diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 0c1569fd4..06711f73b 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.02.10*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.02.10** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.02.16*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.02.16** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -35,7 +35,7 @@ $ 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 2017.02.10 +[debug] youtube-dl version 2017.02.16 [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/.travis.yml b/.travis.yml index 4833c76e9..f41e11137 100644 --- a/.travis.yml +++ b/.travis.yml @@ -8,7 +8,10 @@ python: - "3.5" - "3.6" sudo: false -script: nosetests test --verbose +env: + - YTDL_TEST_SET=core + - YTDL_TEST_SET=download +script: ./devscripts/run_tests.sh notifications: email: - filippo.valsorda@gmail.com diff --git a/ChangeLog b/ChangeLog index d4c8081f7..8ef8a8307 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,58 @@ +version 2017.02.16 + +Core ++ [utils] Add support for quoted string literals in --match-filter (#8050, + #12142, #12144) + +Extractors +* [ceskatelevize] Lower priority for audio description sources (#12119) +* [amcnetworks] Fix extraction (#12127) +* [pinkbike] Fix uploader extraction (#12054) ++ [onetpl] Add support for businessinsider.com.pl and plejada.pl ++ [onetpl] Add support for onet.pl (#10507) ++ [onetmvp] Add shortcut extractor ++ [vodpl] Add support for vod.pl (#12122) ++ [pornhub] Extract video URL from tv platform site (#12007, #12129) ++ [ceskatelevize] Extract DASH formats (#12119, #12133) + + +version 2017.02.14 + +Core +* TypeError is fixed with Python 2.7.13 on Windows (#11540, #12085) + +Extractor +* [zdf] Fix extraction (#12117) +* [xtube] Fix extraction for both kinds of video id (#12088) +* [xtube] Improve title extraction (#12088) ++ [lemonde] Fallback delegate extraction to generic extractor (#12115, #12116) +* [bellmedia] Allow video id longer than 6 characters (#12114) ++ [limelight] Add support for referer protected videos +* [disney] Improve extraction (#4975, #11000, #11882, #11936) +* [hotstar] Improve extraction (#12096) +* [einthusan] Fix extraction (#11416) ++ [aenetworks] Add support for lifetimemovieclub.com (#12097) +* [youtube] Fix parsing codecs (#12091) + + +version 2017.02.11 + +Core ++ [utils] Introduce get_elements_by_class and get_elements_by_attribute + utility functions ++ [extractor/common] Skip m3u8 manifests protected with Adobe Flash Access + +Extractor +* [pluralsight:course] Fix extraction (#12075) ++ [bbc] Extract m3u8 formats with 320k audio +* [facebook] Relax video id matching (#11017, #12055, #12056) ++ [corus] Add support for Corus Entertainment sites (#12060, #9164) ++ [pluralsight] Detect blocked account error message (#12070) ++ [bloomberg] Add another video id pattern (#12062) +* [extractor/commonmistakes] Restrict URL regular expression (#12050) ++ [tvplayer] Add support for tvplayer.com + + version 2017.02.10 Extractors diff --git a/devscripts/run_tests.sh b/devscripts/run_tests.sh new file mode 100755 index 000000000..7f4c1e083 --- /dev/null +++ b/devscripts/run_tests.sh @@ -0,0 +1,19 @@ +#!/bin/bash + +DOWNLOAD_TESTS="age_restriction|download|subtitles|write_annotations|iqiyi_sdk_interpreter" + +test_set="" + +case "$YTDL_TEST_SET" in + core) + test_set="-I test_($DOWNLOAD_TESTS)\.py" + ;; + download) + test_set="-I test_(?!$DOWNLOAD_TESTS).+\.py" + ;; + *) + break + ;; +esac + +nosetests test --verbose $test_set diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 76882f3b5..5a436e8f7 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -169,6 +169,7 @@ - **ComedyCentralShortname** - **ComedyCentralTV** - **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED + - **Corus** - **Coub** - **Cracked** - **Crackle** @@ -309,7 +310,6 @@ - **HellPorno** - **Helsinki**: helsinki.fi - **HentaiStigma** - - **HGTV** - **hgtv.com:show** - **HistoricFilms** - **history:topic**: History.com Topic @@ -546,8 +546,10 @@ - **OktoberfestTV** - **on.aol.com** - **OnDemandKorea** + - **onet.pl** - **onet.tv** - **onet.tv:channel** + - **OnetMVP** - **OnionStudios** - **Ooyala** - **OoyalaExternal** @@ -806,6 +808,7 @@ - **tvp**: Telewizja Polska - **tvp:embed**: Telewizja Polska - **tvp:series** + - **TVPlayer** - **Tweakers** - **twitch:chapter** - **twitch:clips** @@ -899,6 +902,7 @@ - **vlive** - **vlive:channel** - **Vodlocker** + - **VODPl** - **VODPlatform** - **VoiceRepublic** - **VoxMedia** diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py index 8bf00bea9..2cfcf743a 100644 --- a/test/test_YoutubeDL.py +++ b/test/test_YoutubeDL.py @@ -1,4 +1,5 @@ #!/usr/bin/env python +# coding: utf-8 from __future__ import unicode_literals @@ -540,10 +541,10 @@ class TestYoutubeDL(unittest.TestCase): self.assertEqual(ydl._format_note({}), '') assertRegexpMatches(self, ydl._format_note({ 'vbr': 10, - }), '^\s*10k$') + }), r'^\s*10k$') assertRegexpMatches(self, ydl._format_note({ 'fps': 30, - }), '^30fps$') + }), r'^30fps$') def test_postprocessors(self): filename = 'post-processor-testfile.mp4' @@ -606,6 +607,8 @@ class TestYoutubeDL(unittest.TestCase): 'duration': 30, 'filesize': 10 * 1024, 'playlist_id': '42', + 'uploader': "變態妍字幕版 太妍 тест", + 'creator': "тест ' 123 ' тест--", } second = { 'id': '2', @@ -616,6 +619,7 @@ class TestYoutubeDL(unittest.TestCase): 'description': 'foo', 'filesize': 5 * 1024, 'playlist_id': '43', + 'uploader': "тест 123", } videos = [first, second] @@ -656,6 +660,26 @@ class TestYoutubeDL(unittest.TestCase): res = get_videos(f) self.assertEqual(res, ['1']) + f = match_filter_func('uploader = "變態妍字幕版 太妍 тест"') + res = get_videos(f) + self.assertEqual(res, ['1']) + + f = match_filter_func('uploader != "變態妍字幕版 太妍 тест"') + res = get_videos(f) + self.assertEqual(res, ['2']) + + f = match_filter_func('creator = "тест \' 123 \' тест--"') + res = get_videos(f) + self.assertEqual(res, ['1']) + + f = match_filter_func("creator = 'тест \\' 123 \\' тест--'") + res = get_videos(f) + self.assertEqual(res, ['1']) + + f = match_filter_func(r"creator = 'тест \' 123 \' тест--' & duration > 30") + res = get_videos(f) + self.assertEqual(res, []) + def test_playlist_items_selection(self): entries = [{ 'id': compat_str(i), diff --git a/test/test_utils.py b/test/test_utils.py index edc712f07..3cdb21d40 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -34,6 +34,9 @@ from youtube_dl.utils import ( find_xpath_attr, fix_xml_ampersands, get_element_by_class, + get_element_by_attribute, + get_elements_by_class, + get_elements_by_attribute, InAdvancePagedList, intlist_to_bytes, is_html, @@ -1124,6 +1127,32 @@ The first line self.assertEqual(get_element_by_class('foo', html), 'nice') self.assertEqual(get_element_by_class('no-such-class', html), None) + def test_get_element_by_attribute(self): + html = ''' + nice + ''' + + self.assertEqual(get_element_by_attribute('class', 'foo bar', html), 'nice') + self.assertEqual(get_element_by_attribute('class', 'foo', html), None) + self.assertEqual(get_element_by_attribute('class', 'no-such-foo', html), None) + + def test_get_elements_by_class(self): + html = ''' + nicealso nice + ''' + + self.assertEqual(get_elements_by_class('foo', html), ['nice', 'also nice']) + self.assertEqual(get_elements_by_class('no-such-class', html), []) + + def test_get_elements_by_attribute(self): + html = ''' + nicealso nice + ''' + + self.assertEqual(get_elements_by_attribute('class', 'foo bar', html), ['nice', 'also nice']) + self.assertEqual(get_elements_by_attribute('class', 'foo', html), []) + self.assertEqual(get_elements_by_attribute('class', 'no-such-foo', html), []) + if __name__ == '__main__': unittest.main() diff --git a/youtube_dl/extractor/aenetworks.py b/youtube_dl/extractor/aenetworks.py index c97317400..dd96a47ce 100644 --- a/youtube_dl/extractor/aenetworks.py +++ b/youtube_dl/extractor/aenetworks.py @@ -23,7 +23,7 @@ class AENetworksBaseIE(ThePlatformIE): class AENetworksIE(AENetworksBaseIE): IE_NAME = 'aenetworks' IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network' - _VALID_URL = r'https?://(?:www\.)