not first_e: first_e = e From bf45295c5387d0d90b97ca34d377cdaa07c71bcb Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 4 Nov 2019 11:13:14 +0100 Subject: [PATCH 160/422] [mediaset] relax URL guid matching(closes #18352) --- youtube_dl/extractor/mediaset.py | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/mediaset.py b/youtube_dl/extractor/mediaset.py index fcbc064ff..f976506f4 100644 --- a/youtube_dl/extractor/mediaset.py +++ b/youtube_dl/extractor/mediaset.py @@ -27,7 +27,7 @@ class MediasetIE(ThePlatformBaseIE): (?:video|on-demand)/(?:[^/]+/)+[^/]+_| player/index\.html\?.*?\bprogramGuid= ) - )(?P[0-9A-Z]{16}) + )(?P[0-9A-Z]{16,}) ''' _TESTS = [{ # full episode @@ -77,6 +77,18 @@ class MediasetIE(ThePlatformBaseIE): }, { 'url': 'mediaset:FAFU000000665924', 'only_matching': True, + }, { + 'url': 'https://www.mediasetplay.mediaset.it/video/mediasethaacuoreilfuturo/palmieri-alicudi-lisola-dei-tre-bambini-felici--un-decreto-per-alicudi-e-tutte-le-microscuole_FD00000000102295', + 'only_matching': True, + }, { + 'url': 'https://www.mediasetplay.mediaset.it/video/cherryseason/anticipazioni-degli-episodi-del-23-ottobre_F306837101005C02', + 'only_matching': True, + }, { + 'url': 'https://www.mediasetplay.mediaset.it/video/tg5/ambiente-onda-umana-per-salvare-il-pianeta_F309453601079D01', + 'only_matching': True, + }, { + 'url': 'https://www.mediasetplay.mediaset.it/video/grandefratellovip/benedetta-una-doccia-gelata_F309344401044C135', + 'only_matching': True, }] @staticmethod From e452345fc5cee5e79d2cad6be575da563987a4ff Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 4 Nov 2019 15:43:52 +0100 Subject: [PATCH 161/422] [jamendo] improve extraction - fix album extraction(closes #18564) - improve metadata extraction(closes #18565)(closes #21379) --- youtube_dl/extractor/jamendo.py | 162 +++++++++++++++++++------------- 1 file changed, 99 insertions(+), 63 deletions(-) diff --git a/youtube_dl/extractor/jamendo.py b/youtube_dl/extractor/jamendo.py index c21827618..12e21eb6f 100644 --- a/youtube_dl/extractor/jamendo.py +++ b/youtube_dl/extractor/jamendo.py @@ -1,38 +1,26 @@ # coding: utf-8 from __future__ import unicode_literals -import re +import hashlib +import random -from ..compat import compat_urlparse +from ..compat import compat_str from .common import InfoExtractor -from ..utils import parse_duration +from ..utils import ( + clean_html, + int_or_none, + try_get, +) -class JamendoBaseIE(InfoExtractor): - def _extract_meta(self, webpage, fatal=True): - title = self._og_search_title( - webpage, default=None) or self._search_regex( - r'([^<]+)', webpage, - 'title', default=None) - if title: - title = self._search_regex( - r'(.+?)\s*\|\s*Jamendo Music', title, 'title', default=None) - if not title: - title = self._html_search_meta( - 'name', webpage, 'title', fatal=fatal) - mobj = re.search(r'(.+) - (.+)', title or '') - artist, second = mobj.groups() if mobj else [None] * 2 - return title, artist, second - - -class JamendoIE(JamendoBaseIE): +class JamendoIE(InfoExtractor): _VALID_URL = r'''(?x) https?:// (?: licensing\.jamendo\.com/[^/]+| (?:www\.)?jamendo\.com ) - /track/(?P<id>[0-9]+)/(?P<display_id>[^/?#&]+) + /track/(?P<id>[0-9]+)(?:/(?P<display_id>[^/?#&]+))? ''' _TESTS = [{ 'url': 'https://www.jamendo.com/track/196219/stories-from-emona-i', @@ -45,7 +33,9 @@ class JamendoIE(JamendoBaseIE): 'artist': 'Maya Filipič', 'track': 'Stories from Emona I', 'duration': 210, - 'thumbnail': r're:^https?://.*\.jpg' + 'thumbnail': r're:^https?://.*\.jpg', + 'timestamp': 1217438117, + 'upload_date': '20080730', } }, { 'url': 'https://licensing.jamendo.com/en/track/1496667/energetic-rock', @@ -53,15 +43,19 @@ class JamendoIE(JamendoBaseIE): }] def _real_extract(self, url): - mobj = self._VALID_URL_RE.match(url) - track_id = mobj.group('id') - display_id = mobj.group('display_id') - - webpage = self._download_webpage( - 'https://www.jamendo.com/track/%s/%s' % (track_id, display_id), - display_id) - - title, artist, track = self._extract_meta(webpage) + track_id, display_id = self._VALID_URL_RE.match(url).groups() + webpage = self._download_webpage(url, track_id) + models = self._parse_json(self._html_search_regex( + r"data-bundled-models='([^']+)", + webpage, 'bundled models'), track_id) + track = models['track']['models'][0] + title = track_name = track['name'] + get_model = lambda x: try_get(models, lambda y: y[x]['models'][0], dict) or {} + artist = get_model('artist') + artist_name = artist.get('name') + if artist_name: + title = '%s - %s' % (artist_name, title) + album = get_model('album') formats = [{ 'url': 'https://%s.jamendo.com/?trackid=%s&format=%s&from=app-97dab294' @@ -77,31 +71,58 @@ class JamendoIE(JamendoBaseIE): ))] self._sort_formats(formats) - thumbnail = self._html_search_meta( - 'image', webpage, 'thumbnail', fatal=False) - duration = parse_duration(self._search_regex( - r'<span[^>]+itemprop=["\']duration["\'][^>]+content=["\'](.+?)["\']', - webpage, 'duration', fatal=False)) + urls = [] + thumbnails = [] + for _, covers in track.get('cover', {}).items(): + for cover_id, cover_url in covers.items(): + if not cover_url or cover_url in urls: + continue + urls.append(cover_url) + size = int_or_none(cover_id.lstrip('size')) + thumbnails.append({ + 'id': cover_id, + 'url': cover_url, + 'width': size, + 'height': size, + }) + + tags = [] + for tag in track.get('tags', []): + tag_name = tag.get('name') + if not tag_name: + continue + tags.append(tag_name) + + stats = track.get('stats') or {} return { 'id': track_id, 'display_id': display_id, - 'thumbnail': thumbnail, + 'thumbnails': thumbnails, 'title': title, - 'duration': duration, - 'artist': artist, - 'track': track, - 'formats': formats + 'description': track.get('description'), + 'duration': int_or_none(track.get('duration')), + 'artist': artist_name, + 'track': track_name, + 'album': album.get('name'), + 'formats': formats, + 'license': '-'.join(track.get('licenseCC', [])) or None, + 'timestamp': int_or_none(track.get('dateCreated')), + 'view_count': int_or_none(stats.get('listenedAll')), + 'like_count': int_or_none(stats.get('favorited')), + 'average_rating': int_or_none(stats.get('averageNote')), + 'tags': tags, } -class JamendoAlbumIE(JamendoBaseIE): - _VALID_URL = r'https?://(?:www\.)?jamendo\.com/album/(?P<id>[0-9]+)/(?P<display_id>[\w-]+)' +class JamendoAlbumIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?jamendo\.com/album/(?P<id>[0-9]+)' _TEST = { 'url': 'https://www.jamendo.com/album/121486/duck-on-cover', 'info_dict': { 'id': '121486', - 'title': 'Shearer - Duck On Cover' + 'title': 'Duck On Cover', + 'description': 'md5:c2920eaeef07d7af5b96d7c64daf1239', }, 'playlist': [{ 'md5': 'e1a2fcb42bda30dfac990212924149a8', @@ -111,6 +132,8 @@ class JamendoAlbumIE(JamendoBaseIE): 'title': 'Shearer - Warmachine', 'artist': 'Shearer', 'track': 'Warmachine', + 'timestamp': 1368089771, + 'upload_date': '20130509', } }, { 'md5': '1f358d7b2f98edfe90fd55dac0799d50', @@ -120,6 +143,8 @@ class JamendoAlbumIE(JamendoBaseIE): 'title': 'Shearer - Without Your Ghost', 'artist': 'Shearer', 'track': 'Without Your Ghost', + 'timestamp': 1368089771, + 'upload_date': '20130509', } }], 'params': { @@ -127,24 +152,35 @@ class JamendoAlbumIE(JamendoBaseIE): } } + def _call_api(self, resource, resource_id): + path = '/api/%ss' % resource + rand = compat_str(random.random()) + return self._download_json( + 'https://www.jamendo.com' + path, resource_id, query={ + 'id[]': resource_id, + }, headers={ + 'X-Jam-Call': '$%s*%s~' % (hashlib.sha1((path + rand).encode()).hexdigest(), rand) + })[0] + def _real_extract(self, url): - mobj = self._VALID_URL_RE.match(url) - album_id = mobj.group('id') + album_id = self._match_id(url) + album = self._call_api('album', album_id) + album_name = album.get('name') - webpage = self._download_webpage(url, mobj.group('display_id')) + entries = [] + for track in album.get('tracks', []): + track_id = track.get('id') + if not track_id: + continue + track_id = compat_str(track_id) + entries.append({ + '_type': 'url_transparent', + 'url': 'https://www.jamendo.com/track/' + track_id, + 'ie_key': JamendoIE.ie_key(), + 'id': track_id, + 'album': album_name, + }) - title, artist, album = self._extract_meta(webpage, fatal=False) - - entries = [{ - '_type': 'url_transparent', - 'url': compat_urlparse.urljoin(url, m.group('path')), - 'ie_key': JamendoIE.ie_key(), - 'id': self._search_regex( - r'/track/(\d+)', m.group('path'), 'track id', default=None), - 'artist': artist, - 'album': album, - } for m in re.finditer( - r'<a[^>]+href=(["\'])(?P<path>(?:(?!\1).)+)\1[^>]+class=["\'][^>]*js-trackrow-albumpage-link', - webpage)] - - return self.playlist_result(entries, album_id, title) + return self.playlist_result( + entries, album_id, album_name, + clean_html(try_get(album, lambda x: x['description']['en'], compat_str))) From 2349255abdf822e0bb9508d510db926cae777f8c Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Mon, 4 Nov 2019 15:51:44 +0100 Subject: [PATCH 162/422] [jamendo] restore track url modification --- youtube_dl/extractor/jamendo.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/jamendo.py b/youtube_dl/extractor/jamendo.py index 12e21eb6f..490efa8fb 100644 --- a/youtube_dl/extractor/jamendo.py +++ b/youtube_dl/extractor/jamendo.py @@ -44,7 +44,8 @@ class JamendoIE(InfoExtractor): def _real_extract(self, url): track_id, display_id = self._VALID_URL_RE.match(url).groups() - webpage = self._download_webpage(url, track_id) + webpage = self._download_webpage( + 'https://www.jamendo.com/track/' + track_id, track_id) models = self._parse_json(self._html_search_regex( r"data-bundled-models='([^']+)", webpage, 'bundled models'), track_id) From 3e4908360417bc29e1446bfa85145193fa2c8462 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Mon, 4 Nov 2019 20:05:27 +0100 Subject: [PATCH 163/422] [myspass] fix video URL extraction and improve metadata extraction(closes #22448) --- youtube_dl/extractor/myspass.py | 75 +++++++++++++-------------------- 1 file changed, 29 insertions(+), 46 deletions(-) diff --git a/youtube_dl/extractor/myspass.py b/youtube_dl/extractor/myspass.py index 2afe535b5..db7ebc94c 100644 --- a/youtube_dl/extractor/myspass.py +++ b/youtube_dl/extractor/myspass.py @@ -1,73 +1,56 @@ +# coding: utf-8 from __future__ import unicode_literals -import os.path + +import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse_urlparse, -) +from ..compat import compat_str from ..utils import ( - ExtractorError, + int_or_none, + parse_duration, + xpath_text, ) class MySpassIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?myspass\.de/.*' + _VALID_URL = r'https?://(?:www\.)?myspass\.de/([^/]+/)*(?P<id>\d+)' _TEST = { 'url': 'http://www.myspass.de/myspass/shows/tvshows/absolute-mehrheit/Absolute-Mehrheit-vom-17022013-Die-Highlights-Teil-2--/11741/', 'md5': '0b49f4844a068f8b33f4b7c88405862b', 'info_dict': { 'id': '11741', 'ext': 'mp4', - 'description': 'Wer kann in die Fu\u00dfstapfen von Wolfgang Kubicki treten und die Mehrheit der Zuschauer hinter sich versammeln? Wird vielleicht sogar die Absolute Mehrheit geknackt und der Jackpot von 200.000 Euro mit nach Hause genommen?', - 'title': 'Absolute Mehrheit vom 17.02.2013 - Die Highlights, Teil 2', + 'description': 'Wer kann in die Fußstapfen von Wolfgang Kubicki treten und die Mehrheit der Zuschauer hinter sich versammeln? Wird vielleicht sogar die Absolute Mehrheit geknackt und der Jackpot von 200.000 Euro mit nach Hause genommen?', + 'title': '17.02.2013 - Die Highlights, Teil 2', }, } def _real_extract(self, url): - META_DATA_URL_TEMPLATE = 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=%s' + video_id = self._match_id(url) - # video id is the last path element of the URL - # usually there is a trailing slash, so also try the second but last - url_path = compat_urllib_parse_urlparse(url).path - url_parent_path, video_id = os.path.split(url_path) - if not video_id: - _, video_id = os.path.split(url_parent_path) - - # get metadata - metadata_url = META_DATA_URL_TEMPLATE % video_id metadata = self._download_xml( - metadata_url, video_id, transform_source=lambda s: s.strip()) + 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=' + video_id, + video_id) - # extract values from metadata - url_flv_el = metadata.find('url_flv') - if url_flv_el is None: - raise ExtractorError('Unable to extract download url') - video_url = url_flv_el.text - title_el = metadata.find('title') - if title_el is None: - raise ExtractorError('Unable to extract title') - title = title_el.text - format_id_el = metadata.find('format_id') - if format_id_el is None: - format = 'mp4' - else: - format = format_id_el.text - description_el = metadata.find('description') - if description_el is not None: - description = description_el.text - else: - description = None - imagePreview_el = metadata.find('imagePreview') - if imagePreview_el is not None: - thumbnail = imagePreview_el.text - else: - thumbnail = None + title = xpath_text(metadata, 'title', fatal=True) + video_url = xpath_text(metadata, 'url_flv', 'download url', True) + video_id_int = int(video_id) + for group in re.search(r'/myspass2009/\d+/(\d+)/(\d+)/(\d+)/', video_url).groups(): + group_int = int(group) + if group_int > video_id_int: + video_url = video_url.replace( + group, compat_str(group_int // video_id_int)) return { 'id': video_id, 'url': video_url, 'title': title, - 'format': format, - 'thumbnail': thumbnail, - 'description': description, + 'thumbnail': xpath_text(metadata, 'imagePreview'), + 'description': xpath_text(metadata, 'description'), + 'duration': parse_duration(xpath_text(metadata, 'duration')), + 'series': xpath_text(metadata, 'format'), + 'season_number': int_or_none(xpath_text(metadata, 'season')), + 'season_id': xpath_text(metadata, 'season_id'), + 'episode': title, + 'episode_number': int_or_none(xpath_text(metadata, 'episode')), } From c69e71733d9619cb1a2bee769b9a381b52901de3 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Mon, 4 Nov 2019 22:21:00 +0100 Subject: [PATCH 164/422] [msn] add support for Vidible and AOL embeds(closes #22195)(closes #22227) --- youtube_dl/extractor/msn.py | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/youtube_dl/extractor/msn.py b/youtube_dl/extractor/msn.py index 0460cf4d5..0c3813dda 100644 --- a/youtube_dl/extractor/msn.py +++ b/youtube_dl/extractor/msn.py @@ -41,6 +41,14 @@ class MSNIE(InfoExtractor): }, { 'url': 'http://www.msn.com/en-ae/entertainment/bollywood/watch-how-salman-khan-reacted-when-asked-if-he-would-apologize-for-his-‘raped-woman’-comment/vi-AAhvzW6', 'only_matching': True, + }, { + # Vidible(AOL) Embed + 'url': 'https://www.msn.com/en-us/video/animals/yellowstone-park-staffers-catch-deer-engaged-in-behavior-they-cant-explain/vi-AAGfdg1', + 'only_matching': True, + }, { + # Dailymotion Embed + 'url': 'https://www.msn.com/es-ve/entretenimiento/watch/winston-salem-paire-refait-des-siennes-en-perdant-sa-raquette-au-service/vp-AAG704L', + 'only_matching': True, }] def _real_extract(self, url): @@ -61,6 +69,18 @@ class MSNIE(InfoExtractor): webpage, 'error', group='error')) raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True) + player_name = video.get('playerName') + if player_name: + provider_id = video.get('providerId') + if provider_id: + if player_name == 'AOL': + return self.url_result( + 'aol-video:' + provider_id, 'Aol', provider_id) + elif player_name == 'Dailymotion': + return self.url_result( + 'https://www.dailymotion.com/video/' + provider_id, + 'Dailymotion', provider_id) + title = video['title'] formats = [] From 20218040db2b1e063191cc470ce403d35d394e2a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 5 Nov 2019 05:21:16 +0700 Subject: [PATCH 165/422] [scte] Add extractor (closes #22975) --- youtube_dl/extractor/extractors.py | 4 + youtube_dl/extractor/scte.py | 144 +++++++++++++++++++++++++++++ 2 files changed, 148 insertions(+) create mode 100644 youtube_dl/extractor/scte.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index dd5f68ca3..9f43b284d 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -980,6 +980,10 @@ from .sbs import SBSIE from .screencast import ScreencastIE from .screencastomatic import ScreencastOMaticIE from .scrippsnetworks import ScrippsNetworksWatchIE +from .scte import ( + SCTEIE, + SCTECourseIE, +) from .seeker import SeekerIE from .senateisvp import SenateISVPIE from .sendtonews import SendtoNewsIE diff --git a/youtube_dl/extractor/scte.py b/youtube_dl/extractor/scte.py new file mode 100644 index 000000000..ca1de63b6 --- /dev/null +++ b/youtube_dl/extractor/scte.py @@ -0,0 +1,144 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + decode_packed_codes, + ExtractorError, + urlencode_postdata, +) + + +class SCTEBaseIE(InfoExtractor): + _LOGIN_URL = 'https://www.scte.org/SCTE/Sign_In.aspx' + _NETRC_MACHINE = 'scte' + + def _real_initialize(self): + self._login() + + def _login(self): + username, password = self._get_login_info() + if username is None: + return + + login_popup = self._download_webpage( + self._LOGIN_URL, None, 'Downloading login popup') + + def is_logged(webpage): + return any(re.search(p, webpage) for p in ( + r'class=["\']welcome\b', r'>Sign Out<')) + + # already logged in + if is_logged(login_popup): + return + + login_form = self._hidden_inputs(login_popup) + + login_form.update({ + 'ctl01$TemplateBody$WebPartManager1$gwpciNewContactSignInCommon$ciNewContactSignInCommon$signInUserName': username, + 'ctl01$TemplateBody$WebPartManager1$gwpciNewContactSignInCommon$ciNewContactSignInCommon$signInPassword': password, + 'ctl01$TemplateBody$WebPartManager1$gwpciNewContactSignInCommon$ciNewContactSignInCommon$RememberMe': 'on', + }) + + response = self._download_webpage( + self._LOGIN_URL, None, 'Logging in', + data=urlencode_postdata(login_form)) + + if '|pageRedirect|' not in response and not is_logged(response): + error = self._html_search_regex( + r'(?s)<[^>]+class=["\']AsiError["\'][^>]*>(.+?)</', + response, 'error message', default=None) + if error: + raise ExtractorError('Unable to login: %s' % error, expected=True) + raise ExtractorError('Unable to log in') + + +class SCTEIE(SCTEBaseIE): + _VALID_URL = r'https?://learning\.scte\.org/mod/scorm/view\.php?.*?\bid=(?P<id>\d+)' + _TESTS = [{ + 'url': 'https://learning.scte.org/mod/scorm/view.php?id=31484', + 'info_dict': { + 'title': 'Introduction to DOCSIS Engineering Professional', + 'id': '31484', + }, + 'playlist_count': 5, + 'skip': 'Requires account credentials', + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + title = self._search_regex(r'<h1>(.+?)</h1>', webpage, 'title') + + context_id = self._search_regex(r'context-(\d+)', webpage, video_id) + content_base = 'https://learning.scte.org/pluginfile.php/%s/mod_scorm/content/8/' % context_id + context = decode_packed_codes(self._download_webpage( + '%smobile/data.js' % content_base, video_id)) + + data = self._parse_xml( + self._search_regex( + r'CreateData\(\s*"(.+?)"', context, 'data').replace(r"\'", "'"), + video_id) + + entries = [] + for asset in data.findall('.//asset'): + asset_url = asset.get('url') + if not asset_url or not asset_url.endswith('.mp4'): + continue + asset_id = self._search_regex( + r'video_([^_]+)_', asset_url, 'asset id', default=None) + if not asset_id: + continue + entries.append({ + 'id': asset_id, + 'title': title, + 'url': content_base + asset_url, + }) + + return self.playlist_result(entries, video_id, title) + + +class SCTECourseIE(SCTEBaseIE): + _VALID_URL = r'https?://learning\.scte\.org/(?:mod/sub)?course/view\.php?.*?\bid=(?P<id>\d+)' + _TESTS = [{ + 'url': 'https://learning.scte.org/mod/subcourse/view.php?id=31491', + 'only_matching': True, + }, { + 'url': 'https://learning.scte.org/course/view.php?id=3639', + 'only_matching': True, + }, { + 'url': 'https://learning.scte.org/course/view.php?id=3073', + 'only_matching': True, + }] + + def _real_extract(self, url): + course_id = self._match_id(url) + + webpage = self._download_webpage(url, course_id) + + title = self._search_regex( + r'<h1>(.+?)</h1>', webpage, 'title', default=None) + + entries = [] + for mobj in re.finditer( + r'''(?x) + <a[^>]+ + href=(["\']) + (?P<url> + https?://learning\.scte\.org/mod/ + (?P<kind>scorm|subcourse)/view\.php?(?:(?!\1).)*? + \bid=\d+ + ) + ''', + webpage): + item_url = mobj.group('url') + if item_url == url: + continue + ie = (SCTEIE.ie_key() if mobj.group('kind') == 'scorm' + else SCTECourseIE.ie_key()) + entries.append(self.url_result(item_url, ie=ie)) + + return self.playlist_result(entries, course_id, title) From 1a4e4b0bfeb83b24755f80630d1e7f3427a5bf48 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 5 Nov 2019 05:31:40 +0700 Subject: [PATCH 166/422] [ChangeLog] Actualize [ci skip] --- ChangeLog | 44 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) diff --git a/ChangeLog b/ChangeLog index fcab1102c..338dd456b 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,47 @@ +version <unreleased> + +Extractors ++ [scte] Add support for learning.scte.org (#22975) ++ [msn] Add support for Vidible and AOL embeds (#22195, #22227) +* [myspass] Fix video URL extraction and improve metadata extraction (#22448) +* [jamendo] Improve extraction + * Fix album extraction (#18564) + * Improve metadata extraction (#18565, #21379) +* [mediaset] Relax URL guid matching (#18352) ++ [mediaset] Extract unprotected M3U and MPD manifests (#17204) +* [telegraaf] Fix extraction ++ [bellmedia] Add support for marilyn.ca videos (#22193) +* [stv] Fix extraction (#22928) +- [iconosquare] Remove extractor +- [keek] Remove extractor +- [gameone] Remove extractor (#21778) +- [flipagram] Remove extractor +- [bambuser] Remove extractor +* [wistia] Reduce embed extraction false positives ++ [wistia] Add support for inline embeds (#22931) +- [go90] Remove extractor +* [kakao] Remove raw request ++ [kakao] Extract format total bitrate +* [daum] Fix VOD and Clip extracton (#15015) +* [kakao] Improve extraction + + Add support for embed URLs + + Add support for Kakao Legacy vid based embed URLs + * Only extract fields used for extraction + * Strip description and extract tags +* [mixcloud] Fix cloudcast data extraction (#22821) +* [yahoo] Improve extraction + + Add support for live streams (#3597, #3779, #22178) + * Bypass cookie consent page for european domains (#16948, #22576) + + Add generic support for embeds (#20332) +* [tv2] Fix and improve extraction (#22787) ++ [tv2dk] Add support for TV2 DK sites +* [onet] Improve extraction … + + Add support for onet100.vod.pl + + Extract m3u8 formats + * Correct audio only format info +* [fox9] Fix extraction + + version 2019.10.29 Core From ea07412ebf6fff7c17bcac9960cfe4e92ed62f12 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 5 Nov 2019 05:32:56 +0700 Subject: [PATCH 167/422] release 2019.11.05 --- .github/ISSUE_TEMPLATE/1_broken_site.md | 6 +++--- .github/ISSUE_TEMPLATE/2_site_support_request.md | 4 ++-- .github/ISSUE_TEMPLATE/3_site_feature_request.md | 4 ++-- .github/ISSUE_TEMPLATE/4_bug_report.md | 6 +++--- .github/ISSUE_TEMPLATE/5_feature_request.md | 4 ++-- ChangeLog | 2 +- docs/supportedsites.md | 12 ++++-------- youtube_dl/version.py | 2 +- 8 files changed, 18 insertions(+), 22 deletions(-) diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.md b/.github/ISSUE_TEMPLATE/1_broken_site.md index f82502bd1..12de9add2 100644 --- a/.github/ISSUE_TEMPLATE/1_broken_site.md +++ b/.github/ISSUE_TEMPLATE/1_broken_site.md @@ -18,7 +18,7 @@ title: '' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.29. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.11.05. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape. - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates. @@ -26,7 +26,7 @@ Carefully read and work through this check list in order to prevent the most com --> - [ ] I'm reporting a broken site support -- [ ] I've verified that I'm running youtube-dl version **2019.10.29** +- [ ] I've verified that I'm running youtube-dl version **2019.11.05** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar issues including closed ones @@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.10.29 + [debug] youtube-dl version 2019.11.05 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/2_site_support_request.md b/.github/ISSUE_TEMPLATE/2_site_support_request.md index 5ef983d43..8a6202cf6 100644 --- a/.github/ISSUE_TEMPLATE/2_site_support_request.md +++ b/.github/ISSUE_TEMPLATE/2_site_support_request.md @@ -19,7 +19,7 @@ labels: 'site-support-request' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.29. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.11.05. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that site you are requesting is not dedicated to copyright infringement, see https://yt-dl.org/copyright-infringement. youtube-dl does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights. - Search the bugtracker for similar site support requests: http://yt-dl.org/search-issues. DO NOT post duplicates. @@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com --> - [ ] I'm reporting a new site support request -- [ ] I've verified that I'm running youtube-dl version **2019.10.29** +- [ ] I've verified that I'm running youtube-dl version **2019.11.05** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that none of provided URLs violate any copyrights - [ ] I've searched the bugtracker for similar site support requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/3_site_feature_request.md b/.github/ISSUE_TEMPLATE/3_site_feature_request.md index 8f05aa79f..83f91d5fe 100644 --- a/.github/ISSUE_TEMPLATE/3_site_feature_request.md +++ b/.github/ISSUE_TEMPLATE/3_site_feature_request.md @@ -18,13 +18,13 @@ title: '' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.29. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.11.05. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Search the bugtracker for similar site feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates. - Finally, put x into all relevant boxes (like this [x]) --> - [ ] I'm reporting a site feature request -- [ ] I've verified that I'm running youtube-dl version **2019.10.29** +- [ ] I've verified that I'm running youtube-dl version **2019.11.05** - [ ] I've searched the bugtracker for similar site feature requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/4_bug_report.md b/.github/ISSUE_TEMPLATE/4_bug_report.md index e90900d8d..be8e70f1e 100644 --- a/.github/ISSUE_TEMPLATE/4_bug_report.md +++ b/.github/ISSUE_TEMPLATE/4_bug_report.md @@ -18,7 +18,7 @@ title: '' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.29. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.11.05. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape. - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates. @@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com --> - [ ] I'm reporting a broken site support issue -- [ ] I've verified that I'm running youtube-dl version **2019.10.29** +- [ ] I've verified that I'm running youtube-dl version **2019.11.05** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar bug reports including closed ones @@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.10.29 + [debug] youtube-dl version 2019.11.05 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/5_feature_request.md b/.github/ISSUE_TEMPLATE/5_feature_request.md index 7021d7397..7544d171c 100644 --- a/.github/ISSUE_TEMPLATE/5_feature_request.md +++ b/.github/ISSUE_TEMPLATE/5_feature_request.md @@ -19,13 +19,13 @@ labels: 'request' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.29. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.11.05. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Search the bugtracker for similar feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates. - Finally, put x into all relevant boxes (like this [x]) --> - [ ] I'm reporting a feature request -- [ ] I've verified that I'm running youtube-dl version **2019.10.29** +- [ ] I've verified that I'm running youtube-dl version **2019.11.05** - [ ] I've searched the bugtracker for similar feature requests including closed ones diff --git a/ChangeLog b/ChangeLog index 338dd456b..d46d20082 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2019.11.05 Extractors + [scte] Add support for learning.scte.org (#22975) diff --git a/docs/supportedsites.md b/docs/supportedsites.md index af905db5a..536b87479 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -76,8 +76,6 @@ - **awaan:video** - **AZMedien**: AZ Medien videos - **BaiduVideo**: 百度视频 - - **bambuser** - - **bambuser:channel** - **Bandcamp** - **Bandcamp:album** - **Bandcamp:weekly** @@ -284,12 +282,12 @@ - **FiveThirtyEight** - **FiveTV** - **Flickr** - - **Flipagram** - **Folketinget**: Folketinget (ft.dk; Danish parliament) - **FootyRoom** - **Formula1** - **FOX** - **FOX9** + - **FOX9News** - **Foxgay** - **foxnews**: Fox News and Fox Business Video - **foxnews:article** @@ -315,8 +313,6 @@ - **FXNetworks** - **Gaia** - **GameInformer** - - **GameOne** - - **gameone:playlist** - **GameSpot** - **GameStar** - **Gaskrank** @@ -331,7 +327,6 @@ - **Globo** - **GloboArticle** - **Go** - - **Go90** - **GodTube** - **Golem** - **GoogleDrive** @@ -366,7 +361,6 @@ - **Hungama** - **HungamaSong** - **Hypem** - - **Iconosquare** - **ign.com** - **imdb**: Internet Movie Database trailers - **imdb:list**: Internet Movie Database lists @@ -406,7 +400,6 @@ - **Kankan** - **Karaoketv** - **KarriereVideos** - - **keek** - **KeezMovies** - **Ketnet** - **KhanAcademy** @@ -777,6 +770,8 @@ - **Screencast** - **ScreencastOMatic** - **scrippsnetworks:watch** + - **SCTE** + - **SCTECourse** - **Seeker** - **SenateISVP** - **SendtoNews** @@ -926,6 +921,7 @@ - **TV2** - **tv2.hu** - **TV2Article** + - **TV2DK** - **TV4**: tv4.se and tv4play.se - **TV5MondePlus**: TV5MONDE+ - **TVA** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 924f26ca8..8012a66db 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.10.29' +__version__ = '2019.11.05' From e9b95167af3f9cacd16e379a40bacb27999840b9 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Tue, 5 Nov 2019 10:03:38 +0100 Subject: [PATCH 168/422] [roosterteeth] fix login request(closes #16094)(closes #22689) --- youtube_dl/extractor/roosterteeth.py | 55 +++++++++++----------------- 1 file changed, 22 insertions(+), 33 deletions(-) diff --git a/youtube_dl/extractor/roosterteeth.py b/youtube_dl/extractor/roosterteeth.py index 8d88ee499..8883639b2 100644 --- a/youtube_dl/extractor/roosterteeth.py +++ b/youtube_dl/extractor/roosterteeth.py @@ -1,8 +1,6 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..compat import ( compat_HTTPError, @@ -18,7 +16,6 @@ from ..utils import ( class RoosterTeethIE(InfoExtractor): _VALID_URL = r'https?://(?:.+?\.)?roosterteeth\.com/(?:episode|watch)/(?P<id>[^/?#&]+)' - _LOGIN_URL = 'https://roosterteeth.com/login' _NETRC_MACHINE = 'roosterteeth' _TESTS = [{ 'url': 'http://roosterteeth.com/episode/million-dollars-but-season-2-million-dollars-but-the-game-announcement', @@ -53,48 +50,40 @@ class RoosterTeethIE(InfoExtractor): 'url': 'https://roosterteeth.com/watch/million-dollars-but-season-2-million-dollars-but-the-game-announcement', 'only_matching': True, }] + _EPISODE_BASE_URL = 'https://svod-be.roosterteeth.com/api/v1/episodes/' def _login(self): username, password = self._get_login_info() if username is None: return - login_page = self._download_webpage( - self._LOGIN_URL, None, - note='Downloading login page', - errnote='Unable to download login page') - - login_form = self._hidden_inputs(login_page) - - login_form.update({ - 'username': username, - 'password': password, - }) - - login_request = self._download_webpage( - self._LOGIN_URL, None, - note='Logging in', - data=urlencode_postdata(login_form), - headers={ - 'Referer': self._LOGIN_URL, - }) - - if not any(re.search(p, login_request) for p in ( - r'href=["\']https?://(?:www\.)?roosterteeth\.com/logout"', - r'>Sign Out<')): - error = self._html_search_regex( - r'(?s)<div[^>]+class=(["\']).*?\balert-danger\b.*?\1[^>]*>(?:\s*<button[^>]*>.*?</button>)?(?P<error>.+?)</div>', - login_request, 'alert', default=None, group='error') - if error: - raise ExtractorError('Unable to login: %s' % error, expected=True) - raise ExtractorError('Unable to log in') + try: + self._download_json( + 'https://auth.roosterteeth.com/oauth/token', + None, 'Logging in', data=urlencode_postdata({ + 'client_id': '4338d2b4bdc8db1239360f28e72f0d9ddb1fd01e7a38fbb07b4b1f4ba4564cc5', + 'grant_type': 'password', + 'username': username, + 'password': password, + })) + except ExtractorError as e: + msg = 'Unable to login' + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + resp = self._parse_json(e.cause.read().decode(), None, fatal=False) + if resp: + error = resp.get('extra_info') or resp.get('error_description') or resp.get('error') + if error: + msg += ': ' + error + self.report_warning(msg) def _real_initialize(self): + if self._get_cookies(self._EPISODE_BASE_URL).get('rt_access_token'): + return self._login() def _real_extract(self, url): display_id = self._match_id(url) - api_episode_url = 'https://svod-be.roosterteeth.com/api/v1/episodes/%s' % display_id + api_episode_url = self._EPISODE_BASE_URL + display_id try: m3u8_url = self._download_json( From b77c3949e899902de78b140f6e444dc55bac824f Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Tue, 5 Nov 2019 14:04:17 +0100 Subject: [PATCH 169/422] [patreon] minimize reponse size and extract uploader_id and filesize --- youtube_dl/extractor/patreon.py | 52 +++++++++++++++++++++++---------- 1 file changed, 36 insertions(+), 16 deletions(-) diff --git a/youtube_dl/extractor/patreon.py b/youtube_dl/extractor/patreon.py index 426dd8121..761a4b1de 100644 --- a/youtube_dl/extractor/patreon.py +++ b/youtube_dl/extractor/patreon.py @@ -6,7 +6,11 @@ from ..utils import ( clean_html, determine_ext, int_or_none, + KNOWN_EXTENSIONS, + mimetype2ext, parse_iso8601, + str_or_none, + try_get, ) @@ -24,6 +28,7 @@ class PatreonIE(InfoExtractor): 'thumbnail': 're:^https?://.*$', 'timestamp': 1406473987, 'upload_date': '20140727', + 'uploader_id': '87145', }, }, { 'url': 'http://www.patreon.com/creation?hid=754133', @@ -90,7 +95,13 @@ class PatreonIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) post = self._download_json( - 'https://www.patreon.com/api/posts/' + video_id, video_id) + 'https://www.patreon.com/api/posts/' + video_id, video_id, query={ + 'fields[media]': 'download_url,mimetype,size_bytes', + 'fields[post]': 'comment_count,content,embed,image,like_count,post_file,published_at,title', + 'fields[user]': 'full_name,url', + 'json-api-use-default-includes': 'false', + 'include': 'media,user', + }) attributes = post['data']['attributes'] title = attributes['title'].strip() image = attributes.get('image') or {} @@ -104,33 +115,42 @@ class PatreonIE(InfoExtractor): 'comment_count': int_or_none(attributes.get('comment_count')), } - def add_file(file_data): - file_url = file_data.get('url') - if file_url: - info.update({ - 'url': file_url, - 'ext': determine_ext(file_data.get('name'), 'mp3'), - }) - for i in post.get('included', []): i_type = i.get('type') - if i_type == 'attachment': - add_file(i.get('attributes') or {}) + if i_type == 'media': + media_attributes = i.get('attributes') or {} + download_url = media_attributes.get('download_url') + ext = mimetype2ext(media_attributes.get('mimetype')) + if download_url and ext in KNOWN_EXTENSIONS: + info.update({ + 'ext': ext, + 'filesize': int_or_none(media_attributes.get('size_bytes')), + 'url': download_url, + }) elif i_type == 'user': user_attributes = i.get('attributes') if user_attributes: info.update({ 'uploader': user_attributes.get('full_name'), + 'uploader_id': str_or_none(i.get('id')), 'uploader_url': user_attributes.get('url'), }) if not info.get('url'): - add_file(attributes.get('post_file') or {}) + embed_url = try_get(attributes, lambda x: x['embed']['url']) + if embed_url: + info.update({ + '_type': 'url', + 'url': embed_url, + }) if not info.get('url'): - info.update({ - '_type': 'url', - 'url': attributes['embed']['url'], - }) + post_file = attributes['post_file'] + ext = determine_ext(post_file.get('name')) + if ext in KNOWN_EXTENSIONS: + info.update({ + 'ext': ext, + 'url': post_file['url'], + }) return info From 2318629b2b79cad5fcab743bce86233a7592ed46 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Tue, 5 Nov 2019 14:04:50 +0100 Subject: [PATCH 170/422] [dplay] minimize response size --- youtube_dl/extractor/dplay.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/dplay.py b/youtube_dl/extractor/dplay.py index d9c3d59cd..a7b9db568 100644 --- a/youtube_dl/extractor/dplay.py +++ b/youtube_dl/extractor/dplay.py @@ -146,6 +146,11 @@ class DPlayIE(InfoExtractor): video = self._download_json( disco_base + 'content/videos/' + display_id, display_id, headers=headers, query={ + 'fields[channel]': 'name', + 'fields[image]': 'height,src,width', + 'fields[show]': 'name', + 'fields[tag]': 'name', + 'fields[video]': 'description,episodeNumber,name,publishStart,seasonNumber,videoDuration', 'include': 'images,primaryChannel,show,tags' }) video_id = video['data']['id'] @@ -226,7 +231,6 @@ class DPlayIE(InfoExtractor): 'series': series, 'season_number': int_or_none(info.get('seasonNumber')), 'episode_number': int_or_none(info.get('episodeNumber')), - 'age_limit': int_or_none(info.get('minimum_age')), 'creator': creator, 'tags': tags, 'thumbnails': thumbnails, From b6139cb0c3635eb96e39973ab288c17a9f104067 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Tue, 5 Nov 2019 22:56:25 +0100 Subject: [PATCH 171/422] [common] pass headers to _extract_(m3u8|mpd)_formats methods --- youtube_dl/extractor/common.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 50d48c40d..2688b19e4 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1586,12 +1586,12 @@ class InfoExtractor(object): def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None, entry_protocol='m3u8', preference=None, m3u8_id=None, note=None, errnote=None, - fatal=True, live=False): + fatal=True, live=False, headers=None): res = self._download_webpage_handle( m3u8_url, video_id, note=note or 'Downloading m3u8 information', errnote=errnote or 'Failed to download m3u8 information', - fatal=fatal) + fatal=fatal, headers=headers) if res is False: return [] @@ -2009,12 +2009,12 @@ class InfoExtractor(object): }) return entries - def _extract_mpd_formats(self, mpd_url, video_id, mpd_id=None, note=None, errnote=None, fatal=True, formats_dict={}): + def _extract_mpd_formats(self, mpd_url, video_id, mpd_id=None, note=None, errnote=None, fatal=True, formats_dict={}, headers=None): res = self._download_xml_handle( mpd_url, video_id, note=note or 'Downloading MPD manifest', errnote=errnote or 'Failed to download MPD manifest', - fatal=fatal) + fatal=fatal, headers=None) if res is False: return [] mpd_doc, urlh = res From d7def23d0539430f5d816f1cfd733e436f62c257 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Tue, 5 Nov 2019 23:08:42 +0100 Subject: [PATCH 172/422] [hotstar] pass Referer header to format requests(closes #22836) --- youtube_dl/extractor/hotstar.py | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/hotstar.py b/youtube_dl/extractor/hotstar.py index f9f7c5a64..f97eefa3d 100644 --- a/youtube_dl/extractor/hotstar.py +++ b/youtube_dl/extractor/hotstar.py @@ -118,6 +118,7 @@ class HotStarIE(HotStarBaseIE): if video_data.get('drmProtected'): raise ExtractorError('This video is DRM protected.', expected=True) + headers = {'Referer': url} formats = [] geo_restricted = False playback_sets = self._call_api_v2('h/v2/play', video_id)['playBackSets'] @@ -137,10 +138,11 @@ class HotStarIE(HotStarBaseIE): if 'package:hls' in tags or ext == 'm3u8': formats.extend(self._extract_m3u8_formats( format_url, video_id, 'mp4', - entry_protocol='m3u8_native', m3u8_id='hls')) + entry_protocol='m3u8_native', + m3u8_id='hls', headers=headers)) elif 'package:dash' in tags or ext == 'mpd': formats.extend(self._extract_mpd_formats( - format_url, video_id, mpd_id='dash')) + format_url, video_id, mpd_id='dash', headers=headers)) elif ext == 'f4m': # produce broken files pass @@ -158,6 +160,9 @@ class HotStarIE(HotStarBaseIE): self.raise_geo_restricted(countries=['IN']) self._sort_formats(formats) + for f in formats: + f.setdefault('http_headers', {}).update(headers) + return { 'id': video_id, 'title': title, From 57033e35e58e1d57ab3be5ffe5df5a80a5dbcf83 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Tue, 5 Nov 2019 23:41:57 +0100 Subject: [PATCH 173/422] [common] fix typo --- youtube_dl/extractor/common.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 2688b19e4..1e6b66d25 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -2014,7 +2014,7 @@ class InfoExtractor(object): mpd_url, video_id, note=note or 'Downloading MPD manifest', errnote=errnote or 'Failed to download MPD manifest', - fatal=fatal, headers=None) + fatal=fatal, headers=headers) if res is False: return [] mpd_doc, urlh = res From 3ec86619e33a3d1e29c14ec053d7e420ac8b62ae Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 6 Nov 2019 07:18:29 +0100 Subject: [PATCH 174/422] [common] initialize headers param with empty dict --- youtube_dl/extractor/common.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 1e6b66d25..4a683f6d6 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1586,7 +1586,7 @@ class InfoExtractor(object): def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None, entry_protocol='m3u8', preference=None, m3u8_id=None, note=None, errnote=None, - fatal=True, live=False, headers=None): + fatal=True, live=False, headers={}): res = self._download_webpage_handle( m3u8_url, video_id, note=note or 'Downloading m3u8 information', @@ -2009,7 +2009,7 @@ class InfoExtractor(object): }) return entries - def _extract_mpd_formats(self, mpd_url, video_id, mpd_id=None, note=None, errnote=None, fatal=True, formats_dict={}, headers=None): + def _extract_mpd_formats(self, mpd_url, video_id, mpd_id=None, note=None, errnote=None, fatal=True, formats_dict={}, headers={}): res = self._download_xml_handle( mpd_url, video_id, note=note or 'Downloading MPD manifest', From d64ec1242e9dec03ea2aa86b6e913db78c8619e0 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 6 Nov 2019 10:44:19 +0100 Subject: [PATCH 175/422] [onionstudios] fix extraction --- youtube_dl/extractor/onionstudios.py | 78 ++++++++++++++++------------ 1 file changed, 46 insertions(+), 32 deletions(-) diff --git a/youtube_dl/extractor/onionstudios.py b/youtube_dl/extractor/onionstudios.py index c6e3d5640..7f8c6f0d3 100644 --- a/youtube_dl/extractor/onionstudios.py +++ b/youtube_dl/extractor/onionstudios.py @@ -5,10 +5,11 @@ import re from .common import InfoExtractor from ..utils import ( - determine_ext, + compat_str, int_or_none, - float_or_none, - mimetype2ext, + js_to_json, + parse_iso8601, + try_get, ) @@ -17,14 +18,16 @@ class OnionStudiosIE(InfoExtractor): _TESTS = [{ 'url': 'http://www.onionstudios.com/videos/hannibal-charges-forward-stops-for-a-cocktail-2937', - 'md5': '719d1f8c32094b8c33902c17bcae5e34', + 'md5': '5a118d466d62b5cd03647cf2c593977f', 'info_dict': { 'id': '2937', 'ext': 'mp4', 'title': 'Hannibal charges forward, stops for a cocktail', + 'description': 'md5:545299bda6abf87e5ec666548c6a9448', 'thumbnail': r're:^https?://.*\.jpg$', - 'uploader': 'The A.V. Club', - 'uploader_id': 'the-av-club', + 'uploader': 'a.v. club', + 'upload_date': '20150619', + 'timestamp': 1434728546, }, }, { 'url': 'http://www.onionstudios.com/embed?id=2855&autoplay=true', @@ -44,38 +47,49 @@ class OnionStudiosIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) + webpage = self._download_webpage( + 'http://onionstudios.com/embed/dc94dc2899fe644c0e7241fa04c1b732.js', + video_id) + mcp_id = compat_str(self._parse_json(self._search_regex( + r'window\.mcpMapping\s*=\s*({.+?});', webpage, + 'MCP Mapping'), video_id, js_to_json)[video_id]['mcp_id']) video_data = self._download_json( - 'http://www.onionstudios.com/video/%s.json' % video_id, video_id) - - title = video_data['title'] - + 'https://api.vmh.univision.com/metadata/v1/content/' + mcp_id, + mcp_id)['videoMetadata'] + iptc = video_data['photoVideoMetadataIPTC'] + title = iptc['title']['en'] + fmg = video_data.get('photoVideoMetadata_fmg') or {} + tvss_domain = fmg.get('tvssDomain') or 'https://auth.univision.com' + data = self._download_json( + tvss_domain + '/api/v3/video-auth/url-signature-tokens', + mcp_id, query={'mcpids': mcp_id})['data'][0] formats = [] - for source in video_data.get('sources', []): - source_url = source.get('url') - if not source_url: - continue - ext = mimetype2ext(source.get('content_type')) or determine_ext(source_url) - if ext == 'm3u8': - formats.extend(self._extract_m3u8_formats( - source_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) - else: - tbr = int_or_none(source.get('bitrate')) - formats.append({ - 'format_id': ext + ('-%d' % tbr if tbr else ''), - 'url': source_url, - 'width': int_or_none(source.get('width')), - 'tbr': tbr, - 'ext': ext, - }) + + rendition_url = data.get('renditionUrl') + if rendition_url: + formats = self._extract_m3u8_formats( + rendition_url, mcp_id, 'mp4', + 'm3u8_native', m3u8_id='hls', fatal=False) + + fallback_rendition_url = data.get('fallbackRenditionUrl') + if fallback_rendition_url: + formats.append({ + 'format_id': 'fallback', + 'tbr': int_or_none(self._search_regex( + r'_(\d+)\.mp4', fallback_rendition_url, + 'bitrate', default=None)), + 'url': fallback_rendition_url, + }) + self._sort_formats(formats) return { 'id': video_id, 'title': title, - 'thumbnail': video_data.get('poster_url'), - 'uploader': video_data.get('channel_name'), - 'uploader_id': video_data.get('channel_slug'), - 'duration': float_or_none(video_data.get('duration', 1000)), - 'tags': video_data.get('tags'), + 'thumbnail': try_get(iptc, lambda x: x['cloudinaryLink']['link'], compat_str), + 'uploader': fmg.get('network'), + 'duration': int_or_none(iptc.get('fileDuration')), 'formats': formats, + 'description': try_get(iptc, lambda x: x['description']['en'], compat_str), + 'timestamp': parse_iso8601(iptc.get('dateReleased')), } From 55adb63e5412fa5556be22e97d61b8d27c7a5e67 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 6 Nov 2019 19:56:10 +0100 Subject: [PATCH 176/422] [kinja] add support for Kinja embeds closes #5756 closes #11282 closes #22237 closes #22384 --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/generic.py | 17 ++- youtube_dl/extractor/kinja.py | 221 +++++++++++++++++++++++++++ youtube_dl/extractor/onionstudios.py | 54 +------ 4 files changed, 241 insertions(+), 52 deletions(-) create mode 100644 youtube_dl/extractor/kinja.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 9f43b284d..9e3b554fa 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -513,6 +513,7 @@ from .keezmovies import KeezMoviesIE from .ketnet import KetnetIE from .khanacademy import KhanAcademyIE from .kickstarter import KickStarterIE +from .kinja import KinjaEmbedIE from .kinopoisk import KinoPoiskIE from .konserthusetplay import KonserthusetPlayIE from .kontrtube import KontrTubeIE diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 1c0780e98..3d919f656 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -119,6 +119,7 @@ from .viqeo import ViqeoIE from .expressen import ExpressenIE from .zype import ZypeIE from .odnoklassniki import OdnoklassnikiIE +from .kinja import KinjaEmbedIE class GenericIE(InfoExtractor): @@ -1487,16 +1488,18 @@ class GenericIE(InfoExtractor): 'timestamp': 1432570283, }, }, - # OnionStudios embed + # Kinja embed { 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537', 'info_dict': { - 'id': '2855', + 'id': '106351', 'ext': 'mp4', 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You', + 'description': 'Migrated from OnionStudios', 'thumbnail': r're:^https?://.*\.jpe?g$', - 'uploader': 'ClickHole', - 'uploader_id': 'clickhole', + 'uploader': 'clickhole', + 'upload_date': '20150527', + 'timestamp': 1432744860, } }, # SnagFilms embed @@ -2894,6 +2897,12 @@ class GenericIE(InfoExtractor): if senate_isvp_url: return self.url_result(senate_isvp_url, 'SenateISVP') + # Look for Kinja embeds + kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url) + if kinja_embed_urls: + return self.playlist_from_matches( + kinja_embed_urls, video_id, video_title) + # Look for OnionStudios embeds onionstudios_url = OnionStudiosIE._extract_url(webpage) if onionstudios_url: diff --git a/youtube_dl/extractor/kinja.py b/youtube_dl/extractor/kinja.py new file mode 100644 index 000000000..79e3026d2 --- /dev/null +++ b/youtube_dl/extractor/kinja.py @@ -0,0 +1,221 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import ( + compat_str, + compat_urllib_parse_unquote, +) +from ..utils import ( + int_or_none, + parse_iso8601, + strip_or_none, + try_get, + unescapeHTML, + urljoin, +) + + +class KinjaEmbedIE(InfoExtractor): + IENAME = 'kinja:embed' + _DOMAIN_REGEX = r'''(?:[^.]+\.)? + (?: + avclub| + clickhole| + deadspin| + gizmodo| + jalopnik| + jezebel| + kinja| + kotaku| + lifehacker| + splinternews| + the(?:inventory|onion|root|takeout) + )\.com''' + _COMMON_REGEX = r'''/ + (?: + ajax/inset| + embed/video + )/iframe\?.*?\bid=''' + _VALID_URL = r'''(?x)https?://%s%s + (?P<type> + fb| + imgur| + instagram| + jwp(?:layer)?-video| + kinjavideo| + mcp| + megaphone| + ooyala| + soundcloud(?:-playlist)?| + tumblr-post| + twitch-stream| + twitter| + ustream-channel| + vimeo| + vine| + youtube-(?:list|video) + )-(?P<id>[^&]+)''' % (_DOMAIN_REGEX, _COMMON_REGEX) + _TESTS = [{ + 'url': 'https://kinja.com/ajax/inset/iframe?id=fb-10103303356633621', + 'only_matching': True, + }, { + 'url': 'https://kinja.com/ajax/inset/iframe?id=kinjavideo-100313', + 'only_matching': True, + }, { + 'url': 'https://kinja.com/ajax/inset/iframe?id=megaphone-PPY1300931075', + 'only_matching': True, + }, { + 'url': 'https://kinja.com/ajax/inset/iframe?id=ooyala-xzMXhleDpopuT0u1ijt_qZj3Va-34pEX%2FZTIxYmJjZDM2NWYzZDViZGRiOWJjYzc5', + 'only_matching': True, + }, { + 'url': 'https://kinja.com/ajax/inset/iframe?id=soundcloud-128574047', + 'only_matching': True, + }, { + 'url': 'https://kinja.com/ajax/inset/iframe?id=soundcloud-playlist-317413750', + 'only_matching': True, + }, { + 'url': 'https://kinja.com/ajax/inset/iframe?id=tumblr-post-160130699814-daydreams-at-midnight', + 'only_matching': True, + }, { + 'url': 'https://kinja.com/ajax/inset/iframe?id=twitch-stream-libratus_extra', + 'only_matching': True, + }, { + 'url': 'https://kinja.com/ajax/inset/iframe?id=twitter-1068875942473404422', + 'only_matching': True, + }, { + 'url': 'https://kinja.com/ajax/inset/iframe?id=ustream-channel-10414700', + 'only_matching': True, + }, { + 'url': 'https://kinja.com/ajax/inset/iframe?id=vimeo-120153502', + 'only_matching': True, + }, { + 'url': 'https://kinja.com/ajax/inset/iframe?id=vine-5BlvV5qqPrD', + 'only_matching': True, + }, { + 'url': 'https://kinja.com/ajax/inset/iframe?id=youtube-list-BCQ3KyrPjgA/PLE6509247C270A72E', + 'only_matching': True, + }, { + 'url': 'https://kinja.com/ajax/inset/iframe?id=youtube-video-00QyL0AgPAE', + 'only_matching': True, + }] + _JWPLATFORM_PROVIDER = ('cdn.jwplayer.com/v2/media/', 'JWPlatform') + _PROVIDER_MAP = { + 'fb': ('facebook.com/video.php?v=', 'Facebook'), + 'imgur': ('imgur.com/', 'Imgur'), + 'instagram': ('instagram.com/p/', 'Instagram'), + 'jwplayer-video': _JWPLATFORM_PROVIDER, + 'jwp-video': _JWPLATFORM_PROVIDER, + 'megaphone': ('player.megaphone.fm/', 'Generic'), + 'ooyala': ('player.ooyala.com/player.js?embedCode=', 'Ooyala'), + 'soundcloud': ('api.soundcloud.com/tracks/', 'Soundcloud'), + 'soundcloud-playlist': ('api.soundcloud.com/playlists/', 'SoundcloudPlaylist'), + 'tumblr-post': ('%s.tumblr.com/post/%s', 'Tumblr'), + 'twitch-stream': ('twitch.tv/', 'TwitchStream'), + 'twitter': ('twitter.com/i/cards/tfw/v1/', 'TwitterCard'), + 'ustream-channel': ('ustream.tv/embed/', 'Ustream'), + 'vimeo': ('vimeo.com/', 'Vimeo'), + 'vine': ('vine.co/v/', 'Vine'), + 'youtube-list': ('youtube.com/embed/%s?list=%s', 'YoutubePlaylist'), + 'youtube-video': ('youtube.com/embed/', 'Youtube'), + } + + @staticmethod + def _extract_urls(webpage, url): + return [urljoin(url, unescapeHTML(mobj.group('url'))) for mobj in re.finditer( + r'(?x)<iframe[^>]+?src=(?P<q>["\'])(?P<url>(?:(?:https?:)?//%s)?%s(?:(?!\1).)+)\1' % (KinjaEmbedIE._DOMAIN_REGEX, KinjaEmbedIE._COMMON_REGEX), + webpage)] + + def _real_extract(self, url): + video_type, video_id = re.match(self._VALID_URL, url).groups() + + provider = self._PROVIDER_MAP.get(video_type) + if provider: + video_id = compat_urllib_parse_unquote(video_id) + if video_type == 'tumblr-post': + video_id, blog = video_id.split('-', 1) + result_url = provider[0] % (blog, video_id) + elif video_type == 'youtube-list': + video_id, playlist_id = video_id.split('/') + result_url = provider[0] % (video_id, playlist_id) + else: + if video_type == 'ooyala': + video_id = video_id.split('/')[0] + result_url = provider[0] + video_id + return self.url_result('http://' + result_url, provider[1]) + + if video_type == 'kinjavideo': + data = self._download_json( + 'https://kinja.com/api/core/video/views/videoById', + video_id, query={'videoId': video_id})['data'] + title = data['title'] + + formats = [] + for k in ('signedPlaylist', 'streaming'): + m3u8_url = data.get(k + 'Url') + if m3u8_url: + formats.extend(self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) + self._sort_formats(formats) + + thumbnail = None + poster = data.get('poster') or {} + poster_id = poster.get('id') + if poster_id: + thumbnail = 'https://i.kinja-img.com/gawker-media/image/upload/%s.%s' % (poster_id, poster.get('format') or 'jpg') + + return { + 'id': video_id, + 'title': title, + 'description': strip_or_none(data.get('description')), + 'formats': formats, + 'tags': data.get('tags'), + 'timestamp': int_or_none(try_get( + data, lambda x: x['postInfo']['publishTimeMillis']), 1000), + 'thumbnail': thumbnail, + 'uploader': data.get('network'), + } + else: + video_data = self._download_json( + 'https://api.vmh.univision.com/metadata/v1/content/' + video_id, + video_id)['videoMetadata'] + iptc = video_data['photoVideoMetadataIPTC'] + title = iptc['title']['en'] + fmg = video_data.get('photoVideoMetadata_fmg') or {} + tvss_domain = fmg.get('tvssDomain') or 'https://auth.univision.com' + data = self._download_json( + tvss_domain + '/api/v3/video-auth/url-signature-tokens', + video_id, query={'mcpids': video_id})['data'][0] + formats = [] + + rendition_url = data.get('renditionUrl') + if rendition_url: + formats = self._extract_m3u8_formats( + rendition_url, video_id, 'mp4', + 'm3u8_native', m3u8_id='hls', fatal=False) + + fallback_rendition_url = data.get('fallbackRenditionUrl') + if fallback_rendition_url: + formats.append({ + 'format_id': 'fallback', + 'tbr': int_or_none(self._search_regex( + r'_(\d+)\.mp4', fallback_rendition_url, + 'bitrate', default=None)), + 'url': fallback_rendition_url, + }) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'thumbnail': try_get(iptc, lambda x: x['cloudinaryLink']['link'], compat_str), + 'uploader': fmg.get('network'), + 'duration': int_or_none(iptc.get('fileDuration')), + 'formats': formats, + 'description': try_get(iptc, lambda x: x['description']['en'], compat_str), + 'timestamp': parse_iso8601(iptc.get('dateReleased')), + } diff --git a/youtube_dl/extractor/onionstudios.py b/youtube_dl/extractor/onionstudios.py index 7f8c6f0d3..cf5c39e66 100644 --- a/youtube_dl/extractor/onionstudios.py +++ b/youtube_dl/extractor/onionstudios.py @@ -4,13 +4,8 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( - compat_str, - int_or_none, - js_to_json, - parse_iso8601, - try_get, -) +from ..compat import compat_str +from ..utils import js_to_json class OnionStudiosIE(InfoExtractor): @@ -20,7 +15,7 @@ class OnionStudiosIE(InfoExtractor): 'url': 'http://www.onionstudios.com/videos/hannibal-charges-forward-stops-for-a-cocktail-2937', 'md5': '5a118d466d62b5cd03647cf2c593977f', 'info_dict': { - 'id': '2937', + 'id': '3459881', 'ext': 'mp4', 'title': 'Hannibal charges forward, stops for a cocktail', 'description': 'md5:545299bda6abf87e5ec666548c6a9448', @@ -53,43 +48,6 @@ class OnionStudiosIE(InfoExtractor): mcp_id = compat_str(self._parse_json(self._search_regex( r'window\.mcpMapping\s*=\s*({.+?});', webpage, 'MCP Mapping'), video_id, js_to_json)[video_id]['mcp_id']) - video_data = self._download_json( - 'https://api.vmh.univision.com/metadata/v1/content/' + mcp_id, - mcp_id)['videoMetadata'] - iptc = video_data['photoVideoMetadataIPTC'] - title = iptc['title']['en'] - fmg = video_data.get('photoVideoMetadata_fmg') or {} - tvss_domain = fmg.get('tvssDomain') or 'https://auth.univision.com' - data = self._download_json( - tvss_domain + '/api/v3/video-auth/url-signature-tokens', - mcp_id, query={'mcpids': mcp_id})['data'][0] - formats = [] - - rendition_url = data.get('renditionUrl') - if rendition_url: - formats = self._extract_m3u8_formats( - rendition_url, mcp_id, 'mp4', - 'm3u8_native', m3u8_id='hls', fatal=False) - - fallback_rendition_url = data.get('fallbackRenditionUrl') - if fallback_rendition_url: - formats.append({ - 'format_id': 'fallback', - 'tbr': int_or_none(self._search_regex( - r'_(\d+)\.mp4', fallback_rendition_url, - 'bitrate', default=None)), - 'url': fallback_rendition_url, - }) - - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': title, - 'thumbnail': try_get(iptc, lambda x: x['cloudinaryLink']['link'], compat_str), - 'uploader': fmg.get('network'), - 'duration': int_or_none(iptc.get('fileDuration')), - 'formats': formats, - 'description': try_get(iptc, lambda x: x['description']['en'], compat_str), - 'timestamp': parse_iso8601(iptc.get('dateReleased')), - } + return self.url_result( + 'http://kinja.com/ajax/inset/iframe?id=mcp-' + mcp_id, + 'KinjaEmbed', mcp_id) From 5d92b407e0ea856e3dbadfef35e5258e94e0bb23 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 6 Nov 2019 20:41:49 +0100 Subject: [PATCH 177/422] [mixcloud] improve extraction - improve metadata extraction(closes #11721) - fix playlist extraction(closes #22378) - fix user mixes extraction(closes #15197)(closes #17865) --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/mixcloud.py | 498 +++++++++++++---------------- 2 files changed, 225 insertions(+), 274 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 9e3b554fa..2f9ba6893 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -639,7 +639,6 @@ from .mixcloud import ( MixcloudIE, MixcloudUserIE, MixcloudPlaylistIE, - MixcloudStreamIE, ) from .mlb import MLBIE from .mnet import MnetIE diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index e5f631506..9759560f1 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -1,6 +1,5 @@ from __future__ import unicode_literals -import functools import itertools import re @@ -11,28 +10,37 @@ from ..compat import ( compat_ord, compat_str, compat_urllib_parse_unquote, - compat_urlparse, compat_zip ) from ..utils import ( - clean_html, - ExtractorError, int_or_none, - OnDemandPagedList, - str_to_int, + parse_iso8601, + strip_or_none, try_get, - urljoin, ) -class MixcloudIE(InfoExtractor): +class MixcloudBaseIE(InfoExtractor): + def _call_api(self, object_type, object_fields, display_id, username, slug=None): + lookup_key = object_type + 'Lookup' + return self._download_json( + 'https://www.mixcloud.com/graphql', display_id, query={ + 'query': '''{ + %s(lookup: {username: "%s"%s}) { + %s + } +}''' % (lookup_key, username, ', slug: "%s"' % slug if slug else '', object_fields) + })['data'][lookup_key] + + +class MixcloudIE(MixcloudBaseIE): _VALID_URL = r'https?://(?:(?:www|beta|m)\.)?mixcloud\.com/([^/]+)/(?!stream|uploads|favorites|listens|playlists)([^/]+)' IE_NAME = 'mixcloud' _TESTS = [{ 'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/', 'info_dict': { - 'id': 'dholbach-cryptkeeper', + 'id': 'dholbach_cryptkeeper', 'ext': 'm4a', 'title': 'Cryptkeeper', 'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.', @@ -40,11 +48,13 @@ class MixcloudIE(InfoExtractor): 'uploader_id': 'dholbach', 'thumbnail': r're:https?://.*\.jpg', 'view_count': int, + 'timestamp': 1321359578, + 'upload_date': '20111115', }, }, { 'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/', 'info_dict': { - 'id': 'gillespeterson-caribou-7-inch-vinyl-mix-chat', + 'id': 'gillespeterson_caribou-7-inch-vinyl-mix-chat', 'ext': 'mp3', 'title': 'Caribou 7 inch Vinyl Mix & Chat', 'description': 'md5:2b8aec6adce69f9d41724647c65875e8', @@ -52,11 +62,14 @@ class MixcloudIE(InfoExtractor): 'uploader_id': 'gillespeterson', 'thumbnail': 're:https?://.*', 'view_count': int, + 'timestamp': 1422987057, + 'upload_date': '20150203', }, }, { 'url': 'https://beta.mixcloud.com/RedLightRadio/nosedrip-15-red-light-radio-01-18-2016/', 'only_matching': True, }] + _DECRYPTION_KEY = 'IFYOUWANTTHEARTISTSTOGETPAIDDONOTDOWNLOADFROMMIXCLOUD' @staticmethod def _decrypt_xor_cipher(key, ciphertext): @@ -66,177 +79,193 @@ class MixcloudIE(InfoExtractor): for ch, k in compat_zip(ciphertext, itertools.cycle(key))]) def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - uploader = mobj.group(1) - cloudcast_name = mobj.group(2) - track_id = compat_urllib_parse_unquote('-'.join((uploader, cloudcast_name))) + username, slug = re.match(self._VALID_URL, url).groups() + username, slug = compat_urllib_parse_unquote(username), compat_urllib_parse_unquote(slug) + track_id = '%s_%s' % (username, slug) - webpage = self._download_webpage(url, track_id) + cloudcast = self._call_api('cloudcast', '''audioLength + comments(first: 100) { + edges { + node { + comment + created + user { + displayName + username + } + } + } + totalCount + } + description + favorites { + totalCount + } + featuringArtistList + isExclusive + name + owner { + displayName + url + username + } + picture(width: 1024, height: 1024) { + url + } + plays + publishDate + reposts { + totalCount + } + streamInfo { + dashUrl + hlsUrl + url + } + tags { + tag { + name + } + }''', track_id, username, slug) - # Legacy path - encrypted_play_info = self._search_regex( - r'm-play-info="([^"]+)"', webpage, 'play info', default=None) + title = cloudcast['name'] - if encrypted_play_info is not None: - # Decode - encrypted_play_info = compat_b64decode(encrypted_play_info) - else: - # New path - full_info_json = self._parse_json(self._html_search_regex( - r'<script id="relay-data" type="text/x-mixcloud">([^<]+)</script>', - webpage, 'play info'), 'play info') - for item in full_info_json: - item_data = try_get(item, [ - lambda x: x['cloudcast']['data']['cloudcastLookup'], - lambda x: x['cloudcastLookup']['data']['cloudcastLookup'], - ], dict) - if try_get(item_data, lambda x: x['streamInfo']['url']): - info_json = item_data - break - else: - raise ExtractorError('Failed to extract matching stream info') + stream_info = cloudcast['streamInfo'] + formats = [] - message = self._html_search_regex( - r'(?s)<div[^>]+class="global-message cloudcast-disabled-notice-light"[^>]*>(.+?)<(?:a|/div)', - webpage, 'error message', default=None) - - js_url = self._search_regex( - r'<script[^>]+\bsrc=["\"](https://(?:www\.)?mixcloud\.com/media/(?:js2/www_js_4|js/www)\.[^>]+\.js)', - webpage, 'js url') - js = self._download_webpage(js_url, track_id, 'Downloading JS') - # Known plaintext attack - if encrypted_play_info: - kps = ['{"stream_url":'] - kpa_target = encrypted_play_info - else: - kps = ['https://', 'http://'] - kpa_target = compat_b64decode(info_json['streamInfo']['url']) - for kp in kps: - partial_key = self._decrypt_xor_cipher(kpa_target, kp) - for quote in ["'", '"']: - key = self._search_regex( - r'{0}({1}[^{0}]*){0}'.format(quote, re.escape(partial_key)), - js, 'encryption key', default=None) - if key is not None: - break - else: + for url_key in ('url', 'hlsUrl', 'dashUrl'): + format_url = stream_info.get(url_key) + if not format_url: continue - break - else: - raise ExtractorError('Failed to extract encryption key') + decrypted = self._decrypt_xor_cipher( + self._DECRYPTION_KEY, compat_b64decode(format_url)) + if url_key == 'hlsUrl': + formats.extend(self._extract_m3u8_formats( + decrypted, track_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False)) + elif url_key == 'dashUrl': + formats.extend(self._extract_mpd_formats( + decrypted, track_id, mpd_id='dash', fatal=False)) + else: + formats.append({ + 'format_id': 'http', + 'url': decrypted, + 'downloader_options': { + # Mixcloud starts throttling at >~5M + 'http_chunk_size': 5242880, + }, + }) - if encrypted_play_info is not None: - play_info = self._parse_json(self._decrypt_xor_cipher(key, encrypted_play_info), 'play info') - if message and 'stream_url' not in play_info: - raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True) - song_url = play_info['stream_url'] - formats = [{ - 'format_id': 'normal', - 'url': song_url - }] + if not formats and cloudcast.get('isExclusive'): + self.raise_login_required() - title = self._html_search_regex(r'm-title="([^"]+)"', webpage, 'title') - thumbnail = self._proto_relative_url(self._html_search_regex( - r'm-thumbnail-url="([^"]+)"', webpage, 'thumbnail', fatal=False)) - uploader = self._html_search_regex( - r'm-owner-name="([^"]+)"', webpage, 'uploader', fatal=False) - uploader_id = self._search_regex( - r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False) - description = self._og_search_description(webpage) - view_count = str_to_int(self._search_regex( - [r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"', - r'/listeners/?">([0-9,.]+)</a>', - r'(?:m|data)-tooltip=["\']([\d,.]+) plays'], - webpage, 'play count', default=None)) + self._sort_formats(formats) - else: - title = info_json['name'] - thumbnail = urljoin( - 'https://thumbnailer.mixcloud.com/unsafe/600x600/', - try_get(info_json, lambda x: x['picture']['urlRoot'], compat_str)) - uploader = try_get(info_json, lambda x: x['owner']['displayName']) - uploader_id = try_get(info_json, lambda x: x['owner']['username']) - description = try_get(info_json, lambda x: x['description']) - view_count = int_or_none(try_get(info_json, lambda x: x['plays'])) + comments = [] + for edge in (try_get(cloudcast, lambda x: x['comments']['edges']) or []): + node = edge.get('node') or {} + text = strip_or_none(node.get('comment')) + if not text: + continue + user = node.get('user') or {} + comments.append({ + 'author': user.get('displayName'), + 'author_id': user.get('username'), + 'text': text, + 'timestamp': parse_iso8601(node.get('created')), + }) - stream_info = info_json['streamInfo'] - formats = [] + tags = [] + for t in cloudcast.get('tags'): + tag = try_get(t, lambda x: x['tag']['name'], compat_str) + if not tag: + tags.append(tag) - def decrypt_url(f_url): - for k in (key, 'IFYOUWANTTHEARTISTSTOGETPAIDDONOTDOWNLOADFROMMIXCLOUD'): - decrypted_url = self._decrypt_xor_cipher(k, f_url) - if re.search(r'^https?://[0-9A-Za-z.]