diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.md b/.github/ISSUE_TEMPLATE/1_broken_site.md index fb0d33b8f..ccd033716 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 **2019.07.02** +- [ ] I've verified that I'm running youtube-dl version **2019.07.30** - [ ] 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 2019.07.02 + [debug] youtube-dl version 2019.07.30 [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 3c95565a6..8709937ad 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 **2019.07.02** +- [ ] I've verified that I'm running youtube-dl version **2019.07.30** - [ ] 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 7410776d7..c3a555ed3 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 **2019.07.02** +- [ ] I've verified that I'm running youtube-dl version **2019.07.30** - [ ] 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 cc52bcca6..07042a466 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 **2019.07.02** +- [ ] I've verified that I'm running youtube-dl version **2019.07.30** - [ ] 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 2019.07.02 + [debug] youtube-dl version 2019.07.30 [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 bbd421b1a..4cf75a2eb 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 **2019.07.02** +- [ ] I've verified that I'm running youtube-dl version **2019.07.30** - [ ] I've searched the bugtracker for similar feature requests including closed ones diff --git a/ChangeLog b/ChangeLog index 5ce78b07a..f6f1f7e38 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,84 @@ +version 2019.07.30 + +Extractors +* [youtube] Fix and improve title and description extraction (#21934) + + +version 2019.07.27 + +Extractors ++ [yahoo:japannews] Add support for yahoo.co.jp (#21698, #21265) ++ [discovery] Add support go.discovery.com URLs +* [youtube:playlist] Relax video regular expression (#21844) +* [generic] Restrict --default-search schemeless URLs detection pattern + (#21842) +* [vrv] Fix CMS signing query extraction (#21809) + + +version 2019.07.16 + +Extractors ++ [asiancrush] Add support for yuyutv.com, midnightpulp.com and cocoro.tv + (#21281, #21290) +* [kaltura] Check source format URL (#21290) +* [ctsnews] Fix YouTube embeds extraction (#21678) ++ [einthusan] Add support for einthusan.com (#21748, #21775) ++ [youtube] Add support for invidious.mastodon.host (#21777) ++ [gfycat] Extend URL regular expression (#21779, #21780) +* [youtube] Restrict is_live extraction (#21782) + + +version 2019.07.14 + +Extractors +* [porn91] Fix extraction (#21312) ++ [yandexmusic] Extract track number and disk number (#21421) ++ [yandexmusic] Add support for multi disk albums (#21420, #21421) +* [lynda] Handle missing subtitles (#20490, #20513) ++ [youtube] Add more invidious instances to URL regular expression (#21694) +* [twitter] Improve uploader id extraction (#21705) +* [spankbang] Fix and improve metadata extraction +* [spankbang] Fix extraction (#21763, #21764) ++ [dlive] Add support for dlive.tv (#18080) ++ [livejournal] Add support for livejournal.com (#21526) +* [roosterteeth] Fix free episode extraction (#16094) +* [dbtv] Fix extraction +* [bellator] Fix extraction +- [rudo] Remove extractor (#18430, #18474) +* [facebook] Fallback to twitter:image meta for thumbnail extraction (#21224) +* [bleacherreport] Fix Bleacher Report CMS extraction +* [espn] Fix fivethirtyeight.com extraction +* [5tv] Relax video URL regular expression and support https URLs +* [youtube] Fix is_live extraction (#21734) +* [youtube] Fix authentication (#11270) + + +version 2019.07.12 + +Core ++ [adobepass] Add support for AT&T U-verse (mso ATT) (#13938, #21016) + +Extractors ++ [mgtv] Pass Referer HTTP header for format URLs (#21726) ++ [beeg] Add support for api/v6 v2 URLs without t argument (#21701) +* [voxmedia:volume] Improvevox embed extraction (#16846) +* [funnyordie] Move extraction to VoxMedia extractor (#16846) +* [gameinformer] Fix extraction (#8895, #15363, #17206) +* [funk] Fix extraction (#17915) +* [packtpub] Relax lesson URL regular expression (#21695) +* [packtpub] Fix extraction (#21268) +* [philharmoniedeparis] Relax URL regular expression (#21672) +* [peertube] Detect embed URLs in generic extraction (#21666) +* [mixer:vod] Relax URL regular expression (#21657, #21658) ++ [lecturio] Add support id based URLs (#21630) ++ [go] Add site info for disneynow (#21613) +* [ted] Restrict info regular expression (#21631) +* [twitch:vod] Actualize m3u8 URL (#21538, #21607) +* [vzaar] Fix videos with empty title (#21606) +* [tvland] Fix extraction (#21384) +* [arte] Clean extractor (#15583, #21614) + + version 2019.07.02 Core diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 55ae43144..7cf60eefe 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -58,16 +58,8 @@ - **ARD:mediathek** - **ARDBetaMediathek** - **Arkena** - - **arte.tv** - **arte.tv:+7** - - **arte.tv:cinema** - - **arte.tv:concert** - - **arte.tv:creative** - - **arte.tv:ddc** - **arte.tv:embed** - - **arte.tv:future** - - **arte.tv:info** - - **arte.tv:magazine** - **arte.tv:playlist** - **AsianCrush** - **AsianCrushPlaylist** @@ -231,6 +223,8 @@ - **DiscoveryNetworksDe** - **DiscoveryVR** - **Disney** + - **dlive:stream** + - **dlive:vod** - **Dotsub** - **DouyuShow** - **DouyuTV**: 斗鱼 @@ -313,9 +307,7 @@ - **FrontendMastersCourse** - **FrontendMastersLesson** - **Funimation** - - **FunkChannel** - - **FunkMix** - - **FunnyOrDie** + - **Funk** - **Fusion** - **Fux** - **FXNetworks** @@ -458,6 +450,7 @@ - **linkedin:learning:course** - **LinuxAcademy** - **LiTV** + - **LiveJournal** - **LiveLeak** - **LiveLeakEmbed** - **livestream** @@ -764,7 +757,6 @@ - **rtve.es:television** - **RTVNH** - **RTVS** - - **Rudo** - **RUHD** - **rutube**: Rutube videos - **rutube:channel**: Rutube channels @@ -896,7 +888,6 @@ - **TF1** - **TFO** - **TheIntercept** - - **theoperaplatform** - **ThePlatform** - **ThePlatformFeed** - **TheScene** @@ -1126,6 +1117,7 @@ - **Yahoo**: Yahoo screen and movies - **yahoo:gyao** - **yahoo:gyao:player** + - **yahoo:japannews**: Yahoo! Japan News - **YandexDisk** - **yandexmusic:album**: Яндекс.Музыка - Альбом - **yandexmusic:playlist**: Яндекс.Музыка - Плейлист diff --git a/youtube_dl/downloader/dash.py b/youtube_dl/downloader/dash.py index eaa7adf7c..c6d674bc6 100644 --- a/youtube_dl/downloader/dash.py +++ b/youtube_dl/downloader/dash.py @@ -53,7 +53,7 @@ class DashSegmentsFD(FragmentFD): except compat_urllib_error.HTTPError as err: # YouTube may often return 404 HTTP error for a fragment causing the # whole download to fail. However if the same fragment is immediately - # retried with the same request data this usually succeeds (1-2 attemps + # retried with the same request data this usually succeeds (1-2 attempts # is usually enough) thus allowing to download the whole file successfully. # To be future-proof we will retry all fragments that fail with any # HTTP error. diff --git a/youtube_dl/downloader/ism.py b/youtube_dl/downloader/ism.py index 063fcf444..1ca666b4a 100644 --- a/youtube_dl/downloader/ism.py +++ b/youtube_dl/downloader/ism.py @@ -146,7 +146,7 @@ def write_piff_header(stream, params): sps, pps = codec_private_data.split(u32.pack(1))[1:] avcc_payload = u8.pack(1) # configuration version avcc_payload += sps[1:4] # avc profile indication + profile compatibility + avc level indication - avcc_payload += u8.pack(0xfc | (params.get('nal_unit_length_field', 4) - 1)) # complete represenation (1) + reserved (11111) + length size minus one + avcc_payload += u8.pack(0xfc | (params.get('nal_unit_length_field', 4) - 1)) # complete representation (1) + reserved (11111) + length size minus one avcc_payload += u8.pack(1) # reserved (0) + number of sps (0000001) avcc_payload += u16.pack(len(sps)) avcc_payload += sps diff --git a/youtube_dl/extractor/abcnews.py b/youtube_dl/extractor/abcnews.py index cd29aca77..8b407bf9c 100644 --- a/youtube_dl/extractor/abcnews.py +++ b/youtube_dl/extractor/abcnews.py @@ -15,10 +15,13 @@ class AbcNewsVideoIE(AMPIE): IE_NAME = 'abcnews:video' _VALID_URL = r'''(?x) https?:// - abcnews\.go\.com/ (?: - [^/]+/video/(?P[0-9a-z-]+)-| - video/embed\?.*?\bid= + abcnews\.go\.com/ + (?: + [^/]+/video/(?P[0-9a-z-]+)-| + video/embed\?.*?\bid= + )| + fivethirtyeight\.abcnews\.go\.com/video/embed/\d+/ ) (?P\d+) ''' diff --git a/youtube_dl/extractor/asiancrush.py b/youtube_dl/extractor/asiancrush.py index 6d71c5ad5..0348e680c 100644 --- a/youtube_dl/extractor/asiancrush.py +++ b/youtube_dl/extractor/asiancrush.py @@ -5,14 +5,12 @@ import re from .common import InfoExtractor from .kaltura import KalturaIE -from ..utils import ( - extract_attributes, - remove_end, -) +from ..utils import extract_attributes class AsianCrushIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?asiancrush\.com/video/(?:[^/]+/)?0+(?P\d+)v\b' + _VALID_URL_BASE = r'https?://(?:www\.)?(?P(?:(?:asiancrush|yuyutv|midnightpulp)\.com|cocoro\.tv))' + _VALID_URL = r'%s/video/(?:[^/]+/)?0+(?P\d+)v\b' % _VALID_URL_BASE _TESTS = [{ 'url': 'https://www.asiancrush.com/video/012869v/women-who-flirt/', 'md5': 'c3b740e48d0ba002a42c0b72857beae6', @@ -20,7 +18,7 @@ class AsianCrushIE(InfoExtractor): 'id': '1_y4tmjm5r', 'ext': 'mp4', 'title': 'Women Who Flirt', - 'description': 'md5:3db14e9186197857e7063522cb89a805', + 'description': 'md5:7e986615808bcfb11756eb503a751487', 'timestamp': 1496936429, 'upload_date': '20170608', 'uploader_id': 'craig@crifkin.com', @@ -28,10 +26,27 @@ class AsianCrushIE(InfoExtractor): }, { 'url': 'https://www.asiancrush.com/video/she-was-pretty/011886v-pretty-episode-3/', 'only_matching': True, + }, { + 'url': 'https://www.yuyutv.com/video/013886v/the-act-of-killing/', + 'only_matching': True, + }, { + 'url': 'https://www.yuyutv.com/video/peep-show/013922v-warring-factions/', + 'only_matching': True, + }, { + 'url': 'https://www.midnightpulp.com/video/010400v/drifters/', + 'only_matching': True, + }, { + 'url': 'https://www.midnightpulp.com/video/mononoke/016378v-zashikiwarashi-part-1/', + 'only_matching': True, + }, { + 'url': 'https://www.cocoro.tv/video/the-wonderful-wizard-of-oz/008878v-the-wonderful-wizard-of-oz-ep01/', + 'only_matching': True, }] def _real_extract(self, url): - video_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + host = mobj.group('host') + video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) @@ -51,7 +66,7 @@ class AsianCrushIE(InfoExtractor): r'\bentry_id["\']\s*:\s*["\'](\d+)', webpage, 'entry id') player = self._download_webpage( - 'https://api.asiancrush.com/embeddedVideoPlayer', video_id, + 'https://api.