?(?P(?:history|aetv|mylifetime)\.com|fyi\.tv)/(?:shows/(?P[^/]+(?:/[^/]+){0,2})|movies/(?P[^/]+)/full-movie)' + _VALID_URL = r'https?://(?:www\.)?(?P(?:history|aetv|mylifetime|lifetimemovieclub)\.com|fyi\.tv)/(?:shows/(?P[^/]+(?:/[^/]+){0,2})|movies/(?P[^/]+)(?:/full-movie)?)' _TESTS = [{ 'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1', 'md5': 'a97a65f7e823ae10e9244bc5433d5fe6', @@ -62,11 +62,15 @@ class AENetworksIE(AENetworksBaseIE): }, { 'url': 'http://www.mylifetime.com/movies/center-stage-on-pointe/full-movie', 'only_matching': True + }, { + 'url': 'https://www.lifetimemovieclub.com/movies/a-killer-among-us', + 'only_matching': True }] _DOMAIN_TO_REQUESTOR_ID = { 'history.com': 'HISTORY', 'aetv.com': 'AETV', 'mylifetime.com': 'LIFETIME', + 'lifetimemovieclub.com': 'LIFETIMEMOVIECLUB', 'fyi.tv': 'FYI', } diff --git a/youtube_dl/extractor/amcnetworks.py b/youtube_dl/extractor/amcnetworks.py index 87c803e94..b71d1a093 100644 --- a/youtube_dl/extractor/amcnetworks.py +++ b/youtube_dl/extractor/amcnetworks.py @@ -53,20 +53,30 @@ class AMCNetworksIE(ThePlatformIE): 'mbr': 'true', 'manifest': 'm3u', } - media_url = self._search_regex(r'window\.platformLinkURL\s*=\s*[\'"]([^\'"]+)', webpage, 'media url') + media_url = self._search_regex( + r'window\.platformLinkURL\s*=\s*[\'"]([^\'"]+)', + webpage, 'media url') theplatform_metadata = self._download_theplatform_metadata(self._search_regex( - r'https?://link.theplatform.com/s/([^?]+)', media_url, 'theplatform_path'), display_id) + r'link\.theplatform\.com/s/([^?]+)', + media_url, 'theplatform_path'), display_id) info = self._parse_theplatform_metadata(theplatform_metadata) video_id = theplatform_metadata['pid'] title = theplatform_metadata['title'] rating = theplatform_metadata['ratings'][0]['rating'] - auth_required = self._search_regex(r'window\.authRequired\s*=\s*(true|false);', webpage, 'auth required') + auth_required = self._search_regex( + r'window\.authRequired\s*=\s*(true|false);', + webpage, 'auth required') if auth_required == 'true': - requestor_id = self._search_regex(r'window\.requestor_id\s*=\s*[\'"]([^\'"]+)', webpage, 'requestor id') - resource = self._get_mvpd_resource(requestor_id, title, video_id, rating) - query['auth'] = self._extract_mvpd_auth(url, video_id, requestor_id, resource) + requestor_id = self._search_regex( + r'window\.requestor_id\s*=\s*[\'"]([^\'"]+)', + webpage, 'requestor id') + resource = self._get_mvpd_resource( + requestor_id, title, video_id, rating) + query['auth'] = self._extract_mvpd_auth( + url, video_id, requestor_id, resource) media_url = update_url_query(media_url, query) - formats, subtitles = self._extract_theplatform_smil(media_url, video_id) + formats, subtitles = self._extract_theplatform_smil( + media_url, video_id) self._sort_formats(formats) info.update({ 'id': video_id, @@ -78,9 +88,11 @@ class AMCNetworksIE(ThePlatformIE): if ns_keys: ns = list(ns_keys)[0] series = theplatform_metadata.get(ns + '$show') - season_number = int_or_none(theplatform_metadata.get(ns + '$season')) + season_number = int_or_none( + theplatform_metadata.get(ns + '$season')) episode = theplatform_metadata.get(ns + '$episodeTitle') - episode_number = int_or_none(theplatform_metadata.get(ns + '$episode')) + episode_number = int_or_none( + theplatform_metadata.get(ns + '$episode')) if season_number: title = 'Season %d - %s' % (season_number, title) if series: diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index b17916137..8a2ed0ab6 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -225,6 +225,8 @@ class BBCCoUkIE(InfoExtractor): } ] + _USP_RE = r'/([^/]+?)\.ism(?:\.hlsv2\.ism)?/[^/]+\.m3u8' + class MediaSelectionError(Exception): def __init__(self, id): self.id = id @@ -336,6 +338,15 @@ class BBCCoUkIE(InfoExtractor): formats.extend(self._extract_m3u8_formats( href, programme_id, ext='mp4', entry_protocol='m3u8_native', m3u8_id=format_id, fatal=False)) + if re.search(self._USP_RE, href): + usp_formats = self._extract_m3u8_formats( + re.sub(self._USP_RE, r'/\1.ism/\1.m3u8', href), + programme_id, ext='mp4', entry_protocol='m3u8_native', + m3u8_id=format_id, fatal=False) + for f in usp_formats: + if f.get('height') and f['height'] > 720: + continue + formats.append(f) elif transfer_format == 'hds': formats.extend(self._extract_f4m_formats( href, programme_id, f4m_id=format_id, fatal=False)) diff --git a/youtube_dl/extractor/bellmedia.py b/youtube_dl/extractor/bellmedia.py index 32326ed9e..1f5b6ed92 100644 --- a/youtube_dl/extractor/bellmedia.py +++ b/youtube_dl/extractor/bellmedia.py @@ -24,7 +24,7 @@ class BellMediaIE(InfoExtractor): space )\.ca| much\.com - )/.*?(?:\bvid=|-vid|~|%7E|/(?:episode)?)(?P[0-9]{6})''' + )/.*?(?:\bvid=|-vid|~|%7E|/(?:episode)?)(?P[0-9]{6,})''' _TESTS = [{ 'url': 'http://www.ctv.ca/video/player?vid=706966', 'md5': 'ff2ebbeae0aa2dcc32a830c3fd69b7b0', @@ -55,6 +55,9 @@ class BellMediaIE(InfoExtractor): }, { 'url': 'http://www.much.com/shows/the-almost-impossible-gameshow/928979/episode-6', 'only_matching': True, + }, { + 'url': 'http://www.ctv.ca/DCs-Legends-of-Tomorrow/Video/S2E11-Turncoat-vid1051430', + 'only_matching': True, }] _DOMAINS = { 'thecomedynetwork': 'comedy', diff --git a/youtube_dl/extractor/bloomberg.py b/youtube_dl/extractor/bloomberg.py index c5e11e8eb..2fbfad1ba 100644 --- a/youtube_dl/extractor/bloomberg.py +++ b/youtube_dl/extractor/bloomberg.py @@ -33,6 +33,10 @@ class BloombergIE(InfoExtractor): 'params': { 'format': 'best[format_id^=hds]', }, + }, { + # data-bmmrid= + 'url': 'https://www.bloomberg.com/politics/articles/2017-02-08/le-pen-aide-briefed-french-central-banker-on-plan-to-print-money', + 'only_matching': True, }, { 'url': 'http://www.bloomberg.com/news/articles/2015-11-12/five-strange-things-that-have-been-happening-in-financial-markets', 'only_matching': True, @@ -45,9 +49,10 @@ class BloombergIE(InfoExtractor): name = self._match_id(url) webpage = self._download_webpage(url, name) video_id = self._search_regex( - (r'["\']bmmrId["\']\s*:\s*(["\'])(?P(?:(?!\1).)+)\1', - r'videoId\s*:\s*(["\'])(?P(?:(?!\1).)+)\1'), - webpage, 'id', group='url', default=None) + (r'["\']bmmrId["\']\s*:\s*(["\'])(?P(?:(?!\1).)+)\1', + r'videoId\s*:\s*(["\'])(?P(?:(?!\1).)+)\1', + r'data-bmmrid=(["\'])(?P(?:(?!\1).)+)\1'), + webpage, 'id', group='id', default=None) if not video_id: bplayer_data = self._parse_json(self._search_regex( r'BPlayer\(null,\s*({[^;]+})\);', webpage, 'id'), name) diff --git a/youtube_dl/extractor/ceskatelevize.py b/youtube_dl/extractor/ceskatelevize.py index 4f88c31ad..b1dfacf80 100644 --- a/youtube_dl/extractor/ceskatelevize.py +++ b/youtube_dl/extractor/ceskatelevize.py @@ -13,6 +13,7 @@ from ..utils import ( float_or_none, sanitized_Request, urlencode_postdata, + USER_AGENTS, ) @@ -21,10 +22,10 @@ class CeskaTelevizeIE(InfoExtractor): _TESTS = [{ 'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220', 'info_dict': { - 'id': '61924494876951776', + 'id': '61924494877246241', 'ext': 'mp4', - 'title': 'Hyde Park Civilizace', - 'description': 'md5:fe93f6eda372d150759d11644ebbfb4a', + 'title': 'Hyde Park Civilizace: Život v Grónsku', + 'description': 'md5:3fec8f6bb497be5cdb0c9e8781076626', 'thumbnail': r're:^https?://.