+/[0-9A-Za-z/.?=&_-]+$', decrypted_url): - return decrypted_url + get_count = lambda x: int_or_none(try_get(cloudcast, lambda y: y[x]['totalCount'])) - for url_key in ('url', 'hlsUrl', 'dashUrl'): - format_url = stream_info.get(url_key) - if not format_url: - continue - decrypted = decrypt_url(compat_b64decode(format_url)) - if not decrypted: - continue - if url_key == 'hlsUrl': - formats.extend(self._extract_m3u8_formats( - decrypted, track_id, 'mp4', entry_protocol='m3u8_native', - m3u8_id='hls', fatal=False)) - elif url_key == 'dashUrl': - formats.extend(self._extract_mpd_formats( - decrypted, track_id, mpd_id='dash', fatal=False)) - else: - formats.append({ - 'format_id': 'http', - 'url': decrypted, - 'downloader_options': { - # Mixcloud starts throttling at >~5M - 'http_chunk_size': 5242880, - }, - }) - self._sort_formats(formats) + owner = cloudcast.get('owner') or {} return { 'id': track_id, 'title': title, 'formats': formats, - 'description': description, - 'thumbnail': thumbnail, - 'uploader': uploader, - 'uploader_id': uploader_id, - 'view_count': view_count, + 'description': cloudcast.get('description'), + 'thumbnail': try_get(cloudcast, lambda x: x['picture']['url'], compat_str), + 'uploader': owner.get('displayName'), + 'timestamp': parse_iso8601(cloudcast.get('publishDate')), + 'uploader_id': owner.get('username'), + 'uploader_url': owner.get('url'), + 'duration': int_or_none(cloudcast.get('audioLength')), + 'view_count': int_or_none(cloudcast.get('plays')), + 'like_count': get_count('favorites'), + 'repost_count': get_count('reposts'), + 'comment_count': get_count('comments'), + 'comments': comments, + 'tags': tags, + 'artist': ', '.join(cloudcast.get('featuringArtistList') or []) or None, } -class MixcloudPlaylistBaseIE(InfoExtractor): - _PAGE_SIZE = 24 +class MixcloudPlaylistBaseIE(MixcloudBaseIE): + def _get_cloudcast(self, node): + return node - def _find_urls_in_page(self, page): - for url in re.findall(r'm-play-button m-url="(?P<url>[^"]+)"', page): - yield self.url_result( - compat_urlparse.urljoin('https://www.mixcloud.com', clean_html(url)), - MixcloudIE.ie_key()) + def _get_playlist_title(self, title, slug): + return title - def _fetch_tracks_page(self, path, video_id, page_name, current_page, real_page_number=None): - real_page_number = real_page_number or current_page + 1 - return self._download_webpage( - 'https://www.mixcloud.com/%s/' % path, video_id, - note='Download %s (page %d)' % (page_name, current_page + 1), - errnote='Unable to download %s' % page_name, - query={'page': real_page_number, 'list': 'main', '_ajax': '1'}, - headers={'X-Requested-With': 'XMLHttpRequest'}) + def _real_extract(self, url): + username, slug = re.match(self._VALID_URL, url).groups() + username = compat_urllib_parse_unquote(username) + if not slug: + slug = 'uploads' + else: + slug = compat_urllib_parse_unquote(slug) + playlist_id = '%s_%s' % (username, slug) - def _tracks_page_func(self, page, video_id, page_name, current_page): - resp = self._fetch_tracks_page(page, video_id, page_name, current_page) + is_playlist_type = self._ROOT_TYPE == 'playlist' + playlist_type = 'items' if is_playlist_type else slug + list_filter = '' - for item in self._find_urls_in_page(resp): - yield item + has_next_page = True + entries = [] + while has_next_page: + playlist = self._call_api( + self._ROOT_TYPE, '''%s + %s + %s(first: 100%s) { + edges { + node { + %s + } + } + pageInfo { + endCursor + hasNextPage + } + }''' % (self._TITLE_KEY, self._DESCRIPTION_KEY, playlist_type, list_filter, self._NODE_TEMPLATE), + playlist_id, username, slug if is_playlist_type else None) - def _get_user_description(self, page_content): - return self._html_search_regex( - r'<div[^>]+class="profile-bio"[^>]*>(.+?)</div>', - page_content, 'user description', fatal=False) + items = playlist.get(playlist_type) or {} + for edge in items.get('edges', []): + cloudcast = self._get_cloudcast(edge.get('node') or {}) + cloudcast_url = cloudcast.get('url') + if not cloudcast_url: + continue + entries.append(self.url_result( + cloudcast_url, MixcloudIE.ie_key(), cloudcast.get('slug'))) + + page_info = items['pageInfo'] + has_next_page = page_info['hasNextPage'] + list_filter = ', after: "%s"' % page_info['endCursor'] + + return self.playlist_result( + entries, playlist_id, + self._get_playlist_title(playlist[self._TITLE_KEY], slug), + playlist.get(self._DESCRIPTION_KEY)) class MixcloudUserIE(MixcloudPlaylistBaseIE): - _VALID_URL = r'https?://(?:www\.)?mixcloud\.com/(?P<user>[^/]+)/(?P<type>uploads|favorites|listens)?/?$' + _VALID_URL = r'https?://(?:www\.)?mixcloud\.com/(?P<id>[^/]+)/(?P<type>uploads|favorites|listens|stream)?/?$' IE_NAME = 'mixcloud:user' _TESTS = [{ @@ -244,68 +273,58 @@ class MixcloudUserIE(MixcloudPlaylistBaseIE): 'info_dict': { 'id': 'dholbach_uploads', 'title': 'Daniel Holbach (uploads)', - 'description': 'md5:def36060ac8747b3aabca54924897e47', + 'description': 'md5:b60d776f0bab534c5dabe0a34e47a789', }, - 'playlist_mincount': 11, + 'playlist_mincount': 36, }, { 'url': 'http://www.mixcloud.com/dholbach/uploads/', 'info_dict': { 'id': 'dholbach_uploads', 'title': 'Daniel Holbach (uploads)', - 'description': 'md5:def36060ac8747b3aabca54924897e47', + 'description': 'md5:b60d776f0bab534c5dabe0a34e47a789', }, - 'playlist_mincount': 11, + 'playlist_mincount': 36, }, { 'url': 'http://www.mixcloud.com/dholbach/favorites/', 'info_dict': { 'id': 'dholbach_favorites', 'title': 'Daniel Holbach (favorites)', - 'description': 'md5:def36060ac8747b3aabca54924897e47', + 'description': 'md5:b60d776f0bab534c5dabe0a34e47a789', }, - 'params': { - 'playlist_items': '1-100', - }, - 'playlist_mincount': 100, + # 'params': { + # 'playlist_items': '1-100', + # }, + 'playlist_mincount': 396, }, { 'url': 'http://www.mixcloud.com/dholbach/listens/', 'info_dict': { 'id': 'dholbach_listens', 'title': 'Daniel Holbach (listens)', - 'description': 'md5:def36060ac8747b3aabca54924897e47', + 'description': 'md5:b60d776f0bab534c5dabe0a34e47a789', }, - 'params': { - 'playlist_items': '1-100', + # 'params': { + # 'playlist_items': '1-100', + # }, + 'playlist_mincount': 1623, + 'skip': 'Large list', + }, { + 'url': 'https://www.mixcloud.com/FirstEar/stream/', + 'info_dict': { + 'id': 'FirstEar_stream', + 'title': 'First Ear (stream)', + 'description': 'Curators of good music\r\n\r\nfirstearmusic.com', }, - 'playlist_mincount': 100, + 'playlist_mincount': 271, }] - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - user_id = mobj.group('user') - list_type = mobj.group('type') + _TITLE_KEY = 'displayName' + _DESCRIPTION_KEY = 'biog' + _ROOT_TYPE = 'user' + _NODE_TEMPLATE = '''slug + url''' - # if only a profile URL was supplied, default to download all uploads - if list_type is None: - list_type = 'uploads' - - video_id = '%s_%s' % (user_id, list_type) - - profile = self._download_webpage( - 'https://www.mixcloud.com/%s/' % user_id, video_id, - note='Downloading user profile', - errnote='Unable to download user profile') - - username = self._og_search_title(profile) - description = self._get_user_description(profile) - - entries = OnDemandPagedList( - functools.partial( - self._tracks_page_func, - '%s/%s' % (user_id, list_type), video_id, 'list of %s' % list_type), - self._PAGE_SIZE) - - return self.playlist_result( - entries, video_id, '%s (%s)' % (username, list_type), description) + def _get_playlist_title(self, title, slug): + return '%s (%s)' % (title, slug) class MixcloudPlaylistIE(MixcloudPlaylistBaseIE): @@ -313,87 +332,20 @@ class MixcloudPlaylistIE(MixcloudPlaylistBaseIE): IE_NAME = 'mixcloud:playlist' _TESTS = [{ - 'url': 'https://www.mixcloud.com/RedBullThre3style/playlists/tokyo-finalists-2015/', - 'info_dict': { - 'id': 'RedBullThre3style_tokyo-finalists-2015', - 'title': 'National Champions 2015', - 'description': 'md5:6ff5fb01ac76a31abc9b3939c16243a3', - }, - 'playlist_mincount': 16, - }, { 'url': 'https://www.mixcloud.com/maxvibes/playlists/jazzcat-on-ness-radio/', - 'only_matching': True, - }] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - user_id = mobj.group('user') - playlist_id = mobj.group('playlist') - video_id = '%s_%s' % (user_id, playlist_id) - - webpage = self._download_webpage( - url, user_id, - note='Downloading playlist page', - errnote='Unable to download playlist page') - - title = self._html_search_regex( - r'<a[^>]+class="parent active"[^>]*><b>\d+</b><span[^>]*>([^<]+)', - webpage, 'playlist title', - default=None) or self._og_search_title(webpage, fatal=False) - description = self._get_user_description(webpage) - - entries = OnDemandPagedList( - functools.partial( - self._tracks_page_func, - '%s/playlists/%s' % (user_id, playlist_id), video_id, 'tracklist'), - self._PAGE_SIZE) - - return self.playlist_result(entries, video_id, title, description) - - -class MixcloudStreamIE(MixcloudPlaylistBaseIE): - _VALID_URL = r'https?://(?:www\.)?mixcloud\.com/(?P<id>[^/]+)/stream/?$' - IE_NAME = 'mixcloud:stream' - - _TEST = { - 'url': 'https://www.mixcloud.com/FirstEar/stream/', 'info_dict': { - 'id': 'FirstEar', - 'title': 'First Ear', - 'description': 'Curators of good music\nfirstearmusic.com', + 'id': 'maxvibes_jazzcat-on-ness-radio', + 'title': 'Ness Radio sessions', }, - 'playlist_mincount': 192, - } + 'playlist_mincount': 59, + }] + _TITLE_KEY = 'name' + _DESCRIPTION_KEY = 'description' + _ROOT_TYPE = 'playlist' + _NODE_TEMPLATE = '''cloudcast { + slug + url + }''' - def _real_extract(self, url): - user_id = self._match_id(url) - - webpage = self._download_webpage(url, user_id) - - entries = [] - prev_page_url = None - - def _handle_page(page): - entries.extend(self._find_urls_in_page(page)) - return self._search_regex( - r'm-next-page-url="([^"]+)"', page, - 'next page URL', default=None) - - next_page_url = _handle_page(webpage) - - for idx in itertools.count(0): - if not next_page_url or prev_page_url == next_page_url: - break - - prev_page_url = next_page_url - current_page = int(self._search_regex( - r'\?page=(\d+)', next_page_url, 'next page number')) - - next_page_url = _handle_page(self._fetch_tracks_page( - '%s/stream' % user_id, user_id, 'stream', idx, - real_page_number=current_page)) - - username = self._og_search_title(webpage) - description = self._get_user_description(webpage) - - return self.playlist_result(entries, user_id, username, description) + def _get_cloudcast(self, node): + return node.get('cloudcast') or {} From d4f53af482cc47b0473a3576da7ad902bea4ac39 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 6 Nov 2019 23:14:26 +0100 Subject: [PATCH 178/422] [lnkgo] fix extraction(closes #16834) --- youtube_dl/extractor/lnkgo.py | 100 ++++++++++++---------------------- 1 file changed, 36 insertions(+), 64 deletions(-) diff --git a/youtube_dl/extractor/lnkgo.py b/youtube_dl/extractor/lnkgo.py index cfec0d3d0..3e71852aa 100644 --- a/youtube_dl/extractor/lnkgo.py +++ b/youtube_dl/extractor/lnkgo.py @@ -5,24 +5,27 @@ import re from .common import InfoExtractor from ..utils import ( + clean_html, + compat_str, int_or_none, - unified_strdate, + parse_iso8601, ) class LnkGoIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?lnkgo\.(?:alfa\.)?lt/visi-video/(?P<show>[^/]+)/ziurek-(?P<id>[A-Za-z0-9-]+)' + _VALID_URL = r'https?://(?:www\.)?lnk(?:go)?\.(?:alfa\.)?lt/(?:visi-video/[^/]+|video)/(?P<id>[A-Za-z0-9-]+)(?:/(?P<episode_id>\d+))?' _TESTS = [{ - 'url': 'http://lnkgo.alfa.lt/visi-video/yra-kaip-yra/ziurek-yra-kaip-yra-162', + 'url': 'http://www.lnkgo.lt/visi-video/aktualai-pratesimas/ziurek-putka-trys-klausimai', 'info_dict': { - 'id': '46712', + 'id': '10809', 'ext': 'mp4', - 'title': 'Yra kaip yra', - 'upload_date': '20150107', - 'description': 'md5:d82a5e36b775b7048617f263a0e3475e', - 'age_limit': 7, - 'duration': 3019, - 'thumbnail': r're:^https?://.*\.jpg$' + 'title': "Put'ka: Trys Klausimai", + 'upload_date': '20161216', + 'description': 'Seniai matytas Put’ka užduoda tris klausimėlius. Pabandykime surasti atsakymus.', + 'age_limit': 18, + 'duration': 117, + 'thumbnail': r're:^https?://.*\.jpg$', + 'timestamp': 1481904000, }, 'params': { 'skip_download': True, # HLS download @@ -30,20 +33,21 @@ class LnkGoIE(InfoExtractor): }, { 'url': 'http://lnkgo.alfa.lt/visi-video/aktualai-pratesimas/ziurek-nerdas-taiso-kompiuteri-2', 'info_dict': { - 'id': '47289', + 'id': '10467', 'ext': 'mp4', 'title': 'Nėrdas: Kompiuterio Valymas', 'upload_date': '20150113', 'description': 'md5:7352d113a242a808676ff17e69db6a69', 'age_limit': 18, 'duration': 346, - 'thumbnail': r're:^https?://.*\.jpg$' + 'thumbnail': r're:^https?://.*\.jpg$', + 'timestamp': 1421164800, }, 'params': { 'skip_download': True, # HLS download }, }, { - 'url': 'http://www.lnkgo.lt/visi-video/aktualai-pratesimas/ziurek-putka-trys-klausimai', + 'url': 'https://lnk.lt/video/neigalieji-tv-bokste/37413', 'only_matching': True, }] _AGE_LIMITS = { @@ -51,66 +55,34 @@ class LnkGoIE(InfoExtractor): 'N-14': 14, 'S': 18, } + _M3U8_TEMPL = 'https://vod.lnk.lt/lnk_vod/lnk/lnk/%s:%s/playlist.m3u8%s' def _real_extract(self, url): - display_id = self._match_id(url) + display_id, video_id = re.match(self._VALID_URL, url).groups() - webpage = self._download_webpage( - url, display_id, 'Downloading player webpage') - - video_id = self._search_regex( - r'data-ep="([^"]+)"', webpage, 'video ID') - title = self._og_search_title(webpage) - description = self._og_search_description(webpage) - upload_date = unified_strdate(self._search_regex( - r'class="[^"]*meta-item[^"]*air-time[^"]*">.*?<strong>([^<]+)</strong>', webpage, 'upload date', fatal=False)) - - thumbnail_w = int_or_none( - self._og_search_property('image:width', webpage, 'thumbnail width', fatal=False)) - thumbnail_h = int_or_none( - self._og_search_property('image:height', webpage, 'thumbnail height', fatal=False)) - thumbnail = { - 'url': self._og_search_thumbnail(webpage), - } - if thumbnail_w and thumbnail_h: - thumbnail.update({ - 'width': thumbnail_w, - 'height': thumbnail_h, - }) - - config = self._parse_json(self._search_regex( - r'episodePlayer\((\{.*?\}),\s*\{', webpage, 'sources'), video_id) - - if config.get('pGeo'): - self.report_warning( - 'This content might not be available in your country due to copyright reasons') - - formats = [{ - 'format_id': 'hls', - 'ext': 'mp4', - 'url': config['EpisodeVideoLink_HLS'], - }] - - m = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<play_path>.+)$', config['EpisodeVideoLink']) - if m: - formats.append({ - 'format_id': 'rtmp', - 'ext': 'flv', - 'url': m.group('url'), - 'play_path': m.group('play_path'), - 'page_url': url, - }) + video_info = self._download_json( + 'https://lnk.lt/api/main/video-page/%s/%s/false' % (display_id, video_id or '0'), + display_id)['videoConfig']['videoInfo'] + video_id = compat_str(video_info['id']) + title = video_info['title'] + prefix = 'smil' if video_info.get('isQualityChangeAvailable') else 'mp4' + formats = self._extract_m3u8_formats( + self._M3U8_TEMPL % (prefix, video_info['videoUrl'], video_info.get('secureTokenParams') or ''), + video_id, 'mp4', 'm3u8_native') self._sort_formats(formats) + poster_image = video_info.get('posterImage') + return { 'id': video_id, 'display_id': display_id, 'title': title, 'formats': formats, - 'thumbnails': [thumbnail], - 'duration': int_or_none(config.get('VideoTime')), - 'description': description, - 'age_limit': self._AGE_LIMITS.get(config.get('PGRating'), 0), - 'upload_date': upload_date, + 'thumbnail': 'https://lnk.lt/all-images/' + poster_image if poster_image else None, + 'duration': int_or_none(video_info.get('duration')), + 'description': clean_html(video_info.get('htmlDescription')), + 'age_limit': self._AGE_LIMITS.get(video_info.get('pgRating'), 0), + 'timestamp': parse_iso8601(video_info.get('airDate')), + 'view_count': int_or_none(video_info.get('viewsCount')), } From 0b16b3c2d35d1706ec5c55e5b06352c753127368 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sat, 9 Nov 2019 09:22:24 +0100 Subject: [PATCH 179/422] [twitch] add support for Clip embed URLs --- youtube_dl/extractor/twitch.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py index ca7676fe2..a5681409c 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -644,7 +644,7 @@ class TwitchStreamIE(TwitchBaseIE): class TwitchClipsIE(TwitchBaseIE): IE_NAME = 'twitch:clips' - _VALID_URL = r'https?://(?:clips\.twitch\.tv/(?:[^/]+/)*|(?:www\.)?twitch\.tv/[^/]+/clip/)(?P<id>[^/?#&]+)' + _VALID_URL = r'https?://(?:clips\.twitch\.tv/(?:embed\?.*?\bclip=|(?:[^/]+/)*)|(?:www\.)?twitch\.tv/[^/]+/clip/)(?P<id>[^/?#&]+)' _TESTS = [{ 'url': 'https://clips.twitch.tv/FaintLightGullWholeWheat', @@ -667,6 +667,9 @@ class TwitchClipsIE(TwitchBaseIE): }, { 'url': 'https://www.twitch.tv/sergeynixon/clip/StormyThankfulSproutFutureMan', 'only_matching': True, + }, { + 'url': 'https://clips.twitch.tv/embed?clip=InquisitiveBreakableYogurtJebaited', + 'only_matching': True, }] def _real_extract(self, url): From 18ca61c5e153d1c1cb8b9a2de3c8b9dfdaa69b0e Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sat, 9 Nov 2019 09:23:20 +0100 Subject: [PATCH 180/422] [twitter] improve extraction - add support for generic embeds(closes #22168) - always extract http formats for native videos(closes #14934) - add support for Twitter Broadcasts(closes #21369) - extract more metadata - improve VMap format extraction - unify extraction code for both twitter statuses and cards --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/periscope.py | 80 ++-- youtube_dl/extractor/twitter.py | 570 +++++++++++++++-------------- 3 files changed, 344 insertions(+), 307 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 2f9ba6893..598006061 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1241,6 +1241,7 @@ from .twitter import ( TwitterCardIE, TwitterIE, TwitterAmplifyIE, + TwitterBroadcastIE, ) from .udemy import ( UdemyIE, diff --git a/youtube_dl/extractor/periscope.py b/youtube_dl/extractor/periscope.py index b337a56c0..c02e34aba 100644 --- a/youtube_dl/extractor/periscope.py +++ b/youtube_dl/extractor/periscope.py @@ -17,12 +17,54 @@ class PeriscopeBaseIE(InfoExtractor): 'https://api.periscope.tv/api/v2/%s' % method, item_id, query=query) + def _parse_broadcast_data(self, broadcast, video_id): + title = broadcast['status'] + uploader = broadcast.get('user_display_name') or broadcast.get('username') + title = '%s - %s' % (uploader, title) if uploader else title + is_live = broadcast.get('state').lower() == 'running' + + thumbnails = [{ + 'url': broadcast[image], + } for image in ('image_url', 'image_url_small') if broadcast.get(image)] + + return { + 'id': broadcast.get('id') or video_id, + 'title': self._live_title(title) if is_live else title, + 'timestamp': parse_iso8601(broadcast.get('created_at')), + 'uploader': uploader, + 'uploader_id': broadcast.get('user_id') or broadcast.get('username'), + 'thumbnails': thumbnails, + 'view_count': int_or_none(broadcast.get('total_watched')), + 'tags': broadcast.get('tags'), + 'is_live': is_live, + } + + @staticmethod + def _extract_common_format_info(broadcast): + return broadcast.get('state').lower(), int_or_none(broadcast.get('width')), int_or_none(broadcast.get('height')) + + @staticmethod + def _add_width_and_height(f, width, height): + for key, val in (('width', width), ('height', height)): + if not f.get(key): + f[key] = val + + def _extract_pscp_m3u8_formats(self, m3u8_url, video_id, format_id, state, width, height, fatal=True): + m3u8_formats = self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', + entry_protocol='m3u8_native' + if state in ('ended', 'timed_out') else 'm3u8', + m3u8_id=format_id, fatal=fatal) + if len(m3u8_formats) == 1: + self._add_width_and_height(m3u8_formats[0], width, height) + return m3u8_formats + class PeriscopeIE(PeriscopeBaseIE): IE_DESC = 'Periscope' IE_NAME = 'periscope' _VALID_URL = r'https?://(?:www\.)?(?:periscope|pscp)\.tv/[^/]+/(?P<id>[^/?#]+)' - # Alive example URLs can be found here http://onperiscope.com/ + # Alive example URLs can be found here https://www.periscope.tv/ _TESTS = [{ 'url': 'https://www.periscope.tv/w/aJUQnjY3MjA3ODF8NTYxMDIyMDl2zCg2pECBgwTqRpQuQD352EMPTKQjT4uqlM3cgWFA-g==', 'md5': '65b57957972e503fcbbaeed8f4fa04ca', @@ -61,21 +103,9 @@ class PeriscopeIE(PeriscopeBaseIE): 'accessVideoPublic', {'broadcast_id': token}, token) broadcast = stream['broadcast'] - title = broadcast['status'] + info = self._parse_broadcast_data(broadcast, token) - uploader = broadcast.get('user_display_name') or broadcast.get('username') - uploader_id = (broadcast.get('user_id') or broadcast.get('username')) - - title = '%s - %s' % (uploader, title) if uploader else title state = broadcast.get('state').lower() - if state == 'running': - title = self._live_title(title) - timestamp = parse_iso8601(broadcast.get('created_at')) - - thumbnails = [{ - 'url': broadcast[image], - } for image in ('image_url', 'image_url_small') if broadcast.get(image)] - width = int_or_none(broadcast.get('width')) height = int_or_none(broadcast.get('height')) @@ -92,32 +122,20 @@ class PeriscopeIE(PeriscopeBaseIE): continue video_urls.add(video_url) if format_id != 'rtmp': - m3u8_formats = self._extract_m3u8_formats( - video_url, token, 'mp4', - entry_protocol='m3u8_native' - if state in ('ended', 'timed_out') else 'm3u8', - m3u8_id=format_id, fatal=False) - if len(m3u8_formats) == 1: - add_width_and_height(m3u8_formats[0]) + m3u8_formats = self._extract_pscp_m3u8_formats( + video_url, token, format_id, state, width, height, False) formats.extend(m3u8_formats) continue rtmp_format = { 'url': video_url, 'ext': 'flv' if format_id == 'rtmp' else 'mp4', } - add_width_and_height(rtmp_format) + self._add_width_and_height(rtmp_format) formats.append(rtmp_format) self._sort_formats(formats) - return { - 'id': broadcast.get('id') or token, - 'title': title, - 'timestamp': timestamp, - 'uploader': uploader, - 'uploader_id': uploader_id, - 'thumbnails': thumbnails, - 'formats': formats, - } + info['formats'] = formats + return info class PeriscopeUserIE(PeriscopeBaseIE): diff --git a/youtube_dl/extractor/twitter.py b/youtube_dl/extractor/twitter.py index cebb6238c..5f8d90fb4 100644 --- a/youtube_dl/extractor/twitter.py +++ b/youtube_dl/extractor/twitter.py @@ -4,32 +4,67 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_urlparse +from ..compat import ( + compat_HTTPError, + compat_parse_qs, + compat_urllib_parse_unquote, + compat_urllib_parse_urlparse, +) from ..utils import ( - determine_ext, dict_get, ExtractorError, float_or_none, int_or_none, - remove_end, try_get, + strip_or_none, + unified_timestamp, + update_url_query, xpath_text, ) -from .periscope import PeriscopeIE +from .periscope import ( + PeriscopeBaseIE, + PeriscopeIE, +) class TwitterBaseIE(InfoExtractor): + _API_BASE = 'https://api.twitter.com/1.1/' + _BASE_REGEX = r'https?://(?:(?:www|m(?:obile)?)\.)?twitter\.com/' + _GUEST_TOKEN = None + + def _extract_variant_formats(self, variant, video_id): + variant_url = variant.get('url') + if not variant_url: + return [] + elif '.m3u8' in variant_url: + return self._extract_m3u8_formats( + variant_url, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False) + else: + tbr = int_or_none(dict_get(variant, ('bitrate', 'bit_rate')), 1000) or None + f = { + 'url': variant_url, + 'format_id': 'http' + ('-%d' % tbr if tbr else ''), + 'tbr': tbr, + } + self._search_dimensions_in_video_url(f, variant_url) + return [f] + def _extract_formats_from_vmap_url(self, vmap_url, video_id): vmap_data = self._download_xml(vmap_url, video_id) - video_url = xpath_text(vmap_data, './/MediaFile').strip() - if determine_ext(video_url) == 'm3u8': - return self._extract_m3u8_formats( - video_url, video_id, ext='mp4', m3u8_id='hls', - entry_protocol='m3u8_native') - return [{ - 'url': video_url, - }] + formats = [] + urls = [] + for video_variant in vmap_data.findall('.//{http://twitter.com/schema/videoVMapV2.xsd}videoVariant'): + video_variant.attrib['url'] = compat_urllib_parse_unquote( + video_variant.attrib['url']) + urls.append(video_variant.attrib['url']) + formats.extend(self._extract_variant_formats( + video_variant.attrib, video_id)) + video_url = strip_or_none(xpath_text(vmap_data, './/MediaFile')) + if video_url not in urls: + formats.extend(self._extract_variant_formats({'url': video_url}, video_id)) + return formats @staticmethod def _search_dimensions_in_video_url(a_format, video_url): @@ -40,10 +75,30 @@ class TwitterBaseIE(InfoExtractor): 'height': int(m.group('height')), }) + def _call_api(self, path, video_id, query={}): + headers = { + 'Authorization': 'Bearer AAAAAAAAAAAAAAAAAAAAAPYXBAAAAAAACLXUNDekMxqa8h%2F40K4moUkGsoc%3DTYfbDKbT3jJPCEVnMYqilB28NHfOPqkca3qaAxGfsyKCs0wRbw', + } + if not self._GUEST_TOKEN: + self._GUEST_TOKEN = self._download_json( + self._API_BASE + 'guest/activate.json', video_id, + 'Downloading guest token', data=b'', + headers=headers)['guest_token'] + headers['x-guest-token'] = self._GUEST_TOKEN + try: + return self._download_json( + self._API_BASE + path, video_id, headers=headers, query=query) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + raise ExtractorError(self._parse_json( + e.cause.read().decode(), + video_id)['errors'][0]['message'], expected=True) + raise -class TwitterCardIE(TwitterBaseIE): + +class TwitterCardIE(InfoExtractor): IE_NAME = 'twitter:card' - _VALID_URL = r'https?://(?:www\.)?twitter\.com/i/(?P<path>cards/tfw/v1|videos(?:/tweet)?)/(?P<id>\d+)' + _VALID_URL = TwitterBaseIE._BASE_REGEX + r'i/(?:cards/tfw/v1|videos(?:/tweet)?)/(?P<id>\d+)' _TESTS = [ { 'url': 'https://twitter.com/i/cards/tfw/v1/560070183650213889', @@ -51,19 +106,28 @@ class TwitterCardIE(TwitterBaseIE): 'info_dict': { 'id': '560070183650213889', 'ext': 'mp4', - 'title': 'Twitter web player', - 'thumbnail': r're:^https?://.*\.jpg$', + 'title': "Twitter - You can now shoot, edit and share video on Twitter. Capture life's most moving moments from your perspective.", + 'description': 'md5:18d3e24bb4f6e5007487dd546e53bd96', + 'uploader': 'Twitter', + 'uploader_id': 'Twitter', + 'thumbnail': r're:^https?://.*\.jpg', 'duration': 30.033, + 'timestamp': 1422366112, + 'upload_date': '20150127', }, }, { 'url': 'https://twitter.com/i/cards/tfw/v1/623160978427936768', - 'md5': '7ee2a553b63d1bccba97fbed97d9e1c8', + 'md5': '7137eca597f72b9abbe61e5ae0161399', 'info_dict': { 'id': '623160978427936768', 'ext': 'mp4', - 'title': 'Twitter web player', - 'thumbnail': r're:^https?://.*$', + 'title': "NASA - Fly over Pluto's icy Norgay Mountains and Sputnik Plain in this @NASANewHorizons #PlutoFlyby video.", + 'description': "Fly over Pluto's icy Norgay Mountains and Sputnik Plain in this @NASANewHorizons #PlutoFlyby video. https://t.co/BJYgOjSeGA", + 'uploader': 'NASA', + 'uploader_id': 'NASA', + 'timestamp': 1437408129, + 'upload_date': '20150720', }, }, { @@ -75,7 +139,7 @@ class TwitterCardIE(TwitterBaseIE): 'title': 'Ubuntu 11.10 Overview', 'description': 'md5:a831e97fa384863d6e26ce48d1c43376', 'upload_date': '20111013', - 'uploader': 'OMG! Ubuntu!', + 'uploader': 'OMG! UBUNTU!', 'uploader_id': 'omgubuntu', }, 'add_ie': ['Youtube'], @@ -99,190 +163,30 @@ class TwitterCardIE(TwitterBaseIE): 'info_dict': { 'id': '705235433198714880', 'ext': 'mp4', - 'title': 'Twitter web player', - 'thumbnail': r're:^https?://.*', + 'title': "Brent Yarina - Khalil Iverson's missed highlight dunk. And made highlight dunk. In one highlight.", + 'description': "Khalil Iverson's missed highlight dunk. And made highlight dunk. In one highlight. https://t.co/OrxcJ28Bns", + 'uploader': 'Brent Yarina', + 'uploader_id': 'BTNBrentYarina', + 'timestamp': 1456976204, + 'upload_date': '20160303', }, + 'skip': 'This content is no longer available.', }, { 'url': 'https://twitter.com/i/videos/752274308186120192', 'only_matching': True, }, ] - _API_BASE = 'https://api.twitter.com/1.1' - - def _parse_media_info(self, media_info, video_id): - formats = [] - for media_variant in media_info.get('variants', []): - media_url = media_variant['url'] - if media_url.endswith('.m3u8'): - formats.extend(self._extract_m3u8_formats(media_url, video_id, ext='mp4', m3u8_id='hls')) - elif media_url.endswith('.mpd'): - formats.extend(self._extract_mpd_formats(media_url, video_id, mpd_id='dash')) - else: - tbr = int_or_none(dict_get(media_variant, ('bitRate', 'bitrate')), scale=1000) - a_format = { - 'url': media_url, - 'format_id': 'http-%d' % tbr if tbr else 'http', - 'tbr': tbr, - } - # Reported bitRate may be zero - if not a_format['tbr']: - del a_format['tbr'] - - self._search_dimensions_in_video_url(a_format, media_url) - - formats.append(a_format) - return formats - - def _extract_mobile_formats(self, username, video_id): - webpage = self._download_webpage( - 'https://mobile.twitter.com/%s/status/%s' % (username, video_id), - video_id, 'Downloading mobile webpage', - headers={ - # A recent mobile UA is necessary for `gt` cookie - 'User-Agent': 'Mozilla/5.0 (Android 6.0.1; Mobile; rv:54.0) Gecko/54.0 Firefox/54.0', - }) - main_script_url = self._html_search_regex( - r'<script[^>]+src="([^"]+main\.[^"]+)"', webpage, 'main script URL') - main_script = self._download_webpage( - main_script_url, video_id, 'Downloading main script') - bearer_token = self._search_regex( - r'BEARER_TOKEN\s*:\s*"([^"]+)"', - main_script, 'bearer token') - # https://developer.twitter.com/en/docs/tweets/post-and-engage/api-reference/get-statuses-show-id - api_data = self._download_json( - '%s/statuses/show/%s.json' % (self._API_BASE, video_id), - video_id, 'Downloading API data', - headers={ - 'Authorization': 'Bearer ' + bearer_token, - }) - media_info = try_get(api_data, lambda o: o['extended_entities']['media'][0]['video_info']) or {} - return self._parse_media_info(media_info, video_id) - def _real_extract(self, url): - path, video_id = re.search(self._VALID_URL, url).groups() - - config = None - formats = [] - duration = None - - urls = [url] - if path.startswith('cards/'): - urls.append('https://twitter.com/i/videos/' + video_id) - - for u in urls: - webpage = self._download_webpage( - u, video_id, headers={'Referer': 'https://twitter.com/'}) - - iframe_url = self._html_search_regex( - r'<iframe[^>]+src="((?:https?:)?//(?:www\.youtube\.com/embed/[^"]+|(?:www\.)?vine\.co/v/\w+/card))"', - webpage, 'video iframe', default=None) - if iframe_url: - return self.url_result(iframe_url) - - config = self._parse_json(self._html_search_regex( - r'data-(?:player-)?config="([^"]+)"', webpage, - 'data player config', default='{}'), - video_id) - - if config.get('source_type') == 'vine': - return self.url_result(config['player_url'], 'Vine') - - periscope_url = PeriscopeIE._extract_url(webpage) - if periscope_url: - return self.url_result(periscope_url, PeriscopeIE.ie_key()) - - video_url = config.get('video_url') or config.get('playlist', [{}])[0].get('source') - - if video_url: - if determine_ext(video_url) == 'm3u8': - formats.extend(self._extract_m3u8_formats(video_url, video_id, ext='mp4', m3u8_id='hls')) - else: - f = { - 'url': video_url, - } - - self._search_dimensions_in_video_url(f, video_url) - - formats.append(f) - - vmap_url = config.get('vmapUrl') or config.get('vmap_url') - if vmap_url: - formats.extend( - self._extract_formats_from_vmap_url(vmap_url, video_id)) - - media_info = None - - for entity in config.get('status', {}).get('entities', []): - if 'mediaInfo' in entity: - media_info = entity['mediaInfo'] - - if media_info: - formats.extend(self._parse_media_info(media_info, video_id)) - duration = float_or_none(media_info.get('duration', {}).get('nanos'), scale=1e9) - - username = config.get('user', {}).get('screen_name') - if username: - formats.extend(self._extract_mobile_formats(username, video_id)) - - if formats: - title = self._search_regex(r'<title>([^<]+)', webpage, 'title') - thumbnail = config.get('posterImageUrl') or config.get('image_src') - duration = float_or_none(config.get('duration'), scale=1000) or duration - break - - if not formats: - headers = { - 'Authorization': 'Bearer AAAAAAAAAAAAAAAAAAAAAPYXBAAAAAAACLXUNDekMxqa8h%2F40K4moUkGsoc%3DTYfbDKbT3jJPCEVnMYqilB28NHfOPqkca3qaAxGfsyKCs0wRbw', - 'Referer': url, - } - ct0 = self._get_cookies(url).get('ct0') - if ct0: - headers['csrf_token'] = ct0.value - guest_token = self._download_json( - '%s/guest/activate.json' % self._API_BASE, video_id, - 'Downloading guest token', data=b'', - headers=headers)['guest_token'] - headers['x-guest-token'] = guest_token - self._set_cookie('api.twitter.com', 'gt', guest_token) - config = self._download_json( - '%s/videos/tweet/config/%s.json' % (self._API_BASE, video_id), - video_id, headers=headers) - track = config['track'] - vmap_url = track.get('vmapUrl') - if vmap_url: - formats = self._extract_formats_from_vmap_url(vmap_url, video_id) - else: - playback_url = track['playbackUrl'] - if determine_ext(playback_url) == 'm3u8': - formats = self._extract_m3u8_formats( - playback_url, video_id, 'mp4', - entry_protocol='m3u8_native', m3u8_id='hls') - else: - formats = [{ - 'url': playback_url, - }] - title = 'Twitter web player' - thumbnail = config.get('posterImage') - duration = float_or_none(track.get('durationMs'), scale=1000) - - self._remove_duplicate_formats(formats) - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': title, - 'thumbnail': thumbnail, - 'duration': duration, - 'formats': formats, - } + status_id = self._match_id(url) + return self.url_result( + 'https://twitter.com/statuses/' + status_id, + TwitterIE.ie_key(), status_id) -class TwitterIE(InfoExtractor): +class TwitterIE(TwitterBaseIE): IE_NAME = 'twitter' - _VALID_URL = r'https?://(?:www\.|m\.|mobile\.)?twitter\.com/(?:i/web|(?P[^/]+))/status/(?P\d+)' - _TEMPLATE_URL = 'https://twitter.com/%s/status/%s' - _TEMPLATE_STATUSES_URL = 'https://twitter.com/statuses/%s' + _VALID_URL = TwitterBaseIE._BASE_REGEX + r'(?:(?:i/web|[^/]+)/status|statuses)/(?P\d+)' _TESTS = [{ 'url': 'https://twitter.com/freethenipple/status/643211948184596480', @@ -291,10 +195,13 @@ class TwitterIE(InfoExtractor): 'ext': 'mp4', 'title': 'FREE THE NIPPLE - FTN supporters on Hollywood Blvd today!', 'thumbnail': r're:^https?://.*\.jpg', - 'description': 'FREE THE NIPPLE on Twitter: "FTN supporters on Hollywood Blvd today! http://t.co/c7jHH749xJ"', + 'description': 'FTN supporters on Hollywood Blvd today! http://t.co/c7jHH749xJ', 'uploader': 'FREE THE NIPPLE', 'uploader_id': 'freethenipple', 'duration': 12.922, + 'timestamp': 1442188653, + 'upload_date': '20150913', + 'age_limit': 18, }, }, { 'url': 'https://twitter.com/giphz/status/657991469417025536/photo/1', @@ -316,19 +223,23 @@ class TwitterIE(InfoExtractor): 'id': '665052190608723968', 'ext': 'mp4', 'title': 'Star Wars - A new beginning is coming December 18. Watch the official 60 second #TV spot for #StarWars: #TheForceAwakens.', - 'description': 'Star Wars on Twitter: "A new beginning is coming December 18. Watch the official 60 second #TV spot for #StarWars: #TheForceAwakens."', + 'description': 'A new beginning is coming December 18. Watch the official 60 second #TV spot for #StarWars: #TheForceAwakens. https://t.co/OkSqT2fjWJ', 'uploader_id': 'starwars', 'uploader': 'Star Wars', + 'timestamp': 1447395772, + 'upload_date': '20151113', }, }, { 'url': 'https://twitter.com/BTNBrentYarina/status/705235433198714880', 'info_dict': { 'id': '705235433198714880', 'ext': 'mp4', - 'title': 'Brent Yarina - Khalil Iverson\'s missed highlight dunk. And made highlight dunk. In one highlight.', - 'description': 'Brent Yarina on Twitter: "Khalil Iverson\'s missed highlight dunk. And made highlight dunk. In one highlight."', + 'title': "Brent Yarina - Khalil Iverson's missed highlight dunk. And made highlight dunk. In one highlight.", + 'description': "Khalil Iverson's missed highlight dunk. And made highlight dunk. In one highlight. https://t.co/OrxcJ28Bns", 'uploader_id': 'BTNBrentYarina', 'uploader': 'Brent Yarina', + 'timestamp': 1456976204, + 'upload_date': '20160303', }, 'params': { # The same video as https://twitter.com/i/videos/tweet/705235433198714880 @@ -340,12 +251,14 @@ class TwitterIE(InfoExtractor): 'info_dict': { 'id': '700207533655363584', 'ext': 'mp4', - 'title': 'JG - BEAT PROD: @suhmeduh #Damndaniel', - 'description': 'JG on Twitter: "BEAT PROD: @suhmeduh https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ"', + 'title': 'Simon Vertugo - BEAT PROD: @suhmeduh #Damndaniel', + 'description': 'BEAT PROD: @suhmeduh https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ', 'thumbnail': r're:^https?://.*\.jpg', - 'uploader': 'JG', - 'uploader_id': 'jaydingeer', + 'uploader': 'Simon Vertugo', + 'uploader_id': 'simonvertugo', 'duration': 30.0, + 'timestamp': 1455777459, + 'upload_date': '20160218', }, }, { 'url': 'https://twitter.com/Filmdrunk/status/713801302971588609', @@ -353,10 +266,9 @@ class TwitterIE(InfoExtractor): 'info_dict': { 'id': 'MIOxnrUteUd', 'ext': 'mp4', - 'title': 'Vince Mancini - Vine of the day', - 'description': 'Vince Mancini on Twitter: "Vine of the day https://t.co/xmTvRdqxWf"', - 'uploader': 'Vince Mancini', - 'uploader_id': 'Filmdrunk', + 'title': 'Dr.Pepperの飲み方 #japanese #バカ #ドクペ #電動ガン', + 'uploader': 'TAKUMA', + 'uploader_id': '1004126642786242560', 'timestamp': 1402826626, 'upload_date': '20140615', }, @@ -367,21 +279,22 @@ class TwitterIE(InfoExtractor): 'id': '719944021058060289', 'ext': 'mp4', 'title': 'Captain America - @King0fNerd Are you sure you made the right choice? Find out in theaters.', - 'description': 'Captain America on Twitter: "@King0fNerd Are you sure you made the right choice? Find out in theaters. https://t.co/GpgYi9xMJI"', - 'uploader_id': 'captainamerica', + 'description': '@King0fNerd Are you sure you made the right choice? Find out in theaters. https://t.co/GpgYi9xMJI', + 'uploader_id': 'CaptainAmerica', 'uploader': 'Captain America', 'duration': 3.17, + 'timestamp': 1460483005, + 'upload_date': '20160412', }, }, { 'url': 'https://twitter.com/OPP_HSD/status/779210622571536384', 'info_dict': { 'id': '1zqKVVlkqLaKB', 'ext': 'mp4', - 'title': 'Sgt Kerry Schmidt - LIVE on #Periscope: Road rage, mischief, assault, rollover and fire in one occurrence', - 'description': 'Sgt Kerry Schmidt on Twitter: "LIVE on #Periscope: Road rage, mischief, assault, rollover and fire in one occurrence https://t.co/EKrVgIXF3s"', + 'title': 'Sgt Kerry Schmidt - Ontario Provincial Police - Road rage, mischief, assault, rollover and fire in one occurrence', 'upload_date': '20160923', - 'uploader_id': 'OPP_HSD', - 'uploader': 'Sgt Kerry Schmidt', + 'uploader_id': '1PmKqpJdOJQoY', + 'uploader': 'Sgt Kerry Schmidt - Ontario Provincial Police', 'timestamp': 1474613214, }, 'add_ie': ['Periscope'], @@ -392,10 +305,12 @@ class TwitterIE(InfoExtractor): 'id': '852138619213144067', 'ext': 'mp4', 'title': 'عالم الأخبار - كلمة تاريخية بجلسة الجناسي التاريخية.. النائب خالد مؤنس العتيبي للمعارضين : اتقوا الله .. الظلم ظلمات يوم القيامة', - 'description': 'عالم الأخبار on Twitter: "كلمة تاريخية بجلسة الجناسي التاريخية.. النائب خالد مؤنس العتيبي للمعارضين : اتقوا الله .. الظلم ظلمات يوم القيامة https://t.co/xg6OhpyKfN"', + 'description': 'كلمة تاريخية بجلسة الجناسي التاريخية.. النائب خالد مؤنس العتيبي للمعارضين : اتقوا الله .. الظلم ظلمات يوم القيامة https://t.co/xg6OhpyKfN', 'uploader': 'عالم الأخبار', 'uploader_id': 'news_al3alm', 'duration': 277.4, + 'timestamp': 1492000653, + 'upload_date': '20170412', }, }, { 'url': 'https://twitter.com/i/web/status/910031516746514432', @@ -404,10 +319,12 @@ class TwitterIE(InfoExtractor): 'ext': 'mp4', 'title': 'Préfet de Guadeloupe - [Direct] #Maria Le centre se trouve actuellement au sud de Basse-Terre. Restez confinés. Réfugiez-vous dans la pièce la + sûre.', 'thumbnail': r're:^https?://.*\.jpg', - 'description': 'Préfet de Guadeloupe on Twitter: "[Direct] #Maria Le centre se trouve actuellement au sud de Basse-Terre. Restez confinés. Réfugiez-vous dans la pièce la + sûre. https://t.co/mwx01Rs4lo"', + 'description': '[Direct] #Maria Le centre se trouve actuellement au sud de Basse-Terre. Restez confinés. Réfugiez-vous dans la pièce la + sûre. https://t.co/mwx01Rs4lo', 'uploader': 'Préfet de Guadeloupe', 'uploader_id': 'Prefet971', 'duration': 47.48, + 'timestamp': 1505803395, + 'upload_date': '20170919', }, 'params': { 'skip_download': True, # requires ffmpeg @@ -420,10 +337,12 @@ class TwitterIE(InfoExtractor): 'ext': 'mp4', 'title': 're:.*?Shep is on a roll today.*?', 'thumbnail': r're:^https?://.*\.jpg', - 'description': 'md5:63b036c228772523ae1924d5f8e5ed6b', + 'description': 'md5:37b9f2ff31720cef23b2bd42ee8a0f09', 'uploader': 'Lis Power', 'uploader_id': 'LisPower1', 'duration': 111.278, + 'timestamp': 1527623489, + 'upload_date': '20180529', }, 'params': { 'skip_download': True, # requires ffmpeg @@ -435,88 +354,163 @@ class TwitterIE(InfoExtractor): 'ext': 'mp4', 'title': 'Twitter - A new is coming. Some of you got an opt-in to try it now. Check out the emoji button, quick keyboard shortcuts, upgraded trends, advanced search, and more. Let us know your thoughts!', 'thumbnail': r're:^https?://.*\.jpg', - 'description': 'md5:66d493500c013e3e2d434195746a7f78', + 'description': 'md5:6dfd341a3310fb97d80d2bf7145df976', 'uploader': 'Twitter', 'uploader_id': 'Twitter', 'duration': 61.567, + 'timestamp': 1548184644, + 'upload_date': '20190122', }, + }, { + # not available in Periscope + 'url': 'https://twitter.com/ViviEducation/status/1136534865145286656', + 'info_dict': { + 'id': '1vOGwqejwoWxB', + 'ext': 'mp4', + 'title': 'Vivi - Vivi founder @lior_rauchy announcing our new student feedback tool live at @EduTECH_AU #EduTECH2019', + 'uploader': 'Vivi', + 'uploader_id': '1eVjYOLGkGrQL', + }, + 'add_ie': ['TwitterBroadcast'], + }, { + # Twitch Clip Embed + 'url': 'https://twitter.com/GunB1g/status/1163218564784017422', + 'only_matching': True, }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - twid = mobj.group('id') - - webpage, urlh = self._download_webpage_handle( - self._TEMPLATE_STATUSES_URL % twid, twid) - - if 'twitter.com/account/suspended' in urlh.geturl(): - raise ExtractorError('Account suspended by Twitter.', expected=True) - - user_id = None - - redirect_mobj = re.match(self._VALID_URL, urlh.geturl()) - if redirect_mobj: - user_id = redirect_mobj.group('user_id') - - if not user_id: - user_id = mobj.group('user_id') - - username = remove_end(self._og_search_title(webpage), ' on Twitter') - - title = description = self._og_search_description(webpage).strip('').replace('\n', ' ').strip('“”') + twid = self._match_id(url) + status = self._call_api( + 'statuses/show/%s.json' % twid, twid, { + 'cards_platform': 'Web-12', + 'include_cards': 1, + 'include_reply_count': 1, + 'include_user_entities': 0, + 'tweet_mode': 'extended', + }) + title = description = status['full_text'].replace('\n', ' ') # strip 'https -_t.co_BJYgOjSeGA' junk from filenames title = re.sub(r'\s+(https?://[^ ]+)', '', title) + user = status.get('user') or {} + uploader = user.get('name') + if uploader: + title = '%s - %s' % (uploader, title) + uploader_id = user.get('screen_name') + + tags = [] + for hashtag in (try_get(status, lambda x: x['entities']['hashtags'], list) or []): + hashtag_text = hashtag.get('text') + if not hashtag_text: + continue + tags.append(hashtag_text) info = { - 'uploader_id': user_id, - 'uploader': username, - 'webpage_url': url, - 'description': '%s on Twitter: "%s"' % (username, description), - 'title': username + ' - ' + title, + 'id': twid, + 'title': title, + 'description': description, + 'uploader': uploader, + 'timestamp': unified_timestamp(status.get('created_at')), + 'uploader_id': uploader_id, + 'uploader_url': 'https://twitter.com/' + uploader_id if uploader_id else None, + 'like_count': int_or_none(status.get('favorite_count')), + 'repost_count': int_or_none(status.get('retweet_count')), + 'comment_count': int_or_none(status.get('reply_count')), + 'age_limit': 18 if status.get('possibly_sensitive') else 0, + 'tags': tags, } - mobj = re.search(r'''(?x) - ]+class="animated-gif"(?P[^>]+)>\s* - ]+video-src="(?P[^"]+)" - ''', webpage) + media = try_get(status, lambda x: x['extended_entities']['media'][0]) + if media and media.get('type') != 'photo': + video_info = media.get('video_info') or {} + + formats = [] + for variant in video_info.get('variants', []): + formats.extend(self._extract_variant_formats(variant, twid)) + self._sort_formats(formats) + + thumbnails = [] + media_url = media.get('media_url_https') or media.get('media_url') + if media_url: + def add_thumbnail(name, size): + thumbnails.append({ + 'id': name, + 'url': update_url_query(media_url, {'name': name}), + 'width': int_or_none(size.get('w') or size.get('width')), + 'height': int_or_none(size.get('h') or size.get('height')), + }) + for name, size in media.get('sizes', {}).items(): + add_thumbnail(name, size) + add_thumbnail('orig', media.get('original_info') or {}) - if mobj: - more_info = mobj.group('more_info') - height = int_or_none(self._search_regex( - r'data-height="(\d+)"', more_info, 'height', fatal=False)) - width = int_or_none(self._search_regex( - r'data-width="(\d+)"', more_info, 'width', fatal=False)) - thumbnail = self._search_regex( - r'poster="([^"]+)"', more_info, 'poster', fatal=False) info.update({ - 'id': twid, - 'url': mobj.group('url'), - 'height': height, - 'width': width, - 'thumbnail': thumbnail, + 'formats': formats, + 'thumbnails': thumbnails, + 'duration': float_or_none(video_info.get('duration_millis'), 1000), }) - return info - - twitter_card_url = None - if 'class="PlayableMedia' in webpage: - twitter_card_url = '%s//twitter.com/i/videos/tweet/%s' % (self.http_scheme(), twid) else: - twitter_card_iframe_url = self._search_regex( - r'data-full-card-iframe-url=([\'"])(?P(?:(?!\1).)+)\1', - webpage, 'Twitter card iframe URL', default=None, group='url') - if twitter_card_iframe_url: - twitter_card_url = compat_urlparse.urljoin(url, twitter_card_iframe_url) + card = status.get('card') + if card: + binding_values = card['binding_values'] - if twitter_card_url: - info.update({ - '_type': 'url_transparent', - 'ie_key': 'TwitterCard', - 'url': twitter_card_url, - }) - return info + def get_binding_value(k): + o = binding_values.get(k) or {} + return try_get(o, lambda x: x[x['type'].lower() + '_value']) - raise ExtractorError('There\'s no video in this tweet.') + card_name = card['name'].split(':')[-1] + if card_name == 'amplify': + formats = self._extract_formats_from_vmap_url( + get_binding_value('amplify_url_vmap'), + get_binding_value('amplify_content_id') or twid) + self._sort_formats(formats) + + thumbnails = [] + for suffix in ('_small', '', '_large', '_x_large', '_original'): + image = get_binding_value('player_image' + suffix) or {} + image_url = image.get('url') + if not image_url or '/player-placeholder' in image_url: + continue + thumbnails.append({ + 'id': suffix[1:] if suffix else 'medium', + 'url': image_url, + 'width': int_or_none(image.get('width')), + 'height': int_or_none(image.get('height')), + }) + + info.update({ + 'formats': formats, + 'thumbnails': thumbnails, + 'duration': int_or_none(get_binding_value( + 'content_duration_seconds')), + }) + elif card_name == 'player': + info.update({ + '_type': 'url', + 'url': get_binding_value('player_url'), + }) + elif card_name == 'periscope_broadcast': + info.update({ + '_type': 'url', + 'url': get_binding_value('url') or get_binding_value('player_url'), + 'ie_key': PeriscopeIE.ie_key(), + }) + elif card_name == 'broadcast': + info.update({ + '_type': 'url', + 'url': get_binding_value('broadcast_url'), + 'ie_key': TwitterBroadcastIE.ie_key(), + }) + else: + raise ExtractorError('Unsupported Twitter Card.') + else: + expanded_url = try_get(status, lambda x: x['entities']['urls'][0]['expanded_url']) + if not expanded_url: + raise ExtractorError("There's no video in this tweet.") + info.update({ + '_type': 'url', + 'url': expanded_url, + }) + return info class TwitterAmplifyIE(TwitterBaseIE): @@ -573,3 +567,27 @@ class TwitterAmplifyIE(TwitterBaseIE): 'formats': formats, 'thumbnails': thumbnails, } + + +class TwitterBroadcastIE(TwitterBaseIE, PeriscopeBaseIE): + IE_NAME = 'twitter:broadcast' + _VALID_URL = TwitterBaseIE._BASE_REGEX + r'i/broadcasts/(?P[0-9a-zA-Z]{13})' + + def _real_extract(self, url): + broadcast_id = self._match_id(url) + broadcast = self._call_api( + 'broadcasts/show.json', broadcast_id, + {'ids': broadcast_id})['broadcasts'][broadcast_id] + info = self._parse_broadcast_data(broadcast, broadcast_id) + media_key = broadcast['media_key'] + source = self._call_api( + 'live_video_stream/status/' + media_key, media_key)['source'] + m3u8_url = source.get('noRedirectPlaybackUrl') or source['location'] + if '/live_video_stream/geoblocked/' in m3u8_url: + self.raise_geo_restricted() + m3u8_id = compat_parse_qs(compat_urllib_parse_urlparse( + m3u8_url).query).get('type', [None])[0] + state, width, height = self._extract_common_format_info(broadcast) + info['formats'] = self._extract_pscp_m3u8_formats( + m3u8_url, broadcast_id, m3u8_id, state, width, height) + return info From ce112a8c19ebcc9d401ff26a5cdcf58ba565901c Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sat, 9 Nov 2019 11:01:07 +0100 Subject: [PATCH 181/422] [twitch] fix video comments URL(#18593)(closes #15828) --- youtube_dl/extractor/twitch.py | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py index a5681409c..8c0d70010 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -344,9 +344,8 @@ class TwitchVodIE(TwitchItemBaseIE): info['subtitles'] = { 'rechat': [{ 'url': update_url_query( - 'https://rechat.twitch.tv/rechat-messages', { - 'video_id': 'v%s' % item_id, - 'start': info['timestamp'], + 'https://api.twitch.tv/v5/videos/%s/comments' % item_id, { + 'client_id': self._CLIENT_ID, }), 'ext': 'json', }], From f81dd65ba2c1e7be549e5c8cfe6cbf0f0829edfe Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sat, 9 Nov 2019 13:11:59 +0100 Subject: [PATCH 182/422] [extractor/common] clean jwplayer description HTML tags --- youtube_dl/extractor/common.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 4a683f6d6..4c2f9303e 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -2689,7 +2689,7 @@ class InfoExtractor(object): entry = { 'id': this_video_id, 'title': unescapeHTML(video_data['title'] if require_title else video_data.get('title')), - 'description': video_data.get('description'), + 'description': clean_html(video_data.get('description')), 'thumbnail': urljoin(base_url, self._proto_relative_url(video_data.get('image'))), 'timestamp': int_or_none(video_data.get('pubdate')), 'duration': float_or_none(jwplayer_data.get('duration') or video_data.get('duration')), From 8fbf5d2f87fbfe0441bc20cf69d506109b2810bc Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sat, 9 Nov 2019 13:14:23 +0100 Subject: [PATCH 183/422] [seeker] remove Revision3 extractors and fix extraction --- youtube_dl/extractor/extractors.py | 4 - youtube_dl/extractor/revision3.py | 170 ----------------------------- youtube_dl/extractor/seeker.py | 45 ++++---- 3 files changed, 23 insertions(+), 196 deletions(-) delete mode 100644 youtube_dl/extractor/revision3.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 598006061..8df9d95b1 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -932,10 +932,6 @@ from .rentv import ( from .restudy import RestudyIE from .reuters import ReutersIE from .reverbnation import ReverbNationIE -from .revision3 import ( - Revision3EmbedIE, - Revision3IE, -) from .rice import RICEIE from .rmcdecouverte import RMCDecouverteIE from .ro220 import Ro220IE diff --git a/youtube_dl/extractor/revision3.py b/youtube_dl/extractor/revision3.py deleted file mode 100644 index 833d8a2f0..000000000 --- a/youtube_dl/extractor/revision3.py +++ /dev/null @@ -1,170 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..compat import compat_str -from ..utils import ( - int_or_none, - parse_iso8601, - unescapeHTML, - qualities, -) - - -class Revision3EmbedIE(InfoExtractor): - IE_NAME = 'revision3:embed' - _VALID_URL = r'(?:revision3:(?:(?P[^:]+):)?|https?://(?:(?:(?:www|embed)\.)?(?:revision3|animalist)|(?:(?:api|embed)\.)?seekernetwork)\.com/player/embed\?videoId=)(?P\d+)' - _TEST = { - 'url': 'http://api.seekernetwork.com/player/embed?videoId=67558', - 'md5': '83bcd157cab89ad7318dd7b8c9cf1306', - 'info_dict': { - 'id': '67558', - 'ext': 'mp4', - 'title': 'The Pros & Cons Of Zoos', - 'description': 'Zoos are often depicted as a terrible place for animals to live, but is there any truth to this?', - 'uploader_id': 'dnews', - 'uploader': 'DNews', - } - } - _API_KEY = 'ba9c741bce1b9d8e3defcc22193f3651b8867e62' - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - playlist_id = mobj.group('playlist_id') - playlist_type = mobj.group('playlist_type') or 'video_id' - video_data = self._download_json( - 'http://revision3.com/api/getPlaylist.json', playlist_id, query={ - 'api_key': self._API_KEY, - 'codecs': 'h264,vp8,theora', - playlist_type: playlist_id, - })['items'][0] - - formats = [] - for vcodec, media in video_data['media'].items(): - for quality_id, quality in media.items(): - if quality_id == 'hls': - formats.extend(self._extract_m3u8_formats( - quality['url'], playlist_id, 'mp4', - 'm3u8_native', m3u8_id='hls', fatal=False)) - else: - formats.append({ - 'url': quality['url'], - 'format_id': '%s-%s' % (vcodec, quality_id), - 'tbr': int_or_none(quality.get('bitrate')), - 'vcodec': vcodec, - }) - self._sort_formats(formats) - - return { - 'id': playlist_id, - 'title': unescapeHTML(video_data['title']), - 'description': unescapeHTML(video_data.get('summary')), - 'uploader': video_data.get('show', {}).get('name'), - 'uploader_id': video_data.get('show', {}).get('slug'), - 'duration': int_or_none(video_data.get('duration')), - 'formats': formats, - } - - -class Revision3IE(InfoExtractor): - IE_NAME = 'revision' - _VALID_URL = r'https?://(?:www\.)?(?P(?:revision3|animalist)\.com)/(?P[^/]+(?:/[^/?#]+)?)' - _TESTS = [{ - 'url': 'http://www.revision3.com/technobuffalo/5-google-predictions-for-2016', - 'md5': 'd94a72d85d0a829766de4deb8daaf7df', - 'info_dict': { - 'id': '71089', - 'display_id': 'technobuffalo/5-google-predictions-for-2016', - 'ext': 'webm', - 'title': '5 Google Predictions for 2016', - 'description': 'Google had a great 2015, but it\'s already time to look ahead. Here are our five predictions for 2016.', - 'upload_date': '20151228', - 'timestamp': 1451325600, - 'duration': 187, - 'uploader': 'TechnoBuffalo', - 'uploader_id': 'technobuffalo', - } - }, { - # Show - 'url': 'http://revision3.com/variant', - 'only_matching': True, - }, { - # Tag - 'url': 'http://revision3.com/vr', - 'only_matching': True, - }] - _PAGE_DATA_TEMPLATE = 'http://www.%s/apiProxy/ddn/%s?domain=%s' - - def _real_extract(self, url): - domain, display_id = re.match(self._VALID_URL, url).groups() - site = domain.split('.')[0] - page_info = self._download_json( - self._PAGE_DATA_TEMPLATE % (domain, display_id, domain), display_id) - - page_data = page_info['data'] - page_type = page_data['type'] - if page_type in ('episode', 'embed'): - show_data = page_data['show']['data'] - page_id = compat_str(page_data['id']) - video_id = compat_str(page_data['video']['data']['id']) - - preference = qualities(['mini', 'small', 'medium', 'large']) - thumbnails = [{ - 'url': image_url, - 'id': image_id, - 'preference': preference(image_id) - } for image_id, image_url in page_data.get('images', {}).items()] - - info = { - 'id': page_id, - 'display_id': display_id, - 'title': unescapeHTML(page_data['name']), - 'description': unescapeHTML(page_data.get('summary')), - 'timestamp': parse_iso8601(page_data.get('publishTime'), ' '), - 'author': page_data.get('author'), - 'uploader': show_data.get('name'), - 'uploader_id': show_data.get('slug'), - 'thumbnails': thumbnails, - 'extractor_key': site, - } - - if page_type == 'embed': - info.update({ - '_type': 'url_transparent', - 'url': page_data['video']['data']['embed'], - }) - return info - - info.update({ - '_type': 'url_transparent', - 'url': 'revision3:%s' % video_id, - }) - return info - else: - list_data = page_info[page_type]['data'] - episodes_data = page_info['episodes']['data'] - num_episodes = page_info['meta']['totalEpisodes'] - processed_episodes = 0 - entries = [] - page_num = 1 - while True: - entries.extend([{ - '_type': 'url', - 'url': 'http://%s%s' % (domain, episode['path']), - 'id': compat_str(episode['id']), - 'ie_key': 'Revision3', - 'extractor_key': site, - } for episode in episodes_data]) - processed_episodes += len(episodes_data) - if processed_episodes == num_episodes: - break - page_num += 1 - episodes_data = self._download_json(self._PAGE_DATA_TEMPLATE % ( - domain, display_id + '/' + compat_str(page_num), domain), - display_id)['episodes']['data'] - - return self.playlist_result( - entries, compat_str(list_data['id']), - list_data.get('name'), list_data.get('summary')) diff --git a/youtube_dl/extractor/seeker.py b/youtube_dl/extractor/seeker.py index 3b9c65e7e..7872dc80d 100644 --- a/youtube_dl/extractor/seeker.py +++ b/youtube_dl/extractor/seeker.py @@ -4,34 +4,37 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..utils import ( + get_element_by_class, + strip_or_none, +) class SeekerIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?seeker\.com/(?P.*)-(?P\d+)\.html' _TESTS = [{ - # player.loadRevision3Item 'url': 'http://www.seeker.com/should-trump-be-required-to-release-his-tax-returns-1833805621.html', - 'md5': '30c1dc4030cc715cf05b423d0947ac18', + 'md5': '897d44bbe0d8986a2ead96de565a92db', 'info_dict': { - 'id': '76243', - 'ext': 'webm', + 'id': 'Elrn3gnY', + 'ext': 'mp4', 'title': 'Should Trump Be Required To Release His Tax Returns?', - 'description': 'Donald Trump has been secretive about his "big," "beautiful" tax returns. So what can we learn if he decides to release them?', - 'uploader': 'Seeker Daily', - 'uploader_id': 'seekerdaily', + 'description': 'md5:41efa8cfa8d627841045eec7b018eb45', + 'timestamp': 1490090165, + 'upload_date': '20170321', } }, { 'url': 'http://www.seeker.com/changes-expected-at-zoos-following-recent-gorilla-lion-shootings-1834116536.html', 'playlist': [ { - 'md5': '83bcd157cab89ad7318dd7b8c9cf1306', + 'md5': '0497b9f20495174be73ae136949707d2', 'info_dict': { - 'id': '67558', + 'id': 'FihYQ8AE', 'ext': 'mp4', 'title': 'The Pros & Cons Of Zoos', - 'description': 'Zoos are often depicted as a terrible place for animals to live, but is there any truth to this?', - 'uploader': 'DNews', - 'uploader_id': 'dnews', + 'description': 'md5:d88f99a8ea8e7d25e6ff77f271b1271c', + 'timestamp': 1490039133, + 'upload_date': '20170320', }, } ], @@ -45,13 +48,11 @@ class SeekerIE(InfoExtractor): def _real_extract(self, url): display_id, article_id = re.match(self._VALID_URL, url).groups() webpage = self._download_webpage(url, display_id) - mobj = re.search(r"player\.loadRevision3Item\('([^']+)'\s*,\s*(\d+)\);", webpage) - if mobj: - playlist_type, playlist_id = mobj.groups() - return self.url_result( - 'revision3:%s:%s' % (playlist_type, playlist_id), 'Revision3Embed', playlist_id) - else: - entries = [self.url_result('revision3:video_id:%s' % video_id, 'Revision3Embed', video_id) for video_id in re.findall( - r']+src=[\'"](?:https?:)?//api\.seekernetwork\.com/player/embed\?videoId=(\d+)', webpage)] - return self.playlist_result( - entries, article_id, self._og_search_title(webpage), self._og_search_description(webpage)) + entries = [] + for jwp_id in re.findall(r'data-video-id="([a-zA-Z0-9]{8})"', webpage): + entries.append(self.url_result( + 'jwplatform:' + jwp_id, 'JWPlatform', jwp_id)) + return self.playlist_result( + entries, article_id, + self._og_search_title(webpage), + strip_or_none(get_element_by_class('subtitle__text', webpage)) or self._og_search_description(webpage)) From 20baa17c0180c7254644abea968792abcf0743cb Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sat, 9 Nov 2019 16:00:12 +0100 Subject: [PATCH 184/422] [daisuki] remove extractor --- youtube_dl/extractor/daisuki.py | 154 ----------------------------- youtube_dl/extractor/extractors.py | 4 - 2 files changed, 158 deletions(-) delete mode 100644 youtube_dl/extractor/daisuki.py diff --git a/youtube_dl/extractor/daisuki.py b/youtube_dl/extractor/daisuki.py deleted file mode 100644 index dbc1aa5d4..000000000 --- a/youtube_dl/extractor/daisuki.py +++ /dev/null @@ -1,154 +0,0 @@ -from __future__ import unicode_literals - -import base64 -import json -import random -import re - -from .common import InfoExtractor -from ..aes import ( - aes_cbc_decrypt, - aes_cbc_encrypt, -) -from ..compat import compat_b64decode -from ..utils import ( - bytes_to_intlist, - bytes_to_long, - extract_attributes, - ExtractorError, - intlist_to_bytes, - js_to_json, - int_or_none, - long_to_bytes, - pkcs1pad, -) - - -class DaisukiMottoIE(InfoExtractor): - _VALID_URL = r'https?://motto\.daisuki\.net/framewatch/embed/[^/]+/(?P[0-9a-zA-Z]{3})' - - _TEST = { - 'url': 'http://motto.daisuki.net/framewatch/embed/embedDRAGONBALLSUPERUniverseSurvivalsaga/V2e/760/428', - 'info_dict': { - 'id': 'V2e', - 'ext': 'mp4', - 'title': '#117 SHOWDOWN OF LOVE! ANDROIDS VS UNIVERSE 2!!', - 'subtitles': { - 'mul': [{ - 'ext': 'ttml', - }], - }, - }, - 'params': { - 'skip_download': True, # AES-encrypted HLS stream - }, - } - - # The public key in PEM format can be found in clientlibs_anime_watch.min.js - _RSA_KEY = (0xc5524c25e8e14b366b3754940beeb6f96cb7e2feef0b932c7659a0c5c3bf173d602464c2df73d693b513ae06ff1be8f367529ab30bf969c5640522181f2a0c51ea546ae120d3d8d908595e4eff765b389cde080a1ef7f1bbfb07411cc568db73b7f521cedf270cbfbe0ddbc29b1ac9d0f2d8f4359098caffee6d07915020077d, 65537) - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - flashvars = self._parse_json(self._search_regex( - r'(?s)var\s+flashvars\s*=\s*({.+?});', webpage, 'flashvars'), - video_id, transform_source=js_to_json) - - iv = [0] * 16 - - data = {} - for key in ('device_cd', 'mv_id', 'ss1_prm', 'ss2_prm', 'ss3_prm', 'ss_id'): - data[key] = flashvars.get(key, '') - - encrypted_rtn = None - - # Some AES keys are rejected. Try it with different AES keys - for idx in range(5): - aes_key = [random.randint(0, 254) for _ in range(32)] - padded_aeskey = intlist_to_bytes(pkcs1pad(aes_key, 128)) - - n, e = self._RSA_KEY - encrypted_aeskey = long_to_bytes(pow(bytes_to_long(padded_aeskey), e, n)) - init_data = self._download_json( - 'http://motto.daisuki.net/fastAPI/bgn/init/', - video_id, query={ - 's': flashvars.get('s', ''), - 'c': flashvars.get('ss3_prm', ''), - 'e': url, - 'd': base64.b64encode(intlist_to_bytes(aes_cbc_encrypt( - bytes_to_intlist(json.dumps(data)), - aes_key, iv))).decode('ascii'), - 'a': base64.b64encode(encrypted_aeskey).decode('ascii'), - }, note='Downloading JSON metadata' + (' (try #%d)' % (idx + 1) if idx > 0 else '')) - - if 'rtn' in init_data: - encrypted_rtn = init_data['rtn'] - break - - self._sleep(5, video_id) - - if encrypted_rtn is None: - raise ExtractorError('Failed to fetch init data') - - rtn = self._parse_json( - intlist_to_bytes(aes_cbc_decrypt(bytes_to_intlist( - compat_b64decode(encrypted_rtn)), - aes_key, iv)).decode('utf-8').rstrip('\0'), - video_id) - - title = rtn['title_str'] - - formats = self._extract_m3u8_formats( - rtn['play_url'], video_id, ext='mp4', entry_protocol='m3u8_native') - - subtitles = {} - caption_url = rtn.get('caption_url') - if caption_url: - # mul: multiple languages - subtitles['mul'] = [{ - 'url': caption_url, - 'ext': 'ttml', - }] - - return { - 'id': video_id, - 'title': title, - 'formats': formats, - 'subtitles': subtitles, - } - - -class DaisukiMottoPlaylistIE(InfoExtractor): - _VALID_URL = r'https?://motto\.daisuki\.net/(?Pinformation)/' - - _TEST = { - 'url': 'http://motto.daisuki.net/information/', - 'info_dict': { - 'title': 'DRAGON BALL SUPER', - }, - 'playlist_mincount': 117, - } - - def _real_extract(self, url): - playlist_id = self._match_id(url) - - webpage = self._download_webpage(url, playlist_id) - - entries = [] - for li in re.findall(r'(]+?data-product_id="[a-zA-Z0-9]{3}"[^>]+>)', webpage): - attr = extract_attributes(li) - ad_id = attr.get('data-ad_id') - product_id = attr.get('data-product_id') - if ad_id and product_id: - episode_id = attr.get('data-chapter') - entries.append({ - '_type': 'url_transparent', - 'url': 'http://motto.daisuki.net/framewatch/embed/%s/%s/760/428' % (ad_id, product_id), - 'episode_id': episode_id, - 'episode_number': int_or_none(episode_id), - 'ie_key': 'DaisukiMotto', - }) - - return self.playlist_result(entries, playlist_title='DRAGON BALL SUPER') diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 8df9d95b1..e2ebe8f95 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -254,10 +254,6 @@ from .dailymotion import ( DailymotionPlaylistIE, DailymotionUserIE, ) -from .daisuki import ( - DaisukiMottoIE, - DaisukiMottoPlaylistIE, -) from .daum import ( DaumIE, DaumClipIE, From 88b87b08b1ed06940053ee018547de051bf8d986 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sat, 9 Nov 2019 17:01:21 +0100 Subject: [PATCH 185/422] [minhateca] remove extractor --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/minhateca.py | 70 ------------------------------ 2 files changed, 71 deletions(-) delete mode 100644 youtube_dl/extractor/minhateca.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index e2ebe8f95..dfd0ef198 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -625,7 +625,6 @@ from .microsoftvirtualacademy import ( MicrosoftVirtualAcademyIE, MicrosoftVirtualAcademyCourseIE, ) -from .minhateca import MinhatecaIE from .ministrygrid import MinistryGridIE from .minoto import MinotoIE from .miomio import MioMioIE diff --git a/youtube_dl/extractor/minhateca.py b/youtube_dl/extractor/minhateca.py deleted file mode 100644 index dccc54249..000000000 --- a/youtube_dl/extractor/minhateca.py +++ /dev/null @@ -1,70 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..utils import ( - int_or_none, - parse_duration, - parse_filesize, - sanitized_Request, - urlencode_postdata, -) - - -class MinhatecaIE(InfoExtractor): - _VALID_URL = r'https?://minhateca\.com\.br/[^?#]+,(?P[0-9]+)\.' - _TEST = { - 'url': 'http://minhateca.com.br/pereba/misc/youtube-dl+test+video,125848331.mp4(video)', - 'info_dict': { - 'id': '125848331', - 'ext': 'mp4', - 'title': 'youtube-dl test video', - 'thumbnail': r're:^https?://.*\.jpg$', - 'filesize_approx': 1530000, - 'duration': 9, - 'view_count': int, - } - } - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - token = self._html_search_regex( - r'(.*?)', webpage, 'title') - title, _, ext = title_str.rpartition('.') - filesize_approx = parse_filesize(self._html_search_regex( - r'

