From e7c3e33456e155106ad08347d8ab9a2ecd0c8a11 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 14 Sep 2017 23:19:53 +0700 Subject: [PATCH 1/5] [downloader/fragment] Restart inconsistent incomplete fragment downloads (#13731) --- youtube_dl/downloader/fragment.py | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/youtube_dl/downloader/fragment.py b/youtube_dl/downloader/fragment.py index bccc8ecc1..6f6fb4a77 100644 --- a/youtube_dl/downloader/fragment.py +++ b/youtube_dl/downloader/fragment.py @@ -151,10 +151,15 @@ class FragmentFD(FileDownloader): if self.__do_ytdl_file(ctx): if os.path.isfile(encodeFilename(self.ytdl_filename(ctx['filename']))): self._read_ytdl_file(ctx) + if ctx['fragment_index'] > 0 and resume_len == 0: + self.report_error( + 'Inconsistent state of incomplete fragment download. ' + 'Restarting from the beginning...') + ctx['fragment_index'] = resume_len = 0 + self._write_ytdl_file(ctx) else: self._write_ytdl_file(ctx) - if ctx['fragment_index'] > 0: - assert resume_len > 0 + assert ctx['fragment_index'] == 0 dest_stream, tmpfilename = sanitize_open(tmpfilename, open_mode) From 319fc70676fea19b71437aab4078d4d72cc1ba5f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 14 Sep 2017 23:50:19 +0700 Subject: [PATCH 2/5] [tv4] Relax _VALID_URL (closes #14206) --- youtube_dl/extractor/tv4.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/tv4.py b/youtube_dl/extractor/tv4.py index 7aeb2c620..6487039e5 100644 --- a/youtube_dl/extractor/tv4.py +++ b/youtube_dl/extractor/tv4.py @@ -18,7 +18,7 @@ class TV4IE(InfoExtractor): tv4\.se/(?:[^/]+)/klipp/(?:.*)-| tv4play\.se/ (?: - (?:program|barn)/(?:[^\?]+)\?video_id=| + (?:program|barn)/(?:[^/]+/|(?:[^\?]+)\?video_id=)| iframe/video/| film/| sport/| @@ -63,6 +63,10 @@ class TV4IE(InfoExtractor): 'url': 'http://www.tv4play.se/barn/looney-tunes?video_id=3062412', 'only_matching': True, }, + { + 'url': ' http://www.tv4play.se/program/farang/3922081', + 'only_matching': True, + } ] def _real_extract(self, url): From 0732a90579091ad60b124fd693bdda8ee526e305 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Thu, 14 Sep 2017 20:37:46 +0200 Subject: [PATCH 3/5] [orf] Add new extractor for f4m stories --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/orf.py | 116 +++++++++++++++++++++++++++-- 2 files changed, 112 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index aefadc56f..a3a97e940 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -768,6 +768,7 @@ from .ora import OraTVIE from .orf import ( ORFTVthekIE, ORFFM4IE, + ORFFM4StoryIE, ORFOE1IE, ORFIPTVIE, ) diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py index cc296eabd..74fe8017e 100644 --- a/youtube_dl/extractor/orf.py +++ b/youtube_dl/extractor/orf.py @@ -6,14 +6,15 @@ import re from .common import InfoExtractor from ..compat import compat_str from ..utils import ( - HEADRequest, - unified_strdate, - strip_jsonp, - int_or_none, - float_or_none, determine_ext, + float_or_none, + HEADRequest, + int_or_none, + orderedSet, remove_end, + strip_jsonp, unescapeHTML, + unified_strdate, ) @@ -307,3 +308,108 @@ class ORFIPTVIE(InfoExtractor): 'upload_date': upload_date, 'formats': formats, } + + +class ORFFM4StoryIE(InfoExtractor): + IE_NAME = 'orf:fm4:story' + IE_DESC = 'fm4.orf.at stories' + _VALID_URL = r'https?://fm4\.orf\.at/stories/(?P\d+)' + + _TEST = { + 'url': 'http://fm4.orf.at/stories/2865738/', + 'playlist': [{ + 'md5': 'e1c2c706c45c7b34cf478bbf409907ca', + 'info_dict': { + 'id': '547792', + 'ext': 'flv', + 'title': 'Manu Delago und Inner Tongue live', + 'description': 'Manu Delago und Inner Tongue haben bei der FM4 Soundpark Session live alles gegeben. Hier gibt es Fotos und die gesamte Session als Video.', + 'duration': 1748.52, + 'thumbnail': r're:^https?://.*\.jpg$', + 'upload_date': '20170913', + }, + }, { + 'md5': 'c6dd2179731f86f4f55a7b49899d515f', + 'info_dict': { + 'id': '547798', + 'ext': 'flv', + 'title': 'Manu Delago und Inner Tongue live (2)', + 'duration': 1504.08, + 'thumbnail': r're:^https?://.*\.jpg$', + 'upload_date': '20170913', + 'description': 'Manu Delago und Inner Tongue haben bei der FM4 Soundpark Session live alles gegeben. Hier gibt es Fotos und die gesamte Session als Video.', + }, + }], + } + + def _real_extract(self, url): + story_id = self._match_id(url) + webpage = self._download_webpage(url, story_id) + + entries = [] + all_ids = orderedSet(re.findall(r'data-video(?:id)?