*\.jpg', 'duration': 3350, }, @@ -114,70 +115,100 @@ class CeskaTelevizeIE(InfoExtractor): 'requestSource': 'iVysilani', } - req = sanitized_Request( - 'http://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist', - data=urlencode_postdata(data)) - - req.add_header('Content-type', 'application/x-www-form-urlencoded') - req.add_header('x-addr', '127.0.0.1') - req.add_header('X-Requested-With', 'XMLHttpRequest') - req.add_header('Referer', url) - - playlistpage = self._download_json(req, playlist_id) - - playlist_url = playlistpage['url'] - if playlist_url == 'error_region': - raise ExtractorError(NOT_AVAILABLE_STRING, expected=True) - - req = sanitized_Request(compat_urllib_parse_unquote(playlist_url)) - req.add_header('Referer', url) - - playlist_title = self._og_search_title(webpage, default=None) - playlist_description = self._og_search_description(webpage, default=None) - - playlist = self._download_json(req, playlist_id)['playlist'] - playlist_len = len(playlist) - entries = [] - for item in playlist: - is_live = item.get('type') == 'LIVE' - formats = [] - for format_id, stream_url in item['streamUrls'].items(): - formats.extend(self._extract_m3u8_formats( - stream_url, playlist_id, 'mp4', - entry_protocol='m3u8' if is_live else 'm3u8_native', - fatal=False)) - self._sort_formats(formats) - item_id = item.get('id') or item['assetId'] - title = item['title'] + for user_agent in (None, USER_AGENTS['Safari']): + req = sanitized_Request( + 'http://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist', + data=urlencode_postdata(data)) - duration = float_or_none(item.get('duration')) - thumbnail = item.get('previewImageUrl') + req.add_header('Content-type', 'application/x-www-form-urlencoded') + req.add_header('x-addr', '127.0.0.1') + req.add_header('X-Requested-With', 'XMLHttpRequest') + if user_agent: + req.add_header('User-Agent', user_agent) + req.add_header('Referer', url) - subtitles = {} - if item.get('type') == 'VOD': - subs = item.get('subtitles') - if subs: - subtitles = self.extract_subtitles(episode_id, subs) + playlistpage = self._download_json(req, playlist_id, fatal=False) - if playlist_len == 1: - final_title = playlist_title or title - if is_live: - final_title = self._live_title(final_title) - else: - final_title = '%s (%s)' % (playlist_title, title) + if not playlistpage: + continue - entries.append({ - 'id': item_id, - 'title': final_title, - 'description': playlist_description if playlist_len == 1 else None, - 'thumbnail': thumbnail, - 'duration': duration, - 'formats': formats, - 'subtitles': subtitles, - 'is_live': is_live, - }) + playlist_url = playlistpage['url'] + if playlist_url == 'error_region': + raise ExtractorError(NOT_AVAILABLE_STRING, expected=True) + + req = sanitized_Request(compat_urllib_parse_unquote(playlist_url)) + req.add_header('Referer', url) + + playlist_title = self._og_search_title(webpage, default=None) + playlist_description = self._og_search_description(webpage, default=None) + + playlist = self._download_json(req, playlist_id, fatal=False) + if not playlist: + continue + + playlist = playlist.get('playlist') + if not isinstance(playlist, list): + continue + + playlist_len = len(playlist) + + for num, item in enumerate(playlist): + is_live = item.get('type') == 'LIVE' + formats = [] + for format_id, stream_url in item.get('streamUrls', {}).items(): + if 'playerType=flash' in stream_url: + stream_formats = self._extract_m3u8_formats( + stream_url, playlist_id, 'mp4', + entry_protocol='m3u8' if is_live else 'm3u8_native', + m3u8_id='hls-%s' % format_id, fatal=False) + else: + stream_formats = self._extract_mpd_formats( + stream_url, playlist_id, + mpd_id='dash-%s' % format_id, fatal=False) + # See https://github.com/rg3/youtube-dl/issues/12119#issuecomment-280037031 + if format_id == 'audioDescription': + for f in stream_formats: + f['source_preference'] = -10 + formats.extend(stream_formats) + + if user_agent and len(entries) == playlist_len: + entries[num]['formats'].extend(formats) + continue + + item_id = item.get('id') or item['assetId'] + title = item['title'] + + duration = float_or_none(item.get('duration')) + thumbnail = item.get('previewImageUrl') + + subtitles = {} + if item.get('type') == 'VOD': + subs = item.get('subtitles') + if subs: + subtitles = self.extract_subtitles(episode_id, subs) + + if playlist_len == 1: + final_title = playlist_title or title + if is_live: + final_title = self._live_title(final_title) + else: + final_title = '%s (%s)' % (playlist_title, title) + + entries.append({ + 'id': item_id, + 'title': final_title, + 'description': playlist_description if playlist_len == 1 else None, + 'thumbnail': thumbnail, + 'duration': duration, + 'formats': formats, + 'subtitles': subtitles, + 'is_live': is_live, + }) + + for e in entries: + self._sort_formats(e['formats']) return self.playlist_result(entries, playlist_id, playlist_title, playlist_description) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 0b4e2ac20..9681453ca 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1208,6 +1208,9 @@ class InfoExtractor(object): m3u8_doc, urlh = res m3u8_url = urlh.geturl() + if '#EXT-X-FAXS-CM:' in m3u8_doc: # Adobe Flash Access + return [] + formats = [self._m3u8_meta_format(m3u8_url, ext, preference, m3u8_id)] format_url = lambda u: ( diff --git a/youtube_dl/extractor/corus.py b/youtube_dl/extractor/corus.py new file mode 100644 index 000000000..7b2f5008b --- /dev/null +++ b/youtube_dl/extractor/corus.py @@ -0,0 +1,72 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .theplatform import ThePlatformFeedIE +from ..utils import int_or_none + + +class CorusIE(ThePlatformFeedIE): + _VALID_URL = r'https?://(?:www\.)?(?P(?:globaltv|etcanada)\.com|(?:hgtv|foodnetwork|slice)\.ca)/(?: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, + }, + }, { + 'url': 'http://www.foodnetwork.ca/shows/chopped/video/episode/chocolate-obsession/video.html?v=872683587753', + 'only_matching': True, + }, { + 'url': 'http://etcanada.com/video/873675331955/meet-the-survivor-game-changers-castaways-part-2/', + '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, + }, + } + + 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']) diff --git a/youtube_dl/extractor/disney.py b/youtube_dl/extractor/disney.py index 396873c6d..939d1338c 100644 --- a/youtube_dl/extractor/disney.py +++ b/youtube_dl/extractor/disney.py @@ -9,13 +9,15 @@ from ..utils import ( unified_strdate, compat_str, determine_ext, + ExtractorError, ) class DisneyIE(InfoExtractor): _VALID_URL = r'''(?x) - https?://(?P(?:[^/]+\.)?(?:disney\.[a-z]{2,3}(?:\.[a-z]{2})?|disney(?:(?:me|latino)\.com|turkiye\.com\.tr)|starwars\.com))/(?:embed/|(?:[^/]+/)+[\w-]+-)(?P[a-z0-9]{24})''' + https?://(?P(?:[^/]+\.)?(?:disney\.[a-z]{2,3}(?:\.[a-z]{2})?|disney(?:(?:me|latino)\.com|turkiye\.com\.tr)|(?:starwars|marvelkids)\.com))/(?:(?:embed/|(?:[^/]+/)+[\w-]+-)(?P[a-z0-9]{24})|(?:[^/]+/)?(?P[^/?#]+))''' _TESTS = [{ + # Disney.EmbedVideo 'url': 'http://video.disney.com/watch/moana-trailer-545ed1857afee5a0ec239977', 'info_dict': { 'id': '545ed1857afee5a0ec239977', @@ -28,6 +30,20 @@ class DisneyIE(InfoExtractor): # m3u8 download 'skip_download': True, } + }, { + # Grill.burger + 'url': 'http://www.starwars.com/video/rogue-one-a-star-wars-story-intro-featurette', + 'info_dict': { + 'id': '5454e9f4e9804a552e3524c8', + 'ext': 'mp4', + 'title': '"Intro" Featurette: Rogue One: A Star Wars Story', + 'upload_date': '20170104', + 'description': 'Go behind-the-scenes of Rogue One: A Star Wars Story in this featurette with Director Gareth Edwards and the cast of the film.', + }, + 'params': { + # m3u8 download + 'skip_download': True, + } }, { 'url': 'http://videos.disneylatino.com/ver/spider-man-de-regreso-a-casa-primer-adelanto-543a33a1850bdcfcca13bae2', 'only_matching': True, @@ -43,31 +59,55 @@ class DisneyIE(InfoExtractor): }, { 'url': 'http://www.starwars.com/embed/54690d1e6c42e5f09a0fb097', 'only_matching': True, + }, { + 'url': 'http://spiderman.marvelkids.com/embed/522900d2ced3c565e4cc0677', + 'only_matching': True, + }, { + 'url': 'http://spiderman.marvelkids.com/videos/contest-of-champions-part-four-clip-1', + 'only_matching': True, + }, { + 'url': 'http://disneyjunior.en.disneyme.com/dj/watch-my-friends-tigger-and-pooh-promo', + 'only_matching': True, + }, { + 'url': 'http://disneyjunior.disney.com/galactech-the-galactech-grab-galactech-an-admiral-rescue', + 'only_matching': True, }] def _real_extract(self, url): - domain, video_id = re.match(self._VALID_URL, url).groups() - webpage = self._download_webpage( - 'http://%s/embed/%s' % (domain, video_id), video_id) - video_data = self._parse_json(self._search_regex( - r'Disney\.EmbedVideo=({.