    (.*?)

    ', - webpage, 'file size approximation', fatal=False)) - duration = parse_duration(self._html_search_regex( - r'(?s)

    .*?class="bold">(.*?)<', - webpage, 'duration', fatal=False)) - view_count = int_or_none(self._html_search_regex( - r'

    ([0-9]+)

    ', - webpage, 'view count', fatal=False)) - - return { - 'id': video_id, - 'url': video_url, - 'title': title, - 'ext': ext, - 'filesize_approx': filesize_approx, - 'duration': duration, - 'view_count': view_count, - 'thumbnail': self._og_search_thumbnail(webpage), - } From 9e46d1f8aadd38f6de7c2b921b294e67ed2267eb Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sat, 9 Nov 2019 17:15:15 +0100 Subject: [PATCH 186/422] [addanime] remove extractor --- youtube_dl/extractor/addanime.py | 95 ------------------------------ youtube_dl/extractor/extractors.py | 1 - 2 files changed, 96 deletions(-) delete mode 100644 youtube_dl/extractor/addanime.py diff --git a/youtube_dl/extractor/addanime.py b/youtube_dl/extractor/addanime.py deleted file mode 100644 index 5e7c0724e..000000000 --- a/youtube_dl/extractor/addanime.py +++ /dev/null @@ -1,95 +0,0 @@ -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..compat import ( - compat_HTTPError, - compat_str, - compat_urllib_parse_urlencode, - compat_urllib_parse_urlparse, -) -from ..utils import ( - ExtractorError, - qualities, -) - - -class AddAnimeIE(InfoExtractor): - _VALID_URL = r'https?://(?:\w+\.)?add-anime\.net/(?:watch_video\.php\?(?:.*?)v=|video/)(?P[\w_]+)' - _TESTS = [{ - 'url': 'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9', - 'md5': '72954ea10bc979ab5e2eb288b21425a0', - 'info_dict': { - 'id': '24MR3YO5SAS9', - 'ext': 'mp4', - 'description': 'One Piece 606', - 'title': 'One Piece 606', - }, - 'skip': 'Video is gone', - }, { - 'url': 'http://add-anime.net/video/MDUGWYKNGBD8/One-Piece-687', - 'only_matching': True, - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - - try: - webpage = self._download_webpage(url, video_id) - except ExtractorError as ee: - if not isinstance(ee.cause, compat_HTTPError) or \ - ee.cause.code != 503: - raise - - redir_webpage = ee.cause.read().decode('utf-8') - action = self._search_regex( - r'
    ', - redir_webpage, 'redirect vc value') - av = re.search( - r'a\.value = ([0-9]+)[+]([0-9]+)[*]([0-9]+);', - redir_webpage) - if av is None: - raise ExtractorError('Cannot find redirect math task') - av_res = int(av.group(1)) + int(av.group(2)) * int(av.group(3)) - - parsed_url = compat_urllib_parse_urlparse(url) - av_val = av_res + len(parsed_url.netloc) - confirm_url = ( - parsed_url.scheme + '://' + parsed_url.netloc - + action + '?' - + compat_urllib_parse_urlencode({ - 'jschl_vc': vc, 'jschl_answer': compat_str(av_val)})) - self._download_webpage( - confirm_url, video_id, - note='Confirming after redirect') - webpage = self._download_webpage(url, video_id) - - FORMATS = ('normal', 'hq') - quality = qualities(FORMATS) - formats = [] - for format_id in FORMATS: - rex = r"var %s_video_file = '(.*?)';" % re.escape(format_id) - video_url = self._search_regex(rex, webpage, 'video file URLx', - fatal=False) - if not video_url: - continue - formats.append({ - 'format_id': format_id, - 'url': video_url, - 'quality': quality(format_id), - }) - self._sort_formats(formats) - video_title = self._og_search_title(webpage) - video_description = self._og_search_description(webpage) - - return { - '_type': 'video', - 'id': video_id, - 'formats': formats, - 'title': video_title, - 'description': video_description - } diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index dfd0ef198..d96f0d284 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -18,7 +18,6 @@ from .acast import ( ACastIE, ACastChannelIE, ) -from .addanime import AddAnimeIE from .adn import ADNIE from .adobeconnect import AdobeConnectIE from .adobetv import ( From 433e0710585e2414697cff6d444204e1db950bd7 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sun, 10 Nov 2019 17:02:47 +0100 Subject: [PATCH 187/422] [facebook] fix posts video data extraction(closes #22473) --- youtube_dl/extractor/facebook.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index c723726b7..ce64e2683 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -334,7 +334,7 @@ class FacebookIE(InfoExtractor): if not video_data: server_js_data = self._parse_json( self._search_regex( - r'bigPipe\.onPageletArrive\(({.+?})\)\s*;\s*}\s*\)\s*,\s*["\']onPageletArrive\s+(?:stream_pagelet|pagelet_group_mall|permalink_video_pagelet)', + r'bigPipe\.onPageletArrive\(({.+?})\)\s*;\s*}\s*\)\s*,\s*["\']onPageletArrive\s+(?:pagelet_group_mall|permalink_video_pagelet|hyperfeed_story_id_\d+)', webpage, 'js data', default='{}'), video_id, transform_source=js_to_json, fatal=False) video_data = extract_from_jsmods_instances(server_js_data) From 2e9ad59a4d6dfd82b34a965cfc5b8c5a647d1598 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 11 Nov 2019 09:53:04 +0100 Subject: [PATCH 188/422] [soundcloud] check if the soundtrack has downloads left(closes #23045) --- youtube_dl/extractor/soundcloud.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 875b9d887..e8ffb2cbe 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -276,7 +276,7 @@ class SoundcloudIE(InfoExtractor): if secret_token: query['secret_token'] = secret_token - if info.get('downloadable'): + if info.get('downloadable') and info.get('has_downloads_left'): format_url = update_url_query( info.get('download_url') or track_base_url + '/download', query) format_urls.add(format_url) From 48970d5cc8838ac404a64462d175b248401e2bd2 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Tue, 12 Nov 2019 10:51:54 +0100 Subject: [PATCH 189/422] [teamcoco] add support for new videos(closes #23054) --- youtube_dl/extractor/teamcoco.py | 68 +++++++++++++++++--------------- 1 file changed, 37 insertions(+), 31 deletions(-) diff --git a/youtube_dl/extractor/teamcoco.py b/youtube_dl/extractor/teamcoco.py index 7640cf00a..5793b711f 100644 --- a/youtube_dl/extractor/teamcoco.py +++ b/youtube_dl/extractor/teamcoco.py @@ -84,6 +84,19 @@ class TeamcocoIE(TurnerBaseIE): 'only_matching': True, } ] + _RECORD_TEMPL = '''id + title + teaser + publishOn + thumb { + preview + } + tags { + name + } + duration + turnerMediaId + turnerMediaAuthToken''' def _graphql_call(self, query_template, object_type, object_id): find_object = 'find' + object_type @@ -98,36 +111,36 @@ class TeamcocoIE(TurnerBaseIE): display_id = self._match_id(url) response = self._graphql_call('''{ - %s(slug: "%s") { + %%s(slug: "%%s") { ... on RecordSlug { record { + %s + } + } + ... on PageSlug { + child { id - title - teaser - publishOn - thumb { - preview - } - file { - url - } - tags { - name - } - duration - turnerMediaId - turnerMediaAuthToken } } ... on NotFoundSlug { status } } -}''', 'Slug', display_id) +}''' % self._RECORD_TEMPL, 'Slug', display_id) if response.get('status'): raise ExtractorError('This video is no longer available.', expected=True) - record = response['record'] + child = response.get('child') + if child: + record = self._graphql_call('''{ + %%s(id: "%%s") { + ... on Video { + %s + } + } +}''' % self._RECORD_TEMPL, 'Record', child['id']) + else: + record = response['record'] video_id = record['id'] info = { @@ -150,25 +163,21 @@ class TeamcocoIE(TurnerBaseIE): 'accessTokenType': 'jws', })) else: - d = self._download_json( + video_sources = self._download_json( 'https://teamcoco.com/_truman/d/' + video_id, - video_id, fatal=False) or {} - video_sources = d.get('meta') or {} - if not video_sources: - video_sources = self._graphql_call('''{ - %s(id: "%s") { - src - } -}''', 'RecordVideoSource', video_id) or {} + video_id)['meta']['src'] + if isinstance(video_sources, dict): + video_sources = video_sources.values() formats = [] get_quality = qualities(['low', 'sd', 'hd', 'uhd']) - for format_id, src in video_sources.get('src', {}).items(): + for src in video_sources: if not isinstance(src, dict): continue src_url = src.get('src') if not src_url: continue + format_id = src.get('label') ext = determine_ext(src_url, mimetype2ext(src.get('type'))) if format_id == 'hls' or ext == 'm3u8': # compat_urllib_parse.urljoin does not work here @@ -190,9 +199,6 @@ class TeamcocoIE(TurnerBaseIE): 'format_id': format_id, 'quality': get_quality(format_id), }) - if not formats: - formats = self._extract_m3u8_formats( - record['file']['url'], video_id, 'mp4', fatal=False) self._sort_formats(formats) info['formats'] = formats From eb22d1b55744b69d5ec3556529868acfba6c217f Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 13 Nov 2019 19:09:32 +0100 Subject: [PATCH 190/422] [nexx] Add support for Multi Player JS Setup(closes #23052) --- youtube_dl/extractor/nexx.py | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/nexx.py b/youtube_dl/extractor/nexx.py index f9aad83c4..586c1b7eb 100644 --- a/youtube_dl/extractor/nexx.py +++ b/youtube_dl/extractor/nexx.py @@ -108,7 +108,7 @@ class NexxIE(InfoExtractor): @staticmethod def _extract_domain_id(webpage): mobj = re.search( - r']+\bsrc=["\'](?:https?:)?//require\.nexx(?:\.cloud|cdn\.com)/(?P\d+)', + r']+\bsrc=["\'](?:https?:)?//(?:require|arc)\.nexx(?:\.cloud|cdn\.com)/(?:sdk/)?(?P\d+)', webpage) return mobj.group('id') if mobj else None @@ -123,7 +123,7 @@ class NexxIE(InfoExtractor): domain_id = NexxIE._extract_domain_id(webpage) if domain_id: for video_id in re.findall( - r'(?is)onPLAYReady.+?_play\.init\s*\(.+?\s*,\s*["\']?(\d+)', + r'(?is)onPLAYReady.+?_play\.(?:init|(?:control\.)?addPlayer)\s*\(.+?\s*,\s*["\']?(\d+)', webpage): entries.append( 'https://api.nexx.cloud/v3/%s/videos/byid/%s' @@ -410,8 +410,8 @@ class NexxIE(InfoExtractor): class NexxEmbedIE(InfoExtractor): - _VALID_URL = r'https?://embed\.nexx(?:\.cloud|cdn\.com)/\d+/(?P[^/?#&]+)' - _TEST = { + _VALID_URL = r'https?://embed\.nexx(?:\.cloud|cdn\.com)/\d+/(?:video/)?(?P[^/?#&]+)' + _TESTS = [{ 'url': 'http://embed.nexx.cloud/748/KC1614647Z27Y7T?autoplay=1', 'md5': '16746bfc28c42049492385c989b26c4a', 'info_dict': { @@ -420,7 +420,6 @@ class NexxEmbedIE(InfoExtractor): 'title': 'Nervenkitzel Achterbahn', 'alt_title': 'Karussellbauer in Deutschland', 'description': 'md5:ffe7b1cc59a01f585e0569949aef73cc', - 'release_year': 2005, 'creator': 'SPIEGEL TV', 'thumbnail': r're:^https?://.*\.jpg$', 'duration': 2761, @@ -431,7 +430,10 @@ class NexxEmbedIE(InfoExtractor): 'format': 'bestvideo', 'skip_download': True, }, - } + }, { + 'url': 'https://embed.nexx.cloud/11888/video/DSRTO7UVOX06S7', + 'only_matching': True, + }] @staticmethod def _extract_urls(webpage): From 5709d661a2509fab0c9f3412239ecbe7a621f45b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 14 Nov 2019 01:45:04 +0700 Subject: [PATCH 191/422] [drtv] Add support for new URL schema (closes #23059) --- youtube_dl/extractor/drtv.py | 57 ++++++++++++++++++++++++++++++++---- 1 file changed, 52 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/drtv.py b/youtube_dl/extractor/drtv.py index 218f10209..390e79f8c 100644 --- a/youtube_dl/extractor/drtv.py +++ b/youtube_dl/extractor/drtv.py @@ -17,6 +17,7 @@ from ..utils import ( float_or_none, mimetype2ext, str_or_none, + try_get, unified_timestamp, update_url_query, url_or_none, @@ -24,7 +25,14 @@ from ..utils import ( class DRTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv/se|nyheder|radio(?:/ondemand)?)/(?:[^/]+/)*(?P[\da-z-]+)(?:[/#?]|$)' + _VALID_URL = r'''(?x) + https?:// + (?: + (?:www\.)?dr\.dk/(?:tv/se|nyheder|radio(?:/ondemand)?)/(?:[^/]+/)*| + (?:www\.)?(?:dr\.dk|dr-massive\.com)/drtv/(?:se|episode)/ + ) + (?P[\da-z_-]+) + ''' _GEO_BYPASS = False _GEO_COUNTRIES = ['DK'] IE_NAME = 'drtv' @@ -83,6 +91,26 @@ class DRTVIE(InfoExtractor): }, { 'url': 'https://www.dr.dk/radio/p4kbh/regionale-nyheder-kh4/p4-nyheder-2019-06-26-17-30-9', 'only_matching': True, + }, { + 'url': 'https://www.dr.dk/drtv/se/bonderoeven_71769', + 'info_dict': { + 'id': '00951930010', + 'ext': 'mp4', + 'title': 'Bonderøven (1:8)', + 'description': 'md5:3cf18fc0d3b205745d4505f896af8121', + 'timestamp': 1546542000, + 'upload_date': '20190103', + 'duration': 2576.6, + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://www.dr.dk/drtv/episode/bonderoeven_71769', + 'only_matching': True, + }, { + 'url': 'https://dr-massive.com/drtv/se/bonderoeven_71769', + 'only_matching': True, }] def _real_extract(self, url): @@ -100,13 +128,32 @@ class DRTVIE(InfoExtractor): webpage, 'video id', default=None) if not video_id: - video_id = compat_urllib_parse_unquote(self._search_regex( + video_id = self._search_regex( r'(urn(?:%3A|:)dr(?:%3A|:)mu(?:%3A|:)programcard(?:%3A|:)[\da-f]+)', - webpage, 'urn')) + webpage, 'urn', default=None) + if video_id: + video_id = compat_urllib_parse_unquote(video_id) + + _PROGRAMCARD_BASE = 'https://www.dr.dk/mu-online/api/1.4/programcard' + query = {'expanded': 'true'} + + if video_id: + programcard_url = '%s/%s' % (_PROGRAMCARD_BASE, video_id) + else: + programcard_url = _PROGRAMCARD_BASE + page = self._parse_json( + self._search_regex( + r'data\s*=\s*({.+?})\s*(?:;| Date: Thu, 14 Nov 2019 06:38:55 +0100 Subject: [PATCH 192/422] [comcarcoff] remove extractor --- youtube_dl/extractor/comcarcoff.py | 74 ------------------------------ youtube_dl/extractor/extractors.py | 1 - 2 files changed, 75 deletions(-) delete mode 100644 youtube_dl/extractor/comcarcoff.py diff --git a/youtube_dl/extractor/comcarcoff.py b/youtube_dl/extractor/comcarcoff.py deleted file mode 100644 index 588aad0d9..000000000 --- a/youtube_dl/extractor/comcarcoff.py +++ /dev/null @@ -1,74 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..compat import compat_str -from ..utils import ( - int_or_none, - parse_duration, - parse_iso8601, -) - - -class ComCarCoffIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?comediansincarsgettingcoffee\.com/(?P[a-z0-9\-]*)' - _TESTS = [{ - 'url': 'http://comediansincarsgettingcoffee.com/miranda-sings-happy-thanksgiving-miranda/', - 'info_dict': { - 'id': '2494164', - 'ext': 'mp4', - 'upload_date': '20141127', - 'timestamp': 1417107600, - 'duration': 1232, - 'title': 'Happy Thanksgiving Miranda', - 'description': 'Jerry Seinfeld and his special guest Miranda Sings cruise around town in search of coffee, complaining and apologizing along the way.', - }, - 'params': { - 'skip_download': 'requires ffmpeg', - } - }] - - def _real_extract(self, url): - display_id = self._match_id(url) - if not display_id: - display_id = 'comediansincarsgettingcoffee.com' - webpage = self._download_webpage(url, display_id) - - full_data = self._parse_json( - self._search_regex( - r'window\.app\s*=\s*({.+?});\n', webpage, 'full data json'), - display_id)['videoData'] - - display_id = full_data['activeVideo']['video'] - video_data = full_data.get('videos', {}).get(display_id) or full_data['singleshots'][display_id] - - video_id = compat_str(video_data['mediaId']) - title = video_data['title'] - formats = self._extract_m3u8_formats( - video_data['mediaUrl'], video_id, 'mp4') - self._sort_formats(formats) - - thumbnails = [{ - 'url': video_data['images']['thumb'], - }, { - 'url': video_data['images']['poster'], - }] - - timestamp = int_or_none(video_data.get('pubDateTime')) or parse_iso8601( - video_data.get('pubDate')) - duration = int_or_none(video_data.get('durationSeconds')) or parse_duration( - video_data.get('duration')) - - return { - 'id': video_id, - 'display_id': display_id, - 'title': title, - 'description': video_data.get('description'), - 'timestamp': timestamp, - 'duration': duration, - 'thumbnails': thumbnails, - 'formats': formats, - 'season_number': int_or_none(video_data.get('season')), - 'episode_number': int_or_none(video_data.get('episode')), - 'webpage_url': 'http://comediansincarsgettingcoffee.com/%s' % (video_data.get('urlSlug', video_data.get('slug'))), - } diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index d96f0d284..cf4bb8f20 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -222,7 +222,6 @@ from .comedycentral import ( ComedyCentralTVIE, ToshIE, ) -from .comcarcoff import ComCarCoffIE from .commonmistakes import CommonMistakesIE, UnicodeBOMIE from .commonprotocols import ( MmsIE, From 656c20010f53851c1b01e839744f7fe48497c03f Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Fri, 15 Nov 2019 21:17:47 +0100 Subject: [PATCH 193/422] [ivi] fix format extraction(closes #21991) --- youtube_dl/extractor/ivi.py | 56 ++++++++++++++++++++++++++----------- 1 file changed, 39 insertions(+), 17 deletions(-) diff --git a/youtube_dl/extractor/ivi.py b/youtube_dl/extractor/ivi.py index 86c014b07..efdc3cc98 100644 --- a/youtube_dl/extractor/ivi.py +++ b/youtube_dl/extractor/ivi.py @@ -18,6 +18,8 @@ class IviIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?ivi\.(?:ru|tv)/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P\d+)' _GEO_BYPASS = False _GEO_COUNTRIES = ['RU'] + _LIGHT_KEY = b'\xf1\x02\x32\xb7\xbc\x5c\x7a\xe8\xf7\x96\xc1\x33\x2b\x27\xa1\x8c' + _LIGHT_URL = 'https://api.ivi.ru/light/' _TESTS = [ # Single movie @@ -78,25 +80,41 @@ class IviIE(InfoExtractor): 'MP4-SHQ', 'MP4-HD720', 'MP4-HD1080') def _real_extract(self, url): + try: + from Crypto.Cipher import Blowfish + from Crypto.Hash import CMAC + except ImportError: + raise ExtractorError('pycrypto not found. Please install it.', expected=True) + video_id = self._match_id(url) - data = { + timestamp = self._download_json( + self._LIGHT_URL, video_id, + 'Downloading timestamp JSON', data=json.dumps({ + 'method': 'da.timestamp.get', + 'params': [] + }).encode())['result'] + + data = json.dumps({ 'method': 'da.content.get', 'params': [ video_id, { - 'site': 's183', + 'site': 's353', 'referrer': 'http://www.ivi.ru/watch/%s' % video_id, 'contentid': video_id } ] - } + }).encode() video_json = self._download_json( - 'http://api.digitalaccess.ru/api/json/', video_id, - 'Downloading video JSON', data=json.dumps(data)) + self._LIGHT_URL, video_id, + 'Downloading video JSON', data=data, query={ + 'ts': timestamp, + 'sign': CMAC.new(self._LIGHT_KEY, timestamp.encode() + data, Blowfish).hexdigest(), + }) - if 'error' in video_json: - error = video_json['error'] + error = video_json.get('error') + if error: origin = error['origin'] if origin == 'NotAllowedForLocation': self.raise_geo_restricted( @@ -108,20 +126,24 @@ class IviIE(InfoExtractor): expected=True) result = video_json['result'] + title = result['title'] quality = qualities(self._KNOWN_FORMATS) - formats = [{ - 'url': x['url'], - 'format_id': x.get('content_format'), - 'quality': quality(x.get('content_format')), - } for x in result['files'] if x.get('url')] - + formats = [] + for f in result.get('files', []): + f_url = f.get('url') + content_format = f.get('content_format') + if not f_url or '-MDRM-' in content_format or '-FPS-' in content_format: + continue + formats.append({ + 'url': f_url, + 'format_id': content_format, + 'quality': quality(content_format), + 'filesize': int_or_none(f.get('size_in_bytes')), + }) self._sort_formats(formats) - title = result['title'] - - duration = int_or_none(result.get('duration')) compilation = result.get('compilation') episode = title if compilation else None @@ -158,7 +180,7 @@ class IviIE(InfoExtractor): 'episode_number': episode_number, 'thumbnails': thumbnails, 'description': description, - 'duration': duration, + 'duration': int_or_none(result.get('duration')), 'formats': formats, } From 1bba88efc7e1f82095f7ae38348e56026db4bf3c Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Fri, 15 Nov 2019 23:46:31 +0100 Subject: [PATCH 194/422] [ivi] sign content request only when pycryptodome is available --- youtube_dl/extractor/ivi.py | 42 +++++++++++++++++++++---------------- 1 file changed, 24 insertions(+), 18 deletions(-) diff --git a/youtube_dl/extractor/ivi.py b/youtube_dl/extractor/ivi.py index efdc3cc98..1dcb17c9b 100644 --- a/youtube_dl/extractor/ivi.py +++ b/youtube_dl/extractor/ivi.py @@ -80,38 +80,42 @@ class IviIE(InfoExtractor): 'MP4-SHQ', 'MP4-HD720', 'MP4-HD1080') def _real_extract(self, url): - try: - from Crypto.Cipher import Blowfish - from Crypto.Hash import CMAC - except ImportError: - raise ExtractorError('pycrypto not found. Please install it.', expected=True) - video_id = self._match_id(url) - timestamp = self._download_json( - self._LIGHT_URL, video_id, - 'Downloading timestamp JSON', data=json.dumps({ - 'method': 'da.timestamp.get', - 'params': [] - }).encode())['result'] - data = json.dumps({ 'method': 'da.content.get', 'params': [ video_id, { - 'site': 's353', + 'site': 's%d', 'referrer': 'http://www.ivi.ru/watch/%s' % video_id, 'contentid': video_id } ] }).encode() - video_json = self._download_json( - self._LIGHT_URL, video_id, - 'Downloading video JSON', data=data, query={ + try: + from Crypto.Cipher import Blowfish + from Crypto.Hash import CMAC + + timestamp = self._download_json( + self._LIGHT_URL, video_id, + 'Downloading timestamp JSON', data=json.dumps({ + 'method': 'da.timestamp.get', + 'params': [] + }).encode())['result'] + + data = data % 353 + query = { 'ts': timestamp, 'sign': CMAC.new(self._LIGHT_KEY, timestamp.encode() + data, Blowfish).hexdigest(), - }) + } + except ImportError: + data = data % 183 + query = {} + + video_json = self._download_json( + self._LIGHT_URL, video_id, + 'Downloading video JSON', data=data, query=query) error = video_json.get('error') if error: @@ -121,6 +125,8 @@ class IviIE(InfoExtractor): msg=error['message'], countries=self._GEO_COUNTRIES) elif origin == 'NoRedisValidData': raise ExtractorError('Video %s does not exist' % video_id, expected=True) + elif origin == 'NotAllowedError': + raise ExtractorError('pycryptodome not found. Please install it.', expected=True) raise ExtractorError( 'Unable to download video %s: %s' % (video_id, error['message']), expected=True) From 7360c06facfd96ee603ad4fc27f5903d3f8f6694 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 16 Nov 2019 05:44:14 +0700 Subject: [PATCH 195/422] [extractor/common] Add data, headers and query to all major extract methods preserving standard order for potential future use --- youtube_dl/extractor/common.py | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 4c2f9303e..04d676378 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1455,14 +1455,14 @@ class InfoExtractor(object): def _extract_f4m_formats(self, manifest_url, video_id, preference=None, f4m_id=None, transform_source=lambda s: fix_xml_ampersands(s).strip(), - fatal=True, m3u8_id=None): + fatal=True, m3u8_id=None, data=None, headers={}, query={}): manifest = self._download_xml( manifest_url, video_id, 'Downloading f4m manifest', 'Unable to download f4m manifest', # Some manifests may be malformed, e.g. prosiebensat1 generated manifests # (see https://github.com/ytdl-org/youtube-dl/issues/6215#issuecomment-121704244) transform_source=transform_source, - fatal=fatal) + fatal=fatal, data=data, headers=headers, query=query) if manifest is False: return [] @@ -1586,12 +1586,13 @@ class InfoExtractor(object): def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None, entry_protocol='m3u8', preference=None, m3u8_id=None, note=None, errnote=None, - fatal=True, live=False, headers={}): + fatal=True, live=False, data=None, headers={}, + query={}): res = self._download_webpage_handle( m3u8_url, video_id, note=note or 'Downloading m3u8 information', errnote=errnote or 'Failed to download m3u8 information', - fatal=fatal, headers=headers) + fatal=fatal, data=data, headers=headers, query=query) if res is False: return [] @@ -2009,12 +2010,12 @@ class InfoExtractor(object): }) return entries - def _extract_mpd_formats(self, mpd_url, video_id, mpd_id=None, note=None, errnote=None, fatal=True, formats_dict={}, headers={}): + def _extract_mpd_formats(self, mpd_url, video_id, mpd_id=None, note=None, errnote=None, fatal=True, formats_dict={}, data=None, headers={}, query={}): res = self._download_xml_handle( mpd_url, video_id, note=note or 'Downloading MPD manifest', errnote=errnote or 'Failed to download MPD manifest', - fatal=fatal, headers=headers) + fatal=fatal, data=data, headers=headers, query=query) if res is False: return [] mpd_doc, urlh = res @@ -2317,12 +2318,12 @@ class InfoExtractor(object): self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type) return formats - def _extract_ism_formats(self, ism_url, video_id, ism_id=None, note=None, errnote=None, fatal=True): + def _extract_ism_formats(self, ism_url, video_id, ism_id=None, note=None, errnote=None, fatal=True, data=None, headers={}, query={}): res = self._download_xml_handle( ism_url, video_id, note=note or 'Downloading ISM manifest', errnote=errnote or 'Failed to download ISM manifest', - fatal=fatal) + fatal=fatal, data=data, headers=headers, query=query) if res is False: return [] ism_doc, urlh = res From 6c79785bb0c96d6fc22d942946196f0842d70a93 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 16 Nov 2019 07:47:23 +0700 Subject: [PATCH 196/422] [travis] Add python 3.8 build --- .travis.yml | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/.travis.yml b/.travis.yml index 6d16c2955..14d95fa84 100644 --- a/.travis.yml +++ b/.travis.yml @@ -21,6 +21,12 @@ matrix: - python: 3.7 dist: xenial env: YTDL_TEST_SET=download + - python: 3.8 + dist: xenial + env: YTDL_TEST_SET=core + - python: 3.8 + dist: xenial + env: YTDL_TEST_SET=download - python: 3.8-dev dist: xenial env: YTDL_TEST_SET=core From 9e4e864639bf606a1931a684f130e219e869adfd Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sat, 16 Nov 2019 01:51:31 +0100 Subject: [PATCH 197/422] [ivi] improve error detection --- youtube_dl/extractor/ivi.py | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/ivi.py b/youtube_dl/extractor/ivi.py index 1dcb17c9b..7f1146d95 100644 --- a/youtube_dl/extractor/ivi.py +++ b/youtube_dl/extractor/ivi.py @@ -119,17 +119,20 @@ class IviIE(InfoExtractor): error = video_json.get('error') if error: - origin = error['origin'] + origin = error.get('origin') + message = error.get('message') or error.get('user_message') + extractor_msg = 'Unable to download video %s' if origin == 'NotAllowedForLocation': - self.raise_geo_restricted( - msg=error['message'], countries=self._GEO_COUNTRIES) + self.raise_geo_restricted(message, self._GEO_COUNTRIES) elif origin == 'NoRedisValidData': - raise ExtractorError('Video %s does not exist' % video_id, expected=True) - elif origin == 'NotAllowedError': - raise ExtractorError('pycryptodome not found. Please install it.', expected=True) - raise ExtractorError( - 'Unable to download video %s: %s' % (video_id, error['message']), - expected=True) + extractor_msg = 'Video %s does not exist' + elif message: + if 'недоступен для просмотра на площадке s183' in message: + raise ExtractorError( + 'pycryptodome not found. Please install it.', + expected=True) + extractor_msg += ': ' + message + raise ExtractorError(extractor_msg % video_id, expected=True) result = video_json['result'] title = result['title'] From 7e70620a342c57746812d4a8fae6f436bd90cf57 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 18 Nov 2019 12:51:25 +0100 Subject: [PATCH 198/422] [vk] fix wall audio thumbnails extraction(closes #23135) --- youtube_dl/extractor/vk.py | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index 4c8ca4f41..195875938 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -634,14 +634,15 @@ class VKWallPostIE(VKBaseIE): if not a.url: continue title = unescapeHTML(a.title) + performer = unescapeHTML(a.performer) entries.append({ 'id': '%s_%s' % (a.owner_id, a.id), 'url': self._unmask_url(a.url, a.ads['vk_id']), - 'title': '%s - %s' % (a.performer, title) if a.performer else title, - 'thumbnail': a.cover_url.split(',') if a.cover_url else None, - 'duration': a.duration, + 'title': '%s - %s' % (performer, title) if performer else title, + 'thumbnails': [{'url': c_url} for c_url in a.cover_url.split(',')] if a.cover_url else None, + 'duration': int_or_none(a.duration), 'uploader': uploader, - 'artist': a.performer, + 'artist': performer, 'track': title, 'ext': 'mp4', 'protocol': 'm3u8', From f9c4a4521068a02c583803ea422c6fedfa7598e3 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 18 Nov 2019 21:40:53 +0100 Subject: [PATCH 199/422] [ntvru] add support for non relative file URLs(closes #23140) --- youtube_dl/extractor/ntvru.py | 49 +++++++++++++++++------------------ 1 file changed, 24 insertions(+), 25 deletions(-) diff --git a/youtube_dl/extractor/ntvru.py b/youtube_dl/extractor/ntvru.py index 4f9cedb84..c47d1dfa4 100644 --- a/youtube_dl/extractor/ntvru.py +++ b/youtube_dl/extractor/ntvru.py @@ -3,9 +3,10 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( - clean_html, - xpath_text, int_or_none, + strip_or_none, + unescapeHTML, + xpath_text, ) @@ -47,10 +48,10 @@ class NTVRuIE(InfoExtractor): 'duration': 1496, }, }, { - 'url': 'http://www.ntv.ru/kino/Koma_film', - 'md5': 'f825770930937aa7e5aca0dc0d29319a', + 'url': 'https://www.ntv.ru/kino/Koma_film/m70281/o336036/video/', + 'md5': 'e9c7cde24d9d3eaed545911a04e6d4f4', 'info_dict': { - 'id': '1007609', + 'id': '1126480', 'ext': 'mp4', 'title': 'Остросюжетный фильм «Кома»', 'description': 'Остросюжетный фильм «Кома»', @@ -68,6 +69,10 @@ class NTVRuIE(InfoExtractor): 'thumbnail': r're:^http://.*\.jpg', 'duration': 2590, }, + }, { + # Schemeless file URL + 'url': 'https://www.ntv.ru/video/1797442', + 'only_matching': True, }] _VIDEO_ID_REGEXES = [ @@ -96,37 +101,31 @@ class NTVRuIE(InfoExtractor): 'http://www.ntv.ru/vi%s/' % video_id, video_id, 'Downloading video XML') - title = clean_html(xpath_text(player, './data/title', 'title', fatal=True)) - description = clean_html(xpath_text(player, './data/description', 'description')) + title = strip_or_none(unescapeHTML(xpath_text(player, './data/title', 'title', fatal=True))) video = player.find('./data/video') - video_id = xpath_text(video, './id', 'video id') - thumbnail = xpath_text(video, './splash', 'thumbnail') - duration = int_or_none(xpath_text(video, './totaltime', 'duration')) - view_count = int_or_none(xpath_text(video, './views', 'view count')) - - token = self._download_webpage( - 'http://stat.ntv.ru/services/access/token', - video_id, 'Downloading access token') formats = [] for format_id in ['', 'hi', 'webm']: - file_ = video.find('./%sfile' % format_id) - if file_ is None: + file_ = xpath_text(video, './%sfile' % format_id) + if not file_: continue - size = video.find('./%ssize' % format_id) + if file_.startswith('//'): + file_ = self._proto_relative_url(file_) + elif not file_.startswith('http'): + file_ = 'http://media.ntv.ru/vod/' + file_ formats.append({ - 'url': 'http://media2.ntv.ru/vod/%s&tok=%s' % (file_.text, token), - 'filesize': int_or_none(size.text if size is not None else None), + 'url': file_, + 'filesize': int_or_none(xpath_text(video, './%ssize' % format_id)), }) self._sort_formats(formats) return { - 'id': video_id, + 'id': xpath_text(video, './id'), 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'duration': duration, - 'view_count': view_count, + 'description': strip_or_none(unescapeHTML(xpath_text(player, './data/description'))), + 'thumbnail': xpath_text(video, './splash'), + 'duration': int_or_none(xpath_text(video, './totaltime')), + 'view_count': int_or_none(xpath_text(video, './views')), 'formats': formats, } From 76d9eca43dd4fd7698d138b90ab6b2dd159559e0 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Tue, 19 Nov 2019 20:16:31 +0100 Subject: [PATCH 200/422] [ivi] fallback to old extraction method for unknown error codes --- youtube_dl/extractor/ivi.py | 79 +++++++++++++++++++++---------------- 1 file changed, 45 insertions(+), 34 deletions(-) diff --git a/youtube_dl/extractor/ivi.py b/youtube_dl/extractor/ivi.py index 7f1146d95..0db023622 100644 --- a/youtube_dl/extractor/ivi.py +++ b/youtube_dl/extractor/ivi.py @@ -93,46 +93,57 @@ class IviIE(InfoExtractor): ] }).encode() - try: - from Crypto.Cipher import Blowfish - from Crypto.Hash import CMAC + for site in (353, 183): + content_data = data % site + if site == 353: + try: + from Cryptodome.Cipher import Blowfish + from Cryptodome.Hash import CMAC + pycryptodomex_found = True + except ImportError: + pycryptodomex_found = False + continue - timestamp = self._download_json( + timestamp = (self._download_json( + self._LIGHT_URL, video_id, + 'Downloading timestamp JSON', data=json.dumps({ + 'method': 'da.timestamp.get', + 'params': [] + }).encode(), fatal=False) or {}).get('result') + if not timestamp: + continue + + query = { + 'ts': timestamp, + 'sign': CMAC.new(self._LIGHT_KEY, timestamp.encode() + content_data, Blowfish).hexdigest(), + } + else: + query = {} + + video_json = self._download_json( self._LIGHT_URL, video_id, - 'Downloading timestamp JSON', data=json.dumps({ - 'method': 'da.timestamp.get', - 'params': [] - }).encode())['result'] + 'Downloading video JSON', data=content_data, query=query) - data = data % 353 - query = { - 'ts': timestamp, - 'sign': CMAC.new(self._LIGHT_KEY, timestamp.encode() + data, Blowfish).hexdigest(), - } - except ImportError: - data = data % 183 - query = {} - - video_json = self._download_json( - self._LIGHT_URL, video_id, - 'Downloading video JSON', data=data, query=query) - - error = video_json.get('error') - if error: - origin = error.get('origin') - message = error.get('message') or error.get('user_message') - extractor_msg = 'Unable to download video %s' - if origin == 'NotAllowedForLocation': - self.raise_geo_restricted(message, self._GEO_COUNTRIES) - elif origin == 'NoRedisValidData': - extractor_msg = 'Video %s does not exist' - elif message: - if 'недоступен для просмотра на площадке s183' in message: + error = video_json.get('error') + if error: + origin = error.get('origin') + message = error.get('message') or error.get('user_message') + extractor_msg = 'Unable to download video %s' + if origin == 'NotAllowedForLocation': + self.raise_geo_restricted(message, self._GEO_COUNTRIES) + elif origin == 'NoRedisValidData': + extractor_msg = 'Video %s does not exist' + elif site == 353: + continue + elif not pycryptodomex_found: raise ExtractorError( 'pycryptodome not found. Please install it.', expected=True) - extractor_msg += ': ' + message - raise ExtractorError(extractor_msg % video_id, expected=True) + elif message: + extractor_msg += ': ' + message + raise ExtractorError(extractor_msg % video_id, expected=True) + else: + break result = video_json['result'] title = result['title'] From f0f6a7e73f55b6227c40af17c6fcab44b5a2df79 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 21 Nov 2019 23:21:03 +0700 Subject: [PATCH 201/422] [chaturbate] Fix extraction (closes #23010, closes #23012) --- youtube_dl/extractor/chaturbate.py | 42 +++++++++++++++++++++++++----- 1 file changed, 35 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/chaturbate.py b/youtube_dl/extractor/chaturbate.py index 656e715ae..a459dcb8d 100644 --- a/youtube_dl/extractor/chaturbate.py +++ b/youtube_dl/extractor/chaturbate.py @@ -3,7 +3,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ExtractorError +from ..utils import ( + ExtractorError, + lowercase_escape, + url_or_none, +) class ChaturbateIE(InfoExtractor): @@ -38,12 +42,31 @@ class ChaturbateIE(InfoExtractor): 'https://chaturbate.com/%s/' % video_id, video_id, headers=self.geo_verification_headers()) - m3u8_urls = [] + found_m3u8_urls = [] - for m in re.finditer( - r'(["\'])(?Phttp.+?\.m3u8.*?)\1', webpage): - m3u8_fast_url, m3u8_no_fast_url = m.group('url'), m.group( - 'url').replace('_fast', '') + data = self._parse_json( + self._search_regex( + r'initialRoomDossier\s*=\s*(["\'])(?P(?:(?!\1).)+)\1', + webpage, 'data', default='{}', group='value'), + video_id, transform_source=lowercase_escape, fatal=False) + if data: + m3u8_url = url_or_none(data.get('hls_source')) + if m3u8_url: + found_m3u8_urls.append(m3u8_url) + + if not found_m3u8_urls: + for m in re.finditer( + r'(\\u002[27])(?Phttp.+?\.m3u8.*?)\1', webpage): + found_m3u8_urls.append(lowercase_escape(m.group('url'))) + + if not found_m3u8_urls: + for m in re.finditer( + r'(["\'])(?Phttp.+?\.m3u8.*?)\1', webpage): + found_m3u8_urls.append(m.group('url')) + + m3u8_urls = [] + for found_m3u8_url in found_m3u8_urls: + m3u8_fast_url, m3u8_no_fast_url = found_m3u8_url, found_m3u8_url.replace('_fast', '') for m3u8_url in (m3u8_fast_url, m3u8_no_fast_url): if m3u8_url not in m3u8_urls: m3u8_urls.append(m3u8_url) @@ -63,7 +86,12 @@ class ChaturbateIE(InfoExtractor): formats = [] for m3u8_url in m3u8_urls: - m3u8_id = 'fast' if '_fast' in m3u8_url else 'slow' + for known_id in ('fast', 'slow'): + if '_%s' % known_id in m3u8_url: + m3u8_id = known_id + break + else: + m3u8_id = None formats.extend(self._extract_m3u8_formats( m3u8_url, video_id, ext='mp4', # ffmpeg skips segments for fast m3u8 From 25d3f770e6ef518a4230ad41bd4ea69dd2e851af Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 21 Nov 2019 23:22:59 +0700 Subject: [PATCH 202/422] [ivi] Ask for pycryptodomex instead of pycryptodome See discussion at https://github.com/ytdl-org/youtube-dl/commit/1bba88efc7e1f82095f7ae38348e56026db4bf3c#r35982110 --- youtube_dl/extractor/ivi.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/ivi.py b/youtube_dl/extractor/ivi.py index 0db023622..52b53bfeb 100644 --- a/youtube_dl/extractor/ivi.py +++ b/youtube_dl/extractor/ivi.py @@ -137,7 +137,7 @@ class IviIE(InfoExtractor): continue elif not pycryptodomex_found: raise ExtractorError( - 'pycryptodome not found. Please install it.', + 'pycryptodomex not found. Please install it.', expected=True) elif message: extractor_msg += ': ' + message From f8015c15746e83394ecc395c6a13823d20971772 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 21 Nov 2019 23:38:39 +0700 Subject: [PATCH 203/422] [ivi] Fix python 3.4 support --- youtube_dl/extractor/ivi.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/ivi.py b/youtube_dl/extractor/ivi.py index 52b53bfeb..315ea03fa 100644 --- a/youtube_dl/extractor/ivi.py +++ b/youtube_dl/extractor/ivi.py @@ -91,10 +91,10 @@ class IviIE(InfoExtractor): 'contentid': video_id } ] - }).encode() + }) for site in (353, 183): - content_data = data % site + content_data = (data % site).encode() if site == 353: try: from Cryptodome.Cipher import Blowfish From 80a51fc2ef3ebb7d3e3d5fd0b6e9942bb4be6f4d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 22 Nov 2019 01:10:24 +0700 Subject: [PATCH 204/422] [ivi] Skip s353 for bundled exe See https://github.com/Legrandin/pycryptodome/issues/228 --- youtube_dl/extractor/ivi.py | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/ivi.py b/youtube_dl/extractor/ivi.py index 315ea03fa..a502e8806 100644 --- a/youtube_dl/extractor/ivi.py +++ b/youtube_dl/extractor/ivi.py @@ -1,8 +1,9 @@ # coding: utf-8 from __future__ import unicode_literals -import re import json +import re +import sys from .common import InfoExtractor from ..utils import ( @@ -93,9 +94,13 @@ class IviIE(InfoExtractor): ] }) + bundled = hasattr(sys, 'frozen') + for site in (353, 183): content_data = (data % site).encode() if site == 353: + if bundled: + continue try: from Cryptodome.Cipher import Blowfish from Cryptodome.Hash import CMAC @@ -135,6 +140,10 @@ class IviIE(InfoExtractor): extractor_msg = 'Video %s does not exist' elif site == 353: continue + elif bundled: + raise ExtractorError( + 'This feature does not work from bundled exe. Run youtube-dl from sources.', + expected=True) elif not pycryptodomex_found: raise ExtractorError( 'pycryptodomex not found. Please install it.', From fb8dfc5a2772ca35dd65bad7b7565ad6ec1ad4dd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 22 Nov 2019 01:21:00 +0700 Subject: [PATCH 205/422] [ChangeLog] Actualize [ci skip] --- ChangeLog | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) diff --git a/ChangeLog b/ChangeLog index d46d20082..acee2a75a 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,49 @@ +version + +Core ++ [extractor/common] Clean jwplayer description HTML tags ++ [extractor/common] Add data, headers and query to all major extract formats + methods + +Extractors +* [chaturbate] Fix extraction (#23010, #23012) ++ [ntvru] Add support for non relative file URLs (#23140) +* [vk] Fix wall audio thumbnails extraction (#23135) +* [ivi] Fix format extraction (#21991) +- [comcarcoff] Remove extractor ++ [drtv] Add support for new URL schema (#23059) ++ [nexx] Add support for Multi Player JS Setup (#23052) ++ [teamcoco] Add support for new videos (#23054) +* [soundcloud] Check if the soundtrack has downloads left (#23045) +* [facebook] Fix posts video data extraction (#22473) +- [addanime] Remove extractor +- [minhateca] Remove extractor +- [daisuki] Remove extractor +* [seeker] Fix extraction +- [revision3] Remove extractors +* [twitch] Fix video comments URL (#18593, #15828) +* [twitter] Improve extraction + + Add support for generic embeds (#22168) + * Always extract http formats for native videos (#14934) + + Add support for Twitter Broadcasts (#21369) + + Extract more metadata + * Improve VMap format extraction + * Unify extraction code for both twitter statuses and cards ++ [twitch] Add support for Clip embed URLs +* [lnkgo] Fix extraction (#16834) +* [mixcloud] Improve extraction + * Improve metadata extraction (#11721) + * Fix playlist extraction (#22378) + * Fix user mixes extraction (#15197, #17865) ++ [kinja] Add support for Kinja embeds (#5756, #11282, #22237, #22384) +* [onionstudios] Fix extraction ++ [hotstar] Pass Referer header to format requests (#22836) +* [dplay] Minimize response size ++ [patreon] Extract uploader_id and filesize +* [patreon] Minimize response size +* [roosterteeth] Fix login request (#16094, #22689) + + version 2019.11.05 Extractors From 0de9fd24dc8723c78a90cb546e4a05818304521e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 22 Nov 2019 01:24:27 +0700 Subject: [PATCH 206/422] release 2019.11.22 --- .github/ISSUE_TEMPLATE/1_broken_site.md | 6 +++--- .github/ISSUE_TEMPLATE/2_site_support_request.md | 4 ++-- .github/ISSUE_TEMPLATE/3_site_feature_request.md | 4 ++-- .github/ISSUE_TEMPLATE/4_bug_report.md | 6 +++--- .github/ISSUE_TEMPLATE/5_feature_request.md | 4 ++-- ChangeLog | 2 +- docs/supportedsites.md | 10 ++-------- youtube_dl/version.py | 2 +- 8 files changed, 16 insertions(+), 22 deletions(-) diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.md b/.github/ISSUE_TEMPLATE/1_broken_site.md index 12de9add2..d3e11cdcf 100644 --- a/.github/ISSUE_TEMPLATE/1_broken_site.md +++ b/.github/ISSUE_TEMPLATE/1_broken_site.md @@ -18,7 +18,7 @@ title: '' - [ ] I'm reporting a broken site support -- [ ] I've verified that I'm running youtube-dl version **2019.11.05** +- [ ] I've verified that I'm running youtube-dl version **2019.11.22** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar issues including closed ones @@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.11.05 + [debug] youtube-dl version 2019.11.22 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/2_site_support_request.md b/.github/ISSUE_TEMPLATE/2_site_support_request.md index 8a6202cf6..51bf4db3b 100644 --- a/.github/ISSUE_TEMPLATE/2_site_support_request.md +++ b/.github/ISSUE_TEMPLATE/2_site_support_request.md @@ -19,7 +19,7 @@ labels: 'site-support-request' - [ ] I'm reporting a new site support request -- [ ] I've verified that I'm running youtube-dl version **2019.11.05** +- [ ] I've verified that I'm running youtube-dl version **2019.11.22** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that none of provided URLs violate any copyrights - [ ] I've searched the bugtracker for similar site support requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/3_site_feature_request.md b/.github/ISSUE_TEMPLATE/3_site_feature_request.md index 83f91d5fe..19025ff25 100644 --- a/.github/ISSUE_TEMPLATE/3_site_feature_request.md +++ b/.github/ISSUE_TEMPLATE/3_site_feature_request.md @@ -18,13 +18,13 @@ title: '' - [ ] I'm reporting a site feature request -- [ ] I've verified that I'm running youtube-dl version **2019.11.05** +- [ ] I've verified that I'm running youtube-dl version **2019.11.22** - [ ] I've searched the bugtracker for similar site feature requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/4_bug_report.md b/.github/ISSUE_TEMPLATE/4_bug_report.md index be8e70f1e..a381b6979 100644 --- a/.github/ISSUE_TEMPLATE/4_bug_report.md +++ b/.github/ISSUE_TEMPLATE/4_bug_report.md @@ -18,7 +18,7 @@ title: '' - [ ] I'm reporting a broken site support issue -- [ ] I've verified that I'm running youtube-dl version **2019.11.05** +- [ ] I've verified that I'm running youtube-dl version **2019.11.22** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar bug reports including closed ones @@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.11.05 + [debug] youtube-dl version 2019.11.22 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/5_feature_request.md b/.github/ISSUE_TEMPLATE/5_feature_request.md index 7544d171c..9c945d5ec 100644 --- a/.github/ISSUE_TEMPLATE/5_feature_request.md +++ b/.github/ISSUE_TEMPLATE/5_feature_request.md @@ -19,13 +19,13 @@ labels: 'request' - [ ] I'm reporting a feature request -- [ ] I've verified that I'm running youtube-dl version **2019.11.05** +- [ ] I've verified that I'm running youtube-dl version **2019.11.22** - [ ] I've searched the bugtracker for similar feature requests including closed ones diff --git a/ChangeLog b/ChangeLog index acee2a75a..daaff3eef 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version +version 2019.11.22 Core + [extractor/common] Clean jwplayer description HTML tags diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 536b87479..3dcb026c5 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -26,7 +26,6 @@ - **AcademicEarth:Course** - **acast** - **acast:channel** - - **AddAnime** - **ADN**: Anime Digital Network - **AdobeConnect** - **AdobeTV** @@ -175,7 +174,6 @@ - **CNN** - **CNNArticle** - **CNNBlogs** - - **ComCarCoff** - **ComedyCentral** - **ComedyCentralFullEpisodes** - **ComedyCentralShortname** @@ -203,8 +201,6 @@ - **dailymotion** - **dailymotion:playlist** - **dailymotion:user** - - **DaisukiMotto** - - **DaisukiMottoPlaylist** - **daum.net** - **daum.net:clip** - **daum.net:playlist** @@ -404,6 +400,7 @@ - **Ketnet** - **KhanAcademy** - **KickStarter** + - **KinjaEmbed** - **KinoPoisk** - **KonserthusetPlay** - **kontrtube**: KontrTube.ru - Труба зовёт @@ -485,14 +482,12 @@ - **Mgoon** - **MGTV**: 芒果TV - **MiaoPai** - - **Minhateca** - **MinistryGrid** - **Minoto** - **miomio.tv** - **MiTele**: mitele.es - **mixcloud** - **mixcloud:playlist** - - **mixcloud:stream** - **mixcloud:user** - **Mixer:live** - **Mixer:vod** @@ -723,8 +718,6 @@ - **Restudy** - **Reuters** - **ReverbNation** - - **revision** - - **revision3:embed** - **RICE** - **RMCDecouverte** - **RockstarGames** @@ -958,6 +951,7 @@ - **twitch:vod** - **twitter** - **twitter:amplify** + - **twitter:broadcast** - **twitter:card** - **udemy** - **udemy:course** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 8012a66db..361809681 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.11.05' +__version__ = '2019.11.22' From cf3c9eafad5e6b83788e15a605aa6804b1ab307c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 27 Nov 2019 00:03:51 +0700 Subject: [PATCH 207/422] [soundcloud] Update client id (closes #23214) --- youtube_dl/extractor/soundcloud.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index e8ffb2cbe..988dec4fa 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -245,7 +245,7 @@ class SoundcloudIE(InfoExtractor): _API_BASE = 'https://api.soundcloud.com/' _API_V2_BASE = 'https://api-v2.soundcloud.com/' _BASE_URL = 'https://soundcloud.com/' - _CLIENT_ID = 'BeGVhOrGmfboy1LtiHTQF6Ejpt9ULJCI' + _CLIENT_ID = 'UW9ajvMgVdMMW3cdeBi8lPfN6dvOVGji' _IMAGE_REPL_RE = r'-([0-9a-z]+)\.jpg' _ARTWORK_MAP = { From 9d30c2132acf2d12bfa8e559987c341c76d9cd24 Mon Sep 17 00:00:00 2001 From: InfernalUnderling <42065091+InfernalUnderling@users.noreply.github.com> Date: Tue, 26 Nov 2019 17:08:37 +0000 Subject: [PATCH 208/422] [utils] Handle rd-suffixed day parts in unified_strdate (#23199) --- test/test_utils.py | 2 ++ youtube_dl/utils.py | 3 +++ 2 files changed, 5 insertions(+) diff --git a/test/test_utils.py b/test/test_utils.py index 3920542bb..0db37d9d8 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -340,6 +340,8 @@ class TestUtil(unittest.TestCase): self.assertEqual(unified_strdate('July 15th, 2013'), '20130715') self.assertEqual(unified_strdate('September 1st, 2013'), '20130901') self.assertEqual(unified_strdate('Sep 2nd, 2013'), '20130902') + self.assertEqual(unified_strdate('November 3rd, 2019'), '20191103') + self.assertEqual(unified_strdate('October 23rd, 2005'), '20051023') def test_unified_timestamps(self): self.assertEqual(unified_timestamp('December 21, 2010'), 1292889600) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index aed988b88..0d30075aa 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -1718,13 +1718,16 @@ DATE_FORMATS = ( '%B %d %Y', '%B %dst %Y', '%B %dnd %Y', + '%B %drd %Y', '%B %dth %Y', '%b %d %Y', '%b %dst %Y', '%b %dnd %Y', + '%b %drd %Y', '%b %dth %Y', '%b %dst %Y %I:%M', '%b %dnd %Y %I:%M', + '%b %drd %Y %I:%M', '%b %dth %Y %I:%M', '%Y %m %d', '%Y-%m-%d', From 6ddd4bf6ac04ae0b8ba39fb4124e844afc49b5a9 Mon Sep 17 00:00:00 2001 From: InfernalUnderling <42065091+InfernalUnderling@users.noreply.github.com> Date: Tue, 26 Nov 2019 17:20:39 +0000 Subject: [PATCH 209/422] [bitchute] Extract upload date (closes #22990) (#23193) --- youtube_dl/extractor/bitchute.py | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/youtube_dl/extractor/bitchute.py b/youtube_dl/extractor/bitchute.py index 430663fbf..0c773e66e 100644 --- a/youtube_dl/extractor/bitchute.py +++ b/youtube_dl/extractor/bitchute.py @@ -7,6 +7,7 @@ import re from .common import InfoExtractor from ..utils import ( orderedSet, + unified_strdate, urlencode_postdata, ) @@ -23,6 +24,7 @@ class BitChuteIE(InfoExtractor): 'description': 'md5:3f21f6fb5b1d17c3dee9cf6b5fe60b3a', 'thumbnail': r're:^https?://.*\.jpg$', 'uploader': 'Victoria X Rave', + 'upload_date': '20170813', }, }, { 'url': 'https://www.bitchute.com/embed/lbb5G1hjPhw/', @@ -74,12 +76,17 @@ class BitChuteIE(InfoExtractor): r'(?s)]+\bclass=["\']video-author[^>]+>(.+?)