="(\d+)"', webpage)) + for idx, video_id in enumerate(all_ids): + data = self._download_json( + 'http://bits.orf.at/filehandler/static-api/json/current/data.json?file=%s' % video_id, + video_id)[0] + + duration = float_or_none(data['duration'], 1000) + + video = data['sources']['q8c'] + load_balancer_url = video['loadBalancerUrl'] + abr = int_or_none(video.get('audioBitrate')) + vbr = int_or_none(video.get('bitrate')) + fps = int_or_none(video.get('videoFps')) + width = int_or_none(video.get('videoWidth')) + height = int_or_none(video.get('videoHeight')) + thumbnail = video.get('preview') + + rendition = self._download_json( + load_balancer_url, video_id, transform_source=strip_jsonp) + + f = { + 'abr': abr, + 'vbr': vbr, + 'fps': fps, + 'width': width, + 'height': height, + } + + formats = [] + for format_id, format_url in rendition['redirect'].items(): + if format_id == 'rtmp': + ff = f.copy() + ff.update({ + 'url': format_url, + 'format_id': format_id, + }) + formats.append(ff) + elif determine_ext(format_url) == 'f4m': + formats.extend(self._extract_f4m_formats( + format_url, video_id, f4m_id=format_id)) + elif determine_ext(format_url) == 'm3u8': + formats.extend(self._extract_m3u8_formats( + format_url, video_id, 'mp4', m3u8_id=format_id)) + else: + continue + self._sort_formats(formats) + + title = remove_end(self._og_search_title(webpage), ' - fm4.ORF.at') + if idx >= 1: + # Titles are duplicates, make them unique + title += ' (' + str(idx + 1) + ')' + description = self._og_search_description(webpage) + upload_date = unified_strdate(self._html_search_meta( + 'dc.date', webpage, 'upload date')) + + entries.append({ + 'id': video_id, + 'title': title, + 'description': description, + 'duration': duration, + 'thumbnail': thumbnail, + 'upload_date': upload_date, + 'formats': formats, + }) + + return self.playlist_result(entries) From fad9fc537d8ab5141f402f6ccdf60161a8d0302a Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Thu, 14 Sep 2017 20:47:23 +0200 Subject: [PATCH 4/5] [tv4] fix a test URL --- 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 6487039e5..cfcce020a 100644 --- a/youtube_dl/extractor/tv4.py +++ b/youtube_dl/extractor/tv4.py @@ -64,7 +64,7 @@ class TV4IE(InfoExtractor): 'only_matching': True, }, { - 'url': ' http://www.tv4play.se/program/farang/3922081', + 'url': 'http://www.tv4play.se/program/farang/3922081', 'only_matching': True, } ] From c46680fb2a0ee61faa25863d3c10b7b098cdbe67 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 15 Sep 2017 01:59:47 +0700 Subject: [PATCH 5/5] [condenast] Fix extraction (closes #14196, closes #14207) --- youtube_dl/extractor/condenast.py | 54 ++++++++++++++++++------------- 1 file changed, 32 insertions(+), 22 deletions(-) diff --git a/youtube_dl/extractor/condenast.py b/youtube_dl/extractor/condenast.py index 0c3f0c0e4..ed278fefc 100644 --- a/youtube_dl/extractor/condenast.py +++ b/youtube_dl/extractor/condenast.py @@ -116,16 +116,16 @@ class CondeNastIE(InfoExtractor): entries = [self.url_result(build_url(path), 'CondeNast') for path in paths] return self.playlist_result(entries, playlist_title=title) - def _extract_video_params(self, webpage): - query = {} - params = self._search_regex( - r'(?s)var params = {(.+?)}[;,]', webpage, 'player params', default=None) - if params: - query.update({ - 'videoId': self._search_regex(r'videoId: [\'"](.+?)[\'"]', params, 'video id'), - 'playerId': self._search_regex(r'playerId: [\'"](.+?)[\'"]', params, 'player id'), - 'target': self._search_regex(r'target: [\'"](.+?)[\'"]', params, 'target'), - }) + def _extract_video_params(self, webpage, display_id): + query = self._parse_json( + self._search_regex( + r'(?s)var\s+params\s*=\s*({.+?})[;,]', webpage, 'player params', + default='{}'), + display_id, transform_source=js_to_json, fatal=False) + if query: + query['videoId'] = self._search_regex( + r'(?:data-video-id=|currentVideoId\s*=\s*)["\']([\da-f]+)', + webpage, 'video id', default=None) else: params = extract_attributes(self._search_regex( r'(<[^>]+data-js="video-player"[^>]+>)', @@ -141,17 +141,27 @@ class CondeNastIE(InfoExtractor): video_id = params['videoId'] video_info = None - if params.get('playerId'): - info_page = self._download_json( - 'http://player.cnevids.com/player/video.js', - video_id, 'Downloading video info', fatal=False, query=params) - if info_page: - video_info = info_page.get('video') - if not video_info: - info_page = self._download_webpage( - 'http://player.cnevids.com/player/loader.js', - video_id, 'Downloading loader info', query=params) - else: + + # New API path + query = params.copy() + query['embedType'] = 'inline' + info_page = self._download_json( + 'http://player.cnevids.com/embed-api.json', video_id, + 'Downloading embed info', fatal=False, query=query) + + # Old fallbacks + if not info_page: + if params.get('playerId'): + info_page = self._download_json( + 'http://player.cnevids.com/player/video.js', video_id, + 'Downloading video info', fatal=False, query=params) + if info_page: + video_info = info_page.get('video') + if not video_info: + info_page = self._download_webpage( + 'http://player.cnevids.com/player/loader.js', + video_id, 'Downloading loader info', query=params) + if not video_info: info_page = self._download_webpage( 'https://player.cnevids.com/inline/video/%s.js' % video_id, video_id, 'Downloading inline info', query={ @@ -215,7 +225,7 @@ class CondeNastIE(InfoExtractor): if url_type == 'series': return self._extract_series(url, webpage) else: - params = self._extract_video_params(webpage) + params = self._extract_video_params(webpage, display_id) info = self._search_json_ld( webpage, display_id, fatal=False) info.update(self._extract_video(params))