+});', webpage, 'embed data'), video_id)['video'] + domain, video_id, display_id = re.match(self._VALID_URL, url).groups() + if not video_id: + webpage = self._download_webpage(url, display_id) + grill = re.sub(r'"\s*\+\s*"', '', self._search_regex( + r'Grill\.burger\s*=\s*({.+})\s*:', + webpage, 'grill data')) + page_data = next(s for s in self._parse_json(grill, display_id)['stack'] if s.get('type') == 'video') + video_data = page_data['data'][0] + else: + webpage = self._download_webpage( + 'http://%s/embed/%s' % (domain, video_id), video_id) + page_data = self._parse_json(self._search_regex( + r'Disney\.EmbedVideo\s*=\s*({.+});', + webpage, 'embed data'), video_id) + video_data = page_data['video'] for external in video_data.get('externals', []): if external.get('source') == 'vevo': return self.url_result('vevo:' + external['data_id'], 'Vevo') + video_id = video_data['id'] title = video_data['title'] formats = [] for flavor in video_data.get('flavors', []): flavor_format = flavor.get('format') flavor_url = flavor.get('url') - if not flavor_url or not re.match(r'https?://', flavor_url): + if not flavor_url or not re.match(r'https?://', flavor_url) or flavor_format == 'mp4_access': continue tbr = int_or_none(flavor.get('bitrate')) if tbr == 99999: formats.extend(self._extract_m3u8_formats( - flavor_url, video_id, 'mp4', m3u8_id=flavor_format, fatal=False)) + flavor_url, video_id, 'mp4', + m3u8_id=flavor_format, fatal=False)) continue format_id = [] if flavor_format: @@ -88,6 +128,10 @@ class DisneyIE(InfoExtractor): 'ext': ext, 'vcodec': 'none' if (width == 0 and height == 0) else None, }) + if not formats and video_data.get('expired'): + raise ExtractorError( + '%s said: %s' % (self.IE_NAME, page_data['translations']['video_expired']), + expected=True) self._sort_formats(formats) subtitles = {} diff --git a/youtube_dl/extractor/einthusan.py b/youtube_dl/extractor/einthusan.py index 6ca07a13d..8a2a17b63 100644 --- a/youtube_dl/extractor/einthusan.py +++ b/youtube_dl/extractor/einthusan.py @@ -1,67 +1,94 @@ # coding: utf-8 from __future__ import unicode_literals +import base64 +import json + from .common import InfoExtractor -from ..compat import compat_urlparse +from ..compat import ( + compat_urlparse, + compat_str, +) from ..utils import ( - remove_start, - sanitized_Request, + extract_attributes, + ExtractorError, + get_elements_by_class, + urlencode_postdata, ) class EinthusanIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?einthusan\.com/movies/watch.php\?([^#]*?)id=(?P[0-9]+)' - _TESTS = [ - { - 'url': 'http://www.einthusan.com/movies/watch.php?id=2447', - 'md5': 'd71379996ff5b7f217eca034c34e3461', - 'info_dict': { - 'id': '2447', - 'ext': 'mp4', - 'title': 'Ek Villain', - 'thumbnail': r're:^https?://.*\.jpg$', - 'description': 'md5:9d29fc91a7abadd4591fb862fa560d93', - } - }, - { - 'url': 'http://www.einthusan.com/movies/watch.php?id=1671', - 'md5': 'b16a6fd3c67c06eb7c79c8a8615f4213', - 'info_dict': { - 'id': '1671', - 'ext': 'mp4', - 'title': 'Soodhu Kavvuum', - 'thumbnail': r're:^https?://.*\.jpg$', - 'description': 'md5:b40f2bf7320b4f9414f3780817b2af8c', - } - }, - ] + _VALID_URL = r'https?://einthusan\.tv/movie/watch/(?P[0-9]+)' + _TEST = { + 'url': 'https://einthusan.tv/movie/watch/9097/', + 'md5': 'ff0f7f2065031b8a2cf13a933731c035', + 'info_dict': { + 'id': '9097', + 'ext': 'mp4', + 'title': 'Ae Dil Hai Mushkil', + 'description': 'md5:33ef934c82a671a94652a9b4e54d931b', + 'thumbnail': r're:^https?://.*\.jpg$', + } + } + + # reversed from jsoncrypto.prototype.decrypt() in einthusan-PGMovieWatcher.js + def _decrypt(self, encrypted_data, video_id): + return self._parse_json(base64.b64decode(( + encrypted_data[:10] + encrypted_data[-1] + encrypted_data[12:-1] + ).encode('ascii')).decode('utf-8'), video_id) def _real_extract(self, url): video_id = self._match_id(url) - request = sanitized_Request(url) - request.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:43.0) Gecko/20100101 Firefox/43.0') - webpage = self._download_webpage(request, video_id) + webpage = self._download_webpage(url, video_id) - title = self._html_search_regex( - r'

]+class=["\']movie-title["\'][^>]*>(.+?)

', - webpage, 'title') + title = self._html_search_regex(r'

([^<]+)

', webpage, 'title') - video_id = self._search_regex( - r'data-movieid=["\'](\d+)', webpage, 'video id', default=video_id) + player_params = extract_attributes(self._search_regex( + r'(]+id="UIVideoPlayer"[^>]+>)', webpage, 'player parameters')) - m3u8_url = self._download_webpage( - 'http://cdn.einthusan.com/geturl/%s/hd/London,Washington,Toronto,Dallas,San,Sydney/' - % video_id, video_id, headers={'Referer': url}) - formats = self._extract_m3u8_formats( - m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native') + page_id = self._html_search_regex( + ']+data-pageid="([^"]+)"', webpage, 'page ID') + video_data = self._download_json( + 'https://einthusan.tv/ajax/movie/watch/%s/' % video_id, video_id, + data=urlencode_postdata({ + 'xEvent': 'UIVideoPlayer.PingOutcome', + 'xJson': json.dumps({ + 'EJOutcomes': player_params['data-ejpingables'], + 'NativeHLS': False + }), + 'arcVersion': 3, + 'appVersion': 59, + 'gorilla.csrf.Token': page_id, + }))['Data'] - description = self._html_search_meta('description', webpage) + if isinstance(video_data, compat_str) and video_data.startswith('/ratelimited/'): + raise ExtractorError( + 'Download rate reached. Please try again later.', expected=True) + + ej_links = self._decrypt(video_data['EJLinks'], video_id) + + formats = [] + + m3u8_url = ej_links.get('HLSLink') + if m3u8_url: + formats.extend(self._extract_m3u8_formats( + m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native')) + + mp4_url = ej_links.get('MP4Link') + if mp4_url: + formats.append({ + 'url': mp4_url, + }) + + self._sort_formats(formats) + + description = get_elements_by_class('synopsis', webpage)[0] thumbnail = self._html_search_regex( - r'''''', - webpage, "thumbnail url", fatal=False) + r''']+src=(["'])(?P(?!\1).+?/moviecovers/(?!\1).+?)\1''', + webpage, 'thumbnail url', fatal=False, group='url') if thumbnail is not None: - thumbnail = compat_urlparse.urljoin(url, remove_start(thumbnail, '..')) + thumbnail = compat_urlparse.urljoin(url, thumbnail) return { 'id': video_id, diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 5115e1a0c..be3688d5a 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -202,6 +202,7 @@ from .commonprotocols import ( RtmpIE, ) from .condenast import CondeNastIE +from .corus import CorusIE from .cracked import CrackedIE from .crackle import CrackleIE from .criterion import CriterionIE @@ -381,10 +382,7 @@ from .heise import HeiseIE from .hellporno import HellPornoIE from .helsinki import HelsinkiIE from .hentaistigma import HentaiStigmaIE -from .hgtv import ( - HGTVIE, - HGTVComShowIE, -) +from .hgtv import HGTVComShowIE from .historicfilms import HistoricFilmsIE from .hitbox import HitboxIE, HitboxLiveIE from .hitrecord import HitRecordIE @@ -696,6 +694,8 @@ from .ondemandkorea import OnDemandKoreaIE from .onet import ( OnetIE, OnetChannelIE, + OnetMVPIE, + OnetPlIE, ) from .onionstudios import OnionStudiosIE from .ooyala import ( @@ -1149,6 +1149,7 @@ from .vlive import ( VLiveChannelIE ) from .vodlocker import VodlockerIE +from .vodpl import VODPlIE from .vodplatform import VODPlatformIE from .voicerepublic import VoiceRepublicIE from .voxmedia import VoxMediaIE diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index 4a3c839f4..70b8c95c5 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -1,3 +1,4 @@ +# coding: utf-8 from __future__ import unicode_literals import re @@ -148,6 +149,32 @@ class FacebookIE(InfoExtractor): 'params': { 'skip_download': True, }, + }, { + 'url': 'https://www.facebook.com/LaGuiaDelVaron/posts/1072691702860471', + 'info_dict': { + 'id': '1072691702860471', + 'ext': 'mp4', + 'title': 'md5:ae2d22a93fbb12dad20dc393a869739d', + 'timestamp': 1477305000, + 'upload_date': '20161024', + 'uploader': 'La Guía Del Varón', + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://www.facebook.com/groups/1024490957622648/permalink/1396382447100162/', + 'info_dict': { + 'id': '1396382447100162', + 'ext': 'mp4', + 'title': 'md5:e2d2700afdf84e121f5d0f999bad13a3', + 'timestamp': 1486035494, + 'upload_date': '20170202', + 'uploader': 'Elisabeth Ahtn', + }, + 'params': { + 'skip_download': True, + }, }, { 'url': 'https://www.facebook.com/video.php?v=10204634152394104', 'only_matching': True, @@ -263,7 +290,7 @@ class FacebookIE(InfoExtractor): for item in instances: if item[1][0] == 'VideoConfig': video_item = item[2][0] - if video_item.get('video_id') == video_id: + if video_item.get('video_id'): return video_item['videoData'] server_js_data = self._parse_json(self._search_regex( diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 1c233f038..a2b0298ec 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -991,19 +991,6 @@ class GenericIE(InfoExtractor): 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014', }, }, - # Kaltura embed protected with referrer - { - 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero', - 'info_dict': { - 'id': '1_g4fbemnq', - 'ext': 'mp4', - 'title': 'Violetta - Achter De Schermen - Ruggero', - 'description': 'Achter de schermen met Ruggero', - 'timestamp': 1435133761, - 'upload_date': '20150624', - 'uploader_id': 'echojecka', - }, - }, # Kaltura embed with single quotes { 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY', @@ -2350,8 +2337,9 @@ class GenericIE(InfoExtractor): 'Channel': 'channel', 'ChannelList': 'channel_list', } - return self.url_result('limelight:%s:%s' % ( - lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2)) + return self.url_result(smuggle_url('limelight:%s:%s' % ( + lm[mobj.group(1)], mobj.group(2)), {'source_url': url}), + 'Limelight%s' % mobj.group(1), mobj.group(2)) mobj = re.search( r'''(?sx) @@ -2361,7 +2349,9 @@ class GenericIE(InfoExtractor): value=(["\'])(?:(?!\3).)*mediaId=(?P[a-z0-9]{32}) ''', webpage) if mobj: - return self.url_result('limelight:media:%s' % mobj.group('id')) + return self.url_result(smuggle_url( + 'limelight:media:%s' % mobj.group('id'), + {'source_url': url}), 'LimelightMedia', mobj.group('id')) # Look for AdobeTVVideo embeds mobj = re.search( diff --git a/youtube_dl/extractor/hgtv.py b/youtube_dl/extractor/hgtv.py index 69543bff2..e854300c7 100644 --- a/youtube_dl/extractor/hgtv.py +++ b/youtube_dl/extractor/hgtv.py @@ -2,50 +2,6 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import ( - int_or_none, - js_to_json, - smuggle_url, -) - - -class HGTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?hgtv\.ca/[^/]+/video/(?P[^/]+)/video.html' - _TEST = { - 'url': 'http://www.hgtv.ca/homefree/video/overnight-success/video.html?v=738081859718&p=1&s=da#video', - 'md5': '', - 'info_dict': { - 'id': 'aFH__I_5FBOX', - 'ext': 'mp4', - 'title': 'Overnight Success', - 'description': 'After weeks of hard work, high stakes, breakdowns and pep talks, the final 2 contestants compete to win the ultimate dream.', - 'uploader': 'SHWM-NEW', - 'timestamp': 1470320034, - 'upload_date': '20160804', - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - } - - def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - embed_vars = self._parse_json(self._search_regex( - r'(?s)embed_vars\s*=\s*({.*?});', - webpage, 'embed vars'), display_id, js_to_json) - return { - '_type': 'url_transparent', - 'url': smuggle_url( - 'http://link.theplatform.com/s/dtjsEC/%s?mbr=true&manifest=m3u' % embed_vars['pid'], { - 'force_smil_url': True - }), - 'series': embed_vars.get('show'), - 'season_number': int_or_none(embed_vars.get('season')), - 'episode_number': int_or_none(embed_vars.get('episode')), - 'ie_key': 'ThePlatform', - } class HGTVComShowIE(InfoExtractor): diff --git a/youtube_dl/extractor/hotstar.py b/youtube_dl/extractor/hotstar.py index f05d765d6..3a7a66a34 100644 --- a/youtube_dl/extractor/hotstar.py +++ b/youtube_dl/extractor/hotstar.py @@ -34,11 +34,9 @@ class HotStarIE(InfoExtractor): 'only_matching': True, }] - _GET_CONTENT_TEMPLATE = 'http://account.hotstar.com/AVS/besc?action=GetAggregatedContentDetails&channel=PCTV&contentId=%s' - _GET_CDN_TEMPLATE = 'http://getcdn.hotstar.com/AVS/besc?action=GetCDN&asJson=Y&channel=%s&id=%s&type=%s' - - def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata', fatal=True): - json_data = super(HotStarIE, self)._download_json(url_or_request, video_id, note, fatal=fatal) + def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata', fatal=True, query=None): + json_data = super(HotStarIE, self)._download_json( + url_or_request, video_id, note, fatal=fatal, query=query) if json_data['resultCode'] != 'OK': if fatal: raise ExtractorError(json_data['errorDescription']) @@ -48,20 +46,37 @@ class HotStarIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) video_data = self._download_json( - self._GET_CONTENT_TEMPLATE % video_id, - video_id)['contentInfo'][0] + 'http://account.hotstar.com/AVS/besc', video_id, query={ + 'action': 'GetAggregatedContentDetails', + 'channel': 'PCTV', + 'contentId': video_id, + })['contentInfo'][0] + title = video_data['episodeTitle'] + + if video_data.get('encrypted') == 'Y': + raise ExtractorError('This video is DRM protected.', expected=True) formats = [] - # PCTV for extracting f4m manifest - for f in ('TABLET',): + for f in ('JIO',): format_data = self._download_json( - self._GET_CDN_TEMPLATE % (f, video_id, 'VOD'), - video_id, 'Downloading %s JSON metadata' % f, fatal=False) + 'http://getcdn.hotstar.com/AVS/besc', + video_id, 'Downloading %s JSON metadata' % f, + fatal=False, query={ + 'action': 'GetCDN', + 'asJson': 'Y', + 'channel': f, + 'id': video_id, + 'type': 'VOD', + }) if format_data: - format_url = format_data['src'] + format_url = format_data.get('src') + if not format_url: + continue ext = determine_ext(format_url) if ext == 'm3u8': - formats.extend(self._extract_m3u8_formats(format_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) + formats.extend(self._extract_m3u8_formats( + format_url, video_id, 'mp4', + m3u8_id='hls', fatal=False)) elif ext == 'f4m': # produce broken files continue @@ -75,9 +90,12 @@ class HotStarIE(InfoExtractor): return { 'id': video_id, - 'title': video_data['episodeTitle'], + 'title': title, 'description': video_data.get('description'), 'duration': int_or_none(video_data.get('duration')), 'timestamp': int_or_none(video_data.get('broadcastDate')), 'formats': formats, + 'episode': title, + 'episode_number': int_or_none(video_data.get('episodeNumber')), + 'series': video_data.get('contentTitle'), } diff --git a/youtube_dl/extractor/iqiyi.py b/youtube_dl/extractor/iqiyi.py index 01c7b3042..2af6a6db4 100644 --- a/youtube_dl/extractor/iqiyi.py +++ b/youtube_dl/extractor/iqiyi.py @@ -173,11 +173,12 @@ class IqiyiIE(InfoExtractor): } }, { 'url': 'http://www.iqiyi.com/v_19rrhnnclk.html', - 'md5': '667171934041350c5de3f5015f7f1152', + 'md5': 'b7dc800a4004b1b57749d9abae0472da', 'info_dict': { 'id': 'e3f585b550a280af23c98b6cb2be19fb', 'ext': 'mp4', - 'title': '名侦探柯南 国语版：第752集 迫近灰原秘密的黑影 下篇', + # This can be either Simplified Chinese or Traditional Chinese + 'title': r're:^(?:名侦探柯南 国语版：第752集 迫近灰原秘密的黑影 下篇|名偵探柯南 國語版：第752集 迫近灰原秘密的黑影 下篇)$', }, 'skip': 'Geo-restricted to China', }, { diff --git a/youtube_dl/extractor/lemonde.py b/youtube_dl/extractor/lemonde.py index 42568f315..3306892e8 100644 --- a/youtube_dl/extractor/lemonde.py +++ b/youtube_dl/extractor/lemonde.py @@ -7,20 +7,40 @@ class LemondeIE(InfoExtractor): _VALID_URL = r'https?://(?:.