    '), webpage, 'uploader', fatal=False) + upload_date = unified_strdate(self._search_regex( + r'class=["\']video-publish-date[^>]+>[^<]+ at \d+:\d+ UTC on (.+?)\.', + webpage, 'upload date', fatal=False)) + return { 'id': video_id, 'title': title, 'description': description, 'thumbnail': thumbnail, 'uploader': uploader, + 'upload_date': upload_date, 'formats': formats, } From 1ced222120c00854865c5b16e89838235ed549ee Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 27 Nov 2019 02:26:42 +0700 Subject: [PATCH 210/422] [utils] Add generic caesar cipher and rot47 --- test/test_utils.py | 16 ++++++++++++++++ youtube_dl/utils.py | 13 +++++++++++++ 2 files changed, 29 insertions(+) diff --git a/test/test_utils.py b/test/test_utils.py index 0db37d9d8..e83c8ea11 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -19,6 +19,7 @@ from youtube_dl.utils import ( age_restricted, args_to_str, encode_base_n, + caesar, clean_html, date_from_str, DateRange, @@ -69,6 +70,7 @@ from youtube_dl.utils import ( remove_start, remove_end, remove_quotes, + rot47, shell_quote, smuggle_url, str_to_int, @@ -1369,6 +1371,20 @@ Line 1 self.assertRaises(ValueError, encode_base_n, 0, 70) self.assertRaises(ValueError, encode_base_n, 0, 60, custom_table) + def test_caesar(self): + self.assertEqual(caesar('ace', 'abcdef', 2), 'cea') + self.assertEqual(caesar('cea', 'abcdef', -2), 'ace') + self.assertEqual(caesar('ace', 'abcdef', -2), 'eac') + self.assertEqual(caesar('eac', 'abcdef', 2), 'ace') + self.assertEqual(caesar('ace', 'abcdef', 0), 'ace') + self.assertEqual(caesar('xyz', 'abcdef', 2), 'xyz') + self.assertEqual(caesar('abc', 'acegik', 2), 'ebg') + self.assertEqual(caesar('ebg', 'acegik', -2), 'abc') + + def test_rot47(self): + self.assertEqual(rot47('youtube-dl'), r'J@FEF36\5=') + self.assertEqual(rot47('YOUTUBE-DL'), r'*~&%&qt\s{') + def test_urshift(self): self.assertEqual(urshift(3, 1), 1) self.assertEqual(urshift(-3, 1), 2147483646) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 0d30075aa..b14603d8a 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -5383,6 +5383,19 @@ def decode_packed_codes(code): obfucasted_code) +def caesar(s, alphabet, shift): + if shift == 0: + return s + l = len(alphabet) + return ''.join( + alphabet[(alphabet.index(c) + shift) % l] if c in alphabet else c + for c in s) + + +def rot47(s): + return caesar(s, r'''!"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~''', 47) + + def parse_m3u8_attributes(attrib): info = {} for (key, val) in re.findall(r'(?P[A-Z0-9-]+)=(?P"[^"]+"|[^",]+)(?:,|$)', attrib): From edc2a1f68b267abc6b4c94991da4ad83fd8374bb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 27 Nov 2019 02:28:06 +0700 Subject: [PATCH 211/422] [vivo] Fix extraction (closes #22328, closes #22279) --- youtube_dl/extractor/shared.py | 27 +++++++++++++++++++-------- 1 file changed, 19 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py index ff575f592..02295d1a4 100644 --- a/youtube_dl/extractor/shared.py +++ b/youtube_dl/extractor/shared.py @@ -1,13 +1,18 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import compat_b64decode +from ..compat import ( + compat_b64decode, + compat_urllib_parse_unquote_plus, +) from ..utils import ( determine_ext, ExtractorError, int_or_none, + js_to_json, KNOWN_EXTENSIONS, parse_filesize, + rot47, url_or_none, urlencode_postdata, ) @@ -112,16 +117,22 @@ class VivoIE(SharedBaseIE): webpage, 'filesize', fatal=False)) def _extract_video_url(self, webpage, video_id, url): - def decode_url(encoded_url): + def decode_url_old(encoded_url): return compat_b64decode(encoded_url).decode('utf-8') - stream_url = url_or_none(decode_url(self._search_regex( + stream_url = self._search_regex( r'data-stream\s*=\s*(["\'])(?P(?:(?!\1).)+)\1', webpage, - 'stream url', default=None, group='url'))) + 'stream url', default=None, group='url') + if stream_url: + stream_url = url_or_none(decode_url_old(stream_url)) if stream_url: return stream_url - return self._parse_json( + + def decode_url(encoded_url): + return rot47(compat_urllib_parse_unquote_plus(encoded_url)) + + return decode_url(self._parse_json( self._search_regex( - r'InitializeStream\s*\(\s*(["\'])(?P(?:(?!\1).)+)\1', - webpage, 'stream', group='url'), - video_id, transform_source=decode_url)[0] + r'(?s)InitializeStream\s*\(\s*({.+?})\s*\)\s*;', webpage, + 'stream'), + video_id, transform_source=js_to_json)['source']) From df65a4a1ed3096b8210c097c77d00f0391f78503 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Tue, 26 Nov 2019 21:53:51 +0100 Subject: [PATCH 212/422] [corus] improve extraction - add support for Series Plus, W Network, YTV, ABC Spark, disneychannel.com and disneylachaine.ca(closes #20861) - add support for self hosted videos(closes #22075) - detect DRM protection(closes #14910)(closes #9164) --- youtube_dl/extractor/corus.py | 169 ++++++++++++++++++++++------------ 1 file changed, 112 insertions(+), 57 deletions(-) diff --git a/youtube_dl/extractor/corus.py b/youtube_dl/extractor/corus.py index a1b251804..e11aadf14 100644 --- a/youtube_dl/extractor/corus.py +++ b/youtube_dl/extractor/corus.py @@ -4,7 +4,12 @@ from __future__ import unicode_literals import re from .theplatform import ThePlatformFeedIE -from ..utils import int_or_none +from ..utils import ( + dict_get, + ExtractorError, + float_or_none, + int_or_none, +) class CorusIE(ThePlatformFeedIE): @@ -12,24 +17,49 @@ class CorusIE(ThePlatformFeedIE): https?:// (?:www\.)? (?P - (?:globaltv|etcanada)\.com| - (?:hgtv|foodnetwork|slice|history|showcase|bigbrothercanada)\.ca + (?: + globaltv| + etcanada| + seriesplus| + wnetwork| + ytv + )\.com| + (?: + hgtv| + foodnetwork| + slice| + history| + showcase| + bigbrothercanada| + abcspark| + disney(?:channel|lachaine) + )\.ca + ) + /(?:[^/]+/)* + (?: + video\.html\?.*?\bv=| + videos?/(?:[^/]+/)*(?:[a-z0-9-]+-)? + ) + (?P + [\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}| + (?:[A-Z]{4})?\d{12,20} ) - /(?:video/(?:[^/]+/)?|(?:[^/]+/)+(?:videos/[a-z0-9-]+-|video\.html\?.*?\bv=)) - (?P\d+) ''' _TESTS = [{ 'url': 'http://www.hgtv.ca/shows/bryan-inc/videos/movie-night-popcorn-with-bryan-870923331648/', - 'md5': '05dcbca777bf1e58c2acbb57168ad3a6', 'info_dict': { 'id': '870923331648', 'ext': 'mp4', 'title': 'Movie Night Popcorn with Bryan', 'description': 'Bryan whips up homemade popcorn, the old fashion way for Jojo and Lincoln.', - 'uploader': 'SHWM-NEW', 'upload_date': '20170206', 'timestamp': 1486392197, }, + 'params': { + 'format': 'bestvideo', + 'skip_download': True, + }, + 'expected_warnings': ['Failed to parse JSON'], }, { 'url': 'http://www.foodnetwork.ca/shows/chopped/video/episode/chocolate-obsession/video.html?v=872683587753', 'only_matching': True, @@ -48,58 +78,83 @@ class CorusIE(ThePlatformFeedIE): }, { 'url': 'https://www.bigbrothercanada.ca/video/big-brother-canada-704/1457812035894/', 'only_matching': True + }, { + 'url': 'https://www.seriesplus.com/emissions/dre-mary-mort-sur-ordonnance/videos/deux-coeurs-battant/SERP0055626330000200/', + 'only_matching': True + }, { + 'url': 'https://www.disneychannel.ca/shows/gabby-duran-the-unsittables/video/crybaby-duran-clip/2f557eec-0588-11ea-ae2b-e2c6776b770e/', + 'only_matching': True }] - - _TP_FEEDS = { - 'globaltv': { - 'feed_id': 'ChQqrem0lNUp', - 'account_id': 2269680845, - }, - 'etcanada': { - 'feed_id': 'ChQqrem0lNUp', - 'account_id': 2269680845, - }, - 'hgtv': { - 'feed_id': 'L0BMHXi2no43', - 'account_id': 2414428465, - }, - 'foodnetwork': { - 'feed_id': 'ukK8o58zbRmJ', - 'account_id': 2414429569, - }, - 'slice': { - 'feed_id': '5tUJLgV2YNJ5', - 'account_id': 2414427935, - }, - 'history': { - 'feed_id': 'tQFx_TyyEq4J', - 'account_id': 2369613659, - }, - 'showcase': { - 'feed_id': '9H6qyshBZU3E', - 'account_id': 2414426607, - }, - 'bigbrothercanada': { - 'feed_id': 'ChQqrem0lNUp', - 'account_id': 2269680845, - }, + _GEO_BYPASS = False + _SITE_MAP = { + 'globaltv': 'series', + 'etcanada': 'series', + 'foodnetwork': 'food', + 'bigbrothercanada': 'series', + 'disneychannel': 'disneyen', + 'disneylachaine': 'disneyfr', } def _real_extract(self, url): domain, video_id = re.match(self._VALID_URL, url).groups() - feed_info = self._TP_FEEDS[domain.split('.')[0]] - return self._extract_feed_info('dtjsEC', feed_info['feed_id'], 'byId=' + video_id, video_id, lambda e: { - 'episode_number': int_or_none(e.get('pl1$episode')), - 'season_number': int_or_none(e.get('pl1$season')), - 'series': e.get('pl1$show'), - }, { - 'HLS': { - 'manifest': 'm3u', - }, - 'DesktopHLS Default': { - 'manifest': 'm3u', - }, - 'MP4 MBR': { - 'manifest': 'm3u', - }, - }, feed_info['account_id']) + site = domain.split('.')[0] + path = self._SITE_MAP.get(site, site) + if path != 'series': + path = 'migration/' + path + video = self._download_json( + 'https://globalcontent.corusappservices.com/templates/%s/playlist/' % path, + video_id, query={'byId': video_id}, + headers={'Accept': 'application/json'})[0] + title = video['title'] + + formats = [] + for source in video.get('sources', []): + smil_url = source.get('file') + if not smil_url: + continue + source_type = source.get('type') + note = 'Downloading%s smil file' % (' ' + source_type if source_type else '') + resp = self._download_webpage( + smil_url, video_id, note, fatal=False, + headers=self.geo_verification_headers()) + if not resp: + continue + error = self._parse_json(resp, video_id, fatal=False) + if error: + if error.get('exception') == 'GeoLocationBlocked': + self.raise_geo_restricted(countries=['CA']) + raise ExtractorError(error['description']) + smil = self._parse_xml(resp, video_id, fatal=False) + if smil is None: + continue + namespace = self._parse_smil_namespace(smil) + formats.extend(self._parse_smil_formats( + smil, smil_url, video_id, namespace)) + if not formats and video.get('drm'): + raise ExtractorError('This video is DRM protected.', expected=True) + self._sort_formats(formats) + + subtitles = {} + for track in video.get('tracks', []): + track_url = track.get('file') + if not track_url: + continue + lang = 'fr' if site in ('disneylachaine', 'seriesplus') else 'en' + subtitles.setdefault(lang, []).append({'url': track_url}) + + metadata = video.get('metadata') or {} + get_number = lambda x: int_or_none(video.get('pl1$' + x) or metadata.get(x + 'Number')) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnail': dict_get(video, ('defaultThumbnailUrl', 'thumbnail', 'image')), + 'description': video.get('description'), + 'timestamp': int_or_none(video.get('availableDate'), 1000), + 'subtitles': subtitles, + 'duration': float_or_none(metadata.get('duration')), + 'series': dict_get(video, ('show', 'pl1$show')), + 'season_number': get_number('season'), + 'episode_number': get_number('episode'), + } From 5ef62fc4ce1f255343d67b70f3cee2f2240cdfba Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Tue, 26 Nov 2019 22:01:34 +0100 Subject: [PATCH 213/422] [dailymotion] improve extraction - extract http formats included in m3u8 manifest - fix user extraction(closes #3553)(closes #21415) - add suport for User Authentication(closes #11491) - fix password protected videos extraction(closes #23176) - respect age limit option and family filter cookie value(closes #18437) - handle video url playlist query param - report alowed countries for geo-restricted videos --- youtube_dl/extractor/common.py | 13 + youtube_dl/extractor/dailymotion.py | 559 +++++++++++----------------- youtube_dl/extractor/vk.py | 3 +- 3 files changed, 234 insertions(+), 341 deletions(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 04d676378..eaae5e484 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1766,6 +1766,19 @@ class InfoExtractor(object): # the same GROUP-ID f['acodec'] = 'none' formats.append(f) + + # for DailyMotion + progressive_uri = last_stream_inf.get('PROGRESSIVE-URI') + if progressive_uri: + http_f = f.copy() + del http_f['manifest_url'] + http_f.update({ + 'format_id': f['format_id'].replace('hls-', 'http-'), + 'protocol': 'http', + 'url': progressive_uri, + }) + formats.append(http_f) + last_stream_inf = {} return formats diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 745971900..327fdb04a 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -1,50 +1,93 @@ # coding: utf-8 from __future__ import unicode_literals -import base64 import functools -import hashlib -import itertools import json -import random import re -import string from .common import InfoExtractor -from ..compat import compat_struct_pack +from ..compat import compat_HTTPError from ..utils import ( - determine_ext, - error_to_compat_str, + age_restricted, + clean_html, ExtractorError, int_or_none, - mimetype2ext, OnDemandPagedList, - parse_iso8601, - sanitized_Request, - str_to_int, try_get, unescapeHTML, - update_url_query, - url_or_none, urlencode_postdata, ) class DailymotionBaseInfoExtractor(InfoExtractor): + _FAMILY_FILTER = None + _HEADERS = { + 'Content-Type': 'application/json', + 'Origin': 'https://www.dailymotion.com', + } + _NETRC_MACHINE = 'dailymotion' + + def _get_dailymotion_cookies(self): + return self._get_cookies('https://www.dailymotion.com/') + @staticmethod - def _build_request(url): - """Build a request with the family filter disabled""" - request = sanitized_Request(url) - request.add_header('Cookie', 'family_filter=off; ff=off') - return request + def _get_cookie_value(cookies, name): + cookie = cookies.get('name') + if cookie: + return cookie.value - def _download_webpage_handle_no_ff(self, url, *args, **kwargs): - request = self._build_request(url) - return self._download_webpage_handle(request, *args, **kwargs) + def _set_dailymotion_cookie(self, name, value): + self._set_cookie('www.dailymotion.com', name, value) - def _download_webpage_no_ff(self, url, *args, **kwargs): - request = self._build_request(url) - return self._download_webpage(request, *args, **kwargs) + def _real_initialize(self): + cookies = self._get_dailymotion_cookies() + ff = self._get_cookie_value(cookies, 'ff') + self._FAMILY_FILTER = ff == 'on' if ff else age_restricted(18, self._downloader.params.get('age_limit')) + self._set_dailymotion_cookie('ff', 'on' if self._FAMILY_FILTER else 'off') + + def _call_api(self, object_type, xid, object_fields, note, filter_extra=None): + if not self._HEADERS.get('Authorization'): + cookies = self._get_dailymotion_cookies() + token = self._get_cookie_value(cookies, 'access_token') or self._get_cookie_value(cookies, 'client_token') + if not token: + data = { + 'client_id': 'f1a362d288c1b98099c7', + 'client_secret': 'eea605b96e01c796ff369935357eca920c5da4c5', + } + username, password = self._get_login_info() + if username: + data.update({ + 'grant_type': 'password', + 'password': password, + 'username': username, + }) + else: + data['grant_type'] = 'client_credentials' + try: + token = self._download_json( + 'https://graphql.api.dailymotion.com/oauth/token', + None, 'Downloading Access Token', + data=urlencode_postdata(data))['access_token'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400: + raise ExtractorError(self._parse_json( + e.cause.read().decode(), xid)['error_description'], expected=True) + raise + self._set_dailymotion_cookie('access_token' if username else 'client_token', token) + self._HEADERS['Authorization'] = 'Bearer ' + token + + resp = self._download_json( + 'https://graphql.api.dailymotion.com/', xid, note, data=json.dumps({ + 'query': '''{ + %s(xid: "%s"%s) { + %s + } +}''' % (object_type, xid, ', ' + filter_extra if filter_extra else '', object_fields), + }).encode(), headers=self._HEADERS) + obj = resp['data'][object_type] + if not obj: + raise ExtractorError(resp['errors'][0]['message'], expected=True) + return obj class DailymotionIE(DailymotionBaseInfoExtractor): @@ -54,18 +97,9 @@ class DailymotionIE(DailymotionBaseInfoExtractor): (?:(?:www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(?:(?:embed|swf|\#)/)?video|swf)| (?:www\.)?lequipe\.fr/video ) - /(?P[^/?_]+) + /(?P[^/?_]+)(?:.+?\bplaylist=(?Px[0-9a-z]+))? ''' IE_NAME = 'dailymotion' - - _FORMATS = [ - ('stream_h264_ld_url', 'ld'), - ('stream_h264_url', 'standard'), - ('stream_h264_hq_url', 'hq'), - ('stream_h264_hd_url', 'hd'), - ('stream_h264_hd1080_url', 'hd180'), - ] - _TESTS = [{ 'url': 'http://www.dailymotion.com/video/x5kesuj_office-christmas-party-review-jason-bateman-olivia-munn-t-j-miller_news', 'md5': '074b95bdee76b9e3654137aee9c79dfe', @@ -74,7 +108,6 @@ class DailymotionIE(DailymotionBaseInfoExtractor): 'ext': 'mp4', 'title': 'Office Christmas Party Review – Jason Bateman, Olivia Munn, T.J. Miller', 'description': 'Office Christmas Party Review - Jason Bateman, Olivia Munn, T.J. Miller', - 'thumbnail': r're:^https?:.*\.(?:jpg|png)$', 'duration': 187, 'timestamp': 1493651285, 'upload_date': '20170501', @@ -146,7 +179,16 @@ class DailymotionIE(DailymotionBaseInfoExtractor): }, { 'url': 'https://www.lequipe.fr/video/k7MtHciueyTcrFtFKA2', 'only_matching': True, + }, { + 'url': 'https://www.dailymotion.com/video/x3z49k?playlist=xv4bw', + 'only_matching': True, }] + _GEO_BYPASS = False + _COMMON_MEDIA_FIELDS = '''description + geoblockedCountries { + allowed + } + xid''' @staticmethod def _extract_urls(webpage): @@ -162,264 +204,140 @@ class DailymotionIE(DailymotionBaseInfoExtractor): return urls def _real_extract(self, url): - video_id = self._match_id(url) + video_id, playlist_id = re.match(self._VALID_URL, url).groups() - webpage = self._download_webpage_no_ff( - 'https://www.dailymotion.com/video/%s' % video_id, video_id) + if playlist_id: + if not self._downloader.params.get('noplaylist'): + self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % playlist_id) + return self.url_result( + 'http://www.dailymotion.com/playlist/' + playlist_id, + 'DailymotionPlaylist', playlist_id) + self.to_screen('Downloading just video %s because of --no-playlist' % video_id) - age_limit = self._rta_search(webpage) - - description = self._og_search_description( - webpage, default=None) or self._html_search_meta( - 'description', webpage, 'description') - - view_count_str = self._search_regex( - (r']+itemprop="interactionCount"[^>]+content="UserPlays:([\s\d,.]+)"', - r'video_views_count[^>]+>\s+([\s\d\,.]+)'), - webpage, 'view count', default=None) - if view_count_str: - view_count_str = re.sub(r'\s', '', view_count_str) - view_count = str_to_int(view_count_str) - comment_count = int_or_none(self._search_regex( - r']+itemprop="interactionCount"[^>]+content="UserComments:(\d+)"', - webpage, 'comment count', default=None)) - - player_v5 = self._search_regex( - [r'buildPlayer\(({.+?})\);\n', # See https://github.com/ytdl-org/youtube-dl/issues/7826 - r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);', - r'buildPlayer\(({.+?})\);', - r'var\s+config\s*=\s*({.+?});', - # New layout regex (see https://github.com/ytdl-org/youtube-dl/issues/13580) - r'__PLAYER_CONFIG__\s*=\s*({.+?});'], - webpage, 'player v5', default=None) - if player_v5: - player = self._parse_json(player_v5, video_id, fatal=False) or {} - metadata = try_get(player, lambda x: x['metadata'], dict) - if not metadata: - metadata_url = url_or_none(try_get( - player, lambda x: x['context']['metadata_template_url1'])) - if metadata_url: - metadata_url = metadata_url.replace(':videoId', video_id) - else: - metadata_url = update_url_query( - 'https://www.dailymotion.com/player/metadata/video/%s' - % video_id, { - 'embedder': url, - 'integration': 'inline', - 'GK_PV5_NEON': '1', - }) - metadata = self._download_json( - metadata_url, video_id, 'Downloading metadata JSON') - - if try_get(metadata, lambda x: x['error']['type']) == 'password_protected': - password = self._downloader.params.get('videopassword') - if password: - r = int(metadata['id'][1:], 36) - us64e = lambda x: base64.urlsafe_b64encode(x).decode().strip('=') - t = ''.join(random.choice(string.ascii_letters) for i in range(10)) - n = us64e(compat_struct_pack('I', r)) - i = us64e(hashlib.md5(('%s%d%s' % (password, r, t)).encode()).digest()) - metadata = self._download_json( - 'http://www.dailymotion.com/player/metadata/video/p' + i + t + n, video_id) - - self._check_error(metadata) - - formats = [] - for quality, media_list in metadata['qualities'].items(): - for media in media_list: - media_url = media.get('url') - if not media_url: - continue - type_ = media.get('type') - if type_ == 'application/vnd.lumberjack.manifest': - continue - ext = mimetype2ext(type_) or determine_ext(media_url) - if ext == 'm3u8': - m3u8_formats = self._extract_m3u8_formats( - media_url, video_id, 'mp4', preference=-1, - m3u8_id='hls', fatal=False) - for f in m3u8_formats: - f['url'] = f['url'].split('#')[0] - formats.append(f) - elif ext == 'f4m': - formats.extend(self._extract_f4m_formats( - media_url, video_id, preference=-1, f4m_id='hds', fatal=False)) - else: - f = { - 'url': media_url, - 'format_id': 'http-%s' % quality, - 'ext': ext, - } - m = re.search(r'H264-(?P\d+)x(?P\d+)', media_url) - if m: - f.update({ - 'width': int(m.group('width')), - 'height': int(m.group('height')), - }) - formats.append(f) - self._sort_formats(formats) - - title = metadata['title'] - duration = int_or_none(metadata.get('duration')) - timestamp = int_or_none(metadata.get('created_time')) - thumbnail = metadata.get('poster_url') - uploader = metadata.get('owner', {}).get('screenname') - uploader_id = metadata.get('owner', {}).get('id') - - subtitles = {} - subtitles_data = metadata.get('subtitles', {}).get('data', {}) - if subtitles_data and isinstance(subtitles_data, dict): - for subtitle_lang, subtitle in subtitles_data.items(): - subtitles[subtitle_lang] = [{ - 'ext': determine_ext(subtitle_url), - 'url': subtitle_url, - } for subtitle_url in subtitle.get('urls', [])] - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'duration': duration, - 'timestamp': timestamp, - 'uploader': uploader, - 'uploader_id': uploader_id, - 'age_limit': age_limit, - 'view_count': view_count, - 'comment_count': comment_count, - 'formats': formats, - 'subtitles': subtitles, - } - - # vevo embed - vevo_id = self._search_regex( - r'[\w]*)', - webpage, 'vevo embed', default=None) - if vevo_id: - return self.url_result('vevo:%s' % vevo_id, 'Vevo') - - # fallback old player - embed_page = self._download_webpage_no_ff( - 'https://www.dailymotion.com/embed/video/%s' % video_id, - video_id, 'Downloading embed page') - - timestamp = parse_iso8601(self._html_search_meta( - 'video:release_date', webpage, 'upload date')) - - info = self._parse_json( - self._search_regex( - r'var info = ({.*?}),$', embed_page, - 'video info', flags=re.MULTILINE), - video_id) - - self._check_error(info) - - formats = [] - for (key, format_id) in self._FORMATS: - video_url = info.get(key) - if video_url is not None: - m_size = re.search(r'H264-(\d+)x(\d+)', video_url) - if m_size is not None: - width, height = map(int_or_none, (m_size.group(1), m_size.group(2))) - else: - width, height = None, None - formats.append({ - 'url': video_url, - 'ext': 'mp4', - 'format_id': format_id, - 'width': width, - 'height': height, - }) - self._sort_formats(formats) - - # subtitles - video_subtitles = self.extract_subtitles(video_id, webpage) - - title = self._og_search_title(webpage, default=None) - if title is None: - title = self._html_search_regex( - r'(?s)]*>(.*?)', webpage, - 'title') - - return { - 'id': video_id, - 'formats': formats, - 'uploader': info['owner.screenname'], - 'timestamp': timestamp, - 'title': title, - 'description': description, - 'subtitles': video_subtitles, - 'thumbnail': info['thumbnail_url'], - 'age_limit': age_limit, - 'view_count': view_count, - 'duration': info['duration'] + password = self._downloader.params.get('videopassword') + media = self._call_api( + 'media', video_id, '''... on Video { + %s + stats { + likes { + total } + views { + total + } + } + } + ... on Live { + %s + audienceCount + isOnAir + }''' % (self._COMMON_MEDIA_FIELDS, self._COMMON_MEDIA_FIELDS), 'Downloading media JSON metadata', + 'password: "%s"' % self._downloader.params.get('videopassword') if password else None) + xid = media['xid'] - def _check_error(self, info): - error = info.get('error') + metadata = self._download_json( + 'https://www.dailymotion.com/player/metadata/video/' + xid, + xid, 'Downloading metadata JSON', + query={'app': 'com.dailymotion.neon'}) + + error = metadata.get('error') if error: - title = error.get('title') or error['message'] + title = error.get('title') or error['raw_message'] # See https://developer.dailymotion.com/api#access-error if error.get('code') == 'DM007': - self.raise_geo_restricted(msg=title) + allowed_countries = try_get(media, lambda x: x['geoblockedCountries']['allowed'], list) + self.raise_geo_restricted(msg=title, countries=allowed_countries) raise ExtractorError( '%s said: %s' % (self.IE_NAME, title), expected=True) - def _get_subtitles(self, video_id, webpage): - try: - sub_list = self._download_webpage( - 'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id, - video_id, note=False) - except ExtractorError as err: - self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err)) - return {} - info = json.loads(sub_list) - if (info['total'] > 0): - sub_lang_list = dict((l['language'], [{'url': l['url'], 'ext': 'srt'}]) for l in info['list']) - return sub_lang_list - self._downloader.report_warning('video doesn\'t have subtitles') - return {} + title = metadata['title'] + is_live = media.get('isOnAir') + formats = [] + for quality, media_list in metadata['qualities'].items(): + for m in media_list: + media_url = m.get('url') + media_type = m.get('type') + if not media_url or media_type == 'application/vnd.lumberjack.manifest': + continue + if media_type == 'application/x-mpegURL': + formats.extend(self._extract_m3u8_formats( + media_url, video_id, 'mp4', + 'm3u8' if is_live else 'm3u8_native', + m3u8_id='hls', fatal=False)) + else: + f = { + 'url': media_url, + 'format_id': 'http-' + quality, + } + m = re.search(r'/H264-(\d+)x(\d+)(?:-(60)/)?', media_url) + if m: + width, height, fps = map(int_or_none, m.groups()) + f.update({ + 'fps': fps, + 'height': height, + 'width': width, + }) + formats.append(f) + for f in formats: + f['url'] = f['url'].split('#')[0] + if not f.get('fps') and f['format_id'].endswith('@60'): + f['fps'] = 60 + self._sort_formats(formats) + + subtitles = {} + subtitles_data = try_get(metadata, lambda x: x['subtitles']['data'], dict) or {} + for subtitle_lang, subtitle in subtitles_data.items(): + subtitles[subtitle_lang] = [{ + 'url': subtitle_url, + } for subtitle_url in subtitle.get('urls', [])] + + thumbnails = [] + for height, poster_url in metadata.get('posters', {}).items(): + thumbnails.append({ + 'height': int_or_none(height), + 'id': height, + 'url': poster_url, + }) + + owner = metadata.get('owner') or {} + stats = media.get('stats') or {} + get_count = lambda x: int_or_none(try_get(stats, lambda y: y[x + 's']['total'])) + + return { + 'id': video_id, + 'title': self._live_title(title) if is_live else title, + 'description': clean_html(media.get('description')), + 'thumbnails': thumbnails, + 'duration': int_or_none(metadata.get('duration')) or None, + 'timestamp': int_or_none(metadata.get('created_time')), + 'uploader': owner.get('screenname'), + 'uploader_id': owner.get('id') or metadata.get('screenname'), + 'age_limit': 18 if metadata.get('explicit') else 0, + 'tags': metadata.get('tags'), + 'view_count': get_count('view') or int_or_none(media.get('audienceCount')), + 'like_count': get_count('like'), + 'formats': formats, + 'subtitles': subtitles, + 'is_live': is_live, + } -class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): - IE_NAME = 'dailymotion:playlist' - _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?Px[0-9a-z]+)' - _TESTS = [{ - 'url': 'http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q', - 'info_dict': { - 'title': 'SPORT', - 'id': 'xv4bw', - }, - 'playlist_mincount': 20, - }] +class DailymotionPlaylistBaseIE(DailymotionBaseInfoExtractor): _PAGE_SIZE = 100 - def _fetch_page(self, playlist_id, authorizaion, page): + def _fetch_page(self, playlist_id, page): page += 1 - videos = self._download_json( - 'https://graphql.api.dailymotion.com', - playlist_id, 'Downloading page %d' % page, - data=json.dumps({ - 'query': '''{ - collection(xid: "%s") { - videos(first: %d, page: %d) { - pageInfo { - hasNextPage - nextPage - } + videos = self._call_api( + self._OBJECT_TYPE, playlist_id, + '''videos(allowExplicit: %s, first: %d, page: %d) { edges { node { xid url } } - } - } -}''' % (playlist_id, self._PAGE_SIZE, page) - }).encode(), headers={ - 'Authorization': authorizaion, - 'Origin': 'https://www.dailymotion.com', - })['data']['collection']['videos'] + }''' % ('false' if self._FAMILY_FILTER else 'true', self._PAGE_SIZE, page), + 'Downloading page %d' % page)['videos'] for edge in videos['edges']: node = edge['node'] yield self.url_result( @@ -427,86 +345,49 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): def _real_extract(self, url): playlist_id = self._match_id(url) - webpage = self._download_webpage(url, playlist_id) - api = self._parse_json(self._search_regex( - r'__PLAYER_CONFIG__\s*=\s*({.+?});', - webpage, 'player config'), playlist_id)['context']['api'] - auth = self._download_json( - api.get('auth_url', 'https://graphql.api.dailymotion.com/oauth/token'), - playlist_id, data=urlencode_postdata({ - 'client_id': api.get('client_id', 'f1a362d288c1b98099c7'), - 'client_secret': api.get('client_secret', 'eea605b96e01c796ff369935357eca920c5da4c5'), - 'grant_type': 'client_credentials', - })) - authorizaion = '%s %s' % (auth.get('token_type', 'Bearer'), auth['access_token']) entries = OnDemandPagedList(functools.partial( - self._fetch_page, playlist_id, authorizaion), self._PAGE_SIZE) + self._fetch_page, playlist_id), self._PAGE_SIZE) return self.playlist_result( - entries, playlist_id, - self._og_search_title(webpage)) + entries, playlist_id) -class DailymotionUserIE(DailymotionBaseInfoExtractor): +class DailymotionPlaylistIE(DailymotionPlaylistBaseIE): + IE_NAME = 'dailymotion:playlist' + _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?Px[0-9a-z]+)' + _TESTS = [{ + 'url': 'http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q', + 'info_dict': { + 'id': 'xv4bw', + }, + 'playlist_mincount': 20, + }] + _OBJECT_TYPE = 'collection' + + +class DailymotionUserIE(DailymotionPlaylistBaseIE): IE_NAME = 'dailymotion:user' - _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|swf|#|video|playlist)/)(?:(?:old/)?user/)?(?P[^/]+)' - _MORE_PAGES_INDICATOR = r'(?s)
    .*?[^/]+)' _TESTS = [{ 'url': 'https://www.dailymotion.com/user/nqtv', 'info_dict': { 'id': 'nqtv', - 'title': 'Rémi Gaillard', }, - 'playlist_mincount': 100, + 'playlist_mincount': 152, }, { 'url': 'http://www.dailymotion.com/user/UnderProject', 'info_dict': { 'id': 'UnderProject', - 'title': 'UnderProject', }, - 'playlist_mincount': 1800, - 'expected_warnings': [ - 'Stopped at duplicated page', - ], + 'playlist_mincount': 1000, 'skip': 'Takes too long time', + }, { + 'url': 'https://www.dailymotion.com/user/nqtv', + 'info_dict': { + 'id': 'nqtv', + }, + 'playlist_mincount': 148, + 'params': { + 'age_limit': 0, + }, }] - - def _extract_entries(self, id): - video_ids = set() - processed_urls = set() - for pagenum in itertools.count(1): - page_url = self._PAGE_TEMPLATE % (id, pagenum) - webpage, urlh = self._download_webpage_handle_no_ff( - page_url, id, 'Downloading page %s' % pagenum) - if urlh.geturl() in processed_urls: - self.report_warning('Stopped at duplicated page %s, which is the same as %s' % ( - page_url, urlh.geturl()), id) - break - - processed_urls.add(urlh.geturl()) - - for video_id in re.findall(r'data-xid="(.+?)"', webpage): - if video_id not in video_ids: - yield self.url_result( - 'http://www.dailymotion.com/video/%s' % video_id, - DailymotionIE.ie_key(), video_id) - video_ids.add(video_id) - - if re.search(self._MORE_PAGES_INDICATOR, webpage) is None: - break - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - user = mobj.group('user') - webpage = self._download_webpage( - 'https://www.dailymotion.com/user/%s' % user, user) - full_user = unescapeHTML(self._html_search_regex( - r'' % re.escape(user), - webpage, 'user')) - - return { - '_type': 'playlist', - 'id': user, - 'title': full_user, - 'entries': self._extract_entries(user), - } + _OBJECT_TYPE = 'channel' diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index 195875938..a5e4a3e67 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -216,8 +216,7 @@ class VKIE(VKBaseIE): 'id': 'k3lz2cmXyRuJQSjGHUv', 'ext': 'mp4', 'title': 'md5:d52606645c20b0ddbb21655adaa4f56f', - # TODO: fix test by fixing dailymotion description extraction - 'description': 'md5:c651358f03c56f1150b555c26d90a0fd', + 'description': 'md5:424b8e88cc873217f520e582ba28bb36', 'uploader': 'AniLibria.Tv', 'upload_date': '20160914', 'uploader_id': 'x1p5vl5', From 6471d0d3b8086b282622c84a9eea968d4edfcf9b Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Tue, 26 Nov 2019 23:57:37 +0100 Subject: [PATCH 214/422] [openload] remove OpenLoad related extractors(closes #11999)(closes #15406) --- youtube_dl/extractor/extractors.py | 5 - youtube_dl/extractor/generic.py | 16 -- youtube_dl/extractor/openload.py | 263 ----------------------------- youtube_dl/extractor/streamango.py | 128 -------------- 4 files changed, 412 deletions(-) delete mode 100644 youtube_dl/extractor/streamango.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index cf4bb8f20..0e349b778 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -796,10 +796,6 @@ from .ooyala import ( OoyalaIE, OoyalaExternalIE, ) -from .openload import ( - OpenloadIE, - VerystreamIE, -) from .ora import OraTVIE from .orf import ( ORFTVthekIE, @@ -1060,7 +1056,6 @@ from .srmediathek import SRMediathekIE from .stanfordoc import StanfordOpenClassroomIE from .steam import SteamIE from .streamable import StreamableIE -from .streamango import StreamangoIE from .streamcloud import StreamcloudIE from .streamcz import StreamCZIE from .streetvoice import StreetVoiceIE diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 3d919f656..743ef47db 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -88,10 +88,6 @@ from .piksel import PikselIE from .videa import VideaIE from .twentymin import TwentyMinutenIE from .ustream import UstreamIE -from .openload import ( - OpenloadIE, - VerystreamIE, -) from .videopress import VideoPressIE from .rutube import RutubeIE from .limelight import LimelightBaseIE @@ -3048,18 +3044,6 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key()) - # Look for Openload embeds - openload_urls = OpenloadIE._extract_urls(webpage) - if openload_urls: - return self.playlist_from_matches( - openload_urls, video_id, video_title, ie=OpenloadIE.ie_key()) - - # Look for Verystream embeds - verystream_urls = VerystreamIE._extract_urls(webpage) - if verystream_urls: - return self.playlist_from_matches( - verystream_urls, video_id, video_title, ie=VerystreamIE.ie_key()) - # Look for VideoPress embeds videopress_urls = VideoPressIE._extract_urls(webpage) if videopress_urls: diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index 66e38cdb4..0c20d0177 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -3,21 +3,17 @@ from __future__ import unicode_literals import json import os -import re import subprocess import tempfile -from .common import InfoExtractor from ..compat import ( compat_urlparse, compat_kwargs, ) from ..utils import ( check_executable, - determine_ext, encodeArgument, ExtractorError, - get_element_by_id, get_exe_version, is_outdated_version, std_headers, @@ -240,262 +236,3 @@ class PhantomJSwrapper(object): self._load_cookies() return (html, encodeArgument(out)) - - -class OpenloadIE(InfoExtractor): - _DOMAINS = r''' - (?: - openload\.(?:co|io|link|pw)| - oload\.(?:tv|best|biz|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|online|monster|press|pw|life|live|space|services|website|vip)| - oladblock\.(?:services|xyz|me)|openloed\.co - ) - ''' - _VALID_URL = r'''(?x) - https?:// - (?P - (?:www\.)? - %s - )/ - (?:f|embed)/ - (?P[a-zA-Z0-9-_]+) - ''' % _DOMAINS - _EMBED_WORD = 'embed' - _STREAM_WORD = 'f' - _REDIR_WORD = 'stream' - _URL_IDS = ('streamurl', 'streamuri', 'streamurj') - _TESTS = [{ - 'url': 'https://openload.co/f/kUEfGclsU9o', - 'md5': 'bf1c059b004ebc7a256f89408e65c36e', - 'info_dict': { - 'id': 'kUEfGclsU9o', - 'ext': 'mp4', - 'title': 'skyrim_no-audio_1080.mp4', - 'thumbnail': r're:^https?://.*\.jpg$', - }, - }, { - 'url': 'https://openload.co/embed/rjC09fkPLYs', - 'info_dict': { - 'id': 'rjC09fkPLYs', - 'ext': 'mp4', - 'title': 'movie.mp4', - 'thumbnail': r're:^https?://.*\.jpg$', - 'subtitles': { - 'en': [{ - 'ext': 'vtt', - }], - }, - }, - 'params': { - 'skip_download': True, # test subtitles only - }, - }, { - 'url': 'https://openload.co/embed/kUEfGclsU9o/skyrim_no-audio_1080.mp4', - 'only_matching': True, - }, { - 'url': 'https://openload.io/f/ZAn6oz-VZGE/', - 'only_matching': True, - }, { - 'url': 'https://openload.co/f/_-ztPaZtMhM/', - 'only_matching': True, - }, { - # unavailable via https://openload.co/f/Sxz5sADo82g/, different layout - # for title and ext - 'url': 'https://openload.co/embed/Sxz5sADo82g/', - 'only_matching': True, - }, { - # unavailable via https://openload.co/embed/e-Ixz9ZR5L0/ but available - # via https://openload.co/f/e-Ixz9ZR5L0/ - 'url': 'https://openload.co/f/e-Ixz9ZR5L0/', - 'only_matching': True, - }, { - 'url': 'https://oload.tv/embed/KnG-kKZdcfY/', - 'only_matching': True, - }, { - 'url': 'http://www.openload.link/f/KnG-kKZdcfY', - 'only_matching': True, - }, { - 'url': 'https://oload.stream/f/KnG-kKZdcfY', - 'only_matching': True, - }, { - 'url': 'https://oload.xyz/f/WwRBpzW8Wtk', - 'only_matching': True, - }, { - 'url': 'https://oload.win/f/kUEfGclsU9o', - 'only_matching': True, - }, { - 'url': 'https://oload.download/f/kUEfGclsU9o', - 'only_matching': True, - }, { - 'url': 'https://oload.cloud/f/4ZDnBXRWiB8', - 'only_matching': True, - }, { - # Its title has not got its extension but url has it - 'url': 'https://oload.download/f/N4Otkw39VCw/Tomb.Raider.2018.HDRip.XviD.AC3-EVO.avi.mp4', - 'only_matching': True, - }, { - 'url': 'https://oload.cc/embed/5NEAbI2BDSk', - 'only_matching': True, - }, { - 'url': 'https://oload.icu/f/-_i4y_F_Hs8', - 'only_matching': True, - }, { - 'url': 'https://oload.fun/f/gb6G1H4sHXY', - 'only_matching': True, - }, { - 'url': 'https://oload.club/f/Nr1L-aZ2dbQ', - 'only_matching': True, - }, { - 'url': 'https://oload.info/f/5NEAbI2BDSk', - 'only_matching': True, - }, { - 'url': 'https://openload.pw/f/WyKgK8s94N0', - 'only_matching': True, - }, { - 'url': 'https://oload.pw/f/WyKgK8s94N0', - 'only_matching': True, - }, { - 'url': 'https://oload.live/f/-Z58UZ-GR4M', - 'only_matching': True, - }, { - 'url': 'https://oload.space/f/IY4eZSst3u8/', - 'only_matching': True, - }, { - 'url': 'https://oload.services/embed/bs1NWj1dCag/', - 'only_matching': True, - }, { - 'url': 'https://oload.online/f/W8o2UfN1vNY/', - 'only_matching': True, - }, { - 'url': 'https://oload.monster/f/W8o2UfN1vNY/', - 'only_matching': True, - }, { - 'url': 'https://oload.press/embed/drTBl1aOTvk/', - 'only_matching': True, - }, { - 'url': 'https://oload.website/embed/drTBl1aOTvk/', - 'only_matching': True, - }, { - 'url': 'https://oload.life/embed/oOzZjNPw9Dc/', - 'only_matching': True, - }, { - 'url': 'https://oload.biz/f/bEk3Gp8ARr4/', - 'only_matching': True, - }, { - 'url': 'https://oload.best/embed/kkz9JgVZeWc/', - 'only_matching': True, - }, { - 'url': 'https://oladblock.services/f/b8NWEgkqNLI/', - 'only_matching': True, - }, { - 'url': 'https://oladblock.xyz/f/b8NWEgkqNLI/', - 'only_matching': True, - }, { - 'url': 'https://oladblock.me/f/b8NWEgkqNLI/', - 'only_matching': True, - }, { - 'url': 'https://openloed.co/f/b8NWEgkqNLI/', - 'only_matching': True, - }, { - 'url': 'https://oload.vip/f/kUEfGclsU9o', - 'only_matching': True, - }] - - @classmethod - def _extract_urls(cls, webpage): - return re.findall( - r'(?x)]+src=["\']((?:https?://)?%s/%s/[a-zA-Z0-9-_]+)' - % (cls._DOMAINS, cls._EMBED_WORD), webpage) - - def _extract_decrypted_page(self, page_url, webpage, video_id): - phantom = PhantomJSwrapper(self, required_version='2.0') - webpage, _ = phantom.get(page_url, html=webpage, video_id=video_id) - return webpage - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - host = mobj.group('host') - video_id = mobj.group('id') - - url_pattern = 'https://%s/%%s/%s/' % (host, video_id) - - for path in (self._EMBED_WORD, self._STREAM_WORD): - page_url = url_pattern % path - last = path == self._STREAM_WORD - webpage = self._download_webpage( - page_url, video_id, 'Downloading %s webpage' % path, - fatal=last) - if not webpage: - continue - if 'File not found' in webpage or 'deleted by the owner' in webpage: - if not last: - continue - raise ExtractorError('File not found', expected=True, video_id=video_id) - break - - webpage = self._extract_decrypted_page(page_url, webpage, video_id) - for element_id in self._URL_IDS: - decoded_id = get_element_by_id(element_id, webpage) - if decoded_id: - break - if not decoded_id: - decoded_id = self._search_regex( - (r'>\s*([\w-]+~\d{10,}~\d+\.\d+\.0\.0~[\w-]+)\s*<', - r'>\s*([\w~-]+~\d+\.\d+\.\d+\.\d+~[\w~-]+)', - r'>\s*([\w-]+~\d{10,}~(?:[a-f\d]+:){2}:~[\w-]+)\s*<', - r'>\s*([\w~-]+~[a-f0-9:]+~[\w~-]+)\s*<', - r'>\s*([\w~-]+~[a-f0-9:]+~[\w~-]+)'), webpage, - 'stream URL') - video_url = 'https://%s/%s/%s?mime=true' % (host, self._REDIR_WORD, decoded_id) - - title = self._og_search_title(webpage, default=None) or self._search_regex( - r']+class=["\']title["\'][^>]*>([^<]+)', webpage, - 'title', default=None) or self._html_search_meta( - 'description', webpage, 'title', fatal=True) - - entries = self._parse_html5_media_entries(page_url, webpage, video_id) - entry = entries[0] if entries else {} - subtitles = entry.get('subtitles') - - return { - 'id': video_id, - 'title': title, - 'thumbnail': entry.get('thumbnail') or self._og_search_thumbnail(webpage, default=None), - 'url': video_url, - 'ext': determine_ext(title, None) or determine_ext(url, 'mp4'), - 'subtitles': subtitles, - } - - -class VerystreamIE(OpenloadIE): - IE_NAME = 'verystream' - - _DOMAINS = r'(?:verystream\.com|woof\.tube)' - _VALID_URL = r'''(?x) - https?:// - (?P - (?:www\.)? - %s - )/ - (?:stream|e)/ - (?P[a-zA-Z0-9-_]+) - ''' % _DOMAINS - _EMBED_WORD = 'e' - _STREAM_WORD = 'stream' - _REDIR_WORD = 'gettoken' - _URL_IDS = ('videolink', ) - _TESTS = [{ - 'url': 'https://verystream.com/stream/c1GWQ9ngBBx/', - 'md5': 'd3e8c5628ccb9970b65fd65269886795', - 'info_dict': { - 'id': 'c1GWQ9ngBBx', - 'ext': 'mp4', - 'title': 'Big Buck Bunny.mp4', - 'thumbnail': r're:^https?://.*\.jpg$', - }, - }, { - 'url': 'https://verystream.com/e/c1GWQ9ngBBx/', - 'only_matching': True, - }] - - def _extract_decrypted_page(self, page_url, webpage, video_id): - return webpage # for Verystream, the webpage is already decrypted diff --git a/youtube_dl/extractor/streamango.py b/youtube_dl/extractor/streamango.py deleted file mode 100644 index f1e17dd88..000000000 --- a/youtube_dl/extractor/streamango.py +++ /dev/null @@ -1,128 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..compat import compat_chr -from ..utils import ( - determine_ext, - ExtractorError, - int_or_none, - js_to_json, -) - - -class StreamangoIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?:streamango\.com|fruithosts\.net|streamcherry\.com)/(?:f|embed)/(?P[^/?#&]+)' - _TESTS = [{ - 'url': 'https://streamango.com/f/clapasobsptpkdfe/20170315_150006_mp4', - 'md5': 'e992787515a182f55e38fc97588d802a', - 'info_dict': { - 'id': 'clapasobsptpkdfe', - 'ext': 'mp4', - 'title': '20170315_150006.mp4', - } - }, { - # no og:title - 'url': 'https://streamango.com/embed/foqebrpftarclpob/asdf_asd_2_mp4', - 'info_dict': { - 'id': 'foqebrpftarclpob', - 'ext': 'mp4', - 'title': 'foqebrpftarclpob', - }, - 'params': { - 'skip_download': True, - }, - 'skip': 'gone', - }, { - 'url': 'https://streamango.com/embed/clapasobsptpkdfe/20170315_150006_mp4', - 'only_matching': True, - }, { - 'url': 'https://fruithosts.net/f/mreodparcdcmspsm/w1f1_r4lph_2018_brrs_720p_latino_mp4', - 'only_matching': True, - }, { - 'url': 'https://streamcherry.com/f/clapasobsptpkdfe/', - 'only_matching': True, - }] - - def _real_extract(self, url): - def decrypt_src(encoded, val): - ALPHABET = '=/+9876543210zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA' - encoded = re.sub(r'[^A-Za-z0-9+/=]', '', encoded) - decoded = '' - sm = [None] * 4 - i = 0 - str_len = len(encoded) - while i < str_len: - for j in range(4): - sm[j % 4] = ALPHABET.index(encoded[i]) - i += 1 - char_code = ((sm[0] << 0x2) | (sm[1] >> 0x4)) ^ val - decoded += compat_chr(char_code) - if sm[2] != 0x40: - char_code = ((sm[1] & 0xf) << 0x4) | (sm[2] >> 0x2) - decoded += compat_chr(char_code) - if sm[3] != 0x40: - char_code = ((sm[2] & 0x3) << 0x6) | sm[3] - decoded += compat_chr(char_code) - return decoded - - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - title = self._og_search_title(webpage, default=video_id) - - formats = [] - for format_ in re.findall(r'({[^}]*\bsrc\s*:\s*[^}]*})', webpage): - mobj = re.search(r'(src\s*:\s*[^(]+\(([^)]*)\)[\s,]*)', format_) - if mobj is None: - continue - - format_ = format_.replace(mobj.group(0), '') - - video = self._parse_json( - format_, video_id, transform_source=js_to_json, - fatal=False) or {} - - mobj = re.search( - r'([\'"])(?P(?:(?!\1).)+)\1\s*,\s*(?P\d+)', - mobj.group(1)) - if mobj is None: - continue - - src = decrypt_src(mobj.group('src'), int_or_none(mobj.group('val'))) - if not src: - continue - - ext = determine_ext(src, default_ext=None) - if video.get('type') == 'application/dash+xml' or ext == 'mpd': - formats.extend(self._extract_mpd_formats( - src, video_id, mpd_id='dash', fatal=False)) - else: - formats.append({ - 'url': src, - 'ext': ext or 'mp4', - 'width': int_or_none(video.get('width')), - 'height': int_or_none(video.get('height')), - 'tbr': int_or_none(video.get('bitrate')), - }) - - if not formats: - error = self._search_regex( - r']+\bclass=["\']lead[^>]+>(.+?)

    ', webpage, - 'error', default=None) - if not error and '>Sorry' in webpage: - error = 'Video %s is not available' % video_id - if error: - raise ExtractorError(error, expected=True) - - self._sort_formats(formats) - - return { - 'id': video_id, - 'url': url, - 'title': title, - 'formats': formats, - } From 681ac7c92abbbd55be9796de86c2cc0d1d70a4c9 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 27 Nov 2019 13:57:30 +0100 Subject: [PATCH 215/422] [vimeo] improve extraction - fix review extraction - fix ondemand extraction - make password protected player case as an expected error(closes #22896) - simplify channel based extractors code --- youtube_dl/extractor/vimeo.py | 177 +++++++++++++++++----------------- 1 file changed, 87 insertions(+), 90 deletions(-) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 9abd59d98..baa46d5f3 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -15,18 +15,20 @@ from ..compat import ( compat_urlparse, ) from ..utils import ( + clean_html, determine_ext, + dict_get, ExtractorError, js_to_json, int_or_none, merge_dicts, - NO_DEFAULT, OnDemandPagedList, parse_filesize, RegexNotFoundError, sanitized_Request, smuggle_url, std_headers, + str_or_none, try_get, unified_timestamp, unsmuggle_url, @@ -210,7 +212,7 @@ class VimeoBaseInfoExtractor(InfoExtractor): video_uploader_url = owner.get('url') return { - 'id': video_id, + 'id': str_or_none(video_data.get('id')) or video_id, 'title': self._live_title(video_title) if is_live else video_title, 'uploader': owner.get('name'), 'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None, @@ -258,11 +260,11 @@ class VimeoIE(VimeoBaseInfoExtractor): (?: (?: www| - (?Pplayer) + player ) \. )? - vimeo(?Ppro)?\.com/ + vimeo(?:pro)?\.com/ (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/) (?:.*?/)? (?: @@ -284,7 +286,7 @@ class VimeoIE(VimeoBaseInfoExtractor): 'id': '56015672', 'ext': 'mp4', 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", - 'description': 'md5:509a9ad5c9bf97c60faee9203aca4479', + 'description': 'md5:2d3305bad981a06ff79f027f19865021', 'timestamp': 1355990239, 'upload_date': '20121220', 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434', @@ -293,6 +295,9 @@ class VimeoIE(VimeoBaseInfoExtractor): 'duration': 10, 'license': 'by-sa', }, + 'params': { + 'format': 'best[protocol=https]', + }, }, { 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876', @@ -305,8 +310,13 @@ class VimeoIE(VimeoBaseInfoExtractor): 'uploader_id': 'openstreetmapus', 'uploader': 'OpenStreetMap US', 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography', - 'description': 'md5:fd69a7b8d8c34a4e1d2ec2e4afd6ec30', + 'description': 'md5:2c362968038d4499f4d79f88458590c1', 'duration': 1595, + 'upload_date': '20130610', + 'timestamp': 1370893156, + }, + 'params': { + 'format': 'best[protocol=https]', }, }, { @@ -323,6 +333,10 @@ class VimeoIE(VimeoBaseInfoExtractor): 'duration': 3610, 'description': None, }, + 'params': { + 'format': 'best[protocol=https]', + }, + 'expected_warnings': ['Unable to download JSON metadata'], }, { 'url': 'http://vimeo.com/68375962', @@ -341,6 +355,7 @@ class VimeoIE(VimeoBaseInfoExtractor): 'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f', }, 'params': { + 'format': 'best[protocol=https]', 'videopassword': 'youtube-dl', }, }, @@ -441,10 +456,14 @@ class VimeoIE(VimeoBaseInfoExtractor): 'uploader': '10Ft Films', 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms', 'uploader_id': 'tenfootfilms', + 'description': 'md5:0fa704e05b04f91f40b7f3ca2e801384', + 'upload_date': '20130830', + 'timestamp': 1377853339, }, 'params': { 'skip_download': True, }, + 'expected_warnings': ['Unable to download JSON metadata'], }, { 'url': 'http://player.vimeo.com/video/68375962', @@ -459,6 +478,7 @@ class VimeoIE(VimeoBaseInfoExtractor): 'duration': 10, }, 'params': { + 'format': 'best[protocol=https]', 'videopassword': 'youtube-dl', }, }, @@ -523,7 +543,7 @@ class VimeoIE(VimeoBaseInfoExtractor): def _verify_player_video_password(self, url, video_id, headers): password = self._downloader.params.get('videopassword') if password is None: - raise ExtractorError('This video is protected by a password, use the --video-password option') + raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True) data = urlencode_postdata({ 'password': base64.b64encode(password.encode()), }) @@ -552,28 +572,26 @@ class VimeoIE(VimeoBaseInfoExtractor): r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None) # Extract ID from URL - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) orig_url = url - if mobj.group('pro'): + is_pro = 'vimeopro.com/' in url + is_player = '://player.vimeo.com/video/' in url + if is_pro: # some videos require portfolio_id to be present in player url # https://github.com/ytdl-org/youtube-dl/issues/20070 url = self._extract_url(url, self._download_webpage(url, video_id)) - elif mobj.group('player'): + if not url: + url = 'https://vimeo.com/' + video_id + elif is_player: url = 'https://player.vimeo.com/video/' + video_id elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')): url = 'https://vimeo.com/' + video_id - # Retrieve video webpage to extract further information - request = sanitized_Request(url, headers=headers) try: - webpage, urlh = self._download_webpage_handle(request, video_id) + # Retrieve video webpage to extract further information + webpage, urlh = self._download_webpage_handle( + url, video_id, headers=headers) redirect_url = compat_str(urlh.geturl()) - # Some URLs redirect to ondemand can't be extracted with - # this extractor right away thus should be passed through - # ondemand extractor (e.g. https://vimeo.com/73445910) - if VimeoOndemandIE.suitable(redirect_url): - return self.url_result(redirect_url, VimeoOndemandIE.ie_key()) except ExtractorError as ee: if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: errmsg = ee.cause.read() @@ -600,6 +618,7 @@ class VimeoIE(VimeoBaseInfoExtractor): cc_license = None timestamp = None + video_description = None # Extract the config JSON try: @@ -611,17 +630,17 @@ class VimeoIE(VimeoBaseInfoExtractor): # Sometimes new react-based page is served instead of old one that require # different config URL extraction approach (see # https://github.com/ytdl-org/youtube-dl/pull/7209) - vimeo_clip_page_config = self._search_regex( - r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage, - 'vimeo clip page config') - page_config = self._parse_json(vimeo_clip_page_config, video_id) + page_config = self._parse_json(self._search_regex( + r'vimeo\.(?:clip|vod_title)_page_config\s*=\s*({.+?});', + webpage, 'page config'), video_id) config_url = page_config['player']['config_url'] cc_license = page_config.get('cc_license') timestamp = try_get( page_config, lambda x: x['clip']['uploaded_on'], compat_str) - config_json = self._download_webpage(config_url, video_id) - config = json.loads(config_json) + video_description = clean_html(dict_get( + page_config, ('description', 'description_html_escaped'))) + config = self._download_json(config_url, video_id) except RegexNotFoundError: # For pro videos or player.vimeo.com urls # We try to find out to which variable is assigned the config dic @@ -675,14 +694,14 @@ class VimeoIE(VimeoBaseInfoExtractor): {'force_feature_id': True}), 'Vimeo') # Extract video description - - video_description = self._html_search_regex( - r'(?s)]*>(.*?)
    ', - webpage, 'description', default=None) + if not video_description: + video_description = self._html_search_regex( + r'(?s)]*>(.*?)', + webpage, 'description', default=None) if not video_description: video_description = self._html_search_meta( 'description', webpage, default=None) - if not video_description and mobj.group('pro'): + if not video_description and is_pro: orig_webpage = self._download_webpage( orig_url, video_id, note='Downloading webpage for description', @@ -690,7 +709,7 @@ class VimeoIE(VimeoBaseInfoExtractor): if orig_webpage: video_description = self._html_search_meta( 'description', orig_webpage, default=None) - if not video_description and not mobj.group('player'): + if not video_description and not is_player: self._downloader.report_warning('Cannot find video description') # Extract upload date @@ -747,9 +766,9 @@ class VimeoIE(VimeoBaseInfoExtractor): return info_dict -class VimeoOndemandIE(VimeoBaseInfoExtractor): +class VimeoOndemandIE(VimeoIE): IE_NAME = 'vimeo:ondemand' - _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?P[^/?#&]+)' + _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/([^/]+/)?(?P[^/?#&]+)' _TESTS = [{ # ondemand video not available via https://vimeo.com/id 'url': 'https://vimeo.com/ondemand/20704', @@ -761,24 +780,32 @@ class VimeoOndemandIE(VimeoBaseInfoExtractor): 'uploader': 'גם סרטים', 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms', 'uploader_id': 'gumfilms', + 'description': 'md5:4c027c965e439de4baab621e48b60791', + 'upload_date': '20140906', + 'timestamp': 1410032453, }, 'params': { 'format': 'best[protocol=https]', }, + 'expected_warnings': ['Unable to download JSON metadata'], }, { # requires Referer to be passed along with og:video:url 'url': 'https://vimeo.com/ondemand/36938/126682985', 'info_dict': { - 'id': '126682985', + 'id': '126584684', 'ext': 'mp4', 'title': 'Rävlock, rätt läte på rätt plats', 'uploader': 'Lindroth & Norin', - 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user14430847', - 'uploader_id': 'user14430847', + 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/lindrothnorin', + 'uploader_id': 'lindrothnorin', + 'description': 'md5:c3c46a90529612c8279fb6af803fc0df', + 'upload_date': '20150502', + 'timestamp': 1430586422, }, 'params': { 'skip_download': True, }, + 'expected_warnings': ['Unable to download JSON metadata'], }, { 'url': 'https://vimeo.com/ondemand/nazmaalik', 'only_matching': True, @@ -790,16 +817,6 @@ class VimeoOndemandIE(VimeoBaseInfoExtractor): 'only_matching': True, }] - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - return self.url_result( - # Some videos require Referer to be passed along with og:video:url - # similarly to generic vimeo embeds (e.g. - # https://vimeo.com/ondemand/36938/126682985). - VimeoIE._smuggle_referrer(self._og_search_video_url(webpage), url), - VimeoIE.ie_key()) - class VimeoChannelIE(VimeoBaseInfoExtractor): IE_NAME = 'vimeo:channel' @@ -815,6 +832,7 @@ class VimeoChannelIE(VimeoBaseInfoExtractor): }, 'playlist_mincount': 25, }] + _BASE_URL_TEMPL = 'https://vimeo.com/channels/%s' def _page_url(self, base_url, pagenum): return '%s/videos/page:%d/' % (base_url, pagenum) @@ -886,14 +904,13 @@ class VimeoChannelIE(VimeoBaseInfoExtractor): return self.playlist_result(title_and_entries, list_id, list_title) def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - channel_id = mobj.group('id') - return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id) + channel_id = self._match_id(url) + return self._extract_videos(channel_id, self._BASE_URL_TEMPL % channel_id) class VimeoUserIE(VimeoChannelIE): IE_NAME = 'vimeo:user' - _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P[^/]+)(?:/videos|[#?]|$)' + _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P[^/]+)(?:/videos|[#?]|$)' _TITLE_RE = r']+?class="user">([^<>]+?)' _TESTS = [{ 'url': 'https://vimeo.com/nkistudio/videos', @@ -903,11 +920,7 @@ class VimeoUserIE(VimeoChannelIE): }, 'playlist_mincount': 66, }] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - name = mobj.group('name') - return self._extract_videos(name, 'https://vimeo.com/%s' % name) + _BASE_URL_TEMPL = 'https://vimeo.com/%s' class VimeoAlbumIE(VimeoChannelIE): @@ -969,25 +982,18 @@ class VimeoAlbumIE(VimeoChannelIE): r'\s*(.+?)(?:\s+on Vimeo)?', webpage, 'title', fatal=False)) -class VimeoGroupsIE(VimeoAlbumIE): +class VimeoGroupsIE(VimeoChannelIE): IE_NAME = 'vimeo:group' - _VALID_URL = r'https://vimeo\.com/groups/(?P[^/]+)(?:/(?!videos?/\d+)|$)' + _VALID_URL = r'https://vimeo\.com/groups/(?P[^/]+)(?:/(?!videos?/\d+)|$)' _TESTS = [{ - 'url': 'https://vimeo.com/groups/rolexawards', + 'url': 'https://vimeo.com/groups/kattykay', 'info_dict': { - 'id': 'rolexawards', - 'title': 'Rolex Awards for Enterprise', + 'id': 'kattykay', + 'title': 'Katty Kay', }, - 'playlist_mincount': 73, + 'playlist_mincount': 27, }] - - def _extract_list_title(self, webpage): - return self._og_search_title(webpage, fatal=False) - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - name = mobj.group('name') - return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name) + _BASE_URL_TEMPL = 'https://vimeo.com/groups/%s' class VimeoReviewIE(VimeoBaseInfoExtractor): @@ -1003,7 +1009,9 @@ class VimeoReviewIE(VimeoBaseInfoExtractor): 'title': "DICK HARDWICK 'Comedian'", 'uploader': 'Richard Hardwick', 'uploader_id': 'user21297594', - } + 'description': "Comedian Dick Hardwick's five minute demo filmed in front of a live theater audience.\nEdit by Doug Mattocks", + }, + 'expected_warnings': ['Unable to download JSON metadata'], }, { 'note': 'video player needs Referer', 'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053', @@ -1016,7 +1024,8 @@ class VimeoReviewIE(VimeoBaseInfoExtractor): 'duration': 2773, 'thumbnail': r're:^https?://.*\.jpg$', 'uploader_id': 'user22258446', - } + }, + 'skip': 'video gone', }, { 'note': 'Password protected', 'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde', @@ -1036,32 +1045,20 @@ class VimeoReviewIE(VimeoBaseInfoExtractor): def _real_initialize(self): self._login() - def _get_config_url(self, webpage_url, video_id, video_password_verified=False): - webpage = self._download_webpage(webpage_url, video_id) - config_url = self._html_search_regex( - r'data-config-url=(["\'])(?P(?:(?!\1).)+)\1', webpage, - 'config URL', default=None, group='url') - if not config_url: - data = self._parse_json(self._search_regex( - r'window\s*=\s*_extend\(window,\s*({.+?})\);', webpage, 'data', - default=NO_DEFAULT if video_password_verified else '{}'), video_id) - config = data.get('vimeo_esi', {}).get('config', {}) - config_url = config.get('configUrl') or try_get(config, lambda x: x['clipData']['configUrl']) - if config_url is None: - self._verify_video_password(webpage_url, video_id, webpage) - config_url = self._get_config_url( - webpage_url, video_id, video_password_verified=True) - return config_url - def _real_extract(self, url): page_url, video_id = re.match(self._VALID_URL, url).groups() - config_url = self._get_config_url(url, video_id) + clip_data = self._download_json( + page_url.replace('/review/', '/review/data/'), + video_id)['clipData'] + config_url = clip_data['configUrl'] config = self._download_json(config_url, video_id) info_dict = self._parse_config(config, video_id) - source_format = self._extract_original_format(page_url, video_id) + source_format = self._extract_original_format( + page_url + '/action', video_id) if source_format: info_dict['formats'].append(source_format) self._vimeo_sort_formats(info_dict['formats']) + info_dict['description'] = clean_html(clip_data.get('description')) return info_dict From e3f00f139fc227217325c8e84e0b340e12ee9bb8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 28 Nov 2019 23:09:48 +0700 Subject: [PATCH 216/422] [ChangeLog] Actualize [ci skip] --- ChangeLog | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) diff --git a/ChangeLog b/ChangeLog index daaff3eef..d724d75ce 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,36 @@ +version + +Core ++ [utils] Add generic caesar cipher and rot47 +* [utils] Handle rd-suffixed day parts in unified_strdate (#23199) + +Extractors +* [vimeo] Improve extraction + * Fix review extraction + * Fix ondemand extraction + * Make password protected player case as an expected error (#22896) + * Simplify channel based extractors code +- [openload] Remove extractor (#11999) +- [verystream] Remove extractor +- [streamango] Remove extractor (#15406) +* [dailymotion] Improve extraction + * Extract http formats included in m3u8 manifest + * Fix user extraction (#3553, #21415) + + Add suport for User Authentication (#11491) + * Fix password protected videos extraction (#23176) + * Respect age limit option and family filter cookie value (#18437) + * Handle video url playlist query param + * Report allowed countries for geo-restricted videos +* [corus] Improve extraction + + Add support for Series Plus, W Network, YTV, ABC Spark, disneychannel.com + and disneylachaine.ca (#20861) + + Add support for self hosted videos (#22075) + * Detect DRM protection (#14910, #9164) +* [vivo] Fix extraction (#22328, #22279) ++ [bitchute] Extract upload date (#22990, #23193) +* [soundcloud] Update client id (#23214) + + version 2019.11.22 Core From b568561eba6f4aceb87419e21aba11567c5de7da Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 28 Nov 2019 23:25:25 +0700 Subject: [PATCH 217/422] release 2019.11.28 --- .github/ISSUE_TEMPLATE/1_broken_site.md | 6 +++--- .github/ISSUE_TEMPLATE/2_site_support_request.md | 4 ++-- .github/ISSUE_TEMPLATE/3_site_feature_request.md | 4 ++-- .github/ISSUE_TEMPLATE/4_bug_report.md | 6 +++--- .github/ISSUE_TEMPLATE/5_feature_request.md | 4 ++-- ChangeLog | 2 +- docs/supportedsites.md | 3 --- youtube_dl/version.py | 2 +- 8 files changed, 14 insertions(+), 17 deletions(-) diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.md b/.github/ISSUE_TEMPLATE/1_broken_site.md index d3e11cdcf..3a94bd621 100644 --- a/.github/ISSUE_TEMPLATE/1_broken_site.md +++ b/.github/ISSUE_TEMPLATE/1_broken_site.md @@ -18,7 +18,7 @@ title: '' - [ ] I'm reporting a broken site support -- [ ] I've verified that I'm running youtube-dl version **2019.11.22** +- [ ] I've verified that I'm running youtube-dl version **2019.11.28** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar issues including closed ones @@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.11.22 + [debug] youtube-dl version 2019.11.28 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/2_site_support_request.md b/.github/ISSUE_TEMPLATE/2_site_support_request.md index 51bf4db3b..72bee12aa 100644 --- a/.github/ISSUE_TEMPLATE/2_site_support_request.md +++ b/.github/ISSUE_TEMPLATE/2_site_support_request.md @@ -19,7 +19,7 @@ labels: 'site-support-request' - [ ] I'm reporting a new site support request -- [ ] I've verified that I'm running youtube-dl version **2019.11.22** +- [ ] I've verified that I'm running youtube-dl version **2019.11.28** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that none of provided URLs violate any copyrights - [ ] I've searched the bugtracker for similar site support requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/3_site_feature_request.md b/.github/ISSUE_TEMPLATE/3_site_feature_request.md index 19025ff25..ddf67e951 100644 --- a/.github/ISSUE_TEMPLATE/3_site_feature_request.md +++ b/.github/ISSUE_TEMPLATE/3_site_feature_request.md @@ -18,13 +18,13 @@ title: '' - [ ] I'm reporting a site feature request -- [ ] I've verified that I'm running youtube-dl version **2019.11.22** +- [ ] I've verified that I'm running youtube-dl version **2019.11.28** - [ ] I've searched the bugtracker for similar site feature requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/4_bug_report.md b/.github/ISSUE_TEMPLATE/4_bug_report.md index a381b6979..7122e2714 100644 --- a/.github/ISSUE_TEMPLATE/4_bug_report.md +++ b/.github/ISSUE_TEMPLATE/4_bug_report.md @@ -18,7 +18,7 @@ title: '' - [ ] I'm reporting a broken site support issue -- [ ] I've verified that I'm running youtube-dl version **2019.11.22** +- [ ] I've verified that I'm running youtube-dl version **2019.11.28** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar bug reports including closed ones @@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.11.22 + [debug] youtube-dl version 2019.11.28 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/5_feature_request.md b/.github/ISSUE_TEMPLATE/5_feature_request.md index 9c945d5ec..a93882b39 100644 --- a/.github/ISSUE_TEMPLATE/5_feature_request.md +++ b/.github/ISSUE_TEMPLATE/5_feature_request.md @@ -19,13 +19,13 @@ labels: 'request' - [ ] I'm reporting a feature request -- [ ] I've verified that I'm running youtube-dl version **2019.11.22** +- [ ] I've verified that I'm running youtube-dl version **2019.11.28** - [ ] I've searched the bugtracker for similar feature requests including closed ones diff --git a/ChangeLog b/ChangeLog index d724d75ce..d4f809fc6 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version +version 2019.11.28 Core + [utils] Add generic caesar cipher and rot47 diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 3dcb026c5..2744dfca8 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -618,7 +618,6 @@ - **OnionStudios** - **Ooyala** - **OoyalaExternal** - - **Openload** - **OraTV** - **orf:fm4**: radio FM4 - **orf:fm4:story**: fm4.orf.at stories @@ -825,7 +824,6 @@ - **Steam** - **Stitcher** - **Streamable** - - **Streamango** - **streamcloud.eu** - **StreamCZ** - **StreetVoice** @@ -976,7 +974,6 @@ - **Vbox7** - **VeeHD** - **Veoh** - - **verystream** - **Vesti**: Вести.Ru - **Vevo** - **VevoPlaylist** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 361809681..1227abc0a 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.11.22' +__version__ = '2019.11.28' From 348c6bf1c1a00eec323d6e21ff7b9b12699afe04 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Fri, 29 Nov 2019 17:05:06 +0100 Subject: [PATCH 218/422] [utils] handle int values passed to str_to_int --- test/test_utils.py | 1 + youtube_dl/utils.py | 4 ++-- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/test/test_utils.py b/test/test_utils.py index e83c8ea11..fed94a906 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -499,6 +499,7 @@ class TestUtil(unittest.TestCase): def test_str_to_int(self): self.assertEqual(str_to_int('123,456'), 123456) self.assertEqual(str_to_int('123.456'), 123456) + self.assertEqual(str_to_int(523), 523) def test_url_basename(self): self.assertEqual(url_basename('http://foo.de/'), '') diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index b14603d8a..328f037a8 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -3519,8 +3519,8 @@ def str_or_none(v, default=None): def str_to_int(int_str): """ A more relaxed version of int_or_none """ - if int_str is None: - return None + if not isinstance(int_str, compat_str): + return int_str int_str = re.sub(r'[,\.\+]', '', int_str) return int(int_str) From 7f641d2c7a68b70d6c1e273af108741e5779bc28 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Fri, 29 Nov 2019 17:06:34 +0100 Subject: [PATCH 219/422] [adobetv] improve extaction - use OnDemandPagedList for list extractors - reduce show extraction requests - extract original video format and subtitles - add support for adobe tv embeds --- youtube_dl/extractor/adobetv.py | 239 ++++++++++++++++++++--------- youtube_dl/extractor/extractors.py | 1 + 2 files changed, 166 insertions(+), 74 deletions(-) diff --git a/youtube_dl/extractor/adobetv.py b/youtube_dl/extractor/adobetv.py index 008c98e51..80060f037 100644 --- a/youtube_dl/extractor/adobetv.py +++ b/youtube_dl/extractor/adobetv.py @@ -1,25 +1,119 @@ from __future__ import unicode_literals +import functools import re from .common import InfoExtractor from ..compat import compat_str from ..utils import ( - parse_duration, - unified_strdate, - str_to_int, - int_or_none, float_or_none, + int_or_none, ISO639Utils, - determine_ext, + OnDemandPagedList, + parse_duration, + str_or_none, + str_to_int, + unified_strdate, ) class AdobeTVBaseIE(InfoExtractor): - _API_BASE_URL = 'http://tv.adobe.com/api/v4/' + def _call_api(self, path, video_id, query, note=None): + return self._download_json( + 'http://tv.adobe.com/api/v4/' + path, + video_id, note, query=query)['data'] + + def _parse_subtitles(self, video_data, url_key): + subtitles = {} + for translation in video_data.get('translations', []): + vtt_path = translation.get(url_key) + if not vtt_path: + continue + lang = translation.get('language_w3c') or ISO639Utils.long2short(translation['language_medium']) + subtitles.setdefault(lang, []).append({ + 'ext': 'vtt', + 'url': vtt_path, + }) + return subtitles + + def _parse_video_data(self, video_data): + video_id = compat_str(video_data['id']) + title = video_data['title'] + + s3_extracted = False + formats = [] + for source in video_data.get('videos', []): + source_url = source.get('url') + if not source_url: + continue + f = { + 'format_id': source.get('quality_level'), + 'fps': int_or_none(source.get('frame_rate')), + 'height': int_or_none(source.get('height')), + 'tbr': int_or_none(source.get('video_data_rate')), + 'width': int_or_none(source.get('width')), + 'url': source_url, + } + original_filename = source.get('original_filename') + if original_filename: + if not (f.get('height') and f.get('width')): + mobj = re.search(r'_(\d+)x(\d+)', original_filename) + if mobj: + f.update({ + 'height': int(mobj.group(2)), + 'width': int(mobj.group(1)), + }) + if original_filename.startswith('s3://') and not s3_extracted: + formats.append({ + 'format_id': 'original', + 'preference': 1, + 'url': original_filename.replace('s3://', 'https://s3.amazonaws.com/'), + }) + s3_extracted = True + formats.append(f) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': video_data.get('description'), + 'thumbnail': video_data.get('thumbnail'), + 'upload_date': unified_strdate(video_data.get('start_date')), + 'duration': parse_duration(video_data.get('duration')), + 'view_count': str_to_int(video_data.get('playcount')), + 'formats': formats, + 'subtitles': self._parse_subtitles(video_data, 'vtt'), + } + + +class AdobeTVEmbedIE(AdobeTVBaseIE): + IE_NAME = 'adobetv:embed' + _VALID_URL = r'https?://tv\.adobe\.com/embed/\d+/(?P\d+)' + _TEST = { + 'url': 'https://tv.adobe.com/embed/22/4153', + 'md5': 'c8c0461bf04d54574fc2b4d07ac6783a', + 'info_dict': { + 'id': '4153', + 'ext': 'flv', + 'title': 'Creating Graphics Optimized for BlackBerry', + 'description': 'md5:eac6e8dced38bdaae51cd94447927459', + 'thumbnail': r're:https?://.*\.jpg$', + 'upload_date': '20091109', + 'duration': 377, + 'view_count': int, + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + video_data = self._call_api( + 'episode/' + video_id, video_id, {'disclosure': 'standard'})[0] + return self._parse_video_data(video_data) class AdobeTVIE(AdobeTVBaseIE): + IE_NAME = 'adobetv' _VALID_URL = r'https?://tv\.adobe\.com/(?:(?Pfr|de|es|jp)/)?watch/(?P[^/]+)/(?P[^/]+)' _TEST = { @@ -42,45 +136,33 @@ class AdobeTVIE(AdobeTVBaseIE): if not language: language = 'en' - video_data = self._download_json( - self._API_BASE_URL + 'episode/get/?language=%s&show_urlname=%s&urlname=%s&disclosure=standard' % (language, show_urlname, urlname), - urlname)['data'][0] - - formats = [{ - 'url': source['url'], - 'format_id': source.get('quality_level') or source['url'].split('-')[-1].split('.')[0] or None, - 'width': int_or_none(source.get('width')), - 'height': int_or_none(source.get('height')), - 'tbr': int_or_none(source.get('video_data_rate')), - } for source in video_data['videos']] - self._sort_formats(formats) - - return { - 'id': compat_str(video_data['id']), - 'title': video_data['title'], - 'description': video_data.get('description'), - 'thumbnail': video_data.get('thumbnail'), - 'upload_date': unified_strdate(video_data.get('start_date')), - 'duration': parse_duration(video_data.get('duration')), - 'view_count': str_to_int(video_data.get('playcount')), - 'formats': formats, - } + video_data = self._call_api( + 'episode/get', urlname, { + 'disclosure': 'standard', + 'language': language, + 'show_urlname': show_urlname, + 'urlname': urlname, + })[0] + return self._parse_video_data(video_data) class AdobeTVPlaylistBaseIE(AdobeTVBaseIE): - def _parse_page_data(self, page_data): - return [self.url_result(self._get_element_url(element_data)) for element_data in page_data] + _PAGE_SIZE = 25 - def _extract_playlist_entries(self, url, display_id): - page = self._download_json(url, display_id) - entries = self._parse_page_data(page['data']) - for page_num in range(2, page['paging']['pages'] + 1): - entries.extend(self._parse_page_data( - self._download_json(url + '&page=%d' % page_num, display_id)['data'])) - return entries + def _fetch_page(self, display_id, query, page): + page += 1 + query['page'] = page + for element_data in self._call_api( + self._RESOURCE, display_id, query, 'Download Page %d' % page): + yield self._process_data(element_data) + + def _extract_playlist_entries(self, display_id, query): + return OnDemandPagedList(functools.partial( + self._fetch_page, display_id, query), self._PAGE_SIZE) class AdobeTVShowIE(AdobeTVPlaylistBaseIE): + IE_NAME = 'adobetv:show' _VALID_URL = r'https?://tv\.adobe\.com/(?:(?Pfr|de|es|jp)/)?show/(?P[^/]+)' _TEST = { @@ -92,26 +174,31 @@ class AdobeTVShowIE(AdobeTVPlaylistBaseIE): }, 'playlist_mincount': 136, } - - def _get_element_url(self, element_data): - return element_data['urls'][0] + _RESOURCE = 'episode' + _process_data = AdobeTVBaseIE._parse_video_data def _real_extract(self, url): language, show_urlname = re.match(self._VALID_URL, url).groups() if not language: language = 'en' - query = 'language=%s&show_urlname=%s' % (language, show_urlname) + query = { + 'disclosure': 'standard', + 'language': language, + 'show_urlname': show_urlname, + } - show_data = self._download_json(self._API_BASE_URL + 'show/get/?%s' % query, show_urlname)['data'][0] + show_data = self._call_api( + 'show/get', show_urlname, query)[0] return self.playlist_result( - self._extract_playlist_entries(self._API_BASE_URL + 'episode/?%s' % query, show_urlname), - compat_str(show_data['id']), - show_data['show_name'], - show_data['show_description']) + self._extract_playlist_entries(show_urlname, query), + str_or_none(show_data.get('id')), + show_data.get('show_name'), + show_data.get('show_description')) class AdobeTVChannelIE(AdobeTVPlaylistBaseIE): + IE_NAME = 'adobetv:channel' _VALID_URL = r'https?://tv\.adobe\.com/(?:(?Pfr|de|es|jp)/)?channel/(?P[^/]+)(?:/(?P[^/]+))?' _TEST = { @@ -121,24 +208,30 @@ class AdobeTVChannelIE(AdobeTVPlaylistBaseIE): }, 'playlist_mincount': 96, } + _RESOURCE = 'show' - def _get_element_url(self, element_data): - return element_data['url'] + def _process_data(self, show_data): + return self.url_result( + show_data['url'], 'AdobeTVShow', str_or_none(show_data.get('id'))) def _real_extract(self, url): language, channel_urlname, category_urlname = re.match(self._VALID_URL, url).groups() if not language: language = 'en' - query = 'language=%s&channel_urlname=%s' % (language, channel_urlname) + query = { + 'channel_urlname': channel_urlname, + 'language': language, + } if category_urlname: - query += '&category_urlname=%s' % category_urlname + query['category_urlname'] = category_urlname return self.playlist_result( - self._extract_playlist_entries(self._API_BASE_URL + 'show/?%s' % query, channel_urlname), + self._extract_playlist_entries(channel_urlname, query), channel_urlname) -class AdobeTVVideoIE(InfoExtractor): +class AdobeTVVideoIE(AdobeTVBaseIE): + IE_NAME = 'adobetv:video' _VALID_URL = r'https?://video\.tv\.adobe\.com/v/(?P\d+)' _TEST = { @@ -160,38 +253,36 @@ class AdobeTVVideoIE(InfoExtractor): video_data = self._parse_json(self._search_regex( r'var\s+bridge\s*=\s*([^;]+);', webpage, 'bridged data'), video_id) + title = video_data['title'] - formats = [{ - 'format_id': '%s-%s' % (determine_ext(source['src']), source.get('height')), - 'url': source['src'], - 'width': int_or_none(source.get('width')), - 'height': int_or_none(source.get('height')), - 'tbr': int_or_none(source.get('bitrate')), - } for source in video_data['sources']] + formats = [] + sources = video_data.get('sources') or [] + for source in sources: + source_src = source.get('src') + if not source_src: + continue + formats.append({ + 'filesize': int_or_none(source.get('kilobytes') or None, invscale=1000), + 'format_id': '-'.join(filter(None, [source.get('format'), source.get('label')])), + 'height': int_or_none(source.get('height') or None), + 'tbr': int_or_none(source.get('bitrate') or None), + 'width': int_or_none(source.get('width') or None), + 'url': source_src, + }) self._sort_formats(formats) # For both metadata and downloaded files the duration varies among # formats. I just pick the max one duration = max(filter(None, [ float_or_none(source.get('duration'), scale=1000) - for source in video_data['sources']])) - - subtitles = {} - for translation in video_data.get('translations', []): - lang_id = translation.get('language_w3c') or ISO639Utils.long2short(translation['language_medium']) - if lang_id not in subtitles: - subtitles[lang_id] = [] - subtitles[lang_id].append({ - 'url': translation['vttPath'], - 'ext': 'vtt', - }) + for source in sources])) return { 'id': video_id, 'formats': formats, - 'title': video_data['title'], + 'title': title, 'description': video_data.get('description'), - 'thumbnail': video_data['video'].get('poster'), + 'thumbnail': video_data.get('video', {}).get('poster'), 'duration': duration, - 'subtitles': subtitles, + 'subtitles': self._parse_subtitles(video_data, 'vttPath'), } diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 0e349b778..0f27c9678 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -21,6 +21,7 @@ from .acast import ( from .adn import ADNIE from .adobeconnect import AdobeConnectIE from .adobetv import ( + AdobeTVEmbedIE, AdobeTVIE, AdobeTVShowIE, AdobeTVChannelIE, From a15adbe461584e2e631d1be97805e81c17cfd3fe Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Fri, 29 Nov 2019 17:12:55 +0100 Subject: [PATCH 220/422] [channel9] reduce response size and update tests --- youtube_dl/extractor/channel9.py | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/youtube_dl/extractor/channel9.py b/youtube_dl/extractor/channel9.py index 81108e704..09cacf6d3 100644 --- a/youtube_dl/extractor/channel9.py +++ b/youtube_dl/extractor/channel9.py @@ -32,7 +32,7 @@ class Channel9IE(InfoExtractor): 'upload_date': '20130828', 'session_code': 'KOS002', 'session_room': 'Arena 1A', - 'session_speakers': ['Andrew Coates', 'Brady Gaster', 'Mads Kristensen', 'Ed Blankenship', 'Patrick Klug'], + 'session_speakers': 'count:5', }, }, { 'url': 'http://channel9.msdn.com/posts/Self-service-BI-with-Power-BI-nuclear-testing', @@ -64,15 +64,15 @@ class Channel9IE(InfoExtractor): 'params': { 'skip_download': True, }, - }, { - 'url': 'https://channel9.msdn.com/Niners/Splendid22/Queue/76acff796e8f411184b008028e0d492b/RSS', - 'info_dict': { - 'id': 'Niners/Splendid22/Queue/76acff796e8f411184b008028e0d492b', - 'title': 'Channel 9', - }, - 'playlist_mincount': 100, }, { 'url': 'https://channel9.msdn.com/Events/DEVintersection/DEVintersection-2016/RSS', + 'info_dict': { + 'id': 'Events/DEVintersection/DEVintersection-2016', + 'title': 'DEVintersection 2016 Orlando Sessions', + }, + 'playlist_mincount': 14, + }, { + 'url': 'https://channel9.msdn.com/Niners/Splendid22/Queue/76acff796e8f411184b008028e0d492b/RSS', 'only_matching': True, }, { 'url': 'https://channel9.msdn.com/Events/Speakers/scott-hanselman/RSS?UrlSafeName=scott-hanselman', @@ -112,11 +112,11 @@ class Channel9IE(InfoExtractor): episode_data), content_path) content_id = episode_data['contentId'] is_session = '/Sessions(' in episode_data['api'] - content_url = 'https://channel9.msdn.com/odata' + episode_data['api'] + content_url = 'https://channel9.msdn.com/odata' + episode_data['api'] + '?$select=Captions,CommentCount,MediaLengthInSeconds,PublishedDate,Rating,RatingCount,Title,VideoMP4High,VideoMP4Low,VideoMP4Medium,VideoPlayerPreviewImage,VideoWMV,VideoWMVHQ,Views,' if is_session: - content_url += '?$expand=Speakers' + content_url += 'Code,Description,Room,Slides,Speakers,ZipFile&$expand=Speakers' else: - content_url += '?$expand=Authors' + content_url += 'Authors,Body&$expand=Authors' content_data = self._download_json(content_url, content_id) title = content_data['Title'] @@ -210,7 +210,7 @@ class Channel9IE(InfoExtractor): 'id': content_id, 'title': title, 'description': clean_html(content_data.get('Description') or content_data.get('Body')), - 'thumbnail': content_data.get('Thumbnail') or content_data.get('VideoPlayerPreviewImage'), + 'thumbnail': content_data.get('VideoPlayerPreviewImage'), 'duration': int_or_none(content_data.get('MediaLengthInSeconds')), 'timestamp': parse_iso8601(content_data.get('PublishedDate')), 'avg_rating': int_or_none(content_data.get('Rating')), From 88a7a9089a0f3ccdd5e0e6f10b529652a24cbc7e Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Fri, 29 Nov 2019 17:22:54 +0100 Subject: [PATCH 221/422] [abcotvs] relax _VALID_URL regex and improve metadata extraction(closes #18014) --- youtube_dl/extractor/abcotvs.py | 79 ++++++++++++++++++++++----------- 1 file changed, 52 insertions(+), 27 deletions(-) diff --git a/youtube_dl/extractor/abcotvs.py b/youtube_dl/extractor/abcotvs.py index 03b92a39c..0bc69a64f 100644 --- a/youtube_dl/extractor/abcotvs.py +++ b/youtube_dl/extractor/abcotvs.py @@ -4,29 +4,30 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( + dict_get, int_or_none, - parse_iso8601, + try_get, ) class ABCOTVSIE(InfoExtractor): IE_NAME = 'abcotvs' IE_DESC = 'ABC Owned Television Stations' - _VALID_URL = r'https?://(?:abc(?:7(?:news|ny|chicago)?|11|13|30)|6abc)\.com(?:/[^/]+/(?P[^/]+))?/(?P\d+)' + _VALID_URL = r'https?://(?Pabc(?:7(?:news|ny|chicago)?|11|13|30)|6abc)\.com(?:(?:/[^/]+)*/(?P[^/]+))?/(?P\d+)' _TESTS = [ { 'url': 'http://abc7news.com/entertainment/east-bay-museum-celebrates-vintage-synthesizers/472581/', 'info_dict': { - 'id': '472581', + 'id': '472548', 'display_id': 'east-bay-museum-celebrates-vintage-synthesizers', 'ext': 'mp4', - 'title': 'East Bay museum celebrates vintage synthesizers', + 'title': 'East Bay museum celebrates synthesized music', 'description': 'md5:24ed2bd527096ec2a5c67b9d5a9005f3', 'thumbnail': r're:^https?://.*\.jpg$', - 'timestamp': 1421123075, + 'timestamp': 1421118520, 'upload_date': '20150113', - 'uploader': 'Jonathan Bloom', }, 'params': { # m3u8 download @@ -37,39 +38,63 @@ class ABCOTVSIE(InfoExtractor): 'url': 'http://abc7news.com/472581', 'only_matching': True, }, + { + 'url': 'https://6abc.com/man-75-killed-after-being-struck-by-vehicle-in-chester/5725182/', + 'only_matching': True, + }, ] + _SITE_MAP = { + '6abc': 'wpvi', + 'abc11': 'wtvd', + 'abc13': 'ktrk', + 'abc30': 'kfsn', + 'abc7': 'kabc', + 'abc7chicago': 'wls', + 'abc7news': 'kgo', + 'abc7ny': 'wabc', + } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - display_id = mobj.group('display_id') or video_id + site, display_id, video_id = re.match(self._VALID_URL, url).groups() + display_id = display_id or video_id + station = self._SITE_MAP[site] - webpage = self._download_webpage(url, display_id) + data = self._download_json( + 'https://api.abcotvs.com/v2/content', display_id, query={ + 'id': video_id, + 'key': 'otv.web.%s.story' % station, + 'station': station, + })['data'] + video = try_get(data, lambda x: x['featuredMedia']['video'], dict) or data + video_id = compat_str(dict_get(video, ('id', 'publishedKey'), video_id)) + title = video.get('title') or video['linkText'] - m3u8 = self._html_search_meta( - 'contentURL', webpage, 'm3u8 url', fatal=True).split('?')[0] - - formats = self._extract_m3u8_formats(m3u8, display_id, 'mp4') + formats = [] + m3u8_url = video.get('m3u8') + if m3u8_url: + formats = self._extract_m3u8_formats( + video['m3u8'].split('?')[0], display_id, 'mp4', m3u8_id='hls', fatal=False) + mp4_url = video.get('mp4') + if mp4_url: + formats.append({ + 'abr': 128, + 'format_id': 'https', + 'height': 360, + 'url': mp4_url, + 'width': 640, + }) self._sort_formats(formats) - title = self._og_search_title(webpage).strip() - description = self._og_search_description(webpage).strip() - thumbnail = self._og_search_thumbnail(webpage) - timestamp = parse_iso8601(self._search_regex( - r'
    \s*
    ', - webpage, 'description', default=None) or self._og_search_description(webpage) - thumbnail = self._og_search_thumbnail(webpage) - duration = parse_duration(self._search_regex( - r'([^<]+)<', - webpage, 'duration', fatal=False)) - categories = re.findall(r'([^<]+)', webpage) - - return { - '_type': 'url_transparent', - 'url': 'http://%s/embed/player?filmId=%s' % (domain, film_id), - 'id': film_id, - 'display_id': display_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'duration': duration, - 'categories': categories, - 'ie_key': 'ViewLiftEmbed', - } + domain, path, display_id = re.match(self._VALID_URL, url).groups() + site = domain.split('.')[-2] + if site in self._SITE_MAP: + site = self._SITE_MAP[site] + modules = self._call_api( + site, 'content/pages', display_id, { + 'includeContent': 'true', + 'moduleOffset': 1, + 'path': path, + 'site': site, + })['modules'] + film_id = next(m['contentData'][0]['gist']['id'] for m in modules if m.get('moduleType') == 'VideoDetailModule') + return { + '_type': 'url_transparent', + 'url': 'http://%s/embed/player?filmId=%s' % (domain, film_id), + 'id': film_id, + 'display_id': display_id, + 'ie_key': 'ViewLiftEmbed', + } From 51c7f40c83a12f9dc0fce0b9e5102a0c13467b6a Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 27 Jan 2020 23:37:29 +0100 Subject: [PATCH 319/422] [vimeo] fix album extraction(closes #23864) --- youtube_dl/extractor/vimeo.py | 68 +++++++++++++++++------------------ 1 file changed, 33 insertions(+), 35 deletions(-) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index baa46d5f3..f378aa283 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -841,33 +841,6 @@ class VimeoChannelIE(VimeoBaseInfoExtractor): return self._TITLE or self._html_search_regex( self._TITLE_RE, webpage, 'list title', fatal=False) - def _login_list_password(self, page_url, list_id, webpage): - login_form = self._search_regex( - r'(?s)]+?id="pw_form"(.*?)', - webpage, 'login form', default=None) - if not login_form: - return webpage - - password = self._downloader.params.get('videopassword') - if password is None: - raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True) - fields = self._hidden_inputs(login_form) - token, vuid = self._extract_xsrft_and_vuid(webpage) - fields['token'] = token - fields['password'] = password - post = urlencode_postdata(fields) - password_path = self._search_regex( - r'action="([^"]+)"', login_form, 'password URL') - password_url = compat_urlparse.urljoin(page_url, password_path) - password_request = sanitized_Request(password_url, post) - password_request.add_header('Content-type', 'application/x-www-form-urlencoded') - self._set_vimeo_cookie('vuid', vuid) - self._set_vimeo_cookie('xsrft', token) - - return self._download_webpage( - password_request, list_id, - 'Verifying the password', 'Wrong password') - def _title_and_entries(self, list_id, base_url): for pagenum in itertools.count(1): page_url = self._page_url(base_url, pagenum) @@ -876,7 +849,6 @@ class VimeoChannelIE(VimeoBaseInfoExtractor): 'Downloading page %s' % pagenum) if pagenum == 1: - webpage = self._login_list_password(page_url, list_id, webpage) yield self._extract_list_title(webpage) # Try extracting href first since not all videos are available via @@ -923,7 +895,7 @@ class VimeoUserIE(VimeoChannelIE): _BASE_URL_TEMPL = 'https://vimeo.com/%s' -class VimeoAlbumIE(VimeoChannelIE): +class VimeoAlbumIE(VimeoBaseInfoExtractor): IE_NAME = 'vimeo:album' _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P\d+)(?:$|[?#]|/(?!video))' _TITLE_RE = r'
    \n\s*

    (.*?)

    ' @@ -973,13 +945,39 @@ class VimeoAlbumIE(VimeoChannelIE): def _real_extract(self, url): album_id = self._match_id(url) webpage = self._download_webpage(url, album_id) - webpage = self._login_list_password(url, album_id, webpage) - api_config = self._extract_vimeo_config(webpage, album_id)['api'] + viewer = self._parse_json(self._search_regex( + r'bootstrap_data\s*=\s*({.+?})', + webpage, 'bootstrap data'), album_id)['viewer'] + jwt = viewer['jwt'] + album = self._download_json( + 'https://api.vimeo.com/albums/' + album_id, + album_id, headers={'Authorization': 'jwt ' + jwt}, + query={'fields': 'description,name,privacy'}) + hashed_pass = None + if try_get(album, lambda x: x['privacy']['view']) == 'password': + password = self._downloader.params.get('videopassword') + if not password: + raise ExtractorError( + 'This album is protected by a password, use the --video-password option', + expected=True) + self._set_vimeo_cookie('vuid', viewer['vuid']) + try: + hashed_pass = self._download_json( + 'https://vimeo.com/showcase/%s/auth' % album_id, + album_id, 'Verifying the password', data=urlencode_postdata({ + 'password': password, + 'token': viewer['xsrft'], + }), headers={ + 'X-Requested-With': 'XMLHttpRequest', + })['hashed_pass'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + raise ExtractorError('Wrong password', expected=True) + raise entries = OnDemandPagedList(functools.partial( - self._fetch_page, album_id, api_config['jwt'], - api_config.get('hashed_pass')), self._PAGE_SIZE) - return self.playlist_result(entries, album_id, self._html_search_regex( - r'\s*(.+?)(?:\s+on Vimeo)?', webpage, 'title', fatal=False)) + self._fetch_page, album_id, jwt, hashed_pass), self._PAGE_SIZE) + return self.playlist_result( + entries, album_id, album.get('name'), album.get('description')) class VimeoGroupsIE(VimeoChannelIE): From 493574973051601606c562c46331806831819ce4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 31 Jan 2020 03:49:16 +0700 Subject: [PATCH 320/422] [tva] Relax _VALID_URL (closes #23903) --- youtube_dl/extractor/tva.py | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/tva.py b/youtube_dl/extractor/tva.py index 0b863df2f..443f46e8a 100644 --- a/youtube_dl/extractor/tva.py +++ b/youtube_dl/extractor/tva.py @@ -9,8 +9,8 @@ from ..utils import ( class TVAIE(InfoExtractor): - _VALID_URL = r'https?://videos\.tva\.ca/details/_(?P\d+)' - _TEST = { + _VALID_URL = r'https?://videos?\.tva\.ca/details/_(?P\d+)' + _TESTS = [{ 'url': 'https://videos.tva.ca/details/_5596811470001', 'info_dict': { 'id': '5596811470001', @@ -24,7 +24,10 @@ class TVAIE(InfoExtractor): # m3u8 download 'skip_download': True, } - } + }, { + 'url': 'https://video.tva.ca/details/_5596811470001', + 'only_matching': True, + }] BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5481942443001/default_default/index.html?videoId=%s' def _real_extract(self, url): From d95a1cc98e83a9e0be291dface57ccc48b29e86b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 31 Jan 2020 04:58:36 +0700 Subject: [PATCH 321/422] [tv5mondeplus] Fix extraction (closes #23907, closes #23911) --- youtube_dl/extractor/tv5mondeplus.py | 84 ++++++++++++++++++++-------- 1 file changed, 61 insertions(+), 23 deletions(-) diff --git a/youtube_dl/extractor/tv5mondeplus.py b/youtube_dl/extractor/tv5mondeplus.py index 88b6baa31..b7fe082b9 100644 --- a/youtube_dl/extractor/tv5mondeplus.py +++ b/youtube_dl/extractor/tv5mondeplus.py @@ -3,31 +3,51 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( - clean_html, determine_ext, extract_attributes, - get_element_by_class, int_or_none, parse_duration, - parse_iso8601, ) class TV5MondePlusIE(InfoExtractor): IE_DESC = 'TV5MONDE+' - _VALID_URL = r'https?://(?:www\.)?tv5mondeplus\.com/toutes-les-videos/[^/]+/(?P[^/?#]+)' - _TEST = { - 'url': 'http://www.tv5mondeplus.com/toutes-les-videos/documentaire/tdah-mon-amour-tele-quebec-tdah-mon-amour-ep001-enfants', - 'md5': '12130fc199f020673138a83466542ec6', + _VALID_URL = r'https?://(?:www\.)?(?:tv5mondeplus|revoir\.tv5monde)\.com/toutes-les-videos/[^/]+/(?P[^/?#]+)' + _TESTS = [{ + # movie + 'url': 'https://revoir.tv5monde.com/toutes-les-videos/cinema/rendez-vous-a-atlit', + 'md5': '8cbde5ea7b296cf635073e27895e227f', 'info_dict': { - 'id': 'tdah-mon-amour-tele-quebec-tdah-mon-amour-ep001-enfants', + 'id': '822a4756-0712-7329-1859-a13ac7fd1407', + 'display_id': 'rendez-vous-a-atlit', 'ext': 'mp4', - 'title': 'Tdah, mon amour - Enfants', - 'description': 'md5:230e3aca23115afcf8006d1bece6df74', - 'upload_date': '20170401', - 'timestamp': 1491022860, - } - } + 'title': 'Rendez-vous à Atlit', + 'description': 'md5:2893a4c5e1dbac3eedff2d87956e4efb', + 'upload_date': '20200130', + }, + }, { + # series episode + 'url': 'https://revoir.tv5monde.com/toutes-les-videos/series-fictions/c-est-la-vie-ennemie-juree', + 'info_dict': { + 'id': '0df7007c-4900-3936-c601-87a13a93a068', + 'display_id': 'c-est-la-vie-ennemie-juree', + 'ext': 'mp4', + 'title': "C'est la vie - Ennemie jurée", + 'description': 'md5:dfb5c63087b6f35fe0cc0af4fe44287e', + 'upload_date': '20200130', + 'series': "C'est la vie", + 'episode': 'Ennemie jurée', + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://revoir.tv5monde.com/toutes-les-videos/series-fictions/neuf-jours-en-hiver-neuf-jours-en-hiver', + 'only_matching': True, + }, { + 'url': 'https://revoir.tv5monde.com/toutes-les-videos/info-societe/le-journal-de-la-rts-edition-du-30-01-20-19h30', + 'only_matching': True, + }] _GEO_BYPASS = False def _real_extract(self, url): @@ -37,11 +57,7 @@ class TV5MondePlusIE(InfoExtractor): if ">Ce programme n'est malheureusement pas disponible pour votre zone géographique.<" in webpage: self.raise_geo_restricted(countries=['FR']) - series = get_element_by_class('video-detail__title', webpage) - title = episode = get_element_by_class( - 'video-detail__subtitle', webpage) or series - if series and series != title: - title = '%s - %s' % (series, title) + title = episode = self._html_search_regex(r'

    ([^<]+)', webpage, 'title') vpl_data = extract_attributes(self._search_regex( r'(<[^>]+class="video_player_loader"[^>]+>)', webpage, 'video player loader')) @@ -65,15 +81,37 @@ class TV5MondePlusIE(InfoExtractor): }) self._sort_formats(formats) + description = self._html_search_regex( + r'(?s)]+class=["\']episode-texte[^>]+>(.+?)', webpage, + 'description', fatal=False) + + series = self._html_search_regex( + r']+class=["\']episode-emission[^>]+>([^<]+)', webpage, + 'series', default=None) + + if series and series != title: + title = '%s - %s' % (series, title) + + upload_date = self._search_regex( + r'(?:date_publication|publish_date)["\']\s*:\s*["\'](\d{4}_\d{2}_\d{2})', + webpage, 'upload date', default=None) + if upload_date: + upload_date = upload_date.replace('_', '') + + video_id = self._search_regex( + (r'data-guid=["\']([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})', + r'id_contenu["\']\s:\s*(\d+)'), webpage, 'video id', + default=display_id) + return { - 'id': display_id, + 'id': video_id, 'display_id': display_id, 'title': title, - 'description': clean_html(get_element_by_class('video-detail__description', webpage)), + 'description': description, 'thumbnail': vpl_data.get('data-image'), 'duration': int_or_none(vpl_data.get('data-duration')) or parse_duration(self._html_search_meta('duration', webpage)), - 'timestamp': parse_iso8601(self._html_search_meta('uploadDate', webpage)), + 'upload_date': upload_date, 'formats': formats, - 'episode': episode, 'series': series, + 'episode': episode, } From 00de61a98feeb2cb03bbc3e467f2366314b61342 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 1 Feb 2020 00:32:25 +0700 Subject: [PATCH 322/422] [twitch:stream] Lowercase channel id for stream request (closes #23917) --- youtube_dl/extractor/twitch.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py index a8c2502af..0db2dca41 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -575,8 +575,8 @@ class TwitchStreamIE(TwitchBaseIE): channel_id = self._match_id(url) stream = self._call_api( - 'kraken/streams/%s?stream_type=all' % channel_id, channel_id, - 'Downloading stream JSON').get('stream') + 'kraken/streams/%s?stream_type=all' % channel_id.lower(), + channel_id, 'Downloading stream JSON').get('stream') if not stream: raise ExtractorError('%s is offline' % channel_id, expected=True) From 0d006fac5c925f95f8ba0d58ee6d7e844e216d29 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Sat, 1 Feb 2020 23:35:55 +0100 Subject: [PATCH 323/422] [sportdeutschland] Update to new sportdeutschland API They switched to SSL, but under a different host AND path... Remove the old test cases because these videos have become unavailable. --- youtube_dl/extractor/sportdeutschland.py | 34 ++++++------------------ 1 file changed, 8 insertions(+), 26 deletions(-) diff --git a/youtube_dl/extractor/sportdeutschland.py b/youtube_dl/extractor/sportdeutschland.py index a3c35a899..378fc7568 100644 --- a/youtube_dl/extractor/sportdeutschland.py +++ b/youtube_dl/extractor/sportdeutschland.py @@ -13,36 +13,18 @@ from ..utils import ( class SportDeutschlandIE(InfoExtractor): _VALID_URL = r'https?://sportdeutschland\.tv/(?P[^/?#]+)/(?P[^?#/]+)(?:$|[?#])' _TESTS = [{ - 'url': 'http://sportdeutschland.tv/badminton/live-li-ning-badminton-weltmeisterschaft-2014-kopenhagen', + 'url': 'https://sportdeutschland.tv/badminton/re-live-deutsche-meisterschaften-2020-halbfinals?playlistId=0', 'info_dict': { - 'id': 'live-li-ning-badminton-weltmeisterschaft-2014-kopenhagen', + 'id': 're-live-deutsche-meisterschaften-2020-halbfinals', 'ext': 'mp4', - 'title': 're:Li-Ning Badminton Weltmeisterschaft 2014 Kopenhagen', - 'categories': ['Badminton'], + 'title': 're:Re-live: Deutsche Meisterschaften 2020.*Halbfinals', + 'categories': ['Badminton-Deutschland'], 'view_count': int, - 'thumbnail': r're:^https?://.*\.jpg$', - 'description': r're:Die Badminton-WM 2014 aus Kopenhagen bei Sportdeutschland\.TV', + 'thumbnail': r're:^https?://.*\.(?:jpg|png)$', 'timestamp': int, - 'upload_date': 're:^201408[23][0-9]$', + 'upload_date': '20200201', + 'description': 're:.*', # meaningless description for THIS video }, - 'params': { - 'skip_download': 'Live stream', - }, - }, { - 'url': 'http://sportdeutschland.tv/li-ning-badminton-wm-2014/lee-li-ning-badminton-weltmeisterschaft-2014-kopenhagen-herren-einzel-wei-vs', - 'info_dict': { - 'id': 'lee-li-ning-badminton-weltmeisterschaft-2014-kopenhagen-herren-einzel-wei-vs', - 'ext': 'mp4', - 'upload_date': '20140825', - 'description': 'md5:60a20536b57cee7d9a4ec005e8687504', - 'timestamp': 1408976060, - 'duration': 2732, - 'title': 'Li-Ning Badminton Weltmeisterschaft 2014 Kopenhagen: Herren Einzel, Wei Lee vs. Keun Lee', - 'thumbnail': r're:^https?://.*\.jpg$', - 'view_count': int, - 'categories': ['Li-Ning Badminton WM 2014'], - - } }] def _real_extract(self, url): @@ -50,7 +32,7 @@ class SportDeutschlandIE(InfoExtractor): video_id = mobj.group('id') sport_id = mobj.group('sport') - api_url = 'http://proxy.vidibusdynamic.net/sportdeutschland.tv/api/permalinks/%s/%s?access_token=true' % ( + api_url = 'https://proxy.vidibusdynamic.net/ssl/backend.sportdeutschland.tv/api/permalinks/%s/%s?access_token=true' % ( sport_id, video_id) req = sanitized_Request(api_url, headers={ 'Accept': 'application/vnd.vidibus.v2.html+json', From 7d55b62ff2e9f3666e6cc4daa969647b917331cd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 3 Feb 2020 06:05:56 +0700 Subject: [PATCH 324/422] [popcorntimes] Add extractor (closes #23949) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/popcorntimes.py | 99 ++++++++++++++++++++++++++++ 2 files changed, 100 insertions(+) create mode 100644 youtube_dl/extractor/popcorntimes.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 1cab440f4..a202a0449 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -850,6 +850,7 @@ from .polskieradio import ( PolskieRadioIE, PolskieRadioCategoryIE, ) +from .popcorntimes import PopcorntimesIE from .popcorntv import PopcornTVIE from .porn91 import Porn91IE from .porncom import PornComIE diff --git a/youtube_dl/extractor/popcorntimes.py b/youtube_dl/extractor/popcorntimes.py new file mode 100644 index 000000000..7bf7f9858 --- /dev/null +++ b/youtube_dl/extractor/popcorntimes.py @@ -0,0 +1,99 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import ( + compat_b64decode, + compat_chr, +) +from ..utils import int_or_none + + +class PopcorntimesIE(InfoExtractor): + _VALID_URL = r'https?://popcorntimes\.tv/[^/]+/m/(?P[^/]+)/(?P[^/?#&]+)' + _TEST = { + 'url': 'https://popcorntimes.tv/de/m/A1XCFvz/haensel-und-gretel-opera-fantasy', + 'md5': '93f210991ad94ba8c3485950a2453257', + 'info_dict': { + 'id': 'A1XCFvz', + 'display_id': 'haensel-und-gretel-opera-fantasy', + 'ext': 'mp4', + 'title': 'Hänsel und Gretel', + 'description': 'md5:1b8146791726342e7b22ce8125cf6945', + 'thumbnail': r're:^https?://.*\.jpg$', + 'creator': 'John Paul', + 'release_date': '19541009', + 'duration': 4260, + 'tbr': 5380, + 'width': 720, + 'height': 540, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id, display_id = mobj.group('id', 'display_id') + + webpage = self._download_webpage(url, display_id) + + title = self._search_regex( + r'

    ([^<]+)', webpage, 'title', + default=None) or self._html_search_meta( + 'ya:ovs:original_name', webpage, 'title', fatal=True) + + loc = self._search_regex( + r'PCTMLOC\s*=\s*(["\'])(?P(?:(?!\1).)+)\1', webpage, 'loc', + group='value') + + loc_b64 = '' + for c in loc: + c_ord = ord(c) + if ord('a') <= c_ord <= ord('z') or ord('A') <= c_ord <= ord('Z'): + upper = ord('Z') if c_ord <= ord('Z') else ord('z') + c_ord += 13 + if upper < c_ord: + c_ord -= 26 + loc_b64 += compat_chr(c_ord) + + video_url = compat_b64decode(loc_b64).decode('utf-8') + + description = self._html_search_regex( + r'(?s)]+class=["\']pt-movie-desc[^>]+>(.+?)', webpage, + 'description', fatal=False) + + thumbnail = self._search_regex( + r']+class=["\']video-preview[^>]+\bsrc=(["\'])(?P(?:(?!\1).)+)\1', + webpage, 'thumbnail', default=None, + group='value') or self._og_search_thumbnail(webpage) + + creator = self._html_search_meta( + 'video:director', webpage, 'creator', default=None) + + release_date = self._html_search_meta( + 'video:release_date', webpage, default=None) + if release_date: + release_date = release_date.replace('-', '') + + def int_meta(name): + return int_or_none(self._html_search_meta( + name, webpage, default=None)) + + return { + 'id': video_id, + 'display_id': display_id, + 'url': video_url, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'creator': creator, + 'release_date': release_date, + 'duration': int_meta('video:duration'), + 'tbr': int_meta('ya:ovs:bitrate'), + 'width': int_meta('og:video:width'), + 'height': int_meta('og:video:height'), + 'http_headers': { + 'Referer': url, + }, + } From 705b1cda9981153f4ced3adc025a8bbfea6caff9 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 3 Feb 2020 13:20:20 +0100 Subject: [PATCH 325/422] [thisoldhouse] fix extraction(closes #23951) --- youtube_dl/extractor/thisoldhouse.py | 33 ++++++++++++++-------------- 1 file changed, 16 insertions(+), 17 deletions(-) diff --git a/youtube_dl/extractor/thisoldhouse.py b/youtube_dl/extractor/thisoldhouse.py index 6ab147ad7..387f955ee 100644 --- a/youtube_dl/extractor/thisoldhouse.py +++ b/youtube_dl/extractor/thisoldhouse.py @@ -2,43 +2,42 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import compat_str -from ..utils import try_get class ThisOldHouseIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?thisoldhouse\.com/(?:watch|how-to|tv-episode)/(?P[^/?#]+)' + _VALID_URL = r'https?://(?:www\.)?thisoldhouse\.com/(?:watch|how-to|tv-episode|(?:[^/]+/)?\d+)/(?P[^/?#]+)' _TESTS = [{ 'url': 'https://www.thisoldhouse.com/how-to/how-to-build-storage-bench', - 'md5': '568acf9ca25a639f0c4ff905826b662f', 'info_dict': { - 'id': '2REGtUDQ', + 'id': '5dcdddf673c3f956ef5db202', 'ext': 'mp4', 'title': 'How to Build a Storage Bench', 'description': 'In the workshop, Tom Silva and Kevin O\'Connor build a storage bench for an entryway.', 'timestamp': 1442548800, 'upload_date': '20150918', - } + }, + 'params': { + 'skip_download': True, + }, }, { 'url': 'https://www.thisoldhouse.com/watch/arlington-arts-crafts-arts-and-crafts-class-begins', 'only_matching': True, }, { 'url': 'https://www.thisoldhouse.com/tv-episode/ask-toh-shelf-rough-electric', 'only_matching': True, + }, { + 'url': 'https://www.thisoldhouse.com/furniture/21017078/how-to-build-a-storage-bench', + 'only_matching': True, + }, { + 'url': 'https://www.thisoldhouse.com/21113884/s41-e13-paradise-lost', + 'only_matching': True, }] + _ZYPE_TMPL = 'https://player.zype.com/embed/%s.html?api_key=hsOk_yMSPYNrT22e9pu8hihLXjaZf0JW5jsOWv4ZqyHJFvkJn6rtToHl09tbbsbe' def _real_extract(self, url): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) video_id = self._search_regex( - (r'data-mid=(["\'])(?P(?:(?!\1).)+)\1', - r'id=(["\'])inline-video-player-(?P(?:(?!\1).)+)\1'), - webpage, 'video id', default=None, group='id') - if not video_id: - drupal_settings = self._parse_json(self._search_regex( - r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);', - webpage, 'drupal settings'), display_id) - video_id = try_get( - drupal_settings, lambda x: x['jwplatform']['video_id'], - compat_str) or list(drupal_settings['comScore'])[0] - return self.url_result('jwplatform:' + video_id, 'JWPlatform', video_id) + r']+src=[\'"](?:https?:)?//thisoldhouse\.chorus\.build/videos/zype/([0-9a-f]{24})', + webpage, 'video id') + return self.url_result(self._ZYPE_TMPL % video_id, 'Zype', video_id) From fffc618c519d10a7335eb5b06ab13d56ecea8561 Mon Sep 17 00:00:00 2001 From: Xaver Hellauer Date: Wed, 5 Feb 2020 16:41:56 +0100 Subject: [PATCH 326/422] [toggle] Add support for mewatch.sg (closes #23895) (#23930) --- youtube_dl/extractor/toggle.py | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/toggle.py b/youtube_dl/extractor/toggle.py index 5e5efda0f..ca2e36efe 100644 --- a/youtube_dl/extractor/toggle.py +++ b/youtube_dl/extractor/toggle.py @@ -17,9 +17,9 @@ from ..utils import ( class ToggleIE(InfoExtractor): IE_NAME = 'toggle' - _VALID_URL = r'https?://video\.toggle\.sg/(?:en|zh)/(?:[^/]+/){2,}(?P[0-9]+)' + _VALID_URL = r'https?://(?:(?:www\.)?mewatch|video\.toggle)\.sg/(?:en|zh)/(?:[^/]+/){2,}(?P[0-9]+)' _TESTS = [{ - 'url': 'http://video.toggle.sg/en/series/lion-moms-tif/trailers/lion-moms-premier/343115', + 'url': 'http://www.mewatch.sg/en/series/lion-moms-tif/trailers/lion-moms-premier/343115', 'info_dict': { 'id': '343115', 'ext': 'mp4', @@ -33,7 +33,7 @@ class ToggleIE(InfoExtractor): } }, { 'note': 'DRM-protected video', - 'url': 'http://video.toggle.sg/en/movies/dug-s-special-mission/341413', + 'url': 'http://www.mewatch.sg/en/movies/dug-s-special-mission/341413', 'info_dict': { 'id': '341413', 'ext': 'wvm', @@ -48,7 +48,7 @@ class ToggleIE(InfoExtractor): }, { # this also tests correct video id extraction 'note': 'm3u8 links are geo-restricted, but Android/mp4 is okay', - 'url': 'http://video.toggle.sg/en/series/28th-sea-games-5-show/28th-sea-games-5-show-ep11/332861', + 'url': 'http://www.mewatch.sg/en/series/28th-sea-games-5-show/28th-sea-games-5-show-ep11/332861', 'info_dict': { 'id': '332861', 'ext': 'mp4', @@ -65,19 +65,22 @@ class ToggleIE(InfoExtractor): 'url': 'http://video.toggle.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331', 'only_matching': True, }, { - 'url': 'http://video.toggle.sg/zh/series/zero-calling-s2-hd/ep13/336367', + 'url': 'http://www.mewatch.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331', 'only_matching': True, }, { - 'url': 'http://video.toggle.sg/en/series/vetri-s2/webisodes/jeeva-is-an-orphan-vetri-s2-webisode-7/342302', + 'url': 'http://www.mewatch.sg/zh/series/zero-calling-s2-hd/ep13/336367', 'only_matching': True, }, { - 'url': 'http://video.toggle.sg/en/movies/seven-days/321936', + 'url': 'http://www.mewatch.sg/en/series/vetri-s2/webisodes/jeeva-is-an-orphan-vetri-s2-webisode-7/342302', 'only_matching': True, }, { - 'url': 'https://video.toggle.sg/en/tv-show/news/may-2017-cna-singapore-tonight/fri-19-may-2017/512456', + 'url': 'http://www.mewatch.sg/en/movies/seven-days/321936', 'only_matching': True, }, { - 'url': 'http://video.toggle.sg/en/channels/eleven-plus/401585', + 'url': 'https://www.mewatch.sg/en/tv-show/news/may-2017-cna-singapore-tonight/fri-19-may-2017/512456', + 'only_matching': True, + }, { + 'url': 'http://www.mewatch.sg/en/channels/eleven-plus/401585', 'only_matching': True, }] From 82fea5b42eadc4ac2d3f4f688613f140967e92b7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 8 Feb 2020 19:36:55 +0700 Subject: [PATCH 327/422] [compat] Introduce compat_realpath (refs #23991) --- youtube_dl/compat.py | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py index c75ab131b..062b338d7 100644 --- a/youtube_dl/compat.py +++ b/youtube_dl/compat.py @@ -2754,6 +2754,17 @@ else: compat_expanduser = os.path.expanduser +if compat_os_name == 'nt' and sys.version_info < (3, 8): + # os.path.realpath on Windows does not follow symbolic links + # prior to Python 3.8 (see https://bugs.python.org/issue9949) + def compat_realpath(path): + while os.path.islink(path): + path = os.path.abspath(os.readlink(path)) + return path +else: + compat_realpath = os.path.realpath + + if sys.version_info < (3, 0): def compat_print(s): from .utils import preferredencoding From bfe2b8cf2ac57c6b66def2d5e0fc3fc424c78d75 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 8 Feb 2020 19:38:36 +0700 Subject: [PATCH 328/422] [update] Fix updating via symlinks (closes #23991) --- youtube_dl/compat.py | 1 + youtube_dl/update.py | 5 ++++- 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py index 062b338d7..d1b86bd13 100644 --- a/youtube_dl/compat.py +++ b/youtube_dl/compat.py @@ -3009,6 +3009,7 @@ __all__ = [ 'compat_os_name', 'compat_parse_qs', 'compat_print', + 'compat_realpath', 'compat_setenv', 'compat_shlex_quote', 'compat_shlex_split', diff --git a/youtube_dl/update.py b/youtube_dl/update.py index 002ea7f33..84c964617 100644 --- a/youtube_dl/update.py +++ b/youtube_dl/update.py @@ -9,6 +9,7 @@ import subprocess import sys from zipimport import zipimporter +from .compat import compat_realpath from .utils import encode_compat_str from .version import __version__ @@ -84,7 +85,9 @@ def update_self(to_screen, verbose, opener): print_notes(to_screen, versions_info['versions']) # sys.executable is set to the full pathname of the exe-file for py2exe - filename = sys.executable if hasattr(sys, 'frozen') else sys.argv[0] + # though symlinks are not followed so that we need to do this manually + # with help of realpath + filename = compat_realpath(sys.executable if hasattr(sys, 'frozen') else sys.argv[0]) if not os.access(filename, os.W_OK): to_screen('ERROR: no write permissions on %s' % filename) From f377edec067a05365824434d0c44c0f22d797190 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 10 Feb 2020 09:42:50 +0100 Subject: [PATCH 329/422] [nytimes] improve format sorting(closes #24010) --- youtube_dl/extractor/nytimes.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/nytimes.py b/youtube_dl/extractor/nytimes.py index 2bb77ab24..fc78ca56c 100644 --- a/youtube_dl/extractor/nytimes.py +++ b/youtube_dl/extractor/nytimes.py @@ -69,10 +69,10 @@ class NYTimesBaseIE(InfoExtractor): 'width': int_or_none(video.get('width')), 'height': int_or_none(video.get('height')), 'filesize': get_file_size(video.get('file_size') or video.get('fileSize')), - 'tbr': int_or_none(video.get('bitrate'), 1000), + 'tbr': int_or_none(video.get('bitrate'), 1000) or None, 'ext': ext, }) - self._sort_formats(formats) + self._sort_formats(formats, ('height', 'width', 'filesize', 'tbr', 'fps', 'format_id')) thumbnails = [] for image in video_data.get('images', []): From d6aa1db7ed0cd70570f1a01c7fc25a49e153d15b Mon Sep 17 00:00:00 2001 From: d2au Date: Fri, 14 Feb 2020 00:22:00 +1030 Subject: [PATCH 330/422] [abc:iview] Support 720p (#22907) (#22921) --- youtube_dl/extractor/abc.py | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/youtube_dl/extractor/abc.py b/youtube_dl/extractor/abc.py index 4ac323bf6..6637f4f35 100644 --- a/youtube_dl/extractor/abc.py +++ b/youtube_dl/extractor/abc.py @@ -110,17 +110,17 @@ class ABCIViewIE(InfoExtractor): # ABC iview programs are normally available for 14 days only. _TESTS = [{ - 'url': 'https://iview.abc.net.au/show/ben-and-hollys-little-kingdom/series/0/video/ZX9371A050S00', - 'md5': 'cde42d728b3b7c2b32b1b94b4a548afc', + 'url': 'https://iview.abc.net.au/show/gruen/series/11/video/LE1927H001S00', + 'md5': '67715ce3c78426b11ba167d875ac6abf', 'info_dict': { - 'id': 'ZX9371A050S00', + 'id': 'LE1927H001S00', 'ext': 'mp4', - 'title': "Gaston's Birthday", - 'series': "Ben And Holly's Little Kingdom", - 'description': 'md5:f9de914d02f226968f598ac76f105bcf', - 'upload_date': '20180604', - 'uploader_id': 'abc4kids', - 'timestamp': 1528140219, + 'title': "Series 11 Ep 1", + 'series': "Gruen", + 'description': 'md5:52cc744ad35045baf6aded2ce7287f67', + 'upload_date': '20190925', + 'uploader_id': 'abc1', + 'timestamp': 1569445289, }, 'params': { 'skip_download': True, @@ -148,7 +148,7 @@ class ABCIViewIE(InfoExtractor): 'hdnea': token, }) - for sd in ('sd', 'sd-low'): + for sd in ('720', 'sd', 'sd-low'): sd_url = try_get( stream, lambda x: x['streams']['hls'][sd], compat_str) if not sd_url: From 8cd809fb3dc446ec06afa2c1d398c9fe31a435cc Mon Sep 17 00:00:00 2001 From: Jan 'Yenda' Trmal Date: Fri, 10 Jan 2020 10:14:18 +0100 Subject: [PATCH 331/422] [nova:embed] Fix extraction (closes #23672) --- youtube_dl/extractor/nova.py | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/youtube_dl/extractor/nova.py b/youtube_dl/extractor/nova.py index 901f44b54..aefd8eab1 100644 --- a/youtube_dl/extractor/nova.py +++ b/youtube_dl/extractor/nova.py @@ -43,6 +43,13 @@ class NovaEmbedIE(InfoExtractor): formats = [] for format_id, format_list in bitrates.items(): + if format_id == 'hls': + m3u8_url = url_or_none(format_list) + if not m3u8_url: + continue + formats.extend(self._extract_m3u8_formats( + m3u8_url, video_id, ext='mp4', m3u8_id='hls', fatal=False)) + if not isinstance(format_list, list): continue for format_url in format_list: From b68a6e32fb01717b24fd2201c3e1a5611fd1c963 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 15 Feb 2020 02:00:26 +0700 Subject: [PATCH 332/422] [nova:embed] Improve (closes #23690) --- youtube_dl/extractor/nova.py | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/nova.py b/youtube_dl/extractor/nova.py index aefd8eab1..62d0552e9 100644 --- a/youtube_dl/extractor/nova.py +++ b/youtube_dl/extractor/nova.py @@ -18,7 +18,7 @@ class NovaEmbedIE(InfoExtractor): _VALID_URL = r'https?://media\.cms\.nova\.cz/embed/(?P[^/?#&]+)' _TEST = { 'url': 'https://media.cms.nova.cz/embed/8o0n0r?autoplay=1', - 'md5': 'b3834f6de5401baabf31ed57456463f7', + 'md5': 'ee009bafcc794541570edd44b71cbea3', 'info_dict': { 'id': '8o0n0r', 'ext': 'mp4', @@ -43,19 +43,18 @@ class NovaEmbedIE(InfoExtractor): formats = [] for format_id, format_list in bitrates.items(): - if format_id == 'hls': - m3u8_url = url_or_none(format_list) - if not m3u8_url: - continue - formats.extend(self._extract_m3u8_formats( - m3u8_url, video_id, ext='mp4', m3u8_id='hls', fatal=False)) - if not isinstance(format_list, list): - continue + format_list = [format_list] for format_url in format_list: format_url = url_or_none(format_url) if not format_url: continue + if format_id == 'hls': + formats.extend(self._extract_m3u8_formats( + format_url, video_id, ext='mp4', + entry_protocol='m3u8_native', m3u8_id='hls', + fatal=False)) + continue f = { 'url': format_url, } From 06f1de2daff8351f572974dafccebefd378b9f99 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 15 Feb 2020 02:16:26 +0700 Subject: [PATCH 333/422] [nova] Improve extraction (refs #23690) --- youtube_dl/extractor/nova.py | 37 +++++++++++++++++++++--------------- 1 file changed, 22 insertions(+), 15 deletions(-) diff --git a/youtube_dl/extractor/nova.py b/youtube_dl/extractor/nova.py index 62d0552e9..2850af5db 100644 --- a/youtube_dl/extractor/nova.py +++ b/youtube_dl/extractor/nova.py @@ -97,7 +97,7 @@ class NovaIE(InfoExtractor): _VALID_URL = r'https?://(?:[^.]+\.)?(?Ptv(?:noviny)?|tn|novaplus|vymena|fanda|krasna|doma|prask)\.nova\.cz/(?:[^/]+/)+(?P[^/]+?)(?:\.html|/|$)' _TESTS = [{ 'url': 'http://tn.nova.cz/clanek/tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci.html#player_13260', - 'md5': '1dd7b9d5ea27bc361f110cd855a19bd3', + 'md5': '249baab7d0104e186e78b0899c7d5f28', 'info_dict': { 'id': '1757139', 'display_id': 'tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci', @@ -119,7 +119,8 @@ class NovaIE(InfoExtractor): 'params': { # rtmp download 'skip_download': True, - } + }, + 'skip': 'gone', }, { # media.cms.nova.cz embed 'url': 'https://novaplus.nova.cz/porad/ulice/epizoda/18760-2180-dil', @@ -134,6 +135,7 @@ class NovaIE(InfoExtractor): 'skip_download': True, }, 'add_ie': [NovaEmbedIE.ie_key()], + 'skip': 'CHYBA 404: STRÁNKA NENALEZENA', }, { 'url': 'http://sport.tn.nova.cz/clanek/sport/hokej/nhl/zivot-jde-dal-hodnotil-po-vyrazeni-z-playoff-jiri-sekac.html', 'only_matching': True, @@ -158,14 +160,29 @@ class NovaIE(InfoExtractor): webpage = self._download_webpage(url, display_id) + description = clean_html(self._og_search_description(webpage, default=None)) + if site == 'novaplus': + upload_date = unified_strdate(self._search_regex( + r'(\d{1,2}-\d{1,2}-\d{4})$', display_id, 'upload date', default=None)) + elif site == 'fanda': + upload_date = unified_strdate(self._search_regex( + r'(\d{1,2}\.\d{1,2}\.\d{4})', webpage, 'upload date', default=None)) + else: + upload_date = None + # novaplus embed_id = self._search_regex( r']+\bsrc=["\'](?:https?:)?//media\.cms\.nova\.cz/embed/([^/?#&]+)', webpage, 'embed url', default=None) if embed_id: - return self.url_result( - 'https://media.cms.nova.cz/embed/%s' % embed_id, - ie=NovaEmbedIE.ie_key(), video_id=embed_id) + return { + '_type': 'url_transparent', + 'url': 'https://media.cms.nova.cz/embed/%s' % embed_id, + 'ie_key': NovaEmbedIE.ie_key(), + 'id': embed_id, + 'description': description, + 'upload_date': upload_date + } video_id = self._search_regex( [r"(?:media|video_id)\s*:\s*'(\d+)'", @@ -239,18 +256,8 @@ class NovaIE(InfoExtractor): self._sort_formats(formats) title = mediafile.get('meta', {}).get('title') or self._og_search_title(webpage) - description = clean_html(self._og_search_description(webpage, default=None)) thumbnail = config.get('poster') - if site == 'novaplus': - upload_date = unified_strdate(self._search_regex( - r'(\d{1,2}-\d{1,2}-\d{4})$', display_id, 'upload date', default=None)) - elif site == 'fanda': - upload_date = unified_strdate(self._search_regex( - r'(\d{1,2}\.\d{1,2}\.\d{4})', webpage, 'upload date', default=None)) - else: - upload_date = None - return { 'id': video_id, 'display_id': display_id, From 293c9f0186334fe8475f67508a8e156fb8b64e1e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 15 Feb 2020 02:23:29 +0700 Subject: [PATCH 334/422] [jpopsuki] Remove extractor (closes #23858) --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/jpopsukitv.py | 68 ------------------------------ 2 files changed, 69 deletions(-) delete mode 100644 youtube_dl/extractor/jpopsukitv.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index a202a0449..64d1fa251 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -497,7 +497,6 @@ from .jeuxvideo import JeuxVideoIE from .jove import JoveIE from .joj import JojIE from .jwplatform import JWPlatformIE -from .jpopsukitv import JpopsukiIE from .kakao import KakaoIE from .kaltura import KalturaIE from .kanalplay import KanalPlayIE diff --git a/youtube_dl/extractor/jpopsukitv.py b/youtube_dl/extractor/jpopsukitv.py deleted file mode 100644 index 4b5f346d1..000000000 --- a/youtube_dl/extractor/jpopsukitv.py +++ /dev/null @@ -1,68 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..utils import ( - int_or_none, - unified_strdate, -) - - -class JpopsukiIE(InfoExtractor): - IE_NAME = 'jpopsuki.tv' - _VALID_URL = r'https?://(?:www\.)?jpopsuki\.tv/(?:category/)?video/[^/]+/(?P\S+)' - - _TEST = { - 'url': 'http://www.jpopsuki.tv/video/ayumi-hamasaki---evolution/00be659d23b0b40508169cdee4545771', - 'md5': '88018c0c1a9b1387940e90ec9e7e198e', - 'info_dict': { - 'id': '00be659d23b0b40508169cdee4545771', - 'ext': 'mp4', - 'title': 'ayumi hamasaki - evolution', - 'description': 'Release date: 2001.01.31\r\n浜崎あゆみ - evolution', - 'thumbnail': 'http://www.jpopsuki.tv/cache/89722c74d2a2ebe58bcac65321c115b2.jpg', - 'uploader': 'plama_chan', - 'uploader_id': '404', - 'upload_date': '20121101' - } - } - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - video_url = 'http://www.jpopsuki.tv' + self._html_search_regex( - r'from: uploaded: (.*?)