+?\.)?lemonde\.fr/(?:[^/]+/)*(?P[^/]+)\.html' _TESTS = [{ 'url': 'http://www.lemonde.fr/police-justice/video/2016/01/19/comprendre-l-affaire-bygmalion-en-cinq-minutes_4849702_1653578.html', - 'md5': '01fb3c92de4c12c573343d63e163d302', + 'md5': 'da120c8722d8632eec6ced937536cc98', 'info_dict': { 'id': 'lqm3kl', 'ext': 'mp4', 'title': "Comprendre l'affaire Bygmalion en 5 minutes", 'thumbnail': r're:^https?://.*\.jpg', - 'duration': 320, + 'duration': 309, 'upload_date': '20160119', 'timestamp': 1453194778, 'uploader_id': '3pmkp', }, + }, { + # standard iframe embed + 'url': 'http://www.lemonde.fr/les-decodeurs/article/2016/10/18/tout-comprendre-du-ceta-le-petit-cousin-du-traite-transatlantique_5015920_4355770.html', + 'info_dict': { + 'id': 'uzsxms', + 'ext': 'mp4', + 'title': "CETA : quelles suites pour l'accord commercial entre l'Europe et le Canada ?", + 'thumbnail': r're:^https?://.*\.jpg', + 'duration': 325, + 'upload_date': '20161021', + 'timestamp': 1477044540, + 'uploader_id': '3pmkp', + }, + 'params': { + 'skip_download': True, + }, }, { 'url': 'http://redaction.actu.lemonde.fr/societe/video/2016/01/18/calais-debut-des-travaux-de-defrichement-dans-la-jungle_4849233_3224.html', 'only_matching': True, + }, { + # YouTube embeds + 'url': 'http://www.lemonde.fr/pixels/article/2016/12/09/pourquoi-pewdiepie-superstar-de-youtube-a-menace-de-fermer-sa-chaine_5046649_4408996.html', + 'only_matching': True, }] def _real_extract(self, url): @@ -30,5 +50,9 @@ class LemondeIE(InfoExtractor): digiteka_url = self._proto_relative_url(self._search_regex( r'url\s*:\s*(["\'])(?P(?:https?://)?//(?:www\.)?(?:digiteka\.net|ultimedia\.com)/deliver/.+?)\1', - webpage, 'digiteka url', group='url')) - return self.url_result(digiteka_url, 'Digiteka') + webpage, 'digiteka url', group='url', default=None)) + + if digiteka_url: + return self.url_result(digiteka_url, 'Digiteka') + + return self.url_result(url, 'Generic') diff --git a/youtube_dl/extractor/limelight.py b/youtube_dl/extractor/limelight.py index e635f3c4d..a3712665b 100644 --- a/youtube_dl/extractor/limelight.py +++ b/youtube_dl/extractor/limelight.py @@ -8,6 +8,7 @@ from ..utils import ( determine_ext, float_or_none, int_or_none, + unsmuggle_url, ) @@ -15,20 +16,23 @@ 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' - def _call_playlist_service(self, item_id, method, fatal=True): + def _call_playlist_service(self, item_id, method, fatal=True, referer=None): + headers = {} + if referer: + headers['Referer'] = referer return self._download_json( self._PLAYLIST_SERVICE_URL % (self._PLAYLIST_SERVICE_PATH, item_id, method), - item_id, 'Downloading PlaylistService %s JSON' % method, fatal=fatal) + item_id, 'Downloading PlaylistService %s JSON' % method, fatal=fatal, headers=headers) 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): - pc = self._call_playlist_service(item_id, pc_method) + def _extract(self, item_id, pc_method, mobile_method, meta_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) + mobile = self._call_playlist_service(item_id, mobile_method, fatal=False, referer=referer) return pc, mobile, metadata def _extract_info(self, streams, mobile_urls, properties): @@ -207,10 +211,13 @@ class LimelightMediaIE(LimelightBaseIE): _API_PATH = 'media' def _real_extract(self, url): + url, smuggled_data = unsmuggle_url(url, {}) video_id = self._match_id(url) pc, mobile, metadata = self._extract( - video_id, 'getPlaylistByMediaId', 'getMobilePlaylistByMediaId', 'properties') + video_id, 'getPlaylistByMediaId', + 'getMobilePlaylistByMediaId', 'properties', + smuggled_data.get('source_url')) return self._extract_info( pc['playlistItems'][0].get('streams', []), @@ -247,11 +254,13 @@ class LimelightChannelIE(LimelightBaseIE): _API_PATH = 'channels' def _real_extract(self, url): + url, smuggled_data = unsmuggle_url(url, {}) channel_id = self._match_id(url) pc, mobile, medias = self._extract( channel_id, 'getPlaylistByChannelId', - 'getMobilePlaylistWithNItemsByChannelId?begin=0&count=-1', 'media') + 'getMobilePlaylistWithNItemsByChannelId?begin=0&count=-1', + 'media', smuggled_data.get('source_url')) entries = [ self._extract_info( diff --git a/youtube_dl/extractor/onet.py b/youtube_dl/extractor/onet.py index 0a501b3e5..94f57990b 100644 --- a/youtube_dl/extractor/onet.py +++ b/youtube_dl/extractor/onet.py @@ -23,7 +23,7 @@ class OnetBaseIE(InfoExtractor): return self._search_regex( r'id=(["\'])mvp:(?P.+?)\1', webpage, 'mvp id', group='id') - def _extract_from_id(self, video_id, webpage): + def _extract_from_id(self, video_id, webpage=None): response = self._download_json( 'http://qi.ckm.onetapi.pl/', video_id, query={ @@ -74,8 +74,10 @@ class OnetBaseIE(InfoExtractor): meta = video.get('meta', {}) - title = self._og_search_title(webpage, default=None) or meta['title'] - description = self._og_search_description(webpage, default=None) or meta.get('description') + title = (self._og_search_title( + webpage, default=None) if webpage else None) or meta['title'] + description = (self._og_search_description( + webpage, default=None) if webpage else None) or meta.get('description') duration = meta.get('length') or meta.get('lenght') timestamp = parse_iso8601(meta.get('addDate'), ' ') @@ -89,6 +91,18 @@ class OnetBaseIE(InfoExtractor): } +class OnetMVPIE(OnetBaseIE): + _VALID_URL = r'onetmvp:(?P\d+\.\d+)' + + _TEST = { + 'url': 'onetmvp:381027.1509591944', + 'only_matching': True, + } + + def _real_extract(self, url): + return self._extract_from_id(self._match_id(url)) + + class OnetIE(OnetBaseIE): _VALID_URL = r'https?://(?:www\.)?onet\.tv/[a-z]/[a-z]+/(?P[0-9a-z-]+)/(?P[0-9a-z]+)' IE_NAME = 'onet.tv' @@ -167,3 +181,44 @@ class OnetChannelIE(OnetBaseIE): channel_title = strip_or_none(get_element_by_class('o_channelName', webpage)) channel_description = strip_or_none(get_element_by_class('o_channelDesc', webpage)) return self.playlist_result(entries, channel_id, channel_title, channel_description) + + +class OnetPlIE(InfoExtractor): + _VALID_URL = r'https?://(?:[^/]+\.)?(?:onet|businessinsider\.com|plejada)\.pl/(?:[^/]+/)+(?P[0-9a-z]+)' + IE_NAME = 'onet.pl' + + _TESTS = [{ + 'url': 'http://eurosport.onet.pl/zimowe/skoki-narciarskie/ziobro-wygral-kwalifikacje-w-pjongczangu/9ckrly', + 'md5': 'b94021eb56214c3969380388b6e73cb0', + 'info_dict': { + 'id': '1561707.1685479', + 'ext': 'mp4', + 'title': 'Ziobro wygrał kwalifikacje w Pjongczangu', + 'description': 'md5:61fb0740084d2d702ea96512a03585b4', + 'upload_date': '20170214', + 'timestamp': 1487078046, + }, + }, { + 'url': 'http://film.onet.pl/zwiastuny/ghost-in-the-shell-drugi-zwiastun-pl/5q6yl3', + 'only_matching': True, + }, { + 'url': 'http://moto.onet.pl/jak-wybierane-sa-miejsca-na-fotoradary/6rs04e', + 'only_matching': True, + }, { + 'url': 'http://businessinsider.com.pl/wideo/scenariusz-na-koniec-swiata-wedlug-nasa/dwnqptk', + 'only_matching': True, + }, { + 'url': 'http://plejada.pl/weronika-rosati-o-swoim-domniemanym-slubie/n2bq89', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + mvp_id = self._search_regex( + r'data-params-mvp=["\'](\d+\.