    • ', webpage, 'video upload_date', - fatal=False)) - view_count_str = self._html_search_regex( - r'
  • Hits: ([0-9]+?)
    • ', webpage, 'video view_count', - fatal=False) - comment_count_str = self._html_search_regex( - r'

    ([0-9]+?) comments

    ', webpage, 'video comment_count', - fatal=False) - - return { - 'id': video_id, - 'url': video_url, - 'title': video_title, - 'description': description, - 'thumbnail': thumbnail, - 'uploader': uploader, - 'uploader_id': uploader_id, - 'upload_date': upload_date, - 'view_count': int_or_none(view_count_str), - 'comment_count': int_or_none(comment_count_str), - } From de1121d749089ea62d17aadb43493c00492bb37a Mon Sep 17 00:00:00 2001 From: jxu <7989982+jxu@users.noreply.github.com> Date: Tue, 28 Jan 2020 05:20:19 -0500 Subject: [PATCH 335/422] [YoutubeDL] Fix playlist entry indexing with --playlist-items (closes #10591, closes #10622) --- youtube_dl/YoutubeDL.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index f5cb46308..b09cb0a79 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -990,7 +990,7 @@ class YoutubeDL(object): 'playlist_title': ie_result.get('title'), 'playlist_uploader': ie_result.get('uploader'), 'playlist_uploader_id': ie_result.get('uploader_id'), - 'playlist_index': i + playliststart, + 'playlist_index': playlistitems[i - 1] if playlistitems else i + playliststart, 'extractor': ie_result['extractor'], 'webpage_url': ie_result['webpage_url'], 'webpage_url_basename': url_basename(ie_result['webpage_url']), From e0abaab29332f22f438617a7c425b1b2ee1c14d5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 15 Feb 2020 03:30:06 +0700 Subject: [PATCH 336/422] [test_YoutubeDL] Fix get_ids --- test/test_YoutubeDL.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py index ce9666171..0769e2ed2 100644 --- a/test/test_YoutubeDL.py +++ b/test/test_YoutubeDL.py @@ -818,8 +818,9 @@ class TestYoutubeDL(unittest.TestCase): def get_ids(params): ydl = YDL(params) - # make a copy because the dictionary can be modified - ydl.process_ie_result(playlist.copy()) + # make a deep copy because the dictionary and nested entries + # can be modified + ydl.process_ie_result(copy.deepcopy(playlist)) return [int(v['id']) for v in ydl.downloaded_info_dicts] result = get_ids({}) From 4e9e1e240dea1c37c95ceef5e52c15534d56ca7c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 15 Feb 2020 03:31:31 +0700 Subject: [PATCH 337/422] [test_YoutubeDL] Add tests for #10591 (closes #23873) --- test/test_YoutubeDL.py | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py index 0769e2ed2..1e204e551 100644 --- a/test/test_YoutubeDL.py +++ b/test/test_YoutubeDL.py @@ -816,12 +816,15 @@ class TestYoutubeDL(unittest.TestCase): 'webpage_url': 'http://example.com', } - def get_ids(params): + def get_downloaded_info_dicts(params): ydl = YDL(params) # make a deep copy because the dictionary and nested entries # can be modified ydl.process_ie_result(copy.deepcopy(playlist)) - return [int(v['id']) for v in ydl.downloaded_info_dicts] + return ydl.downloaded_info_dicts + + def get_ids(params): + return [int(v['id']) for v in get_downloaded_info_dicts(params)] result = get_ids({}) self.assertEqual(result, [1, 2, 3, 4]) @@ -853,6 +856,22 @@ class TestYoutubeDL(unittest.TestCase): result = get_ids({'playlist_items': '2-4,3-4,3'}) self.assertEqual(result, [2, 3, 4]) + # Tests for https://github.com/ytdl-org/youtube-dl/issues/10591 + # @{ + result = get_downloaded_info_dicts({'playlist_items': '2-4,3-4,3'}) + self.assertEqual(result[0]['playlist_index'], 2) + self.assertEqual(result[1]['playlist_index'], 3) + + result = get_downloaded_info_dicts({'playlist_items': '2-4,3-4,3'}) + self.assertEqual(result[0]['playlist_index'], 2) + self.assertEqual(result[1]['playlist_index'], 3) + self.assertEqual(result[2]['playlist_index'], 4) + + result = get_downloaded_info_dicts({'playlist_items': '4,2'}) + self.assertEqual(result[0]['playlist_index'], 4) + self.assertEqual(result[1]['playlist_index'], 2) + # @} + def test_urlopen_no_file_protocol(self): # see https://github.com/ytdl-org/youtube-dl/issues/8227 ydl = YDL() From f6052ec923fbe4270a3733aeb8d4a9d5727ef80f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 15 Feb 2020 03:49:29 +0700 Subject: [PATCH 338/422] [24video] Add support for porn.24video.net (closes #23779, closes #23784) --- youtube_dl/extractor/twentyfourvideo.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/twentyfourvideo.py b/youtube_dl/extractor/twentyfourvideo.py index 2830c212e..74d14049b 100644 --- a/youtube_dl/extractor/twentyfourvideo.py +++ b/youtube_dl/extractor/twentyfourvideo.py @@ -17,7 +17,7 @@ class TwentyFourVideoIE(InfoExtractor): _VALID_URL = r'''(?x) https?:// (?P - (?:(?:www|porno)\.)?24video\. + (?:(?:www|porno?)\.)?24video\. (?:net|me|xxx|sexy?|tube|adult|site|vip) )/ (?: @@ -62,6 +62,9 @@ class TwentyFourVideoIE(InfoExtractor): }, { 'url': 'https://www.24video.vip/video/view/1044982', 'only_matching': True, + }, { + 'url': 'https://porn.24video.net/video/2640421-vsya-takay', + 'only_matching': True, }] def _real_extract(self, url): From 7bf27721d61dadb2e4f2f6215cbc9d66ba3fd708 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 15 Feb 2020 05:35:55 +0700 Subject: [PATCH 339/422] [npr] Add support for streams (closes #24042) --- youtube_dl/extractor/npr.py | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/youtube_dl/extractor/npr.py b/youtube_dl/extractor/npr.py index a5e8baa7e..53acc6e57 100644 --- a/youtube_dl/extractor/npr.py +++ b/youtube_dl/extractor/npr.py @@ -4,6 +4,7 @@ from .common import InfoExtractor from ..utils import ( int_or_none, qualities, + url_or_none, ) @@ -48,6 +49,10 @@ class NprIE(InfoExtractor): }, }], 'expected_warnings': ['Failed to download m3u8 information'], + }, { + # multimedia, no formats, stream + 'url': 'https://www.npr.org/2020/02/14/805476846/laura-stevenson-tiny-desk-concert', + 'only_matching': True, }] def _real_extract(self, url): @@ -95,6 +100,17 @@ class NprIE(InfoExtractor): 'format_id': format_id, 'quality': quality(format_id), }) + for stream_id, stream_entry in media.get('stream', {}).items(): + if not isinstance(stream_entry, dict): + continue + if stream_id != 'hlsUrl': + continue + stream_url = url_or_none(stream_entry.get('$text')) + if not stream_url: + continue + formats.extend(self._extract_m3u8_formats( + stream_url, stream_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) self._sort_formats(formats) entries.append({ From 0d718db6233d1ac93df2fe6cf9c3fb908ad75b33 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 16 Feb 2020 22:40:44 +0700 Subject: [PATCH 340/422] [ChangeLog] Actualize [ci skip] --- ChangeLog | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) diff --git a/ChangeLog b/ChangeLog index 94aa9f327..42f04fa9b 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,37 @@ +version + +Core +* [YoutubeDL] Fix playlist entry indexing with --playlist-items (#10591, + #10622) +* [update] Fix updating via symlinks (#23991) ++ [compat] Introduce compat_realpath (#23991) + +Extractors ++ [npr] Add support for streams (#24042) ++ [24video] Add support for porn.24video.net (#23779, #23784) +- [jpopsuki] Remove extractor (#23858) +* [nova] Improve extraction (#23690) +* [nova:embed] Improve (#23690) +* [nova:embed] Fix extraction (#23672) ++ [abc:iview] Add support for 720p (#22907, #22921) +* [nytimes] Improve format sorting (#24010) ++ [toggle] Add support for mewatch.sg (#23895, #23930) +* [thisoldhouse] Fix extraction (#23951) ++ [popcorntimes] Add support for popcorntimes.tv (#23949) +* [sportdeutschland] Update to new API +* [twitch:stream] Lowercase channel id for stream request (#23917) +* [tv5mondeplus] Fix extraction (#23907, #23911) +* [tva] Relax URL regular expression (#23903) +* [vimeo] Fix album extraction (#23864) +* [viewlift] Improve extraction + * Fix extraction (#23851) + + Add support for authentication + + Add support for more domains +* [svt] Fix series extraction (#22297) +* [svt] Fix article extraction (#22897, #22919) +* [soundcloud] Imporve private playlist/set tracks extraction (#3707) + + version 2020.01.24 Extractors From 117ba9e9df641655f00509b34591e0a6c44395c9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 16 Feb 2020 22:43:42 +0700 Subject: [PATCH 341/422] release 2020.02.16 --- .github/ISSUE_TEMPLATE/1_broken_site.md | 6 +++--- .github/ISSUE_TEMPLATE/2_site_support_request.md | 4 ++-- .github/ISSUE_TEMPLATE/3_site_feature_request.md | 4 ++-- .github/ISSUE_TEMPLATE/4_bug_report.md | 6 +++--- .github/ISSUE_TEMPLATE/5_feature_request.md | 4 ++-- ChangeLog | 2 +- docs/supportedsites.md | 6 +++--- youtube_dl/version.py | 2 +- 8 files changed, 17 insertions(+), 17 deletions(-) diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.md b/.github/ISSUE_TEMPLATE/1_broken_site.md index 73f46ec04..716768242 100644 --- a/.github/ISSUE_TEMPLATE/1_broken_site.md +++ b/.github/ISSUE_TEMPLATE/1_broken_site.md @@ -18,7 +18,7 @@ title: '' - [ ] I'm reporting a broken site support -- [ ] I've verified that I'm running youtube-dl version **2020.01.24** +- [ ] I've verified that I'm running youtube-dl version **2020.02.16** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar issues including closed ones @@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2020.01.24 + [debug] youtube-dl version 2020.02.16 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/2_site_support_request.md b/.github/ISSUE_TEMPLATE/2_site_support_request.md index 7e3c9f669..3fd6a0bd6 100644 --- a/.github/ISSUE_TEMPLATE/2_site_support_request.md +++ b/.github/ISSUE_TEMPLATE/2_site_support_request.md @@ -19,7 +19,7 @@ labels: 'site-support-request' - [ ] I'm reporting a new site support request -- [ ] I've verified that I'm running youtube-dl version **2020.01.24** +- [ ] I've verified that I'm running youtube-dl version **2020.02.16** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that none of provided URLs violate any copyrights - [ ] I've searched the bugtracker for similar site support requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/3_site_feature_request.md b/.github/ISSUE_TEMPLATE/3_site_feature_request.md index b9bb3bd11..d160fcce9 100644 --- a/.github/ISSUE_TEMPLATE/3_site_feature_request.md +++ b/.github/ISSUE_TEMPLATE/3_site_feature_request.md @@ -18,13 +18,13 @@ title: '' - [ ] I'm reporting a site feature request -- [ ] I've verified that I'm running youtube-dl version **2020.01.24** +- [ ] I've verified that I'm running youtube-dl version **2020.02.16** - [ ] I've searched the bugtracker for similar site feature requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/4_bug_report.md b/.github/ISSUE_TEMPLATE/4_bug_report.md index 265ea80c1..f97644f65 100644 --- a/.github/ISSUE_TEMPLATE/4_bug_report.md +++ b/.github/ISSUE_TEMPLATE/4_bug_report.md @@ -18,7 +18,7 @@ title: '' - [ ] I'm reporting a broken site support issue -- [ ] I've verified that I'm running youtube-dl version **2020.01.24** +- [ ] I've verified that I'm running youtube-dl version **2020.02.16** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar bug reports including closed ones @@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2020.01.24 + [debug] youtube-dl version 2020.02.16 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/5_feature_request.md b/.github/ISSUE_TEMPLATE/5_feature_request.md index e71778a3d..dedef6d53 100644 --- a/.github/ISSUE_TEMPLATE/5_feature_request.md +++ b/.github/ISSUE_TEMPLATE/5_feature_request.md @@ -19,13 +19,13 @@ labels: 'request' - [ ] I'm reporting a feature request -- [ ] I've verified that I'm running youtube-dl version **2020.01.24** +- [ ] I've verified that I'm running youtube-dl version **2020.02.16** - [ ] I've searched the bugtracker for similar feature requests including closed ones diff --git a/ChangeLog b/ChangeLog index 42f04fa9b..a6e2c3c19 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version +version 2020.02.16 Core * [YoutubeDL] Fix playlist entry indexing with --playlist-items (#10591, diff --git a/docs/supportedsites.md b/docs/supportedsites.md index e9a8cc27a..02bc088ab 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -389,7 +389,6 @@ - **JeuxVideo** - **Joj** - **Jove** - - **jpopsuki.tv** - **JWPlatform** - **Kakao** - **Kaltura** @@ -663,6 +662,7 @@ - **Pokemon** - **PolskieRadio** - **PolskieRadioCategory** + - **Popcorntimes** - **PopcornTV** - **PornCom** - **PornerBros** @@ -1004,8 +1004,8 @@ - **Vidzi** - **vier**: vier.be and vijf.be - **vier:videos** - - **ViewLift** - - **ViewLiftEmbed** + - **viewlift** + - **viewlift:embed** - **Viidea** - **viki** - **viki:channel** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index fa6f7289a..0163333ac 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2020.01.24' +__version__ = '2020.02.16' From 97c822b3d5221d612748e1b589c87603bbae8a4a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Martin=20Str=C3=B6m?= Date: Tue, 18 Feb 2020 19:02:05 +0100 Subject: [PATCH 342/422] [tv2dk:bornholm:play] Fix extraction (#24076) --- youtube_dl/extractor/tv2dk.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/tv2dk.py b/youtube_dl/extractor/tv2dk.py index 611fdc0c6..8bda9348d 100644 --- a/youtube_dl/extractor/tv2dk.py +++ b/youtube_dl/extractor/tv2dk.py @@ -106,7 +106,7 @@ class TV2DKBornholmPlayIE(InfoExtractor): video_id = self._match_id(url) video = self._download_json( - 'http://play.tv2bornholm.dk/controls/AJAX.aspx/specifikVideo', video_id, + 'https://play.tv2bornholm.dk/controls/AJAX.aspx/specifikVideo', video_id, data=json.dumps({ 'playlist_id': video_id, 'serienavn': '', From 5d9f6cbc5afa033b6f1cfd2abe4327e366da2ad1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 23 Feb 2020 04:33:29 +0700 Subject: [PATCH 343/422] [imdb] Fix extraction (closes #23443) --- youtube_dl/extractor/imdb.py | 58 ++++++++++++++++++++++++++---------- 1 file changed, 42 insertions(+), 16 deletions(-) diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py index 436759da5..a31301985 100644 --- a/youtube_dl/extractor/imdb.py +++ b/youtube_dl/extractor/imdb.py @@ -1,5 +1,7 @@ from __future__ import unicode_literals +import base64 +import json import re from .common import InfoExtractor @@ -8,6 +10,7 @@ from ..utils import ( mimetype2ext, parse_duration, qualities, + try_get, url_or_none, ) @@ -15,15 +18,16 @@ from ..utils import ( class ImdbIE(InfoExtractor): IE_NAME = 'imdb' IE_DESC = 'Internet Movie Database trailers' - _VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video|title|list).+?[/-]vi(?P\d+)' + _VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video|title|list).*?[/-]vi(?P\d+)' _TESTS = [{ 'url': 'http://www.imdb.com/video/imdb/vi2524815897', 'info_dict': { 'id': '2524815897', 'ext': 'mp4', - 'title': 'No. 2 from Ice Age: Continental Drift (2012)', + 'title': 'No. 2', 'description': 'md5:87bd0bdc61e351f21f20d2d7441cb4e7', + 'duration': 152, } }, { 'url': 'http://www.imdb.com/video/_/vi2524815897', @@ -47,21 +51,23 @@ class ImdbIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage( - 'https://www.imdb.com/videoplayer/vi' + video_id, video_id) - video_metadata = self._parse_json(self._search_regex( - r'window\.IMDbReactInitialState\.push\(({.+?})\);', webpage, - 'video metadata'), video_id)['videos']['videoMetadata']['vi' + video_id] - title = self._html_search_meta( - ['og:title', 'twitter:title'], webpage) or self._html_search_regex( - r'(.+?)', webpage, 'title', fatal=False) or video_metadata['title'] + + data = self._download_json( + 'https://www.imdb.com/ve/data/VIDEO_PLAYBACK_DATA', video_id, + query={ + 'key': base64.b64encode(json.dumps({ + 'type': 'VIDEO_PLAYER', + 'subType': 'FORCE_LEGACY', + 'id': 'vi%s' % video_id, + }).encode()).decode(), + })[0] quality = qualities(('SD', '480p', '720p', '1080p')) formats = [] - for encoding in video_metadata.get('encodings', []): + for encoding in data['videoLegacyEncodings']: if not encoding or not isinstance(encoding, dict): continue - video_url = url_or_none(encoding.get('videoUrl')) + video_url = url_or_none(encoding.get('url')) if not video_url: continue ext = mimetype2ext(encoding.get( @@ -69,7 +75,7 @@ class ImdbIE(InfoExtractor): if ext == 'm3u8': formats.extend(self._extract_m3u8_formats( video_url, video_id, 'mp4', entry_protocol='m3u8_native', - m3u8_id='hls', fatal=False)) + preference=1, m3u8_id='hls', fatal=False)) continue format_id = encoding.get('definition') formats.append({ @@ -80,13 +86,33 @@ class ImdbIE(InfoExtractor): }) self._sort_formats(formats) + webpage = self._download_webpage( + 'https://www.imdb.com/video/vi' + video_id, video_id) + video_metadata = self._parse_json(self._search_regex( + r'args\.push\(\s*({.+?})\s*\)\s*;', webpage, + 'video metadata'), video_id) + + video_info = video_metadata.get('VIDEO_INFO') + if video_info and isinstance(video_info, dict): + info = try_get( + video_info, lambda x: x[list(video_info.keys())[0]][0], dict) + else: + info = {} + + title = self._html_search_meta( + ['og:title', 'twitter:title'], webpage) or self._html_search_regex( + r'(.+?)', webpage, 'title', + default=None) or info['videoTitle'] + return { 'id': video_id, 'title': title, + 'alt_title': info.get('videoSubTitle'), 'formats': formats, - 'description': video_metadata.get('description'), - 'thumbnail': video_metadata.get('slate', {}).get('url'), - 'duration': parse_duration(video_metadata.get('duration')), + 'description': info.get('videoDescription'), + 'thumbnail': url_or_none(try_get( + video_metadata, lambda x: x['videoSlate']['source'])), + 'duration': parse_duration(info.get('videoRuntime')), } From fda6d237a5b664cc8a9a45562d4113c51fd0280d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 23 Feb 2020 06:47:11 +0700 Subject: [PATCH 344/422] [wistia] Add support for multiple generic embeds (closes #8347, closes #11385) --- youtube_dl/extractor/generic.py | 17 +++++++++-------- youtube_dl/extractor/wistia.py | 31 ++++++++++++++++--------------- 2 files changed, 25 insertions(+), 23 deletions(-) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 3c002472f..04c026984 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -2537,14 +2537,15 @@ class GenericIE(InfoExtractor): dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key()) # Look for embedded Wistia player - wistia_url = WistiaIE._extract_url(webpage) - if wistia_url: - return { - '_type': 'url_transparent', - 'url': self._proto_relative_url(wistia_url), - 'ie_key': WistiaIE.ie_key(), - 'uploader': video_uploader, - } + wistia_urls = WistiaIE._extract_urls(webpage) + if wistia_urls: + playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key()) + for entry in playlist['entries']: + entry.update({ + '_type': 'url_transparent', + 'uploader': video_uploader, + }) + return playlist # Look for SVT player svt_url = SVTIE._extract_url(webpage) diff --git a/youtube_dl/extractor/wistia.py b/youtube_dl/extractor/wistia.py index 085514d47..168e5e901 100644 --- a/youtube_dl/extractor/wistia.py +++ b/youtube_dl/extractor/wistia.py @@ -45,22 +45,23 @@ class WistiaIE(InfoExtractor): # https://wistia.com/support/embed-and-share/video-on-your-website @staticmethod def _extract_url(webpage): - match = re.search( - r'<(?:meta[^>]+?content|(?:iframe|script)[^>]+?src)=["\'](?P(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/[a-z0-9]{10})', webpage) - if match: - return unescapeHTML(match.group('url')) + urls = WistiaIE._extract_urls(webpage) + return urls[0] if urls else None - match = re.search( - r'''(?sx) - ]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*? - ]+class=(["']).*?\bwistia_async_(?P[a-z0-9]{10})\b.*?\2 - ''', webpage) - if match: - return 'wistia:%s' % match.group('id') - - match = re.search(r'(?:data-wistia-?id=["\']|Wistia\.embed\(["\']|id=["\']wistia_)(?P[a-z0-9]{10})', webpage) - if match: - return 'wistia:%s' % match.group('id') + @staticmethod + def _extract_urls(webpage): + urls = [] + for match in re.finditer( + r'<(?:meta[^>]+?content|(?:iframe|script)[^>]+?src)=["\'](?P(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/[a-z0-9]{10})', webpage): + urls.append(unescapeHTML(match.group('url'))) + for match in re.finditer( + r'''(?sx) + ]+class=(["']).*?\bwistia_async_(?P[a-z0-9]{10})\b.*?\2 + ''', webpage): + urls.append('wistia:%s' % match.group('id')) + for match in re.finditer(r'(?:data-wistia-?id=["\']|Wistia\.embed\(["\']|id=["\']wistia_)(?P[a-z0-9]{10})', webpage): + urls.append('wistia:%s' % match.group('id')) + return urls def _real_extract(self, url): video_id = self._match_id(url) From 00d798b7c25f0a03adb252c882df46abc8c23b1b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 23 Feb 2020 06:49:45 +0700 Subject: [PATCH 345/422] [teachable] Add support for multiple videos per lecture (closes #24101) --- youtube_dl/extractor/teachable.py | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/teachable.py b/youtube_dl/extractor/teachable.py index 6b7f13b43..cca89a4a8 100644 --- a/youtube_dl/extractor/teachable.py +++ b/youtube_dl/extractor/teachable.py @@ -160,8 +160,8 @@ class TeachableIE(TeachableBaseIE): webpage = self._download_webpage(url, video_id) - wistia_url = WistiaIE._extract_url(webpage) - if not wistia_url: + wistia_urls = WistiaIE._extract_urls(webpage) + if not wistia_urls: if any(re.search(p, webpage) for p in ( r'class=["\']lecture-contents-locked', r'>\s*Lecture contents locked', @@ -174,12 +174,14 @@ class TeachableIE(TeachableBaseIE): title = self._og_search_title(webpage, default=None) - return { + entries = [{ '_type': 'url_transparent', 'url': wistia_url, 'ie_key': WistiaIE.ie_key(), 'title': title, - } + } for wistia_url in wistia_urls] + + return self.playlist_result(entries, video_id, title) class TeachableCourseIE(TeachableBaseIE): From bee6451fe88dbe8d983150cb17565d1c3e9024f7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 24 Feb 2020 04:47:56 +0700 Subject: [PATCH 346/422] [pornhd] Fix extraction (closes #24128) --- youtube_dl/extractor/pornhd.py | 36 ++++++++++++++++++++++------------ 1 file changed, 24 insertions(+), 12 deletions(-) diff --git a/youtube_dl/extractor/pornhd.py b/youtube_dl/extractor/pornhd.py index 27d65d4b9..c6052ac9f 100644 --- a/youtube_dl/extractor/pornhd.py +++ b/youtube_dl/extractor/pornhd.py @@ -8,6 +8,7 @@ from ..utils import ( ExtractorError, int_or_none, js_to_json, + merge_dicts, urljoin, ) @@ -27,23 +28,22 @@ class PornHdIE(InfoExtractor): 'view_count': int, 'like_count': int, 'age_limit': 18, - } + }, + 'skip': 'HTTP Error 404: Not Found', }, { - # removed video 'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video', - 'md5': '956b8ca569f7f4d8ec563e2c41598441', + 'md5': '1b7b3a40b9d65a8e5b25f7ab9ee6d6de', 'info_dict': { 'id': '1962', 'display_id': 'sierra-day-gets-his-cum-all-over-herself-hd-porn-video', 'ext': 'mp4', - 'title': 'Sierra loves doing laundry', + 'title': 'md5:98c6f8b2d9c229d0f0fde47f61a1a759', 'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294', 'thumbnail': r're:^https?://.*\.jpg', 'view_count': int, 'like_count': int, 'age_limit': 18, }, - 'skip': 'Not available anymore', }] def _real_extract(self, url): @@ -61,7 +61,13 @@ class PornHdIE(InfoExtractor): r"(?s)sources'?\s*[:=]\s*(\{.+?\})", webpage, 'sources', default='{}')), video_id) + info = {} if not sources: + entries = self._parse_html5_media_entries(url, webpage, video_id) + if entries: + info = entries[0] + + if not sources and not info: message = self._html_search_regex( r'(?s)<(div|p)[^>]+class="no-video"[^>]*>(?P.+?)]+class="description"[^>]*>(?P[^<]+)]+class=["\']video-description[^>]+>(?P.+?)', + r'<(div|p)[^>]+class="description"[^>]*>(?P[^<]+)(?:(?!\1).)+)\1", webpage, - 'thumbnail', fatal=False, group='url') + 'thumbnail', default=None, group='url') like_count = int_or_none(self._search_regex( - (r'(\d+)\s*]+>(?: |\s)*\blikes', + (r'(\d+)\s*likes', + r'(\d+)\s*]+>(?: |\s)*\blikes', r'class=["\']save-count["\'][^>]*>\s*(\d+)'), webpage, 'like count', fatal=False)) - return { + return merge_dicts(info, { 'id': video_id, 'display_id': display_id, 'title': title, @@ -106,4 +118,4 @@ class PornHdIE(InfoExtractor): 'like_count': like_count, 'formats': formats, 'age_limit': 18, - } + }) From b76f0e58f750fd420ac3078c7183b2de66da562c Mon Sep 17 00:00:00 2001 From: The Hatsune Daishi Date: Sat, 29 Feb 2020 18:33:09 +0900 Subject: [PATCH 347/422] [options] Remove duplicate short option -v for --version (#24162) --- youtube_dl/options.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/options.py b/youtube_dl/options.py index 1ffabc62b..8826b382c 100644 --- a/youtube_dl/options.py +++ b/youtube_dl/options.py @@ -134,7 +134,7 @@ def parseOpts(overrideArguments=None): action='help', help='Print this help text and exit') general.add_option( - '-v', '--version', + '--version', action='version', help='Print program version and exit') general.add_option( From e2f8bf5888274b95513b430e0f20261120699b4b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 29 Feb 2020 17:29:30 +0700 Subject: [PATCH 348/422] [extractor/common] Convert ISM manifest to unicode before processing on python 2 (#24152) --- youtube_dl/extractor/common.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index eaae5e484..ab7d473d0 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -2341,7 +2341,7 @@ class InfoExtractor(object): return [] ism_doc, urlh = res - return self._parse_ism_formats(ism_doc, urlh.geturl(), ism_id) + return self._parse_ism_formats(ism_doc, compat_str(urlh.geturl()), ism_id) def _parse_ism_formats(self, ism_doc, ism_url, ism_id=None): """ From fca6dba8b80286ae6d3ca0a60c4799c220a52650 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 29 Feb 2020 19:08:44 +0700 Subject: [PATCH 349/422] [YoutubeDL] Force redirect URL to unicode on python 2 --- youtube_dl/YoutubeDL.py | 4 +++- youtube_dl/utils.py | 9 +++++++++ 2 files changed, 12 insertions(+), 1 deletion(-) diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index b09cb0a79..19370f62b 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -92,6 +92,7 @@ from .utils import ( YoutubeDLCookieJar, YoutubeDLCookieProcessor, YoutubeDLHandler, + YoutubeDLRedirectHandler, ) from .cache import Cache from .extractor import get_info_extractor, gen_extractor_classes, _LAZY_LOADER @@ -2343,6 +2344,7 @@ class YoutubeDL(object): debuglevel = 1 if self.params.get('debug_printtraffic') else 0 https_handler = make_HTTPS_handler(self.params, debuglevel=debuglevel) ydlh = YoutubeDLHandler(self.params, debuglevel=debuglevel) + redirect_handler = YoutubeDLRedirectHandler() data_handler = compat_urllib_request_DataHandler() # When passing our own FileHandler instance, build_opener won't add the @@ -2356,7 +2358,7 @@ class YoutubeDL(object): file_handler.file_open = file_open opener = compat_urllib_request.build_opener( - proxy_handler, https_handler, cookie_processor, ydlh, data_handler, file_handler) + proxy_handler, https_handler, cookie_processor, ydlh, redirect_handler, data_handler, file_handler) # Delete the default user-agent header, which would otherwise apply in # cases where our custom HTTP handler doesn't come into play diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index f6204692a..8ccf25489 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -2795,6 +2795,15 @@ class YoutubeDLCookieProcessor(compat_urllib_request.HTTPCookieProcessor): https_response = http_response +class YoutubeDLRedirectHandler(compat_urllib_request.HTTPRedirectHandler): + if sys.version_info[0] < 3: + def redirect_request(self, req, fp, code, msg, headers, newurl): + # On python 2 urlh.geturl() may sometimes return redirect URL + # as byte string instead of unicode. This workaround allows + # to force it always return unicode. + return compat_urllib_request.HTTPRedirectHandler.redirect_request(self, req, fp, code, msg, headers, compat_str(newurl)) + + def extract_timezone(date_str): m = re.search( r'^.{8,}?(?PZ$| ?(?P\+|-)(?P[0-9]{2}):?(?P[0-9]{2})$)', From 7947a1f7dbc6ba47a6f22ab67fd330e57c0ef87c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 29 Feb 2020 19:17:27 +0700 Subject: [PATCH 350/422] Remove no longer needed compat_str around geturl --- youtube_dl/extractor/common.py | 2 +- youtube_dl/extractor/eporner.py | 3 +-- youtube_dl/extractor/generic.py | 6 +++--- youtube_dl/extractor/lecturio.py | 3 +-- youtube_dl/extractor/linuxacademy.py | 5 ++--- youtube_dl/extractor/mediaset.py | 3 +-- youtube_dl/extractor/mediasite.py | 2 +- youtube_dl/extractor/platzi.py | 2 +- youtube_dl/extractor/safari.py | 5 ++--- youtube_dl/extractor/teachable.py | 3 +-- youtube_dl/extractor/tumblr.py | 3 +-- youtube_dl/extractor/vimeo.py | 2 +- 12 files changed, 16 insertions(+), 23 deletions(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index ab7d473d0..eaae5e484 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -2341,7 +2341,7 @@ class InfoExtractor(object): return [] ism_doc, urlh = res - return self._parse_ism_formats(ism_doc, compat_str(urlh.geturl()), ism_id) + return self._parse_ism_formats(ism_doc, urlh.geturl(), ism_id) def _parse_ism_formats(self, ism_doc, ism_url, ism_id=None): """ diff --git a/youtube_dl/extractor/eporner.py b/youtube_dl/extractor/eporner.py index c050bf9df..fe42821c7 100644 --- a/youtube_dl/extractor/eporner.py +++ b/youtube_dl/extractor/eporner.py @@ -4,7 +4,6 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( encode_base_n, ExtractorError, @@ -55,7 +54,7 @@ class EpornerIE(InfoExtractor): webpage, urlh = self._download_webpage_handle(url, display_id) - video_id = self._match_id(compat_str(urlh.geturl())) + video_id = self._match_id(urlh.geturl()) hash = self._search_regex( r'hash\s*:\s*["\']([\da-f]{32})', webpage, 'hash') diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 04c026984..d1ec56be9 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -2287,7 +2287,7 @@ class GenericIE(InfoExtractor): if head_response is not False: # Check for redirect - new_url = compat_str(head_response.geturl()) + new_url = head_response.geturl() if url != new_url: self.report_following_redirect(new_url) if force_videoid: @@ -2387,12 +2387,12 @@ class GenericIE(InfoExtractor): return self.playlist_result( self._parse_xspf( doc, video_id, xspf_url=url, - xspf_base_url=compat_str(full_response.geturl())), + xspf_base_url=full_response.geturl()), video_id) elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag): info_dict['formats'] = self._parse_mpd_formats( doc, - mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0], + mpd_base_url=full_response.geturl().rpartition('/')[0], mpd_url=url) self._sort_formats(info_dict['formats']) return info_dict diff --git a/youtube_dl/extractor/lecturio.py b/youtube_dl/extractor/lecturio.py index 6ed7da4ab..1b2dcef46 100644 --- a/youtube_dl/extractor/lecturio.py +++ b/youtube_dl/extractor/lecturio.py @@ -4,7 +4,6 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( clean_html, determine_ext, @@ -36,7 +35,7 @@ class LecturioBaseIE(InfoExtractor): self._LOGIN_URL, None, 'Downloading login popup') def is_logged(url_handle): - return self._LOGIN_URL not in compat_str(url_handle.geturl()) + return self._LOGIN_URL not in url_handle.geturl() # Already logged in if is_logged(urlh): diff --git a/youtube_dl/extractor/linuxacademy.py b/youtube_dl/extractor/linuxacademy.py index a78c6556e..23ca965d9 100644 --- a/youtube_dl/extractor/linuxacademy.py +++ b/youtube_dl/extractor/linuxacademy.py @@ -8,7 +8,6 @@ from .common import InfoExtractor from ..compat import ( compat_b64decode, compat_HTTPError, - compat_str, ) from ..utils import ( ExtractorError, @@ -99,7 +98,7 @@ class LinuxAcademyIE(InfoExtractor): 'sso': 'true', }) - login_state_url = compat_str(urlh.geturl()) + login_state_url = urlh.geturl() try: login_page = self._download_webpage( @@ -129,7 +128,7 @@ class LinuxAcademyIE(InfoExtractor): }) access_token = self._search_regex( - r'access_token=([^=&]+)', compat_str(urlh.geturl()), + r'access_token=([^=&]+)', urlh.geturl(), 'access token') self._download_webpage( diff --git a/youtube_dl/extractor/mediaset.py b/youtube_dl/extractor/mediaset.py index 027a790b8..933df1495 100644 --- a/youtube_dl/extractor/mediaset.py +++ b/youtube_dl/extractor/mediaset.py @@ -6,7 +6,6 @@ import re from .theplatform import ThePlatformBaseIE from ..compat import ( compat_parse_qs, - compat_str, compat_urllib_parse_urlparse, ) from ..utils import ( @@ -114,7 +113,7 @@ class MediasetIE(ThePlatformBaseIE): continue urlh = ie._request_webpage( embed_url, video_id, note='Following embed URL redirect') - embed_url = compat_str(urlh.geturl()) + embed_url = urlh.geturl() program_guid = _program_guid(_qs(embed_url)) if program_guid: entries.append(embed_url) diff --git a/youtube_dl/extractor/mediasite.py b/youtube_dl/extractor/mediasite.py index 694a264d6..d6eb15740 100644 --- a/youtube_dl/extractor/mediasite.py +++ b/youtube_dl/extractor/mediasite.py @@ -129,7 +129,7 @@ class MediasiteIE(InfoExtractor): query = mobj.group('query') webpage, urlh = self._download_webpage_handle(url, resource_id) # XXX: add UrlReferrer? - redirect_url = compat_str(urlh.geturl()) + redirect_url = urlh.geturl() # XXX: might have also extracted UrlReferrer and QueryString from the html service_path = compat_urlparse.urljoin(redirect_url, self._html_search_regex( diff --git a/youtube_dl/extractor/platzi.py b/youtube_dl/extractor/platzi.py index 602207beb..23c8256b5 100644 --- a/youtube_dl/extractor/platzi.py +++ b/youtube_dl/extractor/platzi.py @@ -46,7 +46,7 @@ class PlatziBaseIE(InfoExtractor): headers={'Referer': self._LOGIN_URL}) # login succeeded - if 'platzi.com/login' not in compat_str(urlh.geturl()): + if 'platzi.com/login' not in urlh.geturl(): return login_error = self._webpage_read_content( diff --git a/youtube_dl/extractor/safari.py b/youtube_dl/extractor/safari.py index 4942437c7..2cc665122 100644 --- a/youtube_dl/extractor/safari.py +++ b/youtube_dl/extractor/safari.py @@ -8,7 +8,6 @@ from .common import InfoExtractor from ..compat import ( compat_parse_qs, - compat_str, compat_urlparse, ) from ..utils import ( @@ -39,13 +38,13 @@ class SafariBaseIE(InfoExtractor): 'Downloading login page') def is_logged(urlh): - return 'learning.oreilly.com/home/' in compat_str(urlh.geturl()) + return 'learning.oreilly.com/home/' in urlh.geturl() if is_logged(urlh): self.LOGGED_IN = True return - redirect_url = compat_str(urlh.geturl()) + redirect_url = urlh.geturl() parsed_url = compat_urlparse.urlparse(redirect_url) qs = compat_parse_qs(parsed_url.query) next_uri = compat_urlparse.urljoin( diff --git a/youtube_dl/extractor/teachable.py b/youtube_dl/extractor/teachable.py index cca89a4a8..4316a6962 100644 --- a/youtube_dl/extractor/teachable.py +++ b/youtube_dl/extractor/teachable.py @@ -4,7 +4,6 @@ import re from .common import InfoExtractor from .wistia import WistiaIE -from ..compat import compat_str from ..utils import ( clean_html, ExtractorError, @@ -58,7 +57,7 @@ class TeachableBaseIE(InfoExtractor): self._logged_in = True return - login_url = compat_str(urlh.geturl()) + login_url = urlh.geturl() login_form = self._hidden_inputs(login_page) diff --git a/youtube_dl/extractor/tumblr.py b/youtube_dl/extractor/tumblr.py index edbb0aa69..ae584ad69 100644 --- a/youtube_dl/extractor/tumblr.py +++ b/youtube_dl/extractor/tumblr.py @@ -4,7 +4,6 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_str from ..utils import ( ExtractorError, int_or_none, @@ -151,7 +150,7 @@ class TumblrIE(InfoExtractor): url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id) webpage, urlh = self._download_webpage_handle(url, video_id) - redirect_url = compat_str(urlh.geturl()) + redirect_url = urlh.geturl() if 'tumblr.com/safe-mode' in redirect_url or redirect_url.startswith('/safe-mode'): raise ExtractorError( 'This Tumblr may contain sensitive media. ' diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index f378aa283..1da4ced96 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -591,7 +591,7 @@ class VimeoIE(VimeoBaseInfoExtractor): # Retrieve video webpage to extract further information webpage, urlh = self._download_webpage_handle( url, video_id, headers=headers) - redirect_url = compat_str(urlh.geturl()) + redirect_url = urlh.geturl() except ExtractorError as ee: if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: errmsg = ee.cause.read() From 886d9859590c423b1d036d4a2e6f43ee639560d4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 29 Feb 2020 21:58:22 +0700 Subject: [PATCH 351/422] [youjizz] Fix extraction (closes #24181) --- youtube_dl/extractor/youjizz.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/youjizz.py b/youtube_dl/extractor/youjizz.py index dff69fcb7..88aabd272 100644 --- a/youtube_dl/extractor/youjizz.py +++ b/youtube_dl/extractor/youjizz.py @@ -44,7 +44,7 @@ class YouJizzIE(InfoExtractor): encodings = self._parse_json( self._search_regex( - r'encodings\s*=\s*(\[.+?\]);\n', webpage, 'encodings', + r'[Ee]ncodings\s*=\s*(\[.+?\]);\n', webpage, 'encodings', default='[]'), video_id, fatal=False) for encoding in encodings: From ea17979d83e6dcd61de0901fc55e2672d577e5a7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 29 Feb 2020 22:08:43 +0700 Subject: [PATCH 352/422] [test_subtitles] Remove obsolete test --- test/test_subtitles.py | 13 ------------- 1 file changed, 13 deletions(-) diff --git a/test/test_subtitles.py b/test/test_subtitles.py index 7d57a628e..17aaaf20d 100644 --- a/test/test_subtitles.py +++ b/test/test_subtitles.py @@ -26,7 +26,6 @@ from youtube_dl.extractor import ( ThePlatformIE, ThePlatformFeedIE, RTVEALaCartaIE, - FunnyOrDieIE, DemocracynowIE, ) @@ -322,18 +321,6 @@ class TestRtveSubtitles(BaseTestSubtitles): self.assertEqual(md5(subtitles['es']), '69e70cae2d40574fb7316f31d6eb7fca') -class TestFunnyOrDieSubtitles(BaseTestSubtitles): - url = 'http://www.funnyordie.com/videos/224829ff6d/judd-apatow-will-direct-your-vine' - IE = FunnyOrDieIE - - def test_allsubtitles(self): - self.DL.params['writesubtitles'] = True - self.DL.params['allsubtitles'] = True - subtitles = self.getSubtitles() - self.assertEqual(set(subtitles.keys()), set(['en'])) - self.assertEqual(md5(subtitles['en']), 'c5593c193eacd353596c11c2d4f9ecc4') - - class TestDemocracynowSubtitles(BaseTestSubtitles): url = 'http://www.democracynow.org/shows/2015/7/3' IE = DemocracynowIE From b4cbdbd4b37a496c6539694bebd0ec50ef02c864 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 29 Feb 2020 23:06:36 +0700 Subject: [PATCH 353/422] [zdf:channel] Fix tests --- youtube_dl/extractor/zdf.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/zdf.py b/youtube_dl/extractor/zdf.py index 145c123a4..656864b2e 100644 --- a/youtube_dl/extractor/zdf.py +++ b/youtube_dl/extractor/zdf.py @@ -244,14 +244,14 @@ class ZDFChannelIE(ZDFBaseIE): 'id': 'das-aktuelle-sportstudio', 'title': 'das aktuelle sportstudio | ZDF', }, - 'playlist_count': 21, + 'playlist_mincount': 23, }, { 'url': 'https://www.zdf.de/dokumentation/planet-e', 'info_dict': { 'id': 'planet-e', 'title': 'planet e.', }, - 'playlist_count': 4, + 'playlist_mincount': 50, }, { 'url': 'https://www.zdf.de/filme/taunuskrimi/', 'only_matching': True, From 278355bae4b4aed9cd3bf09bdf251fcb7396e303 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 29 Feb 2020 23:09:13 +0700 Subject: [PATCH 354/422] [zapiks] Fix test --- youtube_dl/extractor/zapiks.py | 1 - 1 file changed, 1 deletion(-) diff --git a/youtube_dl/extractor/zapiks.py b/youtube_dl/extractor/zapiks.py index bacb82eee..f6496f516 100644 --- a/youtube_dl/extractor/zapiks.py +++ b/youtube_dl/extractor/zapiks.py @@ -29,7 +29,6 @@ class ZapiksIE(InfoExtractor): 'timestamp': 1359044972, 'upload_date': '20130124', 'view_count': int, - 'comment_count': int, }, }, { From e88b450771027e3a36e7b3721e0bc1f105331cf7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 29 Feb 2020 23:51:34 +0700 Subject: [PATCH 355/422] [xtube] Fix metadata extraction (closes #21073, closes #22455) --- youtube_dl/extractor/xtube.py | 46 +++++++++++++++++++++++++---------- 1 file changed, 33 insertions(+), 13 deletions(-) diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index c6c0b3291..994cf1d0a 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -47,7 +47,7 @@ class XTubeIE(InfoExtractor): 'display_id': 'A-Super-Run-Part-1-YT', 'ext': 'flv', 'title': 'A Super Run - Part 1 (YT)', - 'description': 'md5:ca0d47afff4a9b2942e4b41aa970fd93', + 'description': 'md5:4cc3af1aa1b0413289babc88f0d4f616', 'uploader': 'tshirtguy59', 'duration': 579, 'view_count': int, @@ -87,10 +87,24 @@ class XTubeIE(InfoExtractor): 'Cookie': 'age_verified=1; cookiesAccepted=1', }) - sources = self._parse_json(self._search_regex( - r'(["\'])?sources\1?\s*:\s*(?P{.+?}),', - webpage, 'sources', group='sources'), video_id, - transform_source=js_to_json) + title, thumbnail, duration = [None] * 3 + + config = self._parse_json(self._search_regex( + r'playerConf\s*=\s*({.+?})\s*,\s*\n', webpage, 'config', + default='{}'), video_id, transform_source=js_to_json, fatal=False) + if config: + config = config.get('mainRoll') + if isinstance(config, dict): + title = config.get('title') + thumbnail = config.get('poster') + duration = int_or_none(config.get('duration')) + sources = config.get('sources') + + if isinstance(sources, dict): + sources = self._parse_json(self._search_regex( + r'(["\'])?sources\1?\s*:\s*(?P{.+?}),', + webpage, 'sources', group='sources'), video_id, + transform_source=js_to_json) formats = [] for format_id, format_url in sources.items(): @@ -102,20 +116,25 @@ class XTubeIE(InfoExtractor): self._remove_duplicate_formats(formats) self._sort_formats(formats) - title = self._search_regex( - (r'