\d+)', webpage, 'mvp id') + + return self.url_result( + 'onetmvp:%s' % mvp_id, OnetMVPIE.ie_key(), video_id=mvp_id) diff --git a/youtube_dl/extractor/pinkbike.py b/youtube_dl/extractor/pinkbike.py index 6a4580d54..9f3501f77 100644 --- a/youtube_dl/extractor/pinkbike.py +++ b/youtube_dl/extractor/pinkbike.py @@ -64,7 +64,8 @@ class PinkbikeIE(InfoExtractor): 'video:duration', webpage, 'duration')) uploader = self._search_regex( - r'un:\s*"([^"]+)"', webpage, 'uploader', fatal=False) + r']+\brel=["\']author[^>]+>([^<]+)', webpage, + 'uploader', fatal=False) upload_date = unified_strdate(self._search_regex( r'class="fullTime"[^>]+title="([^"]+)"', webpage, 'upload date', fatal=False)) diff --git a/youtube_dl/extractor/pluralsight.py b/youtube_dl/extractor/pluralsight.py index 5c798e874..e0cbd045e 100644 --- a/youtube_dl/extractor/pluralsight.py +++ b/youtube_dl/extractor/pluralsight.py @@ -18,6 +18,7 @@ from ..utils import ( parse_duration, qualities, srt_subtitles_timecode, + update_url_query, urlencode_postdata, ) @@ -92,6 +93,10 @@ class PluralsightIE(PluralsightBaseIE): raise ExtractorError('Unable to login: %s' % error, expected=True) if all(p not in response for p in ('__INITIAL_STATE__', '"currentUser"')): + BLOCKED = 'Your account has been blocked due to suspicious activity' + if BLOCKED in response: + raise ExtractorError( + 'Unable to login: %s' % BLOCKED, expected=True) raise ExtractorError('Unable to log in') def _get_subtitles(self, author, clip_id, lang, name, duration, video_id): @@ -327,25 +332,44 @@ class PluralsightCourseIE(PluralsightBaseIE): # TODO: PSM cookie course = self._download_json( - '%s/data/course/%s' % (self._API_BASE, course_id), - course_id, 'Downloading course JSON') + '%s/player/functions/rpc' % self._API_BASE, course_id, + 'Downloading course JSON', + data=json.dumps({ + 'fn': 'bootstrapPlayer', + 'payload': { + 'courseId': course_id, + } + }).encode('utf-8'), + headers={ + 'Content-Type': 'application/json;charset=utf-8' + })['payload']['course'] title = course['title'] + course_name = course['name'] + course_data = course['modules'] description = course.get('description') or course.get('shortDescription') - course_data = self._download_json( - '%s/data/course/content/%s' % (self._API_BASE, course_id), - course_id, 'Downloading course data JSON') - entries = [] for num, module in enumerate(course_data, 1): + author = module.get('author') + module_name = module.get('name') + if not author or not module_name: + continue for clip in module.get('clips', []): - player_parameters = clip.get('playerParameters') - if not player_parameters: + clip_index = int_or_none(clip.get('index')) + if clip_index is None: continue + clip_url = update_url_query( + '%s/player' % self._API_BASE, query={ + 'mode': 'live', + 'course': course_name, + 'author': author, + 'name': module_name, + 'clip': clip_index, + }) entries.append({ '_type': 'url_transparent', - 'url': '%s/training/player?%s' % (self._API_BASE, player_parameters), + 'url': clip_url, 'ie_key': PluralsightIE.ie_key(), 'chapter': module.get('title'), 'chapter_number': num, diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 818d99c1f..7a2737032 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -2,27 +2,27 @@ from __future__ import unicode_literals import itertools -import os +# import os import re from .common import InfoExtractor from ..compat import ( compat_HTTPError, - compat_urllib_parse_unquote, - compat_urllib_parse_unquote_plus, - compat_urllib_parse_urlparse, + # compat_urllib_parse_unquote, + # compat_urllib_parse_unquote_plus, + # compat_urllib_parse_urlparse, ) from ..utils import ( ExtractorError, int_or_none, js_to_json, orderedSet, - sanitized_Request, + # sanitized_Request, str_to_int, ) -from ..aes import ( - aes_decrypt_text -) +# from ..aes import ( +# aes_decrypt_text +# ) class PornHubIE(InfoExtractor): @@ -109,10 +109,14 @@ class PornHubIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - req = sanitized_Request( - 'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id) - req.add_header('Cookie', 'age_verified=1') - webpage = self._download_webpage(req, video_id) + def dl_webpage(platform): + return self._download_webpage( + 'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id, + video_id, headers={ + 'Cookie': 'age_verified=1; platform=%s' % platform, + }) + + webpage = dl_webpage('pc') error_msg = self._html_search_regex( r'(?s)]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P.+?)', @@ -123,10 +127,19 @@ class PornHubIE(InfoExtractor): 'PornHub said: %s' % error_msg, expected=True, video_id=video_id) + tv_webpage = dl_webpage('tv') + + video_url = self._search_regex( + r']+\bsrc=(["\'])(?P(?:https?:)?//.+?)\1', tv_webpage, + 'video url', group='url') + + title = self._search_regex( + r'

([^>]+)

', tv_webpage, 'title', default=None) + # video_title from flashvars contains whitespace instead of non-ASCII (see # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying # on that anymore. - title = self._html_search_meta( + title = title or self._html_search_meta( 'twitter:title', webpage, default=None) or self._search_regex( (r']+class=["\']title["\'][^>]*>(?P[^<]+)', r'<div[^>]+data-video-title=(["\'])(?P<title>.+?)\1', @@ -156,6 +169,7 @@ class PornHubIE(InfoExtractor): comment_count = self._extract_count( r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment') + """ video_variables = {} for video_variablename, quote, video_variable in re.findall( r'(player_quality_[0-9]{3,4}p\w+)\s*=\s*(["\'])(.+?)\2;', webpage): @@ -197,6 +211,7 @@ class PornHubIE(InfoExtractor): 'height': height, }) self._sort_formats(formats) + """ page_params = self._parse_json(self._search_regex( r'page_params\.zoneDetails\[([\'"])[^\'"]+\1\]\s*=\s*(?P<data>{[^}]+})', @@ -209,6 +224,7 @@ class PornHubIE(InfoExtractor): return { 'id': video_id, + 'url': video_url, 'uploader': video_uploader, 'title': title, 'thumbnail': thumbnail, @@ -217,7 +233,7 @@ class PornHubIE(InfoExtractor): 'like_count': like_count, 'dislike_count': dislike_count, 'comment_count': comment_count, - 'formats': formats, + # 'formats': formats, 'age_limit': 18, 'tags': tags, 'categories': categories, diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py index 192d8fa29..5c5987c6a 100644 --- a/youtube_dl/extractor/theplatform.py +++ b/youtube_dl/extractor/theplatform.py @@ -306,9 +306,10 @@ class ThePlatformFeedIE(ThePlatformBaseIE): }, }] - def _extract_feed_info(self, provider_id, feed_id, filter_query, video_id, custom_fields=None, asset_types_query={}): + def _extract_feed_info(self, provider_id, feed_id, filter_query, video_id, custom_fields=None, asset_types_query={}, account_id=None): real_url = self._URL_TEMPLATE % (self.http_scheme(), provider_id, feed_id, filter_query) entry = self._download_json(real_url, video_id)['entries'][0] + main_smil_url = 'http://link.theplatform.com/s/%s/media/guid/%d/%s' % (provider_id, account_id, entry['guid']) if account_id else None formats = [] subtitles = {} @@ -333,7 +334,7 @@ class ThePlatformFeedIE(ThePlatformBaseIE): if asset_type in asset_types_query: query.update(asset_types_query[asset_type]) cur_formats, cur_subtitles = self._extract_theplatform_smil(update_url_query( - smil_url, query), video_id, 'Downloading SMIL data for %s' % asset_type) + main_smil_url or smil_url, query), video_id, 'Downloading SMIL data for %s' % asset_type) formats.extend(cur_formats) subtitles = self._merge_subtitles(subtitles, cur_subtitles) diff --git a/youtube_dl/extractor/vodpl.py b/youtube_dl/extractor/vodpl.py new file mode 100644 index 000000000..9e919708e --- /dev/null +++ b/youtube_dl/extractor/vodpl.py @@ -0,0 +1,32 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .onet import OnetBaseIE + + +class VODPlIE(OnetBaseIE): + _VALID_URL = r'https?://vod\.pl/(?:[^/]+/)+(?P<id>[0-9a-zA-Z]+)' + + _TESTS = [{ + 'url': 'https://vod.pl/filmy/chlopaki-nie-placza/3ep3jns', + 'md5': 'a7dc3b2f7faa2421aefb0ecaabf7ec74', + 'info_dict': { + 'id': '3ep3jns', + 'ext': 'mp4', + 'title': 'Chłopaki nie płaczą', + 'description': 'md5:f5f03b84712e55f5ac9f0a3f94445224', + 'timestamp': 1463415154, + 'duration': 