    \s*(?P[^<]+?)\s*</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'), - webpage, 'title', group='title') - description = self._search_regex( + if not title: + title = self._search_regex( + (r'<h1>\s*(?P<title>[^<]+?)\s*</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'), + webpage, 'title', group='title') + description = self._og_search_description( + webpage, default=None) or self._html_search_meta( + 'twitter:description', webpage, default=None) or self._search_regex( r'</h1>\s*<p>([^<]+)', webpage, 'description', fatal=False) uploader = self._search_regex( (r'<input[^>]+name="contentOwnerId"[^>]+value="([^"]+)"', r'<span[^>]+class="nickname"[^>]*>([^<]+)'), webpage, 'uploader', fatal=False) - duration = parse_duration(self._search_regex( - r'<dt>Runtime:?</dt>\s*<dd>([^<]+)</dd>', - webpage, 'duration', fatal=False)) + if not duration: + duration = parse_duration(self._search_regex( + r'<dt>Runtime:?</dt>\s*<dd>([^<]+)</dd>', + webpage, 'duration', fatal=False)) view_count = str_to_int(self._search_regex( - r'<dt>Views:?</dt>\s*<dd>([\d,\.]+)</dd>', + (r'["\']viewsCount["\'][^>]*>(\d+)\s+views', + r'<dt>Views:?</dt>\s*<dd>([\d,\.]+)</dd>'), webpage, 'view count', fatal=False)) comment_count = str_to_int(self._html_search_regex( r'>Comments? \(([\d,\.]+)\)<', @@ -126,6 +145,7 @@ class XTubeIE(InfoExtractor): 'display_id': display_id, 'title': title, 'description': description, + 'thumbnail': thumbnail, 'uploader': uploader, 'duration': duration, 'view_count': view_count, From 838f051c4b9a0c974da32e79c011bbf85fa186fe Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 29 Feb 2020 23:51:56 +0700 Subject: [PATCH 356/422] [xtube:user] Fix test --- youtube_dl/extractor/xtube.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index 994cf1d0a..47caec1de 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -164,7 +164,7 @@ class XTubeUserIE(InfoExtractor): 'id': 'greenshowers-4056496', 'age_limit': 18, }, - 'playlist_mincount': 155, + 'playlist_mincount': 154, } def _real_extract(self, url): From f8cbd8c96367871db974621d5a92b324acb57938 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 1 Mar 2020 01:04:51 +0700 Subject: [PATCH 357/422] [telecinco] Fix extraction (refs #24195) --- youtube_dl/extractor/telecinco.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/telecinco.py b/youtube_dl/extractor/telecinco.py index d37e1b055..d79ab1e82 100644 --- a/youtube_dl/extractor/telecinco.py +++ b/youtube_dl/extractor/telecinco.py @@ -135,7 +135,7 @@ class TelecincoIE(InfoExtractor): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) article = self._parse_json(self._search_regex( - r'window\.\$REACTBASE_STATE\.article\s*=\s*({.+})', + r'window\.\$REACTBASE_STATE\.article(?:_multisite)?\s*=\s*({.+})', webpage, 'article'), display_id)['article'] title = article.get('title') description = clean_html(article.get('leadParagraph')) From 6d475d01d8f1fc9f5e92ac2caa986453bee95ae1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 1 Mar 2020 03:09:19 +0700 Subject: [PATCH 358/422] [telecinco] Add support for article opening videos --- youtube_dl/extractor/telecinco.py | 44 ++++++++++++++++++++++++++----- 1 file changed, 38 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/telecinco.py b/youtube_dl/extractor/telecinco.py index d79ab1e82..9ba3da341 100644 --- a/youtube_dl/extractor/telecinco.py +++ b/youtube_dl/extractor/telecinco.py @@ -11,6 +11,7 @@ from ..utils import ( determine_ext, int_or_none, str_or_none, + try_get, urljoin, ) @@ -24,7 +25,7 @@ class TelecincoIE(InfoExtractor): 'info_dict': { 'id': '1876350223', 'title': 'Bacalao con kokotxas al pil-pil', - 'description': 'md5:1382dacd32dd4592d478cbdca458e5bb', + 'description': 'md5:716caf5601e25c3c5ab6605b1ae71529', }, 'playlist': [{ 'md5': 'adb28c37238b675dad0f042292f209a7', @@ -55,6 +56,26 @@ class TelecincoIE(InfoExtractor): 'description': 'md5:2771356ff7bfad9179c5f5cd954f1477', 'duration': 50, }, + }, { + # video in opening's content + 'url': 'https://www.telecinco.es/vivalavida/fiorella-sobrina-edmundo-arrocet-entrevista_18_2907195140.html', + 'info_dict': { + 'id': '2907195140', + 'title': 'La surrealista entrevista a la sobrina de Edmundo Arrocet: "No puedes venir aquí y tomarnos por tontos"', + 'description': 'md5:73f340a7320143d37ab895375b2bf13a', + }, + 'playlist': [{ + 'md5': 'adb28c37238b675dad0f042292f209a7', + 'info_dict': { + 'id': 'TpI2EttSDAReWpJ1o0NVh2', + 'ext': 'mp4', + 'title': 'La surrealista entrevista a la sobrina de Edmundo Arrocet: "No puedes venir aquí y tomarnos por tontos"', + 'duration': 1015, + }, + }], + 'params': { + 'skip_download': True, + }, }, { 'url': 'http://www.telecinco.es/informativos/nacional/Pablo_Iglesias-Informativos_Telecinco-entrevista-Pedro_Piqueras_2_1945155182.html', 'only_matching': True, @@ -138,14 +159,25 @@ class TelecincoIE(InfoExtractor): r'window\.\$REACTBASE_STATE\.article(?:_multisite)?\s*=\s*({.+})', webpage, 'article'), display_id)['article'] title = article.get('title') - description = clean_html(article.get('leadParagraph')) + description = clean_html(article.get('leadParagraph')) or '' if article.get('editorialType') != 'VID': entries = [] - for p in article.get('body', []): - content = p.get('content') - if p.get('type') != 'video' or not content: + body = [article.get('opening')] + body.extend(try_get(article, lambda x: x['body'], list) or []) + for p in body: + if not isinstance(p, dict): continue - entries.append(self._parse_content(content, url)) + content = p.get('content') + if not content: + continue + type_ = p.get('type') + if type_ == 'paragraph': + content_str = str_or_none(content) + if content_str: + description += content_str + continue + if type_ == 'video' and isinstance(content, dict): + entries.append(self._parse_content(content, url)) return self.playlist_result( entries, str_or_none(article.get('id')), title, description) content = article['opening']['content'] From 50d19895a1a3515d48dc952bf9280cbdc4f405f9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 1 Mar 2020 19:22:09 +0700 Subject: [PATCH 359/422] [franceculture] Fix extraction (closes #24204) --- youtube_dl/extractor/franceculture.py | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/franceculture.py b/youtube_dl/extractor/franceculture.py index b8fa17588..306b45fc9 100644 --- a/youtube_dl/extractor/franceculture.py +++ b/youtube_dl/extractor/franceculture.py @@ -31,7 +31,13 @@ class FranceCultureIE(InfoExtractor): webpage = self._download_webpage(url, display_id) video_data = extract_attributes(self._search_regex( - r'(?s)<div[^>]+class="[^"]*?(?:title-zone-diffusion|heading-zone-(?:wrapper|player-button))[^"]*?"[^>]*>.*?(<button[^>]+data-asset-source="[^"]+"[^>]+>)', + r'''(?sx) + (?: + </h1>| + <div[^>]+class="[^"]*?(?:title-zone-diffusion|heading-zone-(?:wrapper|player-button))[^"]*?"[^>]*> + ).*? + (<button[^>]+data-asset-source="[^"]+"[^>]+>) + ''', webpage, 'video data')) video_url = video_data['data-asset-source'] From b274e48d56cced250f5abbc88b4cda2e5b4338d0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 1 Mar 2020 20:04:48 +0700 Subject: [PATCH 360/422] [xhamster] Fix extraction (closes #24205) --- youtube_dl/extractor/xhamster.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index a5b94d279..0f7be6a7d 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -113,7 +113,7 @@ class XHamsterIE(InfoExtractor): display_id = mobj.group('display_id') or mobj.group('display_id_2') desktop_url = re.sub(r'^(https?://(?:.+?\.)?)m\.', r'\1', url) - webpage = self._download_webpage(desktop_url, video_id) + webpage, urlh = self._download_webpage_handle(desktop_url, video_id) error = self._html_search_regex( r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>', @@ -161,6 +161,9 @@ class XHamsterIE(InfoExtractor): 'ext': determine_ext(format_url, 'mp4'), 'height': get_height(quality), 'filesize': filesize, + 'http_headers': { + 'Referer': urlh.geturl(), + }, }) self._sort_formats(formats) From 170f5b7c27f2e68b0a0a4e799647cbe780399fbf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 1 Mar 2020 20:09:05 +0700 Subject: [PATCH 361/422] [ChangeLog] Actualize [ci skip] --- ChangeLog | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/ChangeLog b/ChangeLog index a6e2c3c19..9002a26e3 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,24 @@ +version <unreleased> + +Core +* [YoutubeDL] Force redirect URL to unicode on python 2 +- [options] Remove duplicate short option -v for --version (#24162) + +Extractors +* [xhamster] Fix extraction (#24205) +* [franceculture] Fix extraction (#24204) ++ [telecinco] Add support for article opening videos +* [telecinco] Fix extraction (#24195) +* [xtube] Fix metadata extraction (#21073, #22455) +* [youjizz] Fix extraction (#24181) +- Remove no longer needed compat_str around geturl +* [pornhd] Fix extraction (#24128) ++ [teachable] Add support for multiple videos per lecture (#24101) ++ [wistia] Add support for multiple generic embeds (#8347, 11385) +* [imdb] Fix extraction (#23443) +* [tv2dk:bornholm:play] Fix extraction (#24076) + + version 2020.02.16 Core From 669625a32cce386d0c19b5a0eea03707570a60d5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 1 Mar 2020 20:11:32 +0700 Subject: [PATCH 362/422] release 2020.03.01 --- .github/ISSUE_TEMPLATE/1_broken_site.md | 6 +++--- .github/ISSUE_TEMPLATE/2_site_support_request.md | 4 ++-- .github/ISSUE_TEMPLATE/3_site_feature_request.md | 4 ++-- .github/ISSUE_TEMPLATE/4_bug_report.md | 6 +++--- .github/ISSUE_TEMPLATE/5_feature_request.md | 4 ++-- ChangeLog | 2 +- youtube_dl/version.py | 2 +- 7 files changed, 14 insertions(+), 14 deletions(-) diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.md b/.github/ISSUE_TEMPLATE/1_broken_site.md index 716768242..0721d49c3 100644 --- a/.github/ISSUE_TEMPLATE/1_broken_site.md +++ b/.github/ISSUE_TEMPLATE/1_broken_site.md @@ -18,7 +18,7 @@ title: '' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.02.16. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.01. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape. - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates. @@ -26,7 +26,7 @@ Carefully read and work through this check list in order to prevent the most com --> - [ ] I'm reporting a broken site support -- [ ] I've verified that I'm running youtube-dl version **2020.02.16** +- [ ] I've verified that I'm running youtube-dl version **2020.03.01** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar issues including closed ones @@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2020.02.16 + [debug] youtube-dl version 2020.03.01 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/2_site_support_request.md b/.github/ISSUE_TEMPLATE/2_site_support_request.md index 3fd6a0bd6..1e67f724d 100644 --- a/.github/ISSUE_TEMPLATE/2_site_support_request.md +++ b/.github/ISSUE_TEMPLATE/2_site_support_request.md @@ -19,7 +19,7 @@ labels: 'site-support-request' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.02.16. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.01. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that site you are requesting is not dedicated to copyright infringement, see https://yt-dl.org/copyright-infringement. youtube-dl does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights. - Search the bugtracker for similar site support requests: http://yt-dl.org/search-issues. DO NOT post duplicates. @@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com --> - [ ] I'm reporting a new site support request -- [ ] I've verified that I'm running youtube-dl version **2020.02.16** +- [ ] I've verified that I'm running youtube-dl version **2020.03.01** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that none of provided URLs violate any copyrights - [ ] I've searched the bugtracker for similar site support requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/3_site_feature_request.md b/.github/ISSUE_TEMPLATE/3_site_feature_request.md index d160fcce9..1290b55c4 100644 --- a/.github/ISSUE_TEMPLATE/3_site_feature_request.md +++ b/.github/ISSUE_TEMPLATE/3_site_feature_request.md @@ -18,13 +18,13 @@ title: '' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.02.16. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.01. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Search the bugtracker for similar site feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates. - Finally, put x into all relevant boxes (like this [x]) --> - [ ] I'm reporting a site feature request -- [ ] I've verified that I'm running youtube-dl version **2020.02.16** +- [ ] I've verified that I'm running youtube-dl version **2020.03.01** - [ ] I've searched the bugtracker for similar site feature requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/4_bug_report.md b/.github/ISSUE_TEMPLATE/4_bug_report.md index f97644f65..3f006bef8 100644 --- a/.github/ISSUE_TEMPLATE/4_bug_report.md +++ b/.github/ISSUE_TEMPLATE/4_bug_report.md @@ -18,7 +18,7 @@ title: '' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.02.16. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.01. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape. - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates. @@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com --> - [ ] I'm reporting a broken site support issue -- [ ] I've verified that I'm running youtube-dl version **2020.02.16** +- [ ] I've verified that I'm running youtube-dl version **2020.03.01** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar bug reports including closed ones @@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2020.02.16 + [debug] youtube-dl version 2020.03.01 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/5_feature_request.md b/.github/ISSUE_TEMPLATE/5_feature_request.md index dedef6d53..202bb9b2f 100644 --- a/.github/ISSUE_TEMPLATE/5_feature_request.md +++ b/.github/ISSUE_TEMPLATE/5_feature_request.md @@ -19,13 +19,13 @@ labels: 'request' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.02.16. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.01. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Search the bugtracker for similar feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates. - Finally, put x into all relevant boxes (like this [x]) --> - [ ] I'm reporting a feature request -- [ ] I've verified that I'm running youtube-dl version **2020.02.16** +- [ ] I've verified that I'm running youtube-dl version **2020.03.01** - [ ] I've searched the bugtracker for similar feature requests including closed ones diff --git a/ChangeLog b/ChangeLog index 9002a26e3..1a676f4f2 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2020.03.01 Core * [YoutubeDL] Force redirect URL to unicode on python 2 diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 0163333ac..fabc1e543 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2020.02.16' +__version__ = '2020.03.01' From 1c45ff5572e0844b2ad26c2c0d477edc81e6b5b0 Mon Sep 17 00:00:00 2001 From: tsia <github@tsia.de> Date: Mon, 2 Mar 2020 19:27:40 +0100 Subject: [PATCH 363/422] [vimeo] Fix subtitles URLs (#24209) --- youtube_dl/extractor/vimeo.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 1da4ced96..8cd611e1e 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -33,6 +33,7 @@ from ..utils import ( unified_timestamp, unsmuggle_url, urlencode_postdata, + urljoin, unescapeHTML, ) @@ -191,7 +192,7 @@ class VimeoBaseInfoExtractor(InfoExtractor): for tt in text_tracks: subtitles[tt['lang']] = [{ 'ext': 'vtt', - 'url': 'https://vimeo.com' + tt['url'], + 'url': urljoin('https://vimeo.com', tt['url']), }] thumbnails = [] From 3b5399ce0f85f46ce856d47c725a437c72dcce6e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 3 Mar 2020 01:40:48 +0700 Subject: [PATCH 364/422] [servus] Add support for new URL schema (closes #23475, closes #23583, closes #24142) --- youtube_dl/extractor/servus.py | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/servus.py b/youtube_dl/extractor/servus.py index e579d42cf..9401bf2cf 100644 --- a/youtube_dl/extractor/servus.py +++ b/youtube_dl/extractor/servus.py @@ -7,9 +7,18 @@ from .common import InfoExtractor class ServusIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?servus\.com/(?:(?:at|de)/p/[^/]+|tv/videos)/(?P<id>[aA]{2}-\w+|\d+-\d+)' + _VALID_URL = r'''(?x) + https?:// + (?:www\.)? + (?: + servus\.com/(?:(?:at|de)/p/[^/]+|tv/videos)| + servustv\.com/videos + ) + /(?P<id>[aA]{2}-\w+|\d+-\d+) + ''' _TESTS = [{ - 'url': 'https://www.servus.com/de/p/Die-Gr%C3%BCnen-aus-Sicht-des-Volkes/AA-1T6VBU5PW1W12/', + # new URL schema + 'url': 'https://www.servustv.com/videos/aa-1t6vbu5pw1w12/', 'md5': '3e1dd16775aa8d5cbef23628cfffc1f4', 'info_dict': { 'id': 'AA-1T6VBU5PW1W12', @@ -18,6 +27,10 @@ class ServusIE(InfoExtractor): 'description': 'md5:1247204d85783afe3682644398ff2ec4', 'thumbnail': r're:^https?://.*\.jpg', } + }, { + # old URL schema + 'url': 'https://www.servus.com/de/p/Die-Gr%C3%BCnen-aus-Sicht-des-Volkes/AA-1T6VBU5PW1W12/', + 'only_matching': True, }, { 'url': 'https://www.servus.com/at/p/Wie-das-Leben-beginnt/1309984137314-381415152/', 'only_matching': True, From 0e30a7b9732dbecc63527df6037c5fbea964b1fd Mon Sep 17 00:00:00 2001 From: jxu <7989982+jxu@users.noreply.github.com> Date: Mon, 2 Mar 2020 13:46:00 -0500 Subject: [PATCH 365/422] [youtube:playlist] Fix tests (closes #23872) (#23885) --- youtube_dl/extractor/youtube.py | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index eacaa5ecd..e06290427 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -2495,20 +2495,23 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): _VIDEO_RE = _VIDEO_RE_TPL % r'(?P<id>[0-9A-Za-z_-]{11})' IE_NAME = 'youtube:playlist' _TESTS = [{ - 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', + 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', 'info_dict': { - 'title': 'ytdl test PL', - 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', + 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA', + 'uploader': 'Sergey M.', + 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', + 'title': 'youtube-dl public playlist', }, - 'playlist_count': 3, + 'playlist_count': 1, }, { - 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx', + 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', 'info_dict': { - 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx', - 'title': 'YDL_Empty_List', + 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA', + 'uploader': 'Sergey M.', + 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', + 'title': 'youtube-dl empty playlist', }, 'playlist_count': 0, - 'skip': 'This playlist is private', }, { 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.', 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', @@ -2518,7 +2521,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): 'uploader': 'Christiaan008', 'uploader_id': 'ChRiStIaAn008', }, - 'playlist_count': 95, + 'playlist_count': 96, }, { 'note': 'issue #673', 'url': 'PLBB231211A4F62143', From ac379fa236c01ed1d3601f013d755066b92709a4 Mon Sep 17 00:00:00 2001 From: 3risian <59593325+3risian@users.noreply.github.com> Date: Tue, 7 Jan 2020 18:34:51 +1100 Subject: [PATCH 366/422] [peertube] Improve extraction --- youtube_dl/extractor/peertube.py | 87 +++++++++++++++++++++++--------- 1 file changed, 64 insertions(+), 23 deletions(-) diff --git a/youtube_dl/extractor/peertube.py b/youtube_dl/extractor/peertube.py index d3a83ea2b..307712196 100644 --- a/youtube_dl/extractor/peertube.py +++ b/youtube_dl/extractor/peertube.py @@ -8,6 +8,7 @@ from ..compat import compat_str from ..utils import ( int_or_none, parse_resolution, + str_or_none, try_get, unified_timestamp, url_or_none, @@ -423,26 +424,30 @@ class PeerTubeIE(InfoExtractor): (?P<id>%s) ''' % (_INSTANCES_RE, _UUID_RE) _TESTS = [{ - 'url': 'https://peertube.cpy.re/videos/watch/2790feb0-8120-4e63-9af3-c943c69f5e6c', - 'md5': '80f24ff364cc9d333529506a263e7feb', + 'url': 'https://framatube.org/videos/watch/9c9de5e8-0a1e-484a-b099-e80766180a6d', + 'md5': '9bed8c0137913e17b86334e5885aacff', 'info_dict': { - 'id': '2790feb0-8120-4e63-9af3-c943c69f5e6c', + 'id': '9c9de5e8-0a1e-484a-b099-e80766180a6d', 'ext': 'mp4', - 'title': 'wow', - 'description': 'wow such video, so gif', + 'title': 'What is PeerTube?', + 'description': '**[Want to help to translate this video?](https://weblate.framasoft.org/projects/what-is-peertube-video/)**\r\n\r\n**Take back the control of your videos! [#JoinPeertube](https://joinpeertube.org)**\r\n*A decentralized video hosting network, based on free/libre software!*\r\n\r\n**Animation Produced by:** [LILA](https://libreart.info) - [ZeMarmot Team](https://film.zemarmot.net)\r\n*Directed by* Aryeom\r\n*Assistant* Jehan\r\n**Licence**: [CC-By-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0/)\r\n\r\n**Sponsored by** [Framasoft](https://framasoft.org)\r\n\r\n**Music**: [Red Step Forward](http://play.dogmazic.net/song.php?song_id=52491) - CC-By Ken Bushima\r\n\r\n**Movie Clip**: [Caminades 3: Llamigos](http://www.caminandes.com/) CC-By Blender Institute\r\n\r\n**Video sources**: https://gitlab.gnome.org/Jehan/what-is-peertube/', 'thumbnail': r're:https?://.*\.(?:jpg|png)', - 'timestamp': 1519297480, - 'upload_date': '20180222', - 'uploader': 'Luclu7', - 'uploader_id': '7fc42640-efdb-4505-a45d-a15b1a5496f1', - 'uploder_url': 'https://peertube.nsa.ovh/accounts/luclu7', - 'license': 'Unknown', - 'duration': 3, + 'timestamp': 1538391166, + 'upload_date': '20181001', + 'uploader': 'Framasoft', + 'uploader_id': '3', + 'uploader_url': 'https://framatube.org/accounts/framasoft', + 'channel': 'Les vidéos de Framasoft', + 'channel_id': '2', + 'channel_url': 'https://framatube.org/video-channels/bf54d359-cfad-4935-9d45-9d6be93f63e8', + 'language': 'en', + 'license': 'Attribution - Share Alike', + 'duration': 113, 'view_count': int, 'like_count': int, 'dislike_count': int, - 'tags': list, - 'categories': list, + 'tags': ['framasoft', 'peertube'], + 'categories': ['Science & Technology'], } }, { 'url': 'https://peertube.tamanoir.foucry.net/videos/watch/0b04f13d-1e18-4f1d-814e-4979aa7c9c44', @@ -484,6 +489,23 @@ class PeerTubeIE(InfoExtractor): entries = [peertube_url] return entries + def _get_subtitles(self, host, video_id): + video_captions = self._download_json( + 'https://%s/api/v1/videos/%s/captions' % (host, video_id), video_id, fatal=False) + if not isinstance(video_captions, dict): + return None + + subtitles = {} + for entry in video_captions.get('data'): + language_id = try_get(entry, lambda x: x['language']['id'], compat_str) + caption_path = str_or_none(entry.get('captionPath')) + if language_id and caption_path: + caption_url = urljoin('https://%s' % host, entry.get('captionPath')) + subtitles.setdefault(language_id, []).append({ + 'url': caption_url, + }) + return subtitles + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) host = mobj.group('host') or mobj.group('host_2') @@ -513,10 +535,25 @@ class PeerTubeIE(InfoExtractor): formats.append(f) self._sort_formats(formats) - def account_data(field): - return try_get(video, lambda x: x['account'][field], compat_str) + video_description = self._download_json( + 'https://%s/api/v1/videos/%s/description' % (host, video_id), video_id, fatal=False) - category = try_get(video, lambda x: x['category']['label'], compat_str) + description = None + if isinstance(video_description, dict): + description = str_or_none(video_description.get('description')) + + subtitles = self.extract_subtitles(host, video_id) + + def data(section, field, type_): + return try_get(video, lambda x: x[section][field], type_) + + def account_data(field, type_): + return data('account', field, type_) + + def channel_data(field, type_): + return data('channel', field, type_) + + category = data('category', 'label', compat_str) categories = [category] if category else None nsfw = video.get('nsfw') @@ -528,14 +565,17 @@ class PeerTubeIE(InfoExtractor): return { 'id': video_id, 'title': title, - 'description': video.get('description'), + 'description': description, 'thumbnail': urljoin(url, video.get('thumbnailPath')), 'timestamp': unified_timestamp(video.get('publishedAt')), - 'uploader': account_data('displayName'), - 'uploader_id': account_data('uuid'), - 'uploder_url': account_data('url'), - 'license': try_get( - video, lambda x: x['licence']['label'], compat_str), + 'uploader': account_data('displayName', compat_str), + 'uploader_id': str(account_data('id', int)), + 'uploader_url': url_or_none(account_data('url', compat_str)), + 'channel': channel_data('displayName', compat_str), + 'channel_id': str(channel_data('id', int)), + 'channel_url': url_or_none(channel_data('url', compat_str)), + 'language': data('language', 'id', compat_str), + 'license': data('licence', 'label', compat_str), 'duration': int_or_none(video.get('duration')), 'view_count': int_or_none(video.get('views')), 'like_count': int_or_none(video.get('likes')), @@ -544,4 +584,5 @@ class PeerTubeIE(InfoExtractor): 'tags': try_get(video, lambda x: x['tags'], list), 'categories': categories, 'formats': formats, + 'subtitles': subtitles } From 1e1c1960aa154a6e257e83e94e86ee6dc8b0b362 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 3 Mar 2020 03:01:23 +0700 Subject: [PATCH 367/422] [peertube] Fix issues and improve extraction (closes #23657) --- youtube_dl/extractor/peertube.py | 56 +++++++++++++++++++------------- 1 file changed, 34 insertions(+), 22 deletions(-) diff --git a/youtube_dl/extractor/peertube.py b/youtube_dl/extractor/peertube.py index 307712196..48fb95416 100644 --- a/youtube_dl/extractor/peertube.py +++ b/youtube_dl/extractor/peertube.py @@ -416,6 +416,7 @@ class PeerTubeIE(InfoExtractor): peertube\.cpy\.re )''' _UUID_RE = r'[\da-fA-F]{8}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{12}' + _API_BASE = 'https://%s/api/v1/videos/%s/%s' _VALID_URL = r'''(?x) (?: peertube:(?P<host>[^:]+):| @@ -430,7 +431,7 @@ class PeerTubeIE(InfoExtractor): 'id': '9c9de5e8-0a1e-484a-b099-e80766180a6d', 'ext': 'mp4', 'title': 'What is PeerTube?', - 'description': '**[Want to help to translate this video?](https://weblate.framasoft.org/projects/what-is-peertube-video/)**\r\n\r\n**Take back the control of your videos! [#JoinPeertube](https://joinpeertube.org)**\r\n*A decentralized video hosting network, based on free/libre software!*\r\n\r\n**Animation Produced by:** [LILA](https://libreart.info) - [ZeMarmot Team](https://film.zemarmot.net)\r\n*Directed by* Aryeom\r\n*Assistant* Jehan\r\n**Licence**: [CC-By-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0/)\r\n\r\n**Sponsored by** [Framasoft](https://framasoft.org)\r\n\r\n**Music**: [Red Step Forward](http://play.dogmazic.net/song.php?song_id=52491) - CC-By Ken Bushima\r\n\r\n**Movie Clip**: [Caminades 3: Llamigos](http://www.caminandes.com/) CC-By Blender Institute\r\n\r\n**Video sources**: https://gitlab.gnome.org/Jehan/what-is-peertube/', + 'description': 'md5:3fefb8dde2b189186ce0719fda6f7b10', 'thumbnail': r're:https?://.*\.(?:jpg|png)', 'timestamp': 1538391166, 'upload_date': '20181001', @@ -489,21 +490,29 @@ class PeerTubeIE(InfoExtractor): entries = [peertube_url] return entries - def _get_subtitles(self, host, video_id): - video_captions = self._download_json( - 'https://%s/api/v1/videos/%s/captions' % (host, video_id), video_id, fatal=False) - if not isinstance(video_captions, dict): - return None + def _call_api(self, host, video_id, path, note=None, errnote=None, fatal=True): + return self._download_json( + self._API_BASE % (host, video_id, path), video_id, + note=note, errnote=errnote, fatal=fatal) + def _get_subtitles(self, host, video_id): + captions = self._call_api( + host, video_id, 'captions', note='Downloading captions JSON', + fatal=False) + if not isinstance(captions, dict): + return + data = captions.get('data') + if not isinstance(data, list): + return subtitles = {} - for entry in video_captions.get('data'): - language_id = try_get(entry, lambda x: x['language']['id'], compat_str) - caption_path = str_or_none(entry.get('captionPath')) - if language_id and caption_path: - caption_url = urljoin('https://%s' % host, entry.get('captionPath')) - subtitles.setdefault(language_id, []).append({ - 'url': caption_url, - }) + for e in data: + language_id = try_get(e, lambda x: x['language']['id'], compat_str) + caption_url = urljoin('https://%s' % host, e.get('captionPath')) + if not caption_url: + continue + subtitles.setdefault(language_id or 'en', []).append({ + 'url': caption_url, + }) return subtitles def _real_extract(self, url): @@ -511,8 +520,8 @@ class PeerTubeIE(InfoExtractor): host = mobj.group('host') or mobj.group('host_2') video_id = mobj.group('id') - video = self._download_json( - 'https://%s/api/v1/videos/%s' % (host, video_id), video_id) + video = self._call_api( + host, video_id, '', note='Downloading video JSON') title = video['name'] @@ -535,12 +544,15 @@ class PeerTubeIE(InfoExtractor): formats.append(f) self._sort_formats(formats) - video_description = self._download_json( - 'https://%s/api/v1/videos/%s/description' % (host, video_id), video_id, fatal=False) + full_description = self._call_api( + host, video_id, 'description', note='Downloading description JSON', + fatal=False) description = None - if isinstance(video_description, dict): - description = str_or_none(video_description.get('description')) + if isinstance(full_description, dict): + description = str_or_none(full_description.get('description')) + if not description: + description = video.get('description') subtitles = self.extract_subtitles(host, video_id) @@ -569,10 +581,10 @@ class PeerTubeIE(InfoExtractor): 'thumbnail': urljoin(url, video.get('thumbnailPath')), 'timestamp': unified_timestamp(video.get('publishedAt')), 'uploader': account_data('displayName', compat_str), - 'uploader_id': str(account_data('id', int)), + 'uploader_id': str_or_none(account_data('id', int)), 'uploader_url': url_or_none(account_data('url', compat_str)), 'channel': channel_data('displayName', compat_str), - 'channel_id': str(channel_data('id', int)), + 'channel_id': str_or_none(channel_data('id', int)), 'channel_url': url_or_none(channel_data('url', compat_str)), 'language': data('language', 'id', compat_str), 'license': data('licence', 'label', compat_str), From 46cc54ca8f13c7b823c1a12446cdd76d060c74b6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 3 Mar 2020 06:23:39 +0700 Subject: [PATCH 368/422] [pornhub] Improve title extraction (closes #24184) --- youtube_dl/extractor/pornhub.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index b3251ccd9..b8f65af7c 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -189,10 +189,10 @@ class PornHubIE(PornHubBaseIE): # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying # on that anymore. title = self._html_search_meta( - 'twitter:title', webpage, default=None) or self._search_regex( - (r'<h1[^>]+class=["\']title["\'][^>]*>(?P<title>[^<]+)', - r'<div[^>]+data-video-title=(["\'])(?P<title>.+?)\1', - r'shareTitle\s*=\s*(["\'])(?P<title>.+?)\1'), + 'twitter:title', webpage, default=None) or self._html_search_regex( + (r'(?s)<h1[^>]+class=["\']title["\'][^>]*>(?P<title>.+?)</h1>', + r'<div[^>]+data-video-title=(["\'])(?P<title>(?:(?!\1).)+)\1', + r'shareTitle["\']\s*[=:]\s*(["\'])(?P<title>(?:(?!\1).)+)\1'), webpage, 'title', group='title') video_urls = [] From 12ee431676bb655f04c7dd416a73c1f142ed368d Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Tue, 3 Mar 2020 12:33:38 +0100 Subject: [PATCH 369/422] [vimeo] fix showcase password protected video extraction(closes #24224) --- youtube_dl/extractor/vimeo.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 8cd611e1e..cea686afc 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -585,7 +585,7 @@ class VimeoIE(VimeoBaseInfoExtractor): url = 'https://vimeo.com/' + video_id elif is_player: url = 'https://player.vimeo.com/video/' + video_id - elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')): + elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf', '/album/', '/showcase/')): url = 'https://vimeo.com/' + video_id try: From dc879c5a37dae588a5bb35d416635678356ad1b7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Thu, 5 Mar 2020 23:48:25 +0700 Subject: [PATCH 370/422] [youtube] Fix age-gated videos support without login (closes #24248) --- youtube_dl/extractor/youtube.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index e06290427..91b9d59c6 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1256,7 +1256,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): def _extract_signature_function(self, video_id, player_url, example_sig): id_m = re.match( - r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2,3}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$', + r'.*?[-.](?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2,3}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$', player_url) if not id_m: raise ExtractorError('Cannot identify player %r' % player_url) @@ -2035,7 +2035,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): else: player_version = self._search_regex( [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', - r'(?:www|player(?:_ias)?)-([^/]+)(?:/[a-z]{2,3}_[A-Z]{2})?/base\.js'], + r'(?:www|player(?:_ias)?)[-.]([^/]+)(?:/[a-z]{2,3}_[A-Z]{2})?/base\.js'], player_url, 'html5 player', fatal=False) player_desc = 'html5 player %s' % player_version From 5429d6a9cb2db07472735b4555eeec89ea4f3c87 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 6 Mar 2020 00:05:50 +0700 Subject: [PATCH 371/422] [youtube] Fix tests --- youtube_dl/extractor/youtube.py | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 91b9d59c6..d3e18a6ad 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -570,7 +570,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'upload_date': '20120506', 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]', 'alt_title': 'I Love It (feat. Charli XCX)', - 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8', + 'description': 'md5:19a2f98d9032b9311e686ed039564f63', 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli', 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop', 'iconic ep', 'iconic', 'love', 'it'], @@ -685,12 +685,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'id': 'nfWlot6h_JM', 'ext': 'm4a', 'title': 'Taylor Swift - Shake It Off', - 'description': 'md5:bec2185232c05479482cb5a9b82719bf', + 'description': 'md5:307195cd21ff7fa352270fe884570ef0', 'duration': 242, 'uploader': 'TaylorSwiftVEVO', 'uploader_id': 'TaylorSwiftVEVO', 'upload_date': '20140818', - 'creator': 'Taylor Swift', }, 'params': { 'youtube_include_dash_manifest': True, @@ -755,11 +754,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'upload_date': '20100430', 'uploader_id': 'deadmau5', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5', - 'creator': 'deadmau5', + 'creator': 'Dada Life, deadmau5', 'description': 'md5:12c56784b8032162bb936a5f76d55360', 'uploader': 'deadmau5', 'title': 'Deadmau5 - Some Chords (HD)', - 'alt_title': 'Some Chords', + 'alt_title': 'This Machine Kills Some Chords', }, 'expected_warnings': [ 'DASH manifest missing', @@ -1135,6 +1134,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'skip_download': True, 'youtube_include_dash_manifest': False, }, + 'skip': 'not actual anymore', }, { # Youtube Music Auto-generated description @@ -1145,8 +1145,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'title': 'Voyeur Girl', 'description': 'md5:7ae382a65843d6df2685993e90a8628f', 'upload_date': '20190312', - 'uploader': 'Various Artists - Topic', - 'uploader_id': 'UCVWKBi1ELZn0QX2CBLSkiyw', + 'uploader': 'Stephen - Topic', + 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA', 'artist': 'Stephen', 'track': 'Voyeur Girl', 'album': 'it\'s too much love to know my dear', @@ -1210,7 +1210,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'id': '-hcAI0g-f5M', 'ext': 'mp4', 'title': 'Put It On Me', - 'description': 'md5:93c55acc682ae7b0c668f2e34e1c069e', + 'description': 'md5:f6422397c07c4c907c6638e1fee380a5', 'upload_date': '20180426', 'uploader': 'Matt Maeson - Topic', 'uploader_id': 'UCnEkIGqtGcQMLk73Kp-Q5LQ', From 2db9ac228d0f7ccc1d8078d5e29030665f0e3239 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 6 Mar 2020 00:23:14 +0700 Subject: [PATCH 372/422] [ChangeLog] Actualize [ci skip] --- ChangeLog | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/ChangeLog b/ChangeLog index 1a676f4f2..00b97f965 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,14 @@ +version <unreleased> + +Extractors +* [youtube] Fix age-gated videos support without login (#24248) +* [vimeo] Fix showcase password protected video extraction (#24224) +* [pornhub] Improve title extraction (#24184) +* [peertube] Improve extraction (#23657) ++ [servus] Add support for new URL schema (#23475, #23583, #24142) +* [vimeo] Fix subtitles URLs (#24209) + + version 2020.03.01 Core From 34525a3885946bbbdb2bfda85f3dcc67c66018f6 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 6 Mar 2020 00:25:43 +0700 Subject: [PATCH 373/422] release 2020.03.06 --- .github/ISSUE_TEMPLATE/1_broken_site.md | 6 +++--- .github/ISSUE_TEMPLATE/2_site_support_request.md | 4 ++-- .github/ISSUE_TEMPLATE/3_site_feature_request.md | 4 ++-- .github/ISSUE_TEMPLATE/4_bug_report.md | 6 +++--- .github/ISSUE_TEMPLATE/5_feature_request.md | 4 ++-- ChangeLog | 2 +- youtube_dl/version.py | 2 +- 7 files changed, 14 insertions(+), 14 deletions(-) diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.md b/.github/ISSUE_TEMPLATE/1_broken_site.md index 0721d49c3..444a86ee3 100644 --- a/.github/ISSUE_TEMPLATE/1_broken_site.md +++ b/.github/ISSUE_TEMPLATE/1_broken_site.md @@ -18,7 +18,7 @@ title: '' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.01. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.06. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape. - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates. @@ -26,7 +26,7 @@ Carefully read and work through this check list in order to prevent the most com --> - [ ] I'm reporting a broken site support -- [ ] I've verified that I'm running youtube-dl version **2020.03.01** +- [ ] I've verified that I'm running youtube-dl version **2020.03.06** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar issues including closed ones @@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2020.03.01 + [debug] youtube-dl version 2020.03.06 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/2_site_support_request.md b/.github/ISSUE_TEMPLATE/2_site_support_request.md index 1e67f724d..a1c69a45b 100644 --- a/.github/ISSUE_TEMPLATE/2_site_support_request.md +++ b/.github/ISSUE_TEMPLATE/2_site_support_request.md @@ -19,7 +19,7 @@ labels: 'site-support-request' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.01. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.06. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that site you are requesting is not dedicated to copyright infringement, see https://yt-dl.org/copyright-infringement. youtube-dl does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights. - Search the bugtracker for similar site support requests: http://yt-dl.org/search-issues. DO NOT post duplicates. @@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com --> - [ ] I'm reporting a new site support request -- [ ] I've verified that I'm running youtube-dl version **2020.03.01** +- [ ] I've verified that I'm running youtube-dl version **2020.03.06** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that none of provided URLs violate any copyrights - [ ] I've searched the bugtracker for similar site support requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/3_site_feature_request.md b/.github/ISSUE_TEMPLATE/3_site_feature_request.md index 1290b55c4..d391b6d6b 100644 --- a/.github/ISSUE_TEMPLATE/3_site_feature_request.md +++ b/.github/ISSUE_TEMPLATE/3_site_feature_request.md @@ -18,13 +18,13 @@ title: '' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.01. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.06. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Search the bugtracker for similar site feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates. - Finally, put x into all relevant boxes (like this [x]) --> - [ ] I'm reporting a site feature request -- [ ] I've verified that I'm running youtube-dl version **2020.03.01** +- [ ] I've verified that I'm running youtube-dl version **2020.03.06** - [ ] I've searched the bugtracker for similar site feature requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/4_bug_report.md b/.github/ISSUE_TEMPLATE/4_bug_report.md index 3f006bef8..7422446b0 100644 --- a/.github/ISSUE_TEMPLATE/4_bug_report.md +++ b/.github/ISSUE_TEMPLATE/4_bug_report.md @@ -18,7 +18,7 @@ title: '' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.01. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.06. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape. - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates. @@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com --> - [ ] I'm reporting a broken site support issue -- [ ] I've verified that I'm running youtube-dl version **2020.03.01** +- [ ] I've verified that I'm running youtube-dl version **2020.03.06** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar bug reports including closed ones @@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2020.03.01 + [debug] youtube-dl version 2020.03.06 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/5_feature_request.md b/.github/ISSUE_TEMPLATE/5_feature_request.md index 202bb9b2f..247d3594d 100644 --- a/.github/ISSUE_TEMPLATE/5_feature_request.md +++ b/.github/ISSUE_TEMPLATE/5_feature_request.md @@ -19,13 +19,13 @@ labels: 'request' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.01. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.06. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Search the bugtracker for similar feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates. - Finally, put x into all relevant boxes (like this [x]) --> - [ ] I'm reporting a feature request -- [ ] I've verified that I'm running youtube-dl version **2020.03.01** +- [ ] I've verified that I'm running youtube-dl version **2020.03.06** - [ ] I've searched the bugtracker for similar feature requests including closed ones diff --git a/ChangeLog b/ChangeLog index 00b97f965..0efae7d9e 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2020.03.06 Extractors * [youtube] Fix age-gated videos support without login (#24248) diff --git a/youtube_dl/version.py b/youtube_dl/version.py index fabc1e543..56330ea2e 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2020.03.01' +__version__ = '2020.03.06' From 0ec9d4e565c1471c1234634bb3be0c7c7662d864 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Fri, 6 Mar 2020 20:12:35 +0100 Subject: [PATCH 374/422] [nhk] update API version(closes #24270) --- youtube_dl/extractor/nhk.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/nhk.py b/youtube_dl/extractor/nhk.py index 6a2c6cb7b..d2cbc9f54 100644 --- a/youtube_dl/extractor/nhk.py +++ b/youtube_dl/extractor/nhk.py @@ -31,7 +31,7 @@ class NhkVodIE(InfoExtractor): 'url': 'https://www3.nhk.or.jp/nhkworld/fr/ondemand/audio/plugin-20190404-1/', 'only_matching': True, }] - _API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sod%slist/v7/episode/%s/%s/all%s.json' + _API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sod%slist/v7a/episode/%s/%s/all%s.json' def _real_extract(self, url): lang, m_type, episode_id = re.match(self._VALID_URL, url).groups() From f93abcf1da5aa1ca122896254bdec3a3c831ac24 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 8 Mar 2020 05:09:02 +0700 Subject: [PATCH 375/422] [youtube] Improve extraction in 429 error conditions (closes #24283) --- youtube_dl/extractor/youtube.py | 23 +++++++++++++++++------ 1 file changed, 17 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index d3e18a6ad..9cbdc7ac5 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1790,11 +1790,19 @@ class YoutubeIE(YoutubeBaseInfoExtractor): query['el'] = el if sts: query['sts'] = sts - video_info_webpage = self._download_webpage( - '%s://www.youtube.com/get_video_info' % proto, - video_id, note=False, - errnote='unable to download video info webpage', - fatal=False, query=query) + try: + video_info_webpage = self._download_webpage( + '%s://www.youtube.com/get_video_info' % proto, + video_id, note=False, + errnote='unable to download video info webpage', + query=query) + except ExtractorError as e: + # Skip further retries if we get 429 since solving + # captcha only unblocks access to website but + # not get_video_info end point + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 429: + break + continue if not video_info_webpage: continue get_video_info = compat_parse_qs(video_info_webpage) @@ -1833,13 +1841,16 @@ class YoutubeIE(YoutubeBaseInfoExtractor): if messages: return '\n'.join(messages) - if not video_info: + if not video_info and not player_response: unavailable_message = extract_unavailable_message() if not unavailable_message: unavailable_message = 'Unable to extract video data' raise ExtractorError( 'YouTube said: %s' % unavailable_message, expected=True, video_id=video_id) + if not isinstance(video_info, dict): + video_info = {} + video_details = try_get( player_response, lambda x: x['videoDetails'], dict) or {} From d332ec725db5b1102473a75b9fc3212913bda618 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 8 Mar 2020 05:37:47 +0700 Subject: [PATCH 376/422] [youtube] Improve age-gated videos extraction in 429 error conditions (refs #24283) --- youtube_dl/extractor/youtube.py | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 9cbdc7ac5..906988e6f 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1726,6 +1726,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): embed_webpage = None if re.search(r'player-age-gate-content">', video_webpage) is not None: age_gate = True + video_info = None # We simulate the access to the video from www.youtube.com/v/{video_id} # this can be viewed without login into Youtube url = proto + '://www.youtube.com/embed/%s' % video_id @@ -1737,15 +1738,19 @@ class YoutubeIE(YoutubeBaseInfoExtractor): r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''), }) video_info_url = proto + '://www.youtube.com/get_video_info?' + data - video_info_webpage = self._download_webpage( - video_info_url, video_id, - note='Refetching age-gated info webpage', - errnote='unable to download video info webpage') - video_info = compat_parse_qs(video_info_webpage) - pl_response = video_info.get('player_response', [None])[0] - player_response = extract_player_response(pl_response, video_id) - add_dash_mpd(video_info) - view_count = extract_view_count(video_info) + try: + video_info_webpage = self._download_webpage( + video_info_url, video_id, + note='Refetching age-gated info webpage', + errnote='unable to download video info webpage') + except ExtractorError: + video_info_webpage = None + if video_info_webpage: + video_info = compat_parse_qs(video_info_webpage) + pl_response = video_info.get('player_response', [None])[0] + player_response = extract_player_response(pl_response, video_id) + add_dash_mpd(video_info) + view_count = extract_view_count(video_info) else: age_gate = False video_info = None From 43ebf77df3bbd93dbbd0336b0243d8d50895ab72 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 8 Mar 2020 08:34:17 +0700 Subject: [PATCH 377/422] [youtube] Remove outdated code Additional get_video_info requests don't seem to provide any extra itags any longer --- youtube_dl/extractor/youtube.py | 108 ++++++-------------------------- 1 file changed, 18 insertions(+), 90 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 906988e6f..908defecd 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -29,7 +29,6 @@ from ..compat import ( from ..utils import ( bool_or_none, clean_html, - dict_get, error_to_compat_str, extract_attributes, ExtractorError, @@ -1708,9 +1707,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): def extract_view_count(v_info): return int_or_none(try_get(v_info, lambda x: x['view_count'][0])) - def extract_token(v_info): - return dict_get(v_info, ('account_playback_token', 'accountPlaybackToken', 'token')) - def extract_player_response(player_response, video_id): pl_response = str_or_none(player_response) if not pl_response: @@ -1723,10 +1719,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): player_response = {} # Get video info + video_info = {} embed_webpage = None if re.search(r'player-age-gate-content">', video_webpage) is not None: age_gate = True - video_info = None # We simulate the access to the video from www.youtube.com/v/{video_id} # this can be viewed without login into Youtube url = proto + '://www.youtube.com/embed/%s' % video_id @@ -1753,8 +1749,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): view_count = extract_view_count(video_info) else: age_gate = False - video_info = None - sts = None # Try looking directly into the video webpage ytplayer_config = self._get_ytplayer_config(video_id, video_webpage) if ytplayer_config: @@ -1771,69 +1765,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor): args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid']) if args.get('livestream') == '1' or args.get('live_playback') == 1: is_live = True - sts = ytplayer_config.get('sts') if not player_response: player_response = extract_player_response(args.get('player_response'), video_id) if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True): add_dash_mpd_pr(player_response) - # We also try looking in get_video_info since it may contain different dashmpd - # URL that points to a DASH manifest with possibly different itag set (some itags - # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH - # manifest pointed by get_video_info's dashmpd). - # The general idea is to take a union of itags of both DASH manifests (for example - # video with such 'manifest behavior' see https://github.com/ytdl-org/youtube-dl/issues/6093) - self.report_video_info_webpage_download(video_id) - for el in ('embedded', 'detailpage', 'vevo', ''): - query = { - 'video_id': video_id, - 'ps': 'default', - 'eurl': '', - 'gl': 'US', - 'hl': 'en', - } - if el: - query['el'] = el - if sts: - query['sts'] = sts - try: - video_info_webpage = self._download_webpage( - '%s://www.youtube.com/get_video_info' % proto, - video_id, note=False, - errnote='unable to download video info webpage', - query=query) - except ExtractorError as e: - # Skip further retries if we get 429 since solving - # captcha only unblocks access to website but - # not get_video_info end point - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 429: - break - continue - if not video_info_webpage: - continue - get_video_info = compat_parse_qs(video_info_webpage) - if not player_response: - pl_response = get_video_info.get('player_response', [None])[0] - player_response = extract_player_response(pl_response, video_id) - add_dash_mpd(get_video_info) - if view_count is None: - view_count = extract_view_count(get_video_info) - if not video_info: - video_info = get_video_info - get_token = extract_token(get_video_info) - if get_token: - # Different get_video_info requests may report different results, e.g. - # some may report video unavailability, but some may serve it without - # any complaint (see https://github.com/ytdl-org/youtube-dl/issues/7362, - # the original webpage as well as el=info and el=embedded get_video_info - # requests report video unavailability due to geo restriction while - # el=detailpage succeeds and returns valid data). This is probably - # due to YouTube measures against IP ranges of hosting providers. - # Working around by preferring the first succeeded video_info containing - # the token if no such video_info yet was found. - token = extract_token(video_info) - if not token: - video_info = get_video_info - break def extract_unavailable_message(): messages = [] @@ -2408,30 +2343,23 @@ class YoutubeIE(YoutubeBaseInfoExtractor): f['stretched_ratio'] = ratio if not formats: - token = extract_token(video_info) - if not token: - if 'reason' in video_info: - if 'The uploader has not made this video available in your country.' in video_info['reason']: - regions_allowed = self._html_search_meta( - 'regionsAllowed', video_webpage, default=None) - countries = regions_allowed.split(',') if regions_allowed else None - self.raise_geo_restricted( - msg=video_info['reason'][0], countries=countries) - reason = video_info['reason'][0] - if 'Invalid parameters' in reason: - unavailable_message = extract_unavailable_message() - if unavailable_message: - reason = unavailable_message - raise ExtractorError( - 'YouTube said: %s' % reason, - expected=True, video_id=video_id) - else: - raise ExtractorError( - '"token" parameter not in video info for unknown reason', - video_id=video_id) - - if not formats and (video_info.get('license_info') or try_get(player_response, lambda x: x['streamingData']['licenseInfos'])): - raise ExtractorError('This video is DRM protected.', expected=True) + if 'reason' in video_info: + if 'The uploader has not made this video available in your country.' in video_info['reason']: + regions_allowed = self._html_search_meta( + 'regionsAllowed', video_webpage, default=None) + countries = regions_allowed.split(',') if regions_allowed else None + self.raise_geo_restricted( + msg=video_info['reason'][0], countries=countries) + reason = video_info['reason'][0] + if 'Invalid parameters' in reason: + unavailable_message = extract_unavailable_message() + if unavailable_message: + reason = unavailable_message + raise ExtractorError( + 'YouTube said: %s' % reason, + expected=True, video_id=video_id) + if video_info.get('license_info') or try_get(player_response, lambda x: x['streamingData']['licenseInfos']): + raise ExtractorError('This video is DRM protected.', expected=True) self._sort_formats(formats) From ea782aca520ff17fbf32771bfcfd9cbd36123900 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 8 Mar 2020 09:17:17 +0700 Subject: [PATCH 378/422] [README.md] Clarify 429 error --- README.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 01f975958..4f54a5240 100644 --- a/README.md +++ b/README.md @@ -835,7 +835,9 @@ In February 2015, the new YouTube player contained a character sequence in a str ### HTTP Error 429: Too Many Requests or 402: Payment Required -These two error codes indicate that the service is blocking your IP address because of overuse. Contact the service and ask them to unblock your IP address, or - if you have acquired a whitelisted IP address already - use the [`--proxy` or `--source-address` options](#network-options) to select another IP address. +These two error codes indicate that the service is blocking your IP address because of overuse. Usually this is a soft block meaning that you can gain access again after solving CAPTCHA. Just open a browser and solve a CAPTCHA the service suggests you and after that [pass cookies](#how-do-i-pass-cookies-to-youtube-dl) to youtube-dl. Note that if your machine has multiple external IPs then you should also pass exactly the same IP you've used for solving CAPTCHA with [`--source-address`](#network-options). Also you may need to pass a `User-Agent` HTTP header of your browser with [`--user-agent`](#workarounds). + +If this is not the case (no CAPTCHA suggested to solve by the service) then you can contact the service and ask them to unblock your IP address, or - if you have acquired a whitelisted IP address already - use the [`--proxy` or `--source-address` options](#network-options) to select another IP address. ### SyntaxError: Non-ASCII character From fa9b8c662808a50605bb05f90af101e13b30fce6 Mon Sep 17 00:00:00 2001 From: Tristan Waddington <tristan.waddington@gmail.com> Date: Sun, 8 Mar 2020 04:00:25 -0700 Subject: [PATCH 379/422] [pornhub] Add support for pornhubpremium.com (#24288) --- youtube_dl/extractor/pornhub.py | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index b8f65af7c..3567a3283 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -52,7 +52,7 @@ class PornHubIE(PornHubBaseIE): _VALID_URL = r'''(?x) https?:// (?: - (?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)| + (?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)| (?:www\.)?thumbzilla\.com/video/ ) (?P<id>[\da-z]+) @@ -149,6 +149,9 @@ class PornHubIE(PornHubBaseIE): }, { 'url': 'https://www.pornhub.net/view_video.php?viewkey=203640933', 'only_matching': True, + }, { + 'url': 'https://www.pornhubpremium.com/view_video.php?viewkey=ph5e4acdae54a82', + 'only_matching': True, }] @staticmethod @@ -166,6 +169,13 @@ class PornHubIE(PornHubBaseIE): host = mobj.group('host') or 'pornhub.com' video_id = mobj.group('id') + if 'premium' in host: + if not self._downloader.params.get('cookiefile'): + raise ExtractorError( + 'PornHub Premium requires authentication.' + ' You may want to use --cookies.', + expected=True) + self._set_cookie(host, 'age_verified', '1') def dl_webpage(platform): @@ -405,7 +415,7 @@ class PornHubPlaylistBaseIE(PornHubBaseIE): class PornHubUserIE(PornHubPlaylistBaseIE): - _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?pornhub\.(?:com|net)/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)' + _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)' _TESTS = [{ 'url': 'https://www.pornhub.com/model/zoe_ph', 'playlist_mincount': 118, @@ -473,7 +483,7 @@ class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE): class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE): - _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?P<id>(?:[^/]+/)*[^/?#&]+)' + _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net))/(?P<id>(?:[^/]+/)*[^/?#&]+)' _TESTS = [{ 'url': 'https://www.pornhub.com/model/zoe_ph/videos', 'only_matching': True, @@ -588,7 +598,7 @@ class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE): class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE): - _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)' + _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)' _TESTS = [{ 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload', 'info_dict': { From cff99c91d150df2a4e21962a3ca8d4ae94533b8c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 8 Mar 2020 17:52:19 +0700 Subject: [PATCH 380/422] [utils] Add support for cookies with spaces used instead of tabs --- test/test_YoutubeDLCookieJar.py | 14 +++++++++----- test/testdata/cookies/cookie_file_with_spaces.txt | 5 +++++ youtube_dl/utils.py | 5 +++++ 3 files changed, 19 insertions(+), 5 deletions(-) create mode 100644 test/testdata/cookies/cookie_file_with_spaces.txt diff --git a/test/test_YoutubeDLCookieJar.py b/test/test_YoutubeDLCookieJar.py index f959798de..f833efac5 100644 --- a/test/test_YoutubeDLCookieJar.py +++ b/test/test_YoutubeDLCookieJar.py @@ -14,6 +14,9 @@ from youtube_dl.utils import YoutubeDLCookieJar class TestYoutubeDLCookieJar(unittest.TestCase): + def __assert_cookie_has_value(self, cookiejar, key): + self.assertEqual(cookiejar._cookies['www.foobar.foobar']['/'][key].value, key + '_VALUE') + def test_keep_session_cookies(self): cookiejar = YoutubeDLCookieJar('./test/testdata/cookies/session_cookies.txt') cookiejar.load(ignore_discard=True, ignore_expires=True) @@ -32,12 +35,13 @@ class TestYoutubeDLCookieJar(unittest.TestCase): def test_strip_httponly_prefix(self): cookiejar = YoutubeDLCookieJar('./test/testdata/cookies/httponly_cookies.txt') cookiejar.load(ignore_discard=True, ignore_expires=True) + self.__assert_cookie_has_value(cookiejar, 'HTTPONLY_COOKIE') + self.__assert_cookie_has_value(cookiejar, 'JS_ACCESSIBLE_COOKIE') - def assert_cookie_has_value(key): - self.assertEqual(cookiejar._cookies['www.foobar.foobar']['/'][key].value, key + '_VALUE') - - assert_cookie_has_value('HTTPONLY_COOKIE') - assert_cookie_has_value('JS_ACCESSIBLE_COOKIE') + def test_convert_spaces_to_tabs(self): + cookiejar = YoutubeDLCookieJar('./test/testdata/cookies/cookie_file_with_spaces.txt') + cookiejar.load(ignore_discard=True, ignore_expires=True) + self.__assert_cookie_has_value(cookiejar, 'COOKIE') if __name__ == '__main__': diff --git a/test/testdata/cookies/cookie_file_with_spaces.txt b/test/testdata/cookies/cookie_file_with_spaces.txt new file mode 100644 index 000000000..6fda35fa0 --- /dev/null +++ b/test/testdata/cookies/cookie_file_with_spaces.txt @@ -0,0 +1,5 @@ +# Netscape HTTP Cookie File +# http://curl.haxx.se/rfc/cookie_spec.html +# This is a generated file! Do not edit. + +www.foobar.foobar FALSE / TRUE 2147483647 COOKIE COOKIE_VALUE diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 8ccf25489..93d1dec05 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -2752,6 +2752,11 @@ class YoutubeDLCookieJar(compat_cookiejar.MozillaCookieJar): for line in f: if line.startswith(self._HTTPONLY_PREFIX): line = line[len(self._HTTPONLY_PREFIX):] + # Cookie file may contain spaces instead of tabs. + # Replace all spaces with tabs to make such cookie files work + # with MozillaCookieJar. + if not line.startswith('#'): + line = re.sub(r' +', r'\t', line) cf.write(compat_str(line)) cf.seek(0) self._really_load(cf, filename, ignore_discard, ignore_expires) From 434f57304683552b5d3c1a76130319ebd8139340 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 8 Mar 2020 18:16:17 +0700 Subject: [PATCH 381/422] [ChangeLog] Actualize [ci skip] --- ChangeLog | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/ChangeLog b/ChangeLog index 0efae7d9e..12815f3e1 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,15 @@ +version <unreleased> + +Core ++ [utils] Add support for cookie files with spaces + +Extractors ++ [pornhub] Add support for pornhubpremium.com (#24288) +- [youtube] Remove outdated code and unnecessary requests +* [youtube] Improve extraction in 429 HTTP error conditions (#24283) +* [nhk] Update API version (#24270) + + version 2020.03.06 Extractors From 68fa15155f40f7d646079e6649df03696a5e7d4b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 8 Mar 2020 18:27:20 +0700 Subject: [PATCH 382/422] release 2020.03.08 --- .github/ISSUE_TEMPLATE/1_broken_site.md | 6 +++--- .github/ISSUE_TEMPLATE/2_site_support_request.md | 4 ++-- .github/ISSUE_TEMPLATE/3_site_feature_request.md | 4 ++-- .github/ISSUE_TEMPLATE/4_bug_report.md | 6 +++--- .github/ISSUE_TEMPLATE/5_feature_request.md | 4 ++-- ChangeLog | 2 +- youtube_dl/version.py | 2 +- 7 files changed, 14 insertions(+), 14 deletions(-) diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.md b/.github/ISSUE_TEMPLATE/1_broken_site.md index 444a86ee3..d82ff9111 100644 --- a/.github/ISSUE_TEMPLATE/1_broken_site.md +++ b/.github/ISSUE_TEMPLATE/1_broken_site.md @@ -18,7 +18,7 @@ title: '' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.06. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.08. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape. - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates. @@ -26,7 +26,7 @@ Carefully read and work through this check list in order to prevent the most com --> - [ ] I'm reporting a broken site support -- [ ] I've verified that I'm running youtube-dl version **2020.03.06** +- [ ] I've verified that I'm running youtube-dl version **2020.03.08** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar issues including closed ones @@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2020.03.06 + [debug] youtube-dl version 2020.03.08 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/2_site_support_request.md b/.github/ISSUE_TEMPLATE/2_site_support_request.md index a1c69a45b..04b350f76 100644 --- a/.github/ISSUE_TEMPLATE/2_site_support_request.md +++ b/.github/ISSUE_TEMPLATE/2_site_support_request.md @@ -19,7 +19,7 @@ labels: 'site-support-request' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.06. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.08. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that site you are requesting is not dedicated to copyright infringement, see https://yt-dl.org/copyright-infringement. youtube-dl does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights. - Search the bugtracker for similar site support requests: http://yt-dl.org/search-issues. DO NOT post duplicates. @@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com --> - [ ] I'm reporting a new site support request -- [ ] I've verified that I'm running youtube-dl version **2020.03.06** +- [ ] I've verified that I'm running youtube-dl version **2020.03.08** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that none of provided URLs violate any copyrights - [ ] I've searched the bugtracker for similar site support requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/3_site_feature_request.md b/.github/ISSUE_TEMPLATE/3_site_feature_request.md index d391b6d6b..6f17ad7bc 100644 --- a/.github/ISSUE_TEMPLATE/3_site_feature_request.md +++ b/.github/ISSUE_TEMPLATE/3_site_feature_request.md @@ -18,13 +18,13 @@ title: '' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.06. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.08. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Search the bugtracker for similar site feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates. - Finally, put x into all relevant boxes (like this [x]) --> - [ ] I'm reporting a site feature request -- [ ] I've verified that I'm running youtube-dl version **2020.03.06** +- [ ] I've verified that I'm running youtube-dl version **2020.03.08** - [ ] I've searched the bugtracker for similar site feature requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/4_bug_report.md b/.github/ISSUE_TEMPLATE/4_bug_report.md index 7422446b0..efb179ea5 100644 --- a/.github/ISSUE_TEMPLATE/4_bug_report.md +++ b/.github/ISSUE_TEMPLATE/4_bug_report.md @@ -18,7 +18,7 @@ title: '' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.06. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.08. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape. - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates. @@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com --> - [ ] I'm reporting a broken site support issue -- [ ] I've verified that I'm running youtube-dl version **2020.03.06** +- [ ] I've verified that I'm running youtube-dl version **2020.03.08** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar bug reports including closed ones @@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2020.03.06 + [debug] youtube-dl version 2020.03.08 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/5_feature_request.md b/.github/ISSUE_TEMPLATE/5_feature_request.md index 247d3594d..cf4874bcc 100644 --- a/.github/ISSUE_TEMPLATE/5_feature_request.md +++ b/.github/ISSUE_TEMPLATE/5_feature_request.md @@ -19,13 +19,13 @@ labels: 'request' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.06. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2020.03.08. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Search the bugtracker for similar feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates. - Finally, put x into all relevant boxes (like this [x]) --> - [ ] I'm reporting a feature request -- [ ] I've verified that I'm running youtube-dl version **2020.03.06** +- [ ] I've verified that I'm running youtube-dl version **2020.03.08** - [ ] I've searched the bugtracker for similar feature requests including closed ones diff --git a/ChangeLog b/ChangeLog index 12815f3e1..84b43c642 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2020.03.08 Core + [utils] Add support for cookie files with spaces diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 56330ea2e..0f768f7c1 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2020.03.06' +__version__ = '2020.03.08' From 042b66493398dd8c3bb31216e3f828b98716810d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 10 Mar 2020 04:51:20 +0700 Subject: [PATCH 383/422] Revert "[utils] Add support for cookies with spaces used instead of tabs" According to [1] TABs must be used as separators between fields. Files produces by some tools with spaces as separators are considered malformed. 1. https://curl.haxx.se/docs/http-cookies.html This reverts commit cff99c91d150df2a4e21962a3ca8d4ae94533b8c. --- test/test_YoutubeDLCookieJar.py | 14 +++++--------- test/testdata/cookies/cookie_file_with_spaces.txt | 5 ----- youtube_dl/utils.py | 5 ----- 3 files changed, 5 insertions(+), 19 deletions(-) delete mode 100644 test/testdata/cookies/cookie_file_with_spaces.txt diff --git a/test/test_YoutubeDLCookieJar.py b/test/test_YoutubeDLCookieJar.py index f833efac5..f959798de 100644 --- a/test/test_YoutubeDLCookieJar.py +++ b/test/test_YoutubeDLCookieJar.py @@ -14,9 +14,6 @@ from youtube_dl.utils import YoutubeDLCookieJar class TestYoutubeDLCookieJar(unittest.TestCase): - def __assert_cookie_has_value(self, cookiejar, key): - self.assertEqual(cookiejar._cookies['www.foobar.foobar']['/'][key].value, key + '_VALUE') - def test_keep_session_cookies(self): cookiejar = YoutubeDLCookieJar('./test/testdata/cookies/session_cookies.txt') cookiejar.load(ignore_discard=True, ignore_expires=True) @@ -35,13 +32,12 @@ class TestYoutubeDLCookieJar(unittest.TestCase): def test_strip_httponly_prefix(self): cookiejar = YoutubeDLCookieJar('./test/testdata/cookies/httponly_cookies.txt') cookiejar.load(ignore_discard=True, ignore_expires=True) - self.__assert_cookie_has_value(cookiejar, 'HTTPONLY_COOKIE') - self.__assert_cookie_has_value(cookiejar, 'JS_ACCESSIBLE_COOKIE') - def test_convert_spaces_to_tabs(self): - cookiejar = YoutubeDLCookieJar('./test/testdata/cookies/cookie_file_with_spaces.txt') - cookiejar.load(ignore_discard=True, ignore_expires=True) - self.__assert_cookie_has_value(cookiejar, 'COOKIE') + def assert_cookie_has_value(key): + self.assertEqual(cookiejar._cookies['www.foobar.foobar']['/'][key].value, key + '_VALUE') + + assert_cookie_has_value('HTTPONLY_COOKIE') + assert_cookie_has_value('JS_ACCESSIBLE_COOKIE') if __name__ == '__main__': diff --git a/test/testdata/cookies/cookie_file_with_spaces.txt b/test/testdata/cookies/cookie_file_with_spaces.txt deleted file mode 100644 index 6fda35fa0..000000000 --- a/test/testdata/cookies/cookie_file_with_spaces.txt +++ /dev/null @@ -1,5 +0,0 @@ -# Netscape HTTP Cookie File -# http://curl.haxx.se/rfc/cookie_spec.html -# This is a generated file! Do not edit. - -www.foobar.foobar FALSE / TRUE 2147483647 COOKIE COOKIE_VALUE diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 93d1dec05..8ccf25489 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -2752,11 +2752,6 @@ class YoutubeDLCookieJar(compat_cookiejar.MozillaCookieJar): for line in f: if line.startswith(self._HTTPONLY_PREFIX): line = line[len(self._HTTPONLY_PREFIX):] - # Cookie file may contain spaces instead of tabs. - # Replace all spaces with tabs to make such cookie files work - # with MozillaCookieJar. - if not line.startswith('#'): - line = re.sub(r' +', r'\t', line) cf.write(compat_str(line)) cf.seek(0) self._really_load(cf, filename, ignore_discard, ignore_expires) From f1a8511f7b5bbbd9e64f597c87791ad3b4310efc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 10 Mar 2020 04:59:02 +0700 Subject: [PATCH 384/422] [utils] Add reference to cookie file format --- youtube_dl/utils.py | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 8ccf25489..38262bee4 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -2729,6 +2729,11 @@ class YoutubeDLHTTPSHandler(compat_urllib_request.HTTPSHandler): class YoutubeDLCookieJar(compat_cookiejar.MozillaCookieJar): + """ + See [1] for cookie file format. + + 1. https://curl.haxx.se/docs/http-cookies.html + """ _HTTPONLY_PREFIX = '#HttpOnly_' def save(self, filename=None, ignore_discard=False, ignore_expires=False): From 40b6495d403a4636ea8be1dd9a2dad33c136a1e3 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Fri, 13 Mar 2020 08:59:10 +0100 Subject: [PATCH 385/422] Revert "[vimeo] fix showcase password protected video extraction(closes #24224)" This reverts commit 12ee431676bb655f04c7dd416a73c1f142ed368d. --- youtube_dl/extractor/vimeo.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index cea686afc..8cd611e1e 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -585,7 +585,7 @@ class VimeoIE(VimeoBaseInfoExtractor): url = 'https://vimeo.com/' + video_id elif is_player: url = 'https://player.vimeo.com/video/' + video_id - elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf', '/album/', '/showcase/')): + elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')): url = 'https://vimeo.com/' + video_id try: From fcaf4d7a067e9ac6b36a5f7b1100be391f492a79 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 14 Mar 2020 04:39:21 +0700 Subject: [PATCH 386/422] [nhk] Relax _VALID_URL (#24329) --- youtube_dl/extractor/nhk.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/nhk.py b/youtube_dl/extractor/nhk.py index d2cbc9f54..45bc4d85e 100644 --- a/youtube_dl/extractor/nhk.py +++ b/youtube_dl/extractor/nhk.py @@ -6,7 +6,7 @@ from .common import InfoExtractor class NhkVodIE(InfoExtractor): - _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/(?P<lang>[a-z]{2})/ondemand/(?P<type>video|audio)/(?P<id>\d{7}|[a-z]+-\d{8}-\d+)' + _VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/(?P<lang>[a-z]{2})/ondemand/(?P<type>video|audio)/(?P<id>\d{7}|[^/]+?-\d{8}-\d+)' # Content available only for a limited period of time. Visit # https://www3.nhk.or.jp/nhkworld/en/ondemand/ for working samples. _TESTS = [{ @@ -30,6 +30,9 @@ class NhkVodIE(InfoExtractor): }, { 'url': 'https://www3.nhk.or.jp/nhkworld/fr/ondemand/audio/plugin-20190404-1/', 'only_matching': True, + }, { + 'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/audio/j_art-20150903-1/', + 'only_matching': True, }] _API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sod%slist/v7a/episode/%s/%s/all%s.json' From 9bfe08859491882e40603ed6c4eb59760ed35ca7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 14 Mar 2020 04:40:11 +0700 Subject: [PATCH 387/422] [nhk] Remove obsolete rtmp formats (closes #24329) --- youtube_dl/extractor/nhk.py | 7 ------- 1 file changed, 7 deletions(-) diff --git a/youtube_dl/extractor/nhk.py b/youtube_dl/extractor/nhk.py index 45bc4d85e..ce13f6bb9 100644 --- a/youtube_dl/extractor/nhk.py +++ b/youtube_dl/extractor/nhk.py @@ -87,13 +87,6 @@ class NhkVodIE(InfoExtractor): info['formats'] = self._extract_m3u8_formats( 'https://nhks-vh.akamaihd.net/i%s/master.m3u8' % audio_path, episode_id, 'm4a', m3u8_id='hls', fatal=False) - for proto in ('rtmpt', 'rtmp'): - info['formats'].append({ - 'ext': 'flv', - 'format_id': proto, - 'url': '%s://flv.nhk.or.jp/ondemand/mp4:flv%s' % (proto, audio_path), - 'vcodec': 'none', - }) for f in info['formats']: f['language'] = lang return info From 541fe3eaff579f72ccc14f97009a8904f739368f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 14 Mar 2020 04:42:40 +0700 Subject: [PATCH 388/422] [nhk] Update m3u8 URL and use native hls (#24329) --- youtube_dl/extractor/nhk.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/nhk.py b/youtube_dl/extractor/nhk.py index ce13f6bb9..de6a707c4 100644 --- a/youtube_dl/extractor/nhk.py +++ b/youtube_dl/extractor/nhk.py @@ -85,8 +85,9 @@ class NhkVodIE(InfoExtractor): audio = episode['audio'] audio_path = audio['audio'] info['formats'] = self._extract_m3u8_formats( - 'https://nhks-vh.akamaihd.net/i%s/master.m3u8' % audio_path, - episode_id, 'm4a', m3u8_id='hls', fatal=False) + 'https://nhkworld-vh.akamaihd.net/i%s/master.m3u8' % audio_path, + episode_id, 'm4a', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False) for f in info['formats']: f['language'] = lang return info From 4cbce88f8b44ab17d55fe1b7615e37a2c1f142d7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 14 Mar 2020 04:58:24 +0700 Subject: [PATCH 389/422] [ndr] Fix extraction (closes #24326) --- youtube_dl/extractor/ndr.py | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/ndr.py b/youtube_dl/extractor/ndr.py index 9c8bf05af..2447c812e 100644 --- a/youtube_dl/extractor/ndr.py +++ b/youtube_dl/extractor/ndr.py @@ -7,6 +7,7 @@ from .common import InfoExtractor from ..utils import ( determine_ext, int_or_none, + merge_dicts, parse_iso8601, qualities, try_get, @@ -87,21 +88,25 @@ class NDRIE(NDRBaseIE): def _extract_embed(self, webpage, display_id): embed_url = self._html_search_meta( - 'embedURL', webpage, 'embed URL', fatal=True) + 'embedURL', webpage, 'embed URL', + default=None) or self._search_regex( + r'\bembedUrl["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, + 'embed URL', group='url') description = self._search_regex( r'<p[^>]+itemprop="description">([^<]+)</p>', webpage, 'description', default=None) or self._og_search_description(webpage) timestamp = parse_iso8601( self._search_regex( r'<span[^>]+itemprop="(?:datePublished|uploadDate)"[^>]+content="([^"]+)"', - webpage, 'upload date', fatal=False)) - return { + webpage, 'upload date', default=None)) + info = self._search_json_ld(webpage, display_id, default={}) + return merge_dicts({ '_type': 'url_transparent', 'url': embed_url, 'display_id': display_id, 'description': description, 'timestamp': timestamp, - } + }, info) class NJoyIE(NDRBaseIE): From 4568a11802b47c22ac43d1187435ab2e6d7a3c6d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 14 Mar 2020 22:57:10 +0700 Subject: [PATCH 390/422] [xtube] Fix formats extraction (closes #24348) --- youtube_dl/extractor/xtube.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index 47caec1de..79dd647b3 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -98,7 +98,7 @@ class XTubeIE(InfoExtractor): title = config.get('title') thumbnail = config.get('poster') duration = int_or_none(config.get('duration')) - sources = config.get('sources') + sources = config.get('sources') or config.get('format') if isinstance(sources, dict): sources = self._parse_json(self._search_regex( From 158bc5ac03a175d95337979afa02f7423c2bf445 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 14 Mar 2020 22:58:10 +0700 Subject: [PATCH 391/422] [xtube] Fix typo --- youtube_dl/extractor/xtube.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index 79dd647b3..01b253dcb 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -100,7 +100,7 @@ class XTubeIE(InfoExtractor): duration = int_or_none(config.get('duration')) sources = config.get('sources') or config.get('format') - if isinstance(sources, dict): + if not isinstance(sources, dict): sources = self._parse_json(self._search_regex( r'(["\'])?sources\1?\s*:\s*(?P<sources>{.+?}),', webpage, 'sources', group='sources'), video_id, From 73453430c11002a7193eaa9fb8cf5349fa326c93 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 21 Mar 2020 00:59:48 +0700 Subject: [PATCH 392/422] [hellporno] Fix extraction (closes #24399) --- youtube_dl/extractor/hellporno.py | 73 ++++++++++++++++--------------- 1 file changed, 37 insertions(+), 36 deletions(-) diff --git a/youtube_dl/extractor/hellporno.py b/youtube_dl/extractor/hellporno.py index 0ee8ea712..fae425103 100644 --- a/youtube_dl/extractor/hellporno.py +++ b/youtube_dl/extractor/hellporno.py @@ -1,12 +1,11 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( - js_to_json, + int_or_none, + merge_dicts, remove_end, - determine_ext, + unified_timestamp, ) @@ -14,15 +13,21 @@ class HellPornoIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?hellporno\.(?:com/videos|net/v)/(?P<id>[^/]+)' _TESTS = [{ 'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/', - 'md5': '1fee339c610d2049699ef2aa699439f1', + 'md5': 'f0a46ebc0bed0c72ae8fe4629f7de5f3', 'info_dict': { 'id': '149116', 'display_id': 'dixie-is-posing-with-naked-ass-very-erotic', 'ext': 'mp4', 'title': 'Dixie is posing with naked ass very erotic', + 'description': 'md5:9a72922749354edb1c4b6e540ad3d215', + 'categories': list, 'thumbnail': r're:https?://.*\.jpg$', + 'duration': 240, + 'timestamp': 1398762720, + 'upload_date': '20140429', + 'view_count': int, 'age_limit': 18, - } + }, }, { 'url': 'http://hellporno.net/v/186271/', 'only_matching': True, @@ -36,40 +41,36 @@ class HellPornoIE(InfoExtractor): title = remove_end(self._html_search_regex( r'<title>([^<]+)', webpage, 'title'), ' - Hell Porno') - flashvars = self._parse_json(self._search_regex( - r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flashvars'), - display_id, transform_source=js_to_json) + info = self._parse_html5_media_entries(url, webpage, display_id)[0] + self._sort_formats(info['formats']) - video_id = flashvars.get('video_id') - thumbnail = flashvars.get('preview_url') - ext = determine_ext(flashvars.get('postfix'), 'mp4') + video_id = self._search_regex( + (r'chs_object\s*=\s*["\'](\d+)', + r'params\[["\']video_id["\']\]\s*=\s*(\d+)'), webpage, 'video id', + default=display_id) + description = self._search_regex( + r'class=["\']desc_video_view_v2[^>]+>([^<]+)', webpage, + 'description', fatal=False) + categories = [ + c.strip() + for c in self._html_search_meta( + 'keywords', webpage, 'categories', default='').split(',') + if c.strip()] + duration = int_or_none(self._og_search_property( + 'video:duration', webpage, fatal=False)) + timestamp = unified_timestamp(self._og_search_property( + 'video:release_date', webpage, fatal=False)) + view_count = int_or_none(self._search_regex( + r'>Views\s+(\d+)', webpage, 'view count', fatal=False)) - formats = [] - for video_url_key in ['video_url', 'video_alt_url']: - video_url = flashvars.get(video_url_key) - if not video_url: - continue - video_text = flashvars.get('%s_text' % video_url_key) - fmt = { - 'url': video_url, - 'ext': ext, - 'format_id': video_text, - } - m = re.search(r'^(?P\d+)[pP]', video_text) - if m: - fmt['height'] = int(m.group('height')) - formats.append(fmt) - self._sort_formats(formats) - - categories = self._html_search_meta( - 'keywords', webpage, 'categories', default='').split(',') - - return { + return merge_dicts(info, { 'id': video_id, 'display_id': display_id, 'title': title, - 'thumbnail': thumbnail, + 'description': description, 'categories': categories, + 'duration': duration, + 'timestamp': timestamp, + 'view_count': view_count, 'age_limit': 18, - 'formats': formats, - } + }) From 787c3604671283bd4945eefb87866d01fb973097 Mon Sep 17 00:00:00 2001 From: Devon Meunier Date: Sun, 19 May 2019 07:32:46 -0400 Subject: [PATCH 393/422] [cbc:watch] Add support for authentication --- youtube_dl/extractor/cbc.py | 36 ++++++++++++++++++++++++++++++++++-- 1 file changed, 34 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/cbc.py b/youtube_dl/extractor/cbc.py index 751a3a8f2..b02cddbfd 100644 --- a/youtube_dl/extractor/cbc.py +++ b/youtube_dl/extractor/cbc.py @@ -3,6 +3,7 @@ from __future__ import unicode_literals import json import re +from xml.sax.saxutils import escape from .common import InfoExtractor from ..compat import ( @@ -216,6 +217,29 @@ class CBCWatchBaseIE(InfoExtractor): 'clearleap': 'http://www.clearleap.com/namespace/clearleap/1.0/', } _GEO_COUNTRIES = ['CA'] + _LOGIN_URL = 'https://api.loginradius.com/identity/v2/auth/login' + _TOKEN_URL = 'https://cloud-api.loginradius.com/sso/jwt/api/token' + _API_KEY = '3f4beddd-2061-49b0-ae80-6f1f2ed65b37' + _NETRC_MACHINE = 'cbcwatch' + + def _signature(self, email, password): + data = json.dumps({ + 'email': email, + 'password': password, + }).encode() + headers = {'content-type': 'application/json'} + query = {'apikey': self._API_KEY} + resp = self._download_json(self._LOGIN_URL, None, data=data, headers=headers, query=query) + access_token = resp['access_token'] + + # token + query = { + 'access_token': access_token, + 'apikey': self._API_KEY, + 'jwtapp': 'jwt', + } + resp = self._download_json(self._TOKEN_URL, None, headers=headers, query=query) + return resp['signature'] def _call_api(self, path, video_id): url = path if path.startswith('http') else self._API_BASE_URL + path @@ -249,13 +273,21 @@ class CBCWatchBaseIE(InfoExtractor): return self._device_id and self._device_token def _register_device(self): - self._device_id = self._device_token = None result = self._download_xml( self._API_BASE_URL + 'device/register', None, 'Acquiring device token', data=b'web') self._device_id = xpath_text(result, 'deviceId', fatal=True) - self._device_token = xpath_text(result, 'deviceToken', fatal=True) + anon_device_token = xpath_text(result, 'deviceToken', fatal=True) + email, password = self._get_login_info() + if email and password: + signature = self._signature(email, password) + data = '{0}{1}web'.format(escape(signature), escape(self._device_id)).encode() + url = self._API_BASE_URL + 'device/login' + result = self._download_xml(url, None, data=data, headers={'content-type': 'application/xml'}) + self._device_token = xpath_text(result, 'token', fatal=True) + else: + self._device_token = anon_device_token self._downloader.cache.store( 'cbcwatch', 'device', { 'id': self._device_id, From c76cdf2382c91af13de0c7580b1b5e1b24484664 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 21 Mar 2020 01:41:54 +0700 Subject: [PATCH 394/422] [cbc:watch] Fix authenticated device token caching (closes #19160) --- youtube_dl/extractor/cbc.py | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/cbc.py b/youtube_dl/extractor/cbc.py index b02cddbfd..fd5ec6033 100644 --- a/youtube_dl/extractor/cbc.py +++ b/youtube_dl/extractor/cbc.py @@ -1,6 +1,7 @@ # coding: utf-8 from __future__ import unicode_literals +import hashlib import json import re from xml.sax.saxutils import escape @@ -263,7 +264,8 @@ class CBCWatchBaseIE(InfoExtractor): def _real_initialize(self): if self._valid_device_token(): return - device = self._downloader.cache.load('cbcwatch', 'device') or {} + device = self._downloader.cache.load( + 'cbcwatch', self._cache_device_key()) or {} self._device_id, self._device_token = device.get('id'), device.get('token') if self._valid_device_token(): return @@ -272,24 +274,30 @@ class CBCWatchBaseIE(InfoExtractor): def _valid_device_token(self): return self._device_id and self._device_token + def _cache_device_key(self): + email, _ = self._get_login_info() + return '%s_device' % hashlib.sha256(email.encode()).hexdigest() if email else 'device' + def _register_device(self): result = self._download_xml( self._API_BASE_URL + 'device/register', None, 'Acquiring device token', data=b'web') self._device_id = xpath_text(result, 'deviceId', fatal=True) - anon_device_token = xpath_text(result, 'deviceToken', fatal=True) email, password = self._get_login_info() if email and password: signature = self._signature(email, password) - data = '{0}{1}web'.format(escape(signature), escape(self._device_id)).encode() + data = '{0}{1}web'.format( + escape(signature), escape(self._device_id)).encode() url = self._API_BASE_URL + 'device/login' - result = self._download_xml(url, None, data=data, headers={'content-type': 'application/xml'}) + result = self._download_xml( + url, None, data=data, + headers={'content-type': 'application/xml'}) self._device_token = xpath_text(result, 'token', fatal=True) else: - self._device_token = anon_device_token + self._device_token = xpath_text(result, 'deviceToken', fatal=True) self._downloader.cache.store( - 'cbcwatch', 'device', { + 'cbcwatch', self._cache_device_key(), { 'id': self._device_id, 'token': self._device_token, }) From a6c5859d6b106733905c3a95fc52b53a784c94da Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sun, 22 Mar 2020 09:24:07 +0100 Subject: [PATCH 395/422] [soundcloud] fix download url extraction(closes #24394) --- youtube_dl/extractor/soundcloud.py | 91 ++++++++---------------------- 1 file changed, 24 insertions(+), 67 deletions(-) diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index a1372d389..ff6be0b54 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -27,6 +27,7 @@ from ..utils import ( unified_timestamp, update_url_query, url_or_none, + urlhandle_detect_ext, ) @@ -96,7 +97,7 @@ class SoundcloudIE(InfoExtractor): 'repost_count': int, } }, - # not streamable song, preview + # geo-restricted { 'url': 'https://soundcloud.com/the-concept-band/goldrushed-mastered?in=the-concept-band/sets/the-royal-concept-ep', 'info_dict': { @@ -108,17 +109,13 @@ class SoundcloudIE(InfoExtractor): 'uploader_id': '9615865', 'timestamp': 1337635207, 'upload_date': '20120521', - 'duration': 30, + 'duration': 227.155, 'license': 'all-rights-reserved', 'view_count': int, 'like_count': int, 'comment_count': int, 'repost_count': int, }, - 'params': { - # rtmp - 'skip_download': True, - }, }, # private link { @@ -229,7 +226,6 @@ class SoundcloudIE(InfoExtractor): 'skip_download': True, }, }, - # not available via api.soundcloud.com/i1/tracks/id/streams { 'url': 'https://soundcloud.com/giovannisarani/mezzo-valzer', 'md5': 'e22aecd2bc88e0e4e432d7dcc0a1abf7', @@ -250,11 +246,9 @@ class SoundcloudIE(InfoExtractor): 'comment_count': int, 'repost_count': int, }, - 'expected_warnings': ['Unable to download JSON metadata'], } ] - _API_BASE = 'https://api.soundcloud.com/' _API_V2_BASE = 'https://api-v2.soundcloud.com/' _BASE_URL = 'https://soundcloud.com/' _IMAGE_REPL_RE = r'-([0-9a-z]+)\.jpg' @@ -316,10 +310,9 @@ class SoundcloudIE(InfoExtractor): def _resolv_url(cls, url): return SoundcloudIE._API_V2_BASE + 'resolve?url=' + url - def _extract_info_dict(self, info, full_title=None, secret_token=None, version=2): + def _extract_info_dict(self, info, full_title=None, secret_token=None): track_id = compat_str(info['id']) title = info['title'] - track_base_url = self._API_BASE + 'tracks/%s' % track_id format_urls = set() formats = [] @@ -328,21 +321,22 @@ class SoundcloudIE(InfoExtractor): query['secret_token'] = secret_token if info.get('downloadable') and info.get('has_downloads_left'): - format_url = update_url_query( - info.get('download_url') or track_base_url + '/download', query) - format_urls.add(format_url) - if version == 2: - v1_info = self._download_json( - track_base_url, track_id, query=query, fatal=False) or {} - else: - v1_info = info - formats.append({ - 'format_id': 'download', - 'ext': v1_info.get('original_format') or 'mp3', - 'filesize': int_or_none(v1_info.get('original_content_size')), - 'url': format_url, - 'preference': 10, - }) + download_url = update_url_query( + self._API_V2_BASE + 'tracks/' + track_id + '/download', query) + redirect_url = (self._download_json(download_url, track_id, fatal=False) or {}).get('redirectUri') + if redirect_url: + urlh = self._request_webpage( + HEADRequest(redirect_url), track_id, fatal=False) + if urlh: + format_url = urlh.geturl() + format_urls.add(format_url) + formats.append({ + 'format_id': 'download', + 'ext': urlhandle_detect_ext(urlh) or 'mp3', + 'filesize': int_or_none(urlh.headers.get('Content-Length')), + 'url': format_url, + 'preference': 10, + }) def invalid_url(url): return not url or url in format_urls @@ -406,42 +400,11 @@ class SoundcloudIE(InfoExtractor): }, 'http' if protocol == 'progressive' else protocol, t.get('snipped') or '/preview/' in format_url) - if not formats: - # Old API, does not work for some tracks (e.g. - # https://soundcloud.com/giovannisarani/mezzo-valzer) - # and might serve preview URLs (e.g. - # http://www.soundcloud.com/snbrn/ele) - format_dict = self._download_json( - track_base_url + '/streams', track_id, - 'Downloading track url', query=query, fatal=False) or {} - - for key, stream_url in format_dict.items(): - if invalid_url(stream_url): - continue - format_urls.add(stream_url) - mobj = re.search(r'(http|hls)_([^_]+)_(\d+)_url', key) - if mobj: - protocol, ext, abr = mobj.groups() - add_format({ - 'abr': abr, - 'ext': ext, - 'url': stream_url, - }, protocol) - - if not formats: - # We fallback to the stream_url in the original info, this - # cannot be always used, sometimes it can give an HTTP 404 error - urlh = self._request_webpage( - HEADRequest(info.get('stream_url') or track_base_url + '/stream'), - track_id, query=query, fatal=False) - if urlh: - stream_url = urlh.geturl() - if not invalid_url(stream_url): - add_format({'url': stream_url}, 'http') - for f in formats: f['vcodec'] = 'none' + if not formats and info.get('policy') == 'BLOCK': + self.raise_geo_restricted() self._sort_formats(formats) user = info.get('user') or {} @@ -511,16 +474,10 @@ class SoundcloudIE(InfoExtractor): resolve_title += '/%s' % token info_json_url = self._resolv_url(self._BASE_URL + resolve_title) - version = 2 info = self._download_json( - info_json_url, full_title, 'Downloading info JSON', query=query, fatal=False) - if not info: - info = self._download_json( - info_json_url.replace(self._API_V2_BASE, self._API_BASE), - full_title, 'Downloading info JSON', query=query) - version = 1 + info_json_url, full_title, 'Downloading info JSON', query=query) - return self._extract_info_dict(info, full_title, token, version) + return self._extract_info_dict(info, full_title, token) class SoundcloudPlaylistBaseIE(SoundcloudIE): From 2e20cb36364b91c1d928ce896064fdc7c49e82f8 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 23 Mar 2020 12:57:10 +0100 Subject: [PATCH 396/422] [limelight] remove disabled API requests(closes #24255) --- youtube_dl/extractor/limelight.py | 125 ++++++++++++----------------- youtube_dl/extractor/pokemon.py | 12 +-- youtube_dl/extractor/telequebec.py | 2 - youtube_dl/extractor/tfo.py | 6 +- 4 files changed, 59 insertions(+), 86 deletions(-) diff --git a/youtube_dl/extractor/limelight.py b/youtube_dl/extractor/limelight.py index 729d8de50..39f74d282 100644 --- a/youtube_dl/extractor/limelight.py +++ b/youtube_dl/extractor/limelight.py @@ -18,7 +18,6 @@ from ..utils import ( class LimelightBaseIE(InfoExtractor): _PLAYLIST_SERVICE_URL = 'http://production-ps.lvp.llnw.net/r/PlaylistService/%s/%s/%s' - _API_URL = 'http://api.video.limelight.com/rest/organizations/%s/%s/%s/%s.json' @classmethod def _extract_urls(cls, webpage, source_url): @@ -70,7 +69,8 @@ class LimelightBaseIE(InfoExtractor): try: return self._download_json( self._PLAYLIST_SERVICE_URL % (self._PLAYLIST_SERVICE_PATH, item_id, method), - item_id, 'Downloading PlaylistService %s JSON' % method, fatal=fatal, headers=headers) + item_id, 'Downloading PlaylistService %s JSON' % method, + fatal=fatal, headers=headers) except ExtractorError as e: if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: error = self._parse_json(e.cause.read().decode(), item_id)['detail']['contentAccessPermission'] @@ -79,22 +79,22 @@ class LimelightBaseIE(InfoExtractor): raise ExtractorError(error, expected=True) raise - def _call_api(self, organization_id, item_id, method): - return self._download_json( - self._API_URL % (organization_id, self._API_PATH, item_id, method), - item_id, 'Downloading API %s JSON' % method) - - def _extract(self, item_id, pc_method, mobile_method, meta_method, referer=None): + def _extract(self, item_id, pc_method, mobile_method, referer=None): pc = self._call_playlist_service(item_id, pc_method, referer=referer) - metadata = self._call_api(pc['orgId'], item_id, meta_method) - mobile = self._call_playlist_service(item_id, mobile_method, fatal=False, referer=referer) - return pc, mobile, metadata + mobile = self._call_playlist_service( + item_id, mobile_method, fatal=False, referer=referer) + return pc, mobile + + def _extract_info(self, pc, mobile, i, referer): + get_item = lambda x, y: try_get(x, lambda x: x[y][i], dict) or {} + pc_item = get_item(pc, 'playlistItems') + mobile_item = get_item(mobile, 'mediaList') + video_id = pc_item.get('mediaId') or mobile_item['mediaId'] + title = pc_item.get('title') or mobile_item['title'] - def _extract_info(self, streams, mobile_urls, properties): - video_id = properties['media_id'] formats = [] urls = [] - for stream in streams: + for stream in pc_item.get('streams', []): stream_url = stream.get('url') if not stream_url or stream.get('drmProtected') or stream_url in urls: continue @@ -155,7 +155,7 @@ class LimelightBaseIE(InfoExtractor): }) formats.append(fmt) - for mobile_url in mobile_urls: + for mobile_url in mobile_item.get('mobileUrls', []): media_url = mobile_url.get('mobileUrl') format_id = mobile_url.get('targetMediaPlatform') if not media_url or format_id in ('Widevine', 'SmoothStreaming') or media_url in urls: @@ -179,54 +179,34 @@ class LimelightBaseIE(InfoExtractor): self._sort_formats(formats) - title = properties['title'] - description = properties.get('description') - timestamp = int_or_none(properties.get('publish_date') or properties.get('create_date')) - duration = float_or_none(properties.get('duration_in_milliseconds'), 1000) - filesize = int_or_none(properties.get('total_storage_in_bytes')) - categories = [properties.get('category')] - tags = properties.get('tags', []) - thumbnails = [{ - 'url': thumbnail['url'], - 'width': int_or_none(thumbnail.get('width')), - 'height': int_or_none(thumbnail.get('height')), - } for thumbnail in properties.get('thumbnails', []) if thumbnail.get('url')] - subtitles = {} - for caption in properties.get('captions', []): - lang = caption.get('language_code') - subtitles_url = caption.get('url') - if lang and subtitles_url: - subtitles.setdefault(lang, []).append({ - 'url': subtitles_url, - }) - closed_captions_url = properties.get('closed_captions_url') - if closed_captions_url: - subtitles.setdefault('en', []).append({ - 'url': closed_captions_url, - 'ext': 'ttml', - }) + for flag in mobile_item.get('flags'): + if flag == 'ClosedCaptions': + closed_captions = self._call_playlist_service( + video_id, 'getClosedCaptionsDetailsByMediaId', + False, referer) or [] + for cc in closed_captions: + cc_url = cc.get('webvttFileUrl') + if not cc_url: + continue + lang = cc.get('languageCode') or self._search_regex(r'/[a-z]{2}\.vtt', cc_url, 'lang', default='en') + subtitles.setdefault(lang, []).append({ + 'url': cc_url, + }) + break + + get_meta = lambda x: pc_item.get(x) or mobile_item.get(x) return { 'id': video_id, 'title': title, - 'description': description, + 'description': get_meta('description'), 'formats': formats, - 'timestamp': timestamp, - 'duration': duration, - 'filesize': filesize, - 'categories': categories, - 'tags': tags, - 'thumbnails': thumbnails, + 'duration': float_or_none(get_meta('durationInMilliseconds'), 1000), + 'thumbnail': get_meta('previewImageUrl') or get_meta('thumbnailImageUrl'), 'subtitles': subtitles, } - def _extract_info_helper(self, pc, mobile, i, metadata): - return self._extract_info( - try_get(pc, lambda x: x['playlistItems'][i]['streams'], list) or [], - try_get(mobile, lambda x: x['mediaList'][i]['mobileUrls'], list) or [], - metadata) - class LimelightMediaIE(LimelightBaseIE): IE_NAME = 'limelight' @@ -251,8 +231,6 @@ class LimelightMediaIE(LimelightBaseIE): 'description': 'md5:8005b944181778e313d95c1237ddb640', 'thumbnail': r're:^https?://.*\.jpeg$', 'duration': 144.23, - 'timestamp': 1244136834, - 'upload_date': '20090604', }, 'params': { # m3u8 download @@ -268,30 +246,29 @@ class LimelightMediaIE(LimelightBaseIE): 'title': '3Play Media Overview Video', 'thumbnail': r're:^https?://.*\.jpeg$', 'duration': 78.101, - 'timestamp': 1338929955, - 'upload_date': '20120605', - 'subtitles': 'mincount:9', + # TODO: extract all languages that were accessible via API + # 'subtitles': 'mincount:9', + 'subtitles': 'mincount:1', }, }, { 'url': 'https://assets.delvenetworks.com/player/loader.swf?mediaId=8018a574f08d416e95ceaccae4ba0452', 'only_matching': True, }] _PLAYLIST_SERVICE_PATH = 'media' - _API_PATH = 'media' def _real_extract(self, url): url, smuggled_data = unsmuggle_url(url, {}) video_id = self._match_id(url) + source_url = smuggled_data.get('source_url') self._initialize_geo_bypass({ 'countries': smuggled_data.get('geo_countries'), }) - pc, mobile, metadata = self._extract( + pc, mobile = self._extract( video_id, 'getPlaylistByMediaId', - 'getMobilePlaylistByMediaId', 'properties', - smuggled_data.get('source_url')) + 'getMobilePlaylistByMediaId', source_url) - return self._extract_info_helper(pc, mobile, 0, metadata) + return self._extract_info(pc, mobile, 0, source_url) class LimelightChannelIE(LimelightBaseIE): @@ -313,6 +290,7 @@ class LimelightChannelIE(LimelightBaseIE): 'info_dict': { 'id': 'ab6a524c379342f9b23642917020c082', 'title': 'Javascript Sample Code', + 'description': 'Javascript Sample Code - http://www.delvenetworks.com/sample-code/playerCode-demo.html', }, 'playlist_mincount': 3, }, { @@ -320,22 +298,23 @@ class LimelightChannelIE(LimelightBaseIE): 'only_matching': True, }] _PLAYLIST_SERVICE_PATH = 'channel' - _API_PATH = 'channels' def _real_extract(self, url): url, smuggled_data = unsmuggle_url(url, {}) channel_id = self._match_id(url) + source_url = smuggled_data.get('source_url') - pc, mobile, medias = self._extract( + pc, mobile = self._extract( channel_id, 'getPlaylistByChannelId', 'getMobilePlaylistWithNItemsByChannelId?begin=0&count=-1', - 'media', smuggled_data.get('source_url')) + source_url) entries = [ - self._extract_info_helper(pc, mobile, i, medias['media_list'][i]) - for i in range(len(medias['media_list']))] + self._extract_info(pc, mobile, i, source_url) + for i in range(len(pc['playlistItems']))] - return self.playlist_result(entries, channel_id, pc['title']) + return self.playlist_result( + entries, channel_id, pc.get('title'), mobile.get('description')) class LimelightChannelListIE(LimelightBaseIE): @@ -368,10 +347,12 @@ class LimelightChannelListIE(LimelightBaseIE): def _real_extract(self, url): channel_list_id = self._match_id(url) - channel_list = self._call_playlist_service(channel_list_id, 'getMobileChannelListById') + channel_list = self._call_playlist_service( + channel_list_id, 'getMobileChannelListById') entries = [ self.url_result('limelight:channel:%s' % channel['id'], 'LimelightChannel') for channel in channel_list['channelList']] - return self.playlist_result(entries, channel_list_id, channel_list['title']) + return self.playlist_result( + entries, channel_list_id, channel_list['title']) diff --git a/youtube_dl/extractor/pokemon.py b/youtube_dl/extractor/pokemon.py index dd5f17f11..80222d428 100644 --- a/youtube_dl/extractor/pokemon.py +++ b/youtube_dl/extractor/pokemon.py @@ -20,20 +20,16 @@ class PokemonIE(InfoExtractor): 'ext': 'mp4', 'title': 'The Ol’ Raise and Switch!', 'description': 'md5:7db77f7107f98ba88401d3adc80ff7af', - 'timestamp': 1511824728, - 'upload_date': '20171127', }, 'add_id': ['LimelightMedia'], }, { # no data-video-title - 'url': 'https://www.pokemon.com/us/pokemon-episodes/pokemon-movies/pokemon-the-rise-of-darkrai-2008', + 'url': 'https://www.pokemon.com/fr/episodes-pokemon/films-pokemon/pokemon-lascension-de-darkrai-2008', 'info_dict': { - 'id': '99f3bae270bf4e5097274817239ce9c8', + 'id': 'dfbaf830d7e54e179837c50c0c6cc0e1', 'ext': 'mp4', - 'title': 'Pokémon: The Rise of Darkrai', - 'description': 'md5:ea8fbbf942e1e497d54b19025dd57d9d', - 'timestamp': 1417778347, - 'upload_date': '20141205', + 'title': "Pokémon : L'ascension de Darkrai", + 'description': 'md5:d1dbc9e206070c3e14a06ff557659fb5', }, 'add_id': ['LimelightMedia'], 'params': { diff --git a/youtube_dl/extractor/telequebec.py b/youtube_dl/extractor/telequebec.py index ae9f66787..c82c94b3a 100644 --- a/youtube_dl/extractor/telequebec.py +++ b/youtube_dl/extractor/telequebec.py @@ -38,8 +38,6 @@ class TeleQuebecIE(TeleQuebecBaseIE): 'ext': 'mp4', 'title': 'Un petit choc et puis repart!', 'description': 'md5:b04a7e6b3f74e32d7b294cffe8658374', - 'upload_date': '20180222', - 'timestamp': 1519326631, }, 'params': { 'skip_download': True, diff --git a/youtube_dl/extractor/tfo.py b/youtube_dl/extractor/tfo.py index 0e2370cd8..0631cb7ab 100644 --- a/youtube_dl/extractor/tfo.py +++ b/youtube_dl/extractor/tfo.py @@ -17,14 +17,12 @@ class TFOIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?tfo\.org/(?:en|fr)/(?:[^/]+/){2}(?P\d+)' _TEST = { 'url': 'http://www.tfo.org/en/universe/tfo-247/100463871/video-game-hackathon', - 'md5': '47c987d0515561114cf03d1226a9d4c7', + 'md5': 'cafbe4f47a8dae0ca0159937878100d6', 'info_dict': { - 'id': '100463871', + 'id': '7da3d50e495c406b8fc0b997659cc075', 'ext': 'mp4', 'title': 'Video Game Hackathon', 'description': 'md5:558afeba217c6c8d96c60e5421795c07', - 'upload_date': '20160212', - 'timestamp': 1455310233, } } From b4eb08bb03f69c587f8440912cf56aadc9e52879 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 24 Mar 2020 00:11:39 +0700 Subject: [PATCH 397/422] [bilibili] Add support for new URL schema with BV ids (closes #24439, closes #24442) --- youtube_dl/extractor/bilibili.py | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py index 80bd696e2..e9d0a8d0c 100644 --- a/youtube_dl/extractor/bilibili.py +++ b/youtube_dl/extractor/bilibili.py @@ -24,7 +24,18 @@ from ..utils import ( class BiliBiliIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.|bangumi\.|)bilibili\.(?:tv|com)/(?:video/av|anime/(?P\d+)/play#)(?P\d+)' + _VALID_URL = r'''(?x) + https?:// + (?:(?:www|bangumi)\.)? + bilibili\.(?:tv|com)/ + (?: + (?: + video/[aA][vV]| + anime/(?P\d+)/play\# + )(?P\d+)| + video/[bB][vV](?P[^/?#&]+) + ) + ''' _TESTS = [{ 'url': 'http://www.bilibili.tv/video/av1074402/', @@ -92,6 +103,10 @@ class BiliBiliIE(InfoExtractor): 'skip_download': True, # Test metadata only }, }] + }, { + # new BV video id format + 'url': 'https://www.bilibili.com/video/BV1JE411F741', + 'only_matching': True, }] _APP_KEY = 'iVGUTjsxvpLeuDCf' @@ -109,7 +124,7 @@ class BiliBiliIE(InfoExtractor): url, smuggled_data = unsmuggle_url(url, {}) mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = mobj.group('id') or mobj.group('id_bv') anime_id = mobj.group('anime_id') webpage = self._download_webpage(url, video_id) From 63dce3094bf45964b49a2c9f26c94b10cf60c2c2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 24 Mar 2020 00:24:39 +0700 Subject: [PATCH 398/422] [bilibili] Add support for player.bilibili.com (closes #24402) --- youtube_dl/extractor/bilibili.py | 14 ++++++++++++++ youtube_dl/extractor/extractors.py | 1 + 2 files changed, 15 insertions(+) diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py index e9d0a8d0c..4dc597e16 100644 --- a/youtube_dl/extractor/bilibili.py +++ b/youtube_dl/extractor/bilibili.py @@ -434,3 +434,17 @@ class BilibiliAudioAlbumIE(BilibiliAudioBaseIE): entries, am_id, album_title, album_data.get('intro')) return self.playlist_result(entries, am_id) + + +class BiliBiliPlayerIE(InfoExtractor): + _VALID_URL = r'https?://player\.bilibili\.com/player\.html\?.*?\baid=(?P\d+)' + _TEST = { + 'url': 'http://player.bilibili.com/player.html?aid=92494333&cid=157926707&page=1', + 'only_matching': True, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + return self.url_result( + 'http://www.bilibili.tv/video/av%s/' % video_id, + ie=BiliBiliIE.ie_key(), video_id=video_id) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 64d1fa251..ef803b8a7 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -105,6 +105,7 @@ from .bilibili import ( BiliBiliBangumiIE, BilibiliAudioIE, BilibiliAudioAlbumIE, + BiliBiliPlayerIE, ) from .biobiochiletv import BioBioChileTVIE from .bitchute import ( From 4560adc820a5d4bda5babc62f0f7fc306b13ad86 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 24 Mar 2020 02:43:24 +0700 Subject: [PATCH 399/422] [teachable] Extract chapter metadata (closes #24421) --- youtube_dl/extractor/teachable.py | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/youtube_dl/extractor/teachable.py b/youtube_dl/extractor/teachable.py index 4316a6962..290c65754 100644 --- a/youtube_dl/extractor/teachable.py +++ b/youtube_dl/extractor/teachable.py @@ -7,7 +7,9 @@ from .wistia import WistiaIE from ..utils import ( clean_html, ExtractorError, + int_or_none, get_element_by_class, + strip_or_none, urlencode_postdata, urljoin, ) @@ -173,11 +175,34 @@ class TeachableIE(TeachableBaseIE): title = self._og_search_title(webpage, default=None) + chapter = None + chapter_number = None + section_item = self._search_regex( + r'(?s)(?P
  • ]+\bdata-lecture-id=["\']%s[^>]+>.+?
    • )' % video_id, + webpage, 'section item', default=None, group='li') + if section_item: + chapter_number = int_or_none(self._search_regex( + r'data-ss-position=["\'](\d+)', section_item, 'section id', + default=None)) + if chapter_number is not None: + sections = [] + for s in re.findall( + r'(?s)]+\bclass=["\']section-title[^>]+>(.+?)', webpage): + section = strip_or_none(clean_html(s)) + if not section: + sections = [] + break + sections.append(section) + if chapter_number <= len(sections): + chapter = sections[chapter_number - 1] + entries = [{ '_type': 'url_transparent', 'url': wistia_url, 'ie_key': WistiaIE.ie_key(), 'title': title, + 'chapter': chapter, + 'chapter_number': chapter_number, } for wistia_url in wistia_urls] return self.playlist_result(entries, video_id, title) From be7dacf9cfc3603ba6e4f818a8988a527f06d6d8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 24 Mar 2020 02:46:37 +0700 Subject: [PATCH 400/422] [generic] Look for teachable embeds before wistia --- youtube_dl/extractor/generic.py | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index d1ec56be9..a495ee15a 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -2536,6 +2536,11 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key()) + # Look for Teachable embeds, must be before Wistia + teachable_url = TeachableIE._extract_url(webpage, url) + if teachable_url: + return self.url_result(teachable_url) + # Look for embedded Wistia player wistia_urls = WistiaIE._extract_urls(webpage) if wistia_urls: @@ -3141,10 +3146,6 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key()) - teachable_url = TeachableIE._extract_url(webpage, url) - if teachable_url: - return self.url_result(teachable_url) - indavideo_urls = IndavideoEmbedIE._extract_urls(webpage) if indavideo_urls: return self.playlist_from_matches( From 08a27407c45745239de819f059a86559e7a75087 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 24 Mar 2020 02:46:55 +0700 Subject: [PATCH 401/422] [teachable] Update upskillcourses domain New version does not use teachable platform any longer --- youtube_dl/extractor/teachable.py | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/teachable.py b/youtube_dl/extractor/teachable.py index 290c65754..4de67b75e 100644 --- a/youtube_dl/extractor/teachable.py +++ b/youtube_dl/extractor/teachable.py @@ -21,7 +21,7 @@ class TeachableBaseIE(InfoExtractor): _SITES = { # Only notable ones here - 'upskillcourses.com': 'upskill', + 'v1.upskillcourses.com': 'upskill', 'academy.gns3.com': 'gns3', 'academyhacker.com': 'academyhacker', 'stackskills.com': 'stackskills', @@ -111,7 +111,7 @@ class TeachableIE(TeachableBaseIE): ''' % TeachableBaseIE._VALID_URL_SUB_TUPLE _TESTS = [{ - 'url': 'http://upskillcourses.com/courses/essential-web-developer-course/lectures/1747100', + 'url': 'http://v1.upskillcourses.com/courses/essential-web-developer-course/lectures/1747100', 'info_dict': { 'id': 'uzw6zw58or', 'ext': 'mp4', @@ -125,13 +125,13 @@ class TeachableIE(TeachableBaseIE): 'skip_download': True, }, }, { - 'url': 'http://upskillcourses.com/courses/119763/lectures/1747100', + 'url': 'http://v1.upskillcourses.com/courses/119763/lectures/1747100', 'only_matching': True, }, { 'url': 'https://academy.gns3.com/courses/423415/lectures/6885939', 'only_matching': True, }, { - 'url': 'teachable:https://upskillcourses.com/courses/essential-web-developer-course/lectures/1747100', + 'url': 'teachable:https://v1.upskillcourses.com/courses/essential-web-developer-course/lectures/1747100', 'only_matching': True, }] @@ -217,17 +217,17 @@ class TeachableCourseIE(TeachableBaseIE): /(?:courses|p)/(?:enrolled/)?(?P[^/?#&]+) ''' % TeachableBaseIE._VALID_URL_SUB_TUPLE _TESTS = [{ - 'url': 'http://upskillcourses.com/courses/essential-web-developer-course/', + 'url': 'http://v1.upskillcourses.com/courses/essential-web-developer-course/', 'info_dict': { 'id': 'essential-web-developer-course', 'title': 'The Essential Web Developer Course (Free)', }, 'playlist_count': 192, }, { - 'url': 'http://upskillcourses.com/courses/119763/', + 'url': 'http://v1.upskillcourses.com/courses/119763/', 'only_matching': True, }, { - 'url': 'http://upskillcourses.com/courses/enrolled/119763', + 'url': 'http://v1.upskillcourses.com/courses/enrolled/119763', 'only_matching': True, }, { 'url': 'https://academy.gns3.com/courses/enrolled/423415', From 38fa761a4549dc2c3b155306a8a9441944bdcf01 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 24 Mar 2020 02:55:17 +0700 Subject: [PATCH 402/422] [teachable] Update gns3 domain --- youtube_dl/extractor/teachable.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/teachable.py b/youtube_dl/extractor/teachable.py index 4de67b75e..2d9d354e8 100644 --- a/youtube_dl/extractor/teachable.py +++ b/youtube_dl/extractor/teachable.py @@ -22,7 +22,7 @@ class TeachableBaseIE(InfoExtractor): _SITES = { # Only notable ones here 'v1.upskillcourses.com': 'upskill', - 'academy.gns3.com': 'gns3', + 'gns3.teachable.com': 'gns3', 'academyhacker.com': 'academyhacker', 'stackskills.com': 'stackskills', 'market.saleshacker.com': 'saleshacker', @@ -128,7 +128,7 @@ class TeachableIE(TeachableBaseIE): 'url': 'http://v1.upskillcourses.com/courses/119763/lectures/1747100', 'only_matching': True, }, { - 'url': 'https://academy.gns3.com/courses/423415/lectures/6885939', + 'url': 'https://gns3.teachable.com/courses/423415/lectures/6885939', 'only_matching': True, }, { 'url': 'teachable:https://v1.upskillcourses.com/courses/essential-web-developer-course/lectures/1747100', @@ -230,7 +230,7 @@ class TeachableCourseIE(TeachableBaseIE): 'url': 'http://v1.upskillcourses.com/courses/enrolled/119763', 'only_matching': True, }, { - 'url': 'https://academy.gns3.com/courses/enrolled/423415', + 'url': 'https://gns3.teachable.com/courses/enrolled/423415', 'only_matching': True, }, { 'url': 'teachable:https://learn.vrdev.school/p/gear-vr-developer-mini', From 6e47200b6ecaeafc65a8f5a19cd12d6e91ad186e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 24 Mar 2020 02:55:52 +0700 Subject: [PATCH 403/422] [teachable] Update test --- youtube_dl/extractor/teachable.py | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/teachable.py b/youtube_dl/extractor/teachable.py index 2d9d354e8..a75369dbe 100644 --- a/youtube_dl/extractor/teachable.py +++ b/youtube_dl/extractor/teachable.py @@ -111,15 +111,17 @@ class TeachableIE(TeachableBaseIE): ''' % TeachableBaseIE._VALID_URL_SUB_TUPLE _TESTS = [{ - 'url': 'http://v1.upskillcourses.com/courses/essential-web-developer-course/lectures/1747100', + 'url': 'https://gns3.teachable.com/courses/gns3-certified-associate/lectures/6842364', 'info_dict': { - 'id': 'uzw6zw58or', - 'ext': 'mp4', - 'title': 'Welcome to the Course!', - 'description': 'md5:65edb0affa582974de4625b9cdea1107', - 'duration': 138.763, - 'timestamp': 1479846621, - 'upload_date': '20161122', + 'id': 'untlgzk1v7', + 'ext': 'bin', + 'title': 'Overview', + 'description': 'md5:071463ff08b86c208811130ea1c2464c', + 'duration': 736.4, + 'timestamp': 1542315762, + 'upload_date': '20181115', + 'chapter': 'Welcome', + 'chapter_number': 1, }, 'params': { 'skip_download': True, From b439634f0e9a1f251d117303dc60f02fd0ab11ef Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 24 Mar 2020 03:07:34 +0700 Subject: [PATCH 404/422] [ChangeLog] Actualize [ci skip] --- ChangeLog | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/ChangeLog b/ChangeLog index 84b43c642..c53cde141 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,22 @@ +version + +Extractors +* [teachable] Update upskillcourses and gns3 domains +* [generic] Look for teachable embeds before wistia ++ [teachable] Extract chapter metadata (#24421) ++ [bilibili] Add support for player.bilibili.com (#24402) ++ [bilibili] Add support for new URL schema with BV ids (#24439, #24442) +* [limelight] Remove disabled API requests (#24255) +* [soundcloud] Fix download URL extraction (#24394) ++ [cbc:watch] Add support for authentication (#19160) +* [hellporno] Fix extraction (#24399) +* [xtube] Fix formats extraction (#24348) +* [ndr] Fix extraction (#24326) +* [nhk] Update m3u8 URL and use native HLS downloader (#24329) +- [nhk] Remove obsolete rtmp formats (#24329) +* [nhk] Relax URL regular expression (#24329) + + version 2020.03.08 Core From 30b5121a1c63c3f84251e9add3c9bf9e3c490228 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 24 Mar 2020 03:12:15 +0700 Subject: [PATCH 405/422] [ChangeLog] Actualize [ci skip] --- ChangeLog | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/ChangeLog b/ChangeLog index c53cde141..fc1e28020 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,5 +1,8 @@ version +Core +- [utils] Revert support for cookie files with spaces used instead of tabs + Extractors * [teachable] Update upskillcourses and gns3 domains * [generic] Look for teachable embeds before wistia @@ -15,12 +18,13 @@ Extractors * [nhk] Update m3u8 URL and use native HLS downloader (#24329) - [nhk] Remove obsolete rtmp formats (#24329) * [nhk] Relax URL regular expression (#24329) +- [vimeo] Revert fix showcase password protected video extraction (#24224) version 2020.03.08 Core -+ [utils] Add support for cookie files with spaces ++ [utils] Add support for cookie files with spaces used instead of tabs Extractors + [pornhub] Add support for pornhubpremium.com (#24288) From 049c0486bbd57a9bb5fb5a6a5eeff82fd4ac03ff Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 24 Mar 2020 03:14:30 +0700 Subject: [PATCH 406/422] release 2020.03.24 --- .github/ISSUE_TEMPLATE/1_broken_site.md | 6 +++--- .github/ISSUE_TEMPLATE/2_site_support_request.md | 4 ++-- .github/ISSUE_TEMPLATE/3_site_feature_request.md | 4 ++-- .github/ISSUE_TEMPLATE/4_bug_report.md | 6 +++--- .github/ISSUE_TEMPLATE/5_feature_request.md | 4 ++-- ChangeLog | 2 +- docs/supportedsites.md | 1 + youtube_dl/version.py | 2 +- 8 files changed, 15 insertions(+), 14 deletions(-) diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.md b/.github/ISSUE_TEMPLATE/1_broken_site.md index d82ff9111..40a869113 100644 --- a/.github/ISSUE_TEMPLATE/1_broken_site.md +++ b/.github/ISSUE_TEMPLATE/1_broken_site.md @@ -18,7 +18,7 @@ title: '' - [ ] I'm reporting a broken site support -- [ ] I've verified that I'm running youtube-dl version **2020.03.08** +- [ ] I've verified that I'm running youtube-dl version **2020.03.24** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar issues including closed ones @@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2020.03.08 + [debug] youtube-dl version 2020.03.24 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/2_site_support_request.md b/.github/ISSUE_TEMPLATE/2_site_support_request.md index 04b350f76..7b10df3d4 100644 --- a/.github/ISSUE_TEMPLATE/2_site_support_request.md +++ b/.github/ISSUE_TEMPLATE/2_site_support_request.md @@ -19,7 +19,7 @@ labels: 'site-support-request' - [ ] I'm reporting a new site support request -- [ ] I've verified that I'm running youtube-dl version **2020.03.08** +- [ ] I've verified that I'm running youtube-dl version **2020.03.24** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that none of provided URLs violate any copyrights - [ ] I've searched the bugtracker for similar site support requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/3_site_feature_request.md b/.github/ISSUE_TEMPLATE/3_site_feature_request.md index 6f17ad7bc..04bbcfa68 100644 --- a/.github/ISSUE_TEMPLATE/3_site_feature_request.md +++ b/.github/ISSUE_TEMPLATE/3_site_feature_request.md @@ -18,13 +18,13 @@ title: '' - [ ] I'm reporting a site feature request -- [ ] I've verified that I'm running youtube-dl version **2020.03.08** +- [ ] I've verified that I'm running youtube-dl version **2020.03.24** - [ ] I've searched the bugtracker for similar site feature requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/4_bug_report.md b/.github/ISSUE_TEMPLATE/4_bug_report.md index efb179ea5..a9e231817 100644 --- a/.github/ISSUE_TEMPLATE/4_bug_report.md +++ b/.github/ISSUE_TEMPLATE/4_bug_report.md @@ -18,7 +18,7 @@ title: '' - [ ] I'm reporting a broken site support issue -- [ ] I've verified that I'm running youtube-dl version **2020.03.08** +- [ ] I've verified that I'm running youtube-dl version **2020.03.24** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar bug reports including closed ones @@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2020.03.08 + [debug] youtube-dl version 2020.03.24 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/5_feature_request.md b/.github/ISSUE_TEMPLATE/5_feature_request.md index cf4874bcc..4a3d32d51 100644 --- a/.github/ISSUE_TEMPLATE/5_feature_request.md +++ b/.github/ISSUE_TEMPLATE/5_feature_request.md @@ -19,13 +19,13 @@ labels: 'request' - [ ] I'm reporting a feature request -- [ ] I've verified that I'm running youtube-dl version **2020.03.08** +- [ ] I've verified that I'm running youtube-dl version **2020.03.24** - [ ] I've searched the bugtracker for similar feature requests including closed ones diff --git a/ChangeLog b/ChangeLog index fc1e28020..f753972c4 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version +version 2020.03.24 Core - [utils] Revert support for cookie files with spaces used instead of tabs diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 02bc088ab..174b83bf3 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -98,6 +98,7 @@ - **BiliBili** - **BilibiliAudio** - **BilibiliAudioAlbum** + - **BiliBiliPlayer** - **BioBioChileTV** - **BIQLE** - **BitChute** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 0f768f7c1..5aedd3268 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2020.03.08' +__version__ = '2020.03.24' From d44a707fdde6c0138e9e275ed5b4ffb0b8f72966 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 5 Apr 2020 20:34:57 +0700 Subject: [PATCH 407/422] [spankwire] Fix extraction (closes #18924, closes #20648) --- youtube_dl/extractor/spankwire.py | 201 +++++++++++++++++++----------- 1 file changed, 125 insertions(+), 76 deletions(-) diff --git a/youtube_dl/extractor/spankwire.py b/youtube_dl/extractor/spankwire.py index 44d8fa52f..8f67463ed 100644 --- a/youtube_dl/extractor/spankwire.py +++ b/youtube_dl/extractor/spankwire.py @@ -3,34 +3,47 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse_unquote, - compat_urllib_parse_urlparse, -) from ..utils import ( - sanitized_Request, + float_or_none, + int_or_none, + merge_dicts, + str_or_none, str_to_int, - unified_strdate, + url_or_none, ) -from ..aes import aes_decrypt_text class SpankwireIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?Pspankwire\.com/[^/]*/video(?P[0-9]+)/?)' + _VALID_URL = r'''(?x) + https?:// + (?:www\.)?spankwire\.com/ + (?: + [^/]+/video| + EmbedPlayer\.aspx/?\?.*?\bArticleId= + ) + (?P\d+) + ''' _TESTS = [{ # download URL pattern: */P_K_.mp4 'url': 'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/', - 'md5': '8bbfde12b101204b39e4b9fe7eb67095', + 'md5': '5aa0e4feef20aad82cbcae3aed7ab7cd', 'info_dict': { 'id': '103545', 'ext': 'mp4', 'title': 'Buckcherry`s X Rated Music Video Crazy Bitch', 'description': 'Crazy Bitch X rated music video.', + 'duration': 222, 'uploader': 'oreusz', 'uploader_id': '124697', - 'upload_date': '20070507', + 'timestamp': 1178587885, + 'upload_date': '20070508', + 'average_rating': float, + 'view_count': int, + 'comment_count': int, 'age_limit': 18, - } + 'categories': list, + 'tags': list, + }, }, { # download URL pattern: */mp4__.mp4 'url': 'http://www.spankwire.com/Titcums-Compiloation-I/video1921551/', @@ -45,83 +58,119 @@ class SpankwireIE(InfoExtractor): 'upload_date': '20150822', 'age_limit': 18, }, + 'params': { + 'proxy': '127.0.0.1:8118' + }, + 'skip': 'removed', + }, { + 'url': 'https://www.spankwire.com/EmbedPlayer.aspx/?ArticleId=156156&autostart=true', + 'only_matching': True, }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) - req = sanitized_Request('http://www.' + mobj.group('url')) - req.add_header('Cookie', 'age_verified=1') - webpage = self._download_webpage(req, video_id) + video = self._download_json( + 'https://www.spankwire.com/api/video/%s.json' % video_id, video_id) - title = self._html_search_regex( - r'