5765, + 'upload_date': '20160516', + }, + }, { + 'url': 'https://vod.pl/seriale/belfer-na-planie-praca-kamery-online/2c10heh', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + info_dict = self._extract_from_id(self._search_mvp_id(webpage), webpage) + info_dict['id'] = video_id + return info_dict diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index 11717fe98..5584674a0 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -44,6 +44,9 @@ class XTubeIE(InfoExtractor): }, { 'url': 'xtube:625837', 'only_matching': True, + }, { + 'url': 'xtube:kVTUy_G222_', + 'only_matching': True, }] def _real_extract(self, url): @@ -53,11 +56,16 @@ class XTubeIE(InfoExtractor): if not display_id: display_id = video_id - url = 'http://www.xtube.com/video-watch/-%s' % video_id - req = sanitized_Request(url) - req.add_header('Cookie', 'age_verified=1; cookiesAccepted=1') - webpage = self._download_webpage(req, display_id) + if video_id.isdigit() and len(video_id) < 11: + url_pattern = 'http://www.xtube.com/video-watch/-%s' + else: + url_pattern = 'http://www.xtube.com/watch.php?v=%s' + + webpage = self._download_webpage( + url_pattern % video_id, display_id, headers={ + 'Cookie': 'age_verified=1; cookiesAccepted=1', + }) sources = self._parse_json(self._search_regex( r'(["\'])sources\1\s*:\s*(?P<sources>{.+?}),', @@ -73,7 +81,7 @@ class XTubeIE(InfoExtractor): self._sort_formats(formats) title = self._search_regex( - (r'<h1>(?P<title>[^<]+)</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'), + (r'<h1>\s*(?P<title>[^<]+?)\s*</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'), webpage, 'title', group='title') description = self._search_regex( r'</h1>\s*<p>([^<]+)', webpage, 'description', fatal=False) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 76710931a..dec02804b 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -34,6 +34,7 @@ from ..utils import ( int_or_none, mimetype2ext, orderedSet, + parse_codecs, parse_duration, remove_quotes, remove_start, @@ -1696,15 +1697,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): codecs = mobj.group('val') break if codecs: - codecs = codecs.split(',') - if len(codecs) == 2: - acodec, vcodec = codecs[1], codecs[0] - else: - acodec, vcodec = (codecs[0], 'none') if kind == 'audio' else ('none', codecs[0]) - dct.update({ - 'acodec': acodec, - 'vcodec': vcodec, - }) + dct.update(parse_codecs(codecs)) formats.append(dct) elif video_info.get('hlsvp'): manifest_url = video_info['hlsvp'][0] diff --git a/youtube_dl/extractor/zdf.py b/youtube_dl/extractor/zdf.py index a365923fb..523bb5c95 100644 --- a/youtube_dl/extractor/zdf.py +++ b/youtube_dl/extractor/zdf.py @@ -20,9 +20,9 @@ from ..utils import ( class ZDFBaseIE(InfoExtractor): - def _call_api(self, url, player, referrer, video_id): + def _call_api(self, url, player, referrer, video_id, item): return self._download_json( - url, video_id, 'Downloading JSON content', + url, video_id, 'Downloading JSON %s' % item, headers={ 'Referer': referrer, 'Api-Auth': 'Bearer %s' % player['apiToken'], @@ -104,7 +104,7 @@ class ZDFIE(ZDFBaseIE): }) formats.append(f) - def _extract_entry(self, url, content, video_id): + def _extract_entry(self, url, player, content, video_id): title = content.get('title') or content['teaserHeadline'] t = content['mainVideoContent']['http://zdf.de/rels/target'] @@ -116,7 +116,8 @@ class ZDFIE(ZDFBaseIE): 'http://zdf.de/rels/streams/ptmd-template'].replace( '{playerId}', 'portal') - ptmd = self._download_json(urljoin(url, ptmd_path), video_id) + ptmd = self._call_api( + urljoin(url, ptmd_path), player, url, video_id, 'metadata') formats = [] track_uris = set() @@ -174,8 +175,9 @@ class ZDFIE(ZDFBaseIE): } def _extract_regular(self, url, player, video_id): - content = self._call_api(player['content'], player, url, video_id) - return self._extract_entry(player['content'], content, video_id) + content = self._call_api( + player['content'], player, url, video_id, 'content') + return self._extract_entry(player['content'], player, content, video_id) def _extract_mobile(self, video_id): document = self._download_json( diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 67a847eba..07c07be6f 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -337,17 +337,30 @@ def get_element_by_id(id, html): def get_element_by_class(class_name, html): - return get_element_by_attribute( + """Return the content of the first tag with the specified class in the passed HTML document""" + retval = get_elements_by_class(class_name, html) + return retval[0] if retval else None + + +def get_element_by_attribute(attribute, value, html, escape_value=True): + retval = get_elements_by_attribute(attribute, value, html, escape_value) + return retval[0] if retval else None + + +def get_elements_by_class(class_name, html): + """Return the content of all tags with the specified class in the passed HTML document as a list""" + return get_elements_by_attribute( 'class', r'[^\'"]*\b%s\b[^\'"]*' % re.escape(class_name), html, escape_value=False) -def get_element_by_attribute(attribute, value, html, escape_value=True): +def get_elements_by_attribute(attribute, value, html, escape_value=True): """Return the content of the tag with the specified attribute in the passed HTML document""" value = re.escape(value) if escape_value else value - m = re.search(r'''(?xs) + retlist = [] + for m in re.finditer(r'''(?xs) <([a-zA-Z0-9:._-]+) (?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'))*? \s+%s=['"]?%s['"]? @@ -355,16 +368,15 @@ def get_element_by_attribute(attribute, value, html, escape_value=True): \s*> (?P<content>.*?) </\1> - ''' % (re.escape(attribute), value), html) + ''' % (re.escape(attribute), value), html): + res = m.group('content') - if not m: - return None - res = m.group('content') + if res.startswith('"') or res.startswith("'"): + res = res[1:-1] - if res.startswith('"') or res.startswith("'"): - res = res[1:-1] + retlist.append(unescapeHTML(res)) - return unescapeHTML(res) + return retlist class HTMLAttributeParser(compat_HTMLParser): @@ -1672,6 +1684,11 @@ def setproctitle(title): libc = ctypes.cdll.LoadLibrary('libc.so.6') except OSError: return + except TypeError: + # LoadLibrary in Windows Python 2.7.13 only expects + # a bytestring, but since unicode_literals turns + # every string into a unicode string, it fails. + return title_bytes = title.encode('utf-8') buf = ctypes.create_string_buffer(len(title_bytes)) buf.value = title_bytes @@ -2366,6 +2383,7 @@ def _match_one(filter_part, dct): \s*(?P<op>%s)(?P<none_inclusive>\s*\?)?\s* (?: (?P<intval>[0-9.]+(?:[kKmMgGtTpPeEzZyY]i?[Bb]?)?)| + (?P<quote>["\'])(?P<quotedstrval>(?:\\.|(?!(?P=quote)|\\).)+?)(?P=quote)| (?P<strval>(?![0-9.])[a-z0-9A-Z]*) ) \s*$ @@ -2374,7 +2392,8 @@ def _match_one(filter_part, dct): if m: op = COMPARISON_OPERATORS[m.group('op')] actual_value = dct.get(m.group('key')) - if (m.group('strval') is not None or + if (m.group('quotedstrval') is not None or + m.group('strval') is not None or # If the original field is a string and matching comparisonvalue is # a number we should respect the origin of the original field # and process comparison value as a string (see @@ -2384,7 +2403,10 @@ def _match_one(filter_part, dct): if m.group('op') not in ('=', '!='): raise ValueError( 'Operator %s does not support string values!' % m.group('op')) - comparison_value = m.group('strval') or m.group('intval') + comparison_value = m.group('quotedstrval') or m.group('strval') or m.group('intval') + quote = m.group('quote') + if quote is not None: + comparison_value = comparison_value.replace(r'\%s' % quote, quote) else: try: comparison_value = int(m.group('intval')) diff --git a/youtube_dl/version.py b/youtube_dl/version.py index a8395ce04..323e80954 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2017.02.10' +__version__ = '2017.02.16'