    ([^<]+)', webpage, 'title') - description = self._html_search_regex( - r'(?s)(.+?)', - webpage, 'description', fatal=False) - thumbnail = self._html_search_regex( - r'playerData\.screenShot\s*=\s*["\']([^"\']+)["\']', - webpage, 'thumbnail', fatal=False) - - uploader = self._html_search_regex( - r'by:\s*]*>(.+?)', - webpage, 'uploader', fatal=False) - uploader_id = self._html_search_regex( - r'by:\s* on (.+?) at \d+:\d+', - webpage, 'upload date', fatal=False)) - - view_count = str_to_int(self._html_search_regex( - r'
    ([\d,\.]+) views
    ', - webpage, 'view count', fatal=False)) - comment_count = str_to_int(self._html_search_regex( - r']*>([\d,\.]+)', - webpage, 'comment count', fatal=False)) - - videos = re.findall( - r'playerData\.cdnPath([0-9]{3,})\s*=\s*(?:encodeURIComponent\()?["\']([^"\']+)["\']', webpage) - heights = [int(video[0]) for video in videos] - video_urls = list(map(compat_urllib_parse_unquote, [video[1] for video in videos])) - if webpage.find(r'flashvars\.encrypted = "true"') != -1: - password = self._search_regex( - r'flashvars\.video_title = "([^"]+)', - webpage, 'password').replace('+', ' ') - video_urls = list(map( - lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), - video_urls)) + title = video['title'] formats = [] - for height, video_url in zip(heights, video_urls): - path = compat_urllib_parse_urlparse(video_url).path - m = re.search(r'/(?P\d+)[pP]_(?P\d+)[kK]', path) - if m: - tbr = int(m.group('tbr')) - height = int(m.group('height')) - else: - tbr = None - formats.append({ - 'url': video_url, - 'format_id': '%dp' % height, - 'height': height, - 'tbr': tbr, + videos = video.get('videos') + if isinstance(videos, dict): + for format_id, format_url in videos.items(): + video_url = url_or_none(format_url) + if not format_url: + continue + height = int_or_none(self._search_regex( + r'(\d+)[pP]', format_id, 'height', default=None)) + m = re.search( + r'/(?P\d+)[pP]_(?P\d+)[kK]', video_url) + if m: + tbr = int(m.group('tbr')) + height = height or int(m.group('height')) + else: + tbr = None + formats.append({ + 'url': video_url, + 'format_id': '%dp' % height if height else format_id, + 'height': height, + 'tbr': tbr, + }) + m3u8_url = url_or_none(video.get('HLS')) + if m3u8_url: + formats.extend(self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False)) + self._sort_formats(formats, ('height', 'tbr', 'width', 'format_id')) + + view_count = str_to_int(video.get('viewed')) + + thumbnails = [] + for preference, t in enumerate(('', '2x'), start=0): + thumbnail_url = url_or_none(video.get('poster%s' % t)) + if not thumbnail_url: + continue + thumbnails.append({ + 'url': thumbnail_url, + 'preference': preference, }) - self._sort_formats(formats) - age_limit = self._rta_search(webpage) + def extract_names(key): + entries_list = video.get(key) + if not isinstance(entries_list, list): + return + entries = [] + for entry in entries_list: + name = str_or_none(entry.get('name')) + if name: + entries.append(name) + return entries - return { + categories = extract_names('categories') + tags = extract_names('tags') + + uploader = None + info = {} + + webpage = self._download_webpage( + 'https://www.spankwire.com/_/video%s/' % video_id, video_id, + fatal=False) + if webpage: + info = self._search_json_ld(webpage, video_id, default={}) + thumbnail_url = None + if 'thumbnail' in info: + thumbnail_url = url_or_none(info['thumbnail']) + del info['thumbnail'] + if not thumbnail_url: + thumbnail_url = self._og_search_thumbnail(webpage) + if thumbnail_url: + thumbnails.append({ + 'url': thumbnail_url, + 'preference': 10, + }) + uploader = self._html_search_regex( + r'(?s)by\s*]+\bclass=["\']uploaded__by[^>]*>(.+?)    ', + webpage, 'uploader', fatal=False) + if not view_count: + view_count = str_to_int(self._search_regex( + r'data-views=["\']([\d,.]+)', webpage, 'view count', + fatal=False)) + + return merge_dicts({ 'id': video_id, 'title': title, - 'description': description, - 'thumbnail': thumbnail, + 'description': video.get('description'), + 'duration': int_or_none(video.get('duration')), + 'thumbnails': thumbnails, 'uploader': uploader, - 'uploader_id': uploader_id, - 'upload_date': upload_date, + 'uploader_id': str_or_none(video.get('userId')), + 'timestamp': int_or_none(video.get('time_approved_on')), + 'average_rating': float_or_none(video.get('rating')), 'view_count': view_count, - 'comment_count': comment_count, + 'comment_count': int_or_none(video.get('comments')), + 'age_limit': 18, + 'categories': categories, + 'tags': tags, 'formats': formats, - 'age_limit': age_limit, - } + }, info) From 8fae1a04eb20279a76d6b1eccdb8249718ad9942 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 5 Apr 2020 20:42:10 +0700 Subject: [PATCH 408/422] [spankwire] Add support for generic embeds (refs #24633) --- youtube_dl/extractor/generic.py | 6 ++++++ youtube_dl/extractor/spankwire.py | 6 ++++++ 2 files changed, 12 insertions(+) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index a495ee15a..63b52306a 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -60,6 +60,7 @@ from .tnaflix import TNAFlixNetworkEmbedIE from .drtuber import DrTuberIE from .redtube import RedTubeIE from .tube8 import Tube8IE +from .spankwire import SpankwireIE from .vimeo import VimeoIE from .dailymotion import DailymotionIE from .dailymail import DailyMailIE @@ -2715,6 +2716,11 @@ class GenericIE(InfoExtractor): if tube8_urls: return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key()) + # Look for embedded Spankwire player + spankwire_urls = SpankwireIE._extract_urls(webpage) + if spankwire_urls: + return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key()) + # Look for embedded Tvigle player mobj = re.search( r']+?src=(["\'])(?P(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage) diff --git a/youtube_dl/extractor/spankwire.py b/youtube_dl/extractor/spankwire.py index 8f67463ed..35ab9ec37 100644 --- a/youtube_dl/extractor/spankwire.py +++ b/youtube_dl/extractor/spankwire.py @@ -67,6 +67,12 @@ class SpankwireIE(InfoExtractor): 'only_matching': True, }] + @staticmethod + def _extract_urls(webpage): + return re.findall( + r']+\bsrc=["\']((?:https?:)?//(?:www\.)?spankwire\.com/EmbedPlayer\.aspx/?\?.*?\bArticleId=\d+)', + webpage) + def _real_extract(self, url): video_id = self._match_id(url) From 52c4c51556df15f98c9cda911e36995fe0fc0a47 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 5 Apr 2020 20:56:14 +0700 Subject: [PATCH 409/422] [youporn] Add support form generic embeds --- youtube_dl/extractor/generic.py | 6 ++++++ youtube_dl/extractor/youporn.py | 23 +++++++++++++++++------ 2 files changed, 23 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 63b52306a..0ada6354e 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -61,6 +61,7 @@ from .drtuber import DrTuberIE from .redtube import RedTubeIE from .tube8 import Tube8IE from .spankwire import SpankwireIE +from .youporn import YouPornIE from .vimeo import VimeoIE from .dailymotion import DailymotionIE from .dailymail import DailyMailIE @@ -2721,6 +2722,11 @@ class GenericIE(InfoExtractor): if spankwire_urls: return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key()) + # Look for embedded YouPorn player + youporn_urls = YouPornIE._extract_urls(webpage) + if youporn_urls: + return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key()) + # Look for embedded Tvigle player mobj = re.search( r']+?src=(["\'])(?P(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage) diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py index d4eccb4b2..e7fca22de 100644 --- a/youtube_dl/extractor/youporn.py +++ b/youtube_dl/extractor/youporn.py @@ -5,7 +5,6 @@ import re from .common import InfoExtractor from ..utils import ( int_or_none, - sanitized_Request, str_to_int, unescapeHTML, unified_strdate, @@ -15,7 +14,7 @@ from ..aes import aes_decrypt_text class YouPornIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?youporn\.com/watch/(?P\d+)/(?P[^/?#&]+)' + _VALID_URL = r'https?://(?:www\.)?youporn\.com/(?:watch|embed)/(?P\d+)(?:/(?P[^/?#&]+))?' _TESTS = [{ 'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/', 'md5': '3744d24c50438cf5b6f6d59feb5055c2', @@ -57,16 +56,28 @@ class YouPornIE(InfoExtractor): 'params': { 'skip_download': True, }, + }, { + 'url': 'https://www.youporn.com/embed/505835/sex-ed-is-it-safe-to-masturbate-daily/', + 'only_matching': True, + }, { + 'url': 'http://www.youporn.com/watch/505835', + 'only_matching': True, }] + @staticmethod + def _extract_urls(webpage): + return re.findall( + r']+\bsrc=["\']((?:https?:)?//(?:www\.)?youporn\.com/embed/\d+)', + webpage) + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - display_id = mobj.group('display_id') + display_id = mobj.group('display_id') or video_id - request = sanitized_Request(url) - request.add_header('Cookie', 'age_verified=1') - webpage = self._download_webpage(request, display_id) + webpage = self._download_webpage( + 'http://www.youporn.com/watch/%s' % video_id, display_id, + headers={'Cookie': 'age_verified=1'}) title = self._html_search_regex( r'(?s)]+class=["\']watchVideoTitle[^>]+>(.+?)', From 4e7b5bba5fb73502476c61e4931284c9c3d3d232 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 5 Apr 2020 21:27:36 +0700 Subject: [PATCH 410/422] [mofosex] Add support for generic embeds (closes #24633) --- youtube_dl/extractor/extractors.py | 5 ++++- youtube_dl/extractor/generic.py | 6 ++++++ youtube_dl/extractor/mofosex.py | 23 +++++++++++++++++++++++ 3 files changed, 33 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index ef803b8a7..e407ab3d9 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -636,7 +636,10 @@ from .mixcloud import ( from .mlb import MLBIE from .mnet import MnetIE from .moevideo import MoeVideoIE -from .mofosex import MofosexIE +from .mofosex import ( + MofosexIE, + MofosexEmbedIE, +) from .mojvideo import MojvideoIE from .morningstar import MorningstarIE from .motherless import ( diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 0ada6354e..ce8252f6a 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -60,6 +60,7 @@ from .tnaflix import TNAFlixNetworkEmbedIE from .drtuber import DrTuberIE from .redtube import RedTubeIE from .tube8 import Tube8IE +from .mofosex import MofosexEmbedIE from .spankwire import SpankwireIE from .youporn import YouPornIE from .vimeo import VimeoIE @@ -2717,6 +2718,11 @@ class GenericIE(InfoExtractor): if tube8_urls: return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key()) + # Look for embedded Mofosex player + mofosex_urls = MofosexEmbedIE._extract_urls(webpage) + if mofosex_urls: + return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key()) + # Look for embedded Spankwire player spankwire_urls = SpankwireIE._extract_urls(webpage) if spankwire_urls: diff --git a/youtube_dl/extractor/mofosex.py b/youtube_dl/extractor/mofosex.py index 1c652813a..5234cac02 100644 --- a/youtube_dl/extractor/mofosex.py +++ b/youtube_dl/extractor/mofosex.py @@ -1,5 +1,8 @@ from __future__ import unicode_literals +import re + +from .common import InfoExtractor from ..utils import ( int_or_none, str_to_int, @@ -54,3 +57,23 @@ class MofosexIE(KeezMoviesIE): }) return info + + +class MofosexEmbedIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?mofosex\.com/embed/?\?.*?\bvideoid=(?P\d+)' + _TESTS = [{ + 'url': 'https://www.mofosex.com/embed/?videoid=318131&referrer=KM', + 'only_matching': True, + }] + + @staticmethod + def _extract_urls(webpage): + return re.findall( + r']+\bsrc=["\']((?:https?:)?//(?:www\.)?mofosex\.com/embed/?\?.*?\bvideoid=\d+)', + webpage) + + def _real_extract(self, url): + video_id = self._match_id(url) + return self.url_result( + 'http://www.mofosex.com/videos/{0}/{0}.html'.format(video_id), + ie=MofosexIE.ie_key(), video_id=video_id) From 6a6e1a0cd8bacf5a23f731eedaa1783503470227 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 6 Apr 2020 02:05:06 +0700 Subject: [PATCH 411/422] [tele5] Fix extraction (closes #24553) --- youtube_dl/extractor/tele5.py | 61 ++++++++++++++++++++++++++++++----- 1 file changed, 53 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/tele5.py b/youtube_dl/extractor/tele5.py index 33a72083b..364556a1f 100644 --- a/youtube_dl/extractor/tele5.py +++ b/youtube_dl/extractor/tele5.py @@ -1,9 +1,19 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor +from .jwplatform import JWPlatformIE from .nexx import NexxIE -from ..compat import compat_urlparse +from ..compat import ( + compat_str, + compat_urlparse, +) +from ..utils import ( + NO_DEFAULT, + try_get, +) class Tele5IE(InfoExtractor): @@ -44,14 +54,49 @@ class Tele5IE(InfoExtractor): qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) video_id = (qs.get('vid') or qs.get('ve_id') or [None])[0] - if not video_id: + NEXX_ID_RE = r'\d{6,}' + JWPLATFORM_ID_RE = r'[a-zA-Z0-9]{8}' + + def nexx_result(nexx_id): + return self.url_result( + 'https://api.nexx.cloud/v3/759/videos/byid/%s' % nexx_id, + ie=NexxIE.ie_key(), video_id=nexx_id) + + nexx_id = jwplatform_id = None + + if video_id: + if re.match(NEXX_ID_RE, video_id): + return nexx_result(video_id) + elif re.match(JWPLATFORM_ID_RE, video_id): + jwplatform_id = video_id + + if not nexx_id: display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) - video_id = self._html_search_regex( - (r'id\s*=\s*["\']video-player["\'][^>]+data-id\s*=\s*["\'](\d+)', - r'\s+id\s*=\s*["\']player_(\d{6,})', - r'\bdata-id\s*=\s*["\'](\d{6,})'), webpage, 'video id') + + def extract_id(pattern, name, default=NO_DEFAULT): + return self._html_search_regex( + (r'id\s*=\s*["\']video-player["\'][^>]+data-id\s*=\s*["\'](%s)' % pattern, + r'\s+id\s*=\s*["\']player_(%s)' % pattern, + r'\bdata-id\s*=\s*["\'](%s)' % pattern), webpage, name, + default=default) + + nexx_id = extract_id(NEXX_ID_RE, 'nexx id', default=None) + if nexx_id: + return nexx_result(nexx_id) + + if not jwplatform_id: + jwplatform_id = extract_id(JWPLATFORM_ID_RE, 'jwplatform id') + + media = self._download_json( + 'https://cdn.jwplayer.com/v2/media/' + jwplatform_id, + display_id) + nexx_id = try_get( + media, lambda x: x['playlist'][0]['nexx_id'], compat_str) + + if nexx_id: + return nexx_result(nexx_id) return self.url_result( - 'https://api.nexx.cloud/v3/759/videos/byid/%s' % video_id, - ie=NexxIE.ie_key(), video_id=video_id) + 'jwplatform:%s' % jwplatform_id, ie=JWPlatformIE.ie_key(), + video_id=jwplatform_id) From 13b08034b53efdcf7055df92199a0f35cf1e172e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 7 Apr 2020 22:54:34 +0700 Subject: [PATCH 412/422] [extractor/common] Skip malformed ISM manifest XMLs while extracting ISM formats (#24667) --- youtube_dl/extractor/common.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index eaae5e484..c51a3a07d 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -2340,6 +2340,8 @@ class InfoExtractor(object): if res is False: return [] ism_doc, urlh = res + if ism_doc is None: + return [] return self._parse_ism_formats(ism_doc, urlh.geturl(), ism_id) From 91bd3bd0194119fccc91b7eafb7afdcda646ad57 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 7 Apr 2020 22:55:36 +0700 Subject: [PATCH 413/422] [tv4] Fix ISM formats extraction (closes #24667) --- youtube_dl/extractor/tv4.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/tv4.py b/youtube_dl/extractor/tv4.py index a819d048c..c498b0191 100644 --- a/youtube_dl/extractor/tv4.py +++ b/youtube_dl/extractor/tv4.py @@ -99,7 +99,7 @@ class TV4IE(InfoExtractor): manifest_url.replace('.m3u8', '.f4m'), video_id, f4m_id='hds', fatal=False)) formats.extend(self._extract_ism_formats( - re.sub(r'\.ism/.+?\.m3u8', r'.ism/Manifest', manifest_url), + re.sub(r'\.ism/.*?\.m3u8', r'.ism/Manifest', manifest_url), video_id, ism_id='mss', fatal=False)) if not formats and info.get('is_geo_restricted'): From c9595ee78027ecf6bedbdc33c690228fa7d3a5bb Mon Sep 17 00:00:00 2001 From: Felix Stupp Date: Tue, 7 Apr 2020 16:21:25 +0000 Subject: [PATCH 414/422] [twitch:clips] Extend _VALID_URL (closes #24290) (#24642) --- youtube_dl/extractor/twitch.py | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py index 0db2dca41..78ee0115c 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -643,7 +643,14 @@ class TwitchStreamIE(TwitchBaseIE): class TwitchClipsIE(TwitchBaseIE): IE_NAME = 'twitch:clips' - _VALID_URL = r'https?://(?:clips\.twitch\.tv/(?:embed\?.*?\bclip=|(?:[^/]+/)*)|(?:www\.)?twitch\.tv/[^/]+/clip/)(?P[^/?#&]+)' + _VALID_URL = r'''(?x) + https?:// + (?: + clips\.twitch\.tv/(?:embed\?.*?\bclip=|(?:[^/]+/)*)| + (?:(?:www|go|m)\.)?twitch\.tv/[^/]+/clip/ + ) + (?P[^/?#&]+) + ''' _TESTS = [{ 'url': 'https://clips.twitch.tv/FaintLightGullWholeWheat', @@ -669,6 +676,12 @@ class TwitchClipsIE(TwitchBaseIE): }, { 'url': 'https://clips.twitch.tv/embed?clip=InquisitiveBreakableYogurtJebaited', 'only_matching': True, + }, { + 'url': 'https://m.twitch.tv/rossbroadcast/clip/ConfidentBraveHumanChefFrank', + 'only_matching': True, + }, { + 'url': 'https://go.twitch.tv/rossbroadcast/clip/ConfidentBraveHumanChefFrank', + 'only_matching': True, }] def _real_extract(self, url): From dcc8522fdba4c9286ebc0548caf05b425bc68773 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 9 Apr 2020 02:11:19 +0700 Subject: [PATCH 415/422] [motherless] Fix extraction (closes #24699) --- youtube_dl/extractor/motherless.py | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/motherless.py b/youtube_dl/extractor/motherless.py index 43fd70f11..b1615b4d8 100644 --- a/youtube_dl/extractor/motherless.py +++ b/youtube_dl/extractor/motherless.py @@ -26,7 +26,7 @@ class MotherlessIE(InfoExtractor): 'categories': ['Gaming', 'anal', 'reluctant', 'rough', 'Wife'], 'upload_date': '20100913', 'uploader_id': 'famouslyfuckedup', - 'thumbnail': r're:http://.*\.jpg', + 'thumbnail': r're:https?://.*\.jpg', 'age_limit': 18, } }, { @@ -40,7 +40,7 @@ class MotherlessIE(InfoExtractor): 'game', 'hairy'], 'upload_date': '20140622', 'uploader_id': 'Sulivana7x', - 'thumbnail': r're:http://.*\.jpg', + 'thumbnail': r're:https?://.*\.jpg', 'age_limit': 18, }, 'skip': '404', @@ -54,7 +54,7 @@ class MotherlessIE(InfoExtractor): 'categories': ['superheroine heroine superher'], 'upload_date': '20140827', 'uploader_id': 'shade0230', - 'thumbnail': r're:http://.*\.jpg', + 'thumbnail': r're:https?://.*\.jpg', 'age_limit': 18, } }, { @@ -76,7 +76,8 @@ class MotherlessIE(InfoExtractor): raise ExtractorError('Video %s is for friends only' % video_id, expected=True) title = self._html_search_regex( - r'id="view-upload-title">\s+([^<]+)<', webpage, 'title') + (r'(?s)]+\bclass=["\']media-meta-title[^>]+>(.+?)', + r'id="view-upload-title">\s+([^<]+)<'), webpage, 'title') video_url = (self._html_search_regex( (r'setup\(\{\s*["\']file["\']\s*:\s*(["\'])(?P(?:(?!\1).)+)\1', r'fileurl\s*=\s*(["\'])(?P(?:(?!\1).)+)\1'), @@ -84,14 +85,15 @@ class MotherlessIE(InfoExtractor): or 'http://cdn4.videos.motherlessmedia.com/videos/%s.mp4?fs=opencloud' % video_id) age_limit = self._rta_search(webpage) view_count = str_to_int(self._html_search_regex( - r'Views\s+([^<]+)<', + (r'>(\d+)\s+Views<', r'Views\s+([^<]+)<'), webpage, 'view count', fatal=False)) like_count = str_to_int(self._html_search_regex( - r'Favorited\s+([^<]+)<', + (r'>(\d+)\s+Favorites<', r'Favorited\s+([^<]+)<'), webpage, 'like count', fatal=False)) upload_date = self._html_search_regex( - r'Uploaded\s+([^<]+)<', webpage, 'upload date') + (r'class=["\']count[^>]+>(\d+\s+[a-zA-Z]{3}\s+\d{4})<', + r'Uploaded\s+([^<]+)<'), webpage, 'upload date') if 'Ago' in upload_date: days = int(re.search(r'([0-9]+)', upload_date).group(1)) upload_date = (datetime.datetime.now() - datetime.timedelta(days=days)).strftime('%Y%m%d') From 5caf88ccb4bfe3d1b53885b78b2bc509ba333f15 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 9 Apr 2020 03:52:29 +0700 Subject: [PATCH 416/422] [nova:embed] Fix extraction (closes #24700) --- youtube_dl/extractor/nova.py | 106 +++++++++++++++++++++++------------ 1 file changed, 71 insertions(+), 35 deletions(-) diff --git a/youtube_dl/extractor/nova.py b/youtube_dl/extractor/nova.py index 2850af5db..47b9748f0 100644 --- a/youtube_dl/extractor/nova.py +++ b/youtube_dl/extractor/nova.py @@ -6,6 +6,7 @@ import re from .common import InfoExtractor from ..utils import ( clean_html, + determine_ext, int_or_none, js_to_json, qualities, @@ -33,42 +34,76 @@ class NovaEmbedIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - bitrates = self._parse_json( - self._search_regex( - r'(?s)(?:src|bitrates)\s*=\s*({.+?})\s*;', webpage, 'formats'), - video_id, transform_source=js_to_json) - - QUALITIES = ('lq', 'mq', 'hq', 'hd') - quality_key = qualities(QUALITIES) - + duration = None formats = [] - for format_id, format_list in bitrates.items(): - if not isinstance(format_list, list): - format_list = [format_list] - for format_url in format_list: - format_url = url_or_none(format_url) - if not format_url: - continue - if format_id == 'hls': - formats.extend(self._extract_m3u8_formats( - format_url, video_id, ext='mp4', - entry_protocol='m3u8_native', m3u8_id='hls', - fatal=False)) - continue - f = { - 'url': format_url, - } - f_id = format_id - for quality in QUALITIES: - if '%s.mp4' % quality in format_url: - f_id += '-%s' % quality - f.update({ - 'quality': quality_key(quality), - 'format_note': quality.upper(), + + player = self._parse_json( + self._search_regex( + r'Player\.init\s*\([^,]+,\s*({.+?})\s*,\s*{.+?}\s*\)\s*;', + webpage, 'player', default='{}'), video_id, fatal=False) + if player: + for format_id, format_list in player['tracks'].items(): + if not isinstance(format_list, list): + format_list = [format_list] + for format_dict in format_list: + if not isinstance(format_dict, dict): + continue + format_url = url_or_none(format_dict.get('src')) + format_type = format_dict.get('type') + ext = determine_ext(format_url) + if (format_type == 'application/x-mpegURL' + or format_id == 'HLS' or ext == 'm3u8'): + formats.extend(self._extract_m3u8_formats( + format_url, video_id, 'mp4', + entry_protocol='m3u8_native', m3u8_id='hls', + fatal=False)) + elif (format_type == 'application/dash+xml' + or format_id == 'DASH' or ext == 'mpd'): + formats.extend(self._extract_mpd_formats( + format_url, video_id, mpd_id='dash', fatal=False)) + else: + formats.append({ + 'url': format_url, }) - break - f['format_id'] = f_id - formats.append(f) + duration = int_or_none(player.get('duration')) + else: + # Old path, not actual as of 08.04.2020 + bitrates = self._parse_json( + self._search_regex( + r'(?s)(?:src|bitrates)\s*=\s*({.+?})\s*;', webpage, 'formats'), + video_id, transform_source=js_to_json) + + QUALITIES = ('lq', 'mq', 'hq', 'hd') + quality_key = qualities(QUALITIES) + + for format_id, format_list in bitrates.items(): + if not isinstance(format_list, list): + format_list = [format_list] + for format_url in format_list: + format_url = url_or_none(format_url) + if not format_url: + continue + if format_id == 'hls': + formats.extend(self._extract_m3u8_formats( + format_url, video_id, ext='mp4', + entry_protocol='m3u8_native', m3u8_id='hls', + fatal=False)) + continue + f = { + 'url': format_url, + } + f_id = format_id + for quality in QUALITIES: + if '%s.mp4' % quality in format_url: + f_id += '-%s' % quality + f.update({ + 'quality': quality_key(quality), + 'format_note': quality.upper(), + }) + break + f['format_id'] = f_id + formats.append(f) + self._sort_formats(formats) title = self._og_search_title( @@ -81,7 +116,8 @@ class NovaEmbedIE(InfoExtractor): r'poster\s*:\s*(["\'])(?P(?:(?!\1).)+)\1', webpage, 'thumbnail', fatal=False, group='value') duration = int_or_none(self._search_regex( - r'videoDuration\s*:\s*(\d+)', webpage, 'duration', fatal=False)) + r'videoDuration\s*:\s*(\d+)', webpage, 'duration', + default=duration)) return { 'id': video_id, From 6b09401b0ba95da5669d249c8930b3adb873d96e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 9 Apr 2020 22:42:43 +0700 Subject: [PATCH 417/422] [youtube] Skip broken multifeed videos (closes #24711) --- youtube_dl/extractor/youtube.py | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 908defecd..633b839e0 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1840,15 +1840,26 @@ class YoutubeIE(YoutubeBaseInfoExtractor): # fields may contain comma as well (see # https://github.com/ytdl-org/youtube-dl/issues/8536) feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed)) + + def feed_entry(name): + return try_get(feed_data, lambda x: x[name][0], compat_str) + + feed_id = feed_entry('id') + if not feed_id: + continue + feed_title = feed_entry('title') + title = video_title + if feed_title: + title += ' (%s)' % feed_title entries.append({ '_type': 'url_transparent', 'ie_key': 'Youtube', 'url': smuggle_url( '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]), {'force_singlefeed': True}), - 'title': '%s (%s)' % (video_title, feed_data['title'][0]), + 'title': title, }) - feed_ids.append(feed_data['id'][0]) + feed_ids.append(feed_id) self.to_screen( 'Downloading multifeed video (%s) - add --no-playlist to just download video %s' % (', '.join(feed_ids), video_id)) From b9e5f872916a7d753ae237459b10622c1c2c3471 Mon Sep 17 00:00:00 2001 From: tom Date: Thu, 9 Apr 2020 21:50:45 +1000 Subject: [PATCH 418/422] [soundcloud] Extract AAC format --- youtube_dl/extractor/soundcloud.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index ff6be0b54..02d56184d 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -350,6 +350,8 @@ class SoundcloudIE(InfoExtractor): format_id_list = [] if protocol: format_id_list.append(protocol) + if f.get('ext') == 'aac': + f['abr'] = '256' for k in ('ext', 'abr'): v = f.get(k) if v: From 75294a5ed03f4443970478f3f4eac572239cec45 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 10 Apr 2020 17:24:21 +0700 Subject: [PATCH 419/422] [soundcloud] Improve AAC format extraction (closes #19173, closes #24708) --- youtube_dl/extractor/soundcloud.py | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 02d56184d..422ce1626 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -246,7 +246,12 @@ class SoundcloudIE(InfoExtractor): 'comment_count': int, 'repost_count': int, }, - } + }, + { + # with AAC HQ format available via OAuth token + 'url': 'https://soundcloud.com/wandw/the-chainsmokers-ft-daya-dont-let-me-down-ww-remix-1', + 'only_matching': True, + }, ] _API_V2_BASE = 'https://api-v2.soundcloud.com/' @@ -350,7 +355,8 @@ class SoundcloudIE(InfoExtractor): format_id_list = [] if protocol: format_id_list.append(protocol) - if f.get('ext') == 'aac': + ext = f.get('ext') + if ext == 'aac': f['abr'] = '256' for k in ('ext', 'abr'): v = f.get(k) @@ -362,9 +368,13 @@ class SoundcloudIE(InfoExtractor): abr = f.get('abr') if abr: f['abr'] = int(abr) + if protocol == 'hls': + protocol = 'm3u8' if ext == 'aac' else 'm3u8_native' + else: + protocol = 'http' f.update({ 'format_id': '_'.join(format_id_list), - 'protocol': 'm3u8_native' if protocol == 'hls' else 'http', + 'protocol': protocol, 'preference': -10 if preview else None, }) formats.append(f) From 533f3e3557af85e28afd72d291cb51a769c7dd7a Mon Sep 17 00:00:00 2001 From: AndrewMBL <62922222+AndrewMBL@users.noreply.github.com> Date: Tue, 31 Mar 2020 15:25:04 +1100 Subject: [PATCH 420/422] [thisoldhouse] Fix video id extraction (closes #24548) Added support for: with of without "www." and either ".chorus.build" or ".com" It now validated correctly on older URL's ```