%s/embeddedVideoPlayer' % host, video_id, query={'id': entry_id}) kaltura_id = self._search_regex( @@ -63,15 +78,23 @@ class AsianCrushIE(InfoExtractor): r'/p(?:artner_id)?/(\d+)', player, 'partner id', default='513551') - return self.url_result( - 'kaltura:%s:%s' % (partner_id, kaltura_id), - ie=KalturaIE.ie_key(), video_id=kaltura_id, - video_title=title) + description = self._html_search_regex( + r'(?s)]+\bclass=["\']description["\'][^>]*>(.+?)', + webpage, 'description', fatal=False) + + return { + '_type': 'url_transparent', + 'url': 'kaltura:%s:%s' % (partner_id, kaltura_id), + 'ie_key': KalturaIE.ie_key(), + 'id': video_id, + 'title': title, + 'description': description, + } class AsianCrushPlaylistIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?asiancrush\.com/series/0+(?P\d+)s\b' - _TEST = { + _VALID_URL = r'%s/series/0+(?P\d+)s\b' % AsianCrushIE._VALID_URL_BASE + _TESTS = [{ 'url': 'https://www.asiancrush.com/series/012481s/scholar-walks-night/', 'info_dict': { 'id': '12481', @@ -79,7 +102,16 @@ class AsianCrushPlaylistIE(InfoExtractor): 'description': 'md5:7addd7c5132a09fd4741152d96cce886', }, 'playlist_count': 20, - } + }, { + 'url': 'https://www.yuyutv.com/series/013920s/peep-show/', + 'only_matching': True, + }, { + 'url': 'https://www.midnightpulp.com/series/016375s/mononoke/', + 'only_matching': True, + }, { + 'url': 'https://www.cocoro.tv/series/008549s/the-wonderful-wizard-of-oz/', + 'only_matching': True, + }] def _real_extract(self, url): playlist_id = self._match_id(url) @@ -96,15 +128,15 @@ class AsianCrushPlaylistIE(InfoExtractor): entries.append(self.url_result( mobj.group('url'), ie=AsianCrushIE.ie_key())) - title = remove_end( - self._html_search_regex( - r'(?s)]\bid=["\']movieTitle[^>]+>(.+?)', webpage, - 'title', default=None) or self._og_search_title( - webpage, default=None) or self._html_search_meta( - 'twitter:title', webpage, 'title', - default=None) or self._search_regex( - r'([^<]+)', webpage, 'title', fatal=False), - ' | AsianCrush') + title = self._html_search_regex( + r'(?s)]\bid=["\']movieTitle[^>]+>(.+?)', webpage, + 'title', default=None) or self._og_search_title( + webpage, default=None) or self._html_search_meta( + 'twitter:title', webpage, 'title', + default=None) or self._search_regex( + r'([^<]+)', webpage, 'title', fatal=False) + if title: + title = re.sub(r'\s*\|\s*.+?$', '', title) description = self._og_search_description( webpage, default=None) or self._html_search_meta( diff --git a/youtube_dl/extractor/beeg.py b/youtube_dl/extractor/beeg.py index c15a0ac8f..5788d13ba 100644 --- a/youtube_dl/extractor/beeg.py +++ b/youtube_dl/extractor/beeg.py @@ -32,6 +32,10 @@ class BeegIE(InfoExtractor): # api/v6 v2 'url': 'https://beeg.com/1941093077?t=911-1391', 'only_matching': True, + }, { + # api/v6 v2 w/o t + 'url': 'https://beeg.com/1277207756', + 'only_matching': True, }, { 'url': 'https://beeg.porn/video/5416503', 'only_matching': True, @@ -49,14 +53,17 @@ class BeegIE(InfoExtractor): r'beeg_version\s*=\s*([\da-zA-Z_-]+)', webpage, 'beeg version', default='1546225636701') - qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) - t = qs.get('t', [''])[0].split('-') - if len(t) > 1: + if len(video_id) >= 10: query = { 'v': 2, - 's': t[0], - 'e': t[1], } + qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) + t = qs.get('t', [''])[0].split('-') + if len(t) > 1: + query.update({ + 's': t[0], + 'e': t[1], + }) else: query = {'v': 1} diff --git a/youtube_dl/extractor/biobiochiletv.py b/youtube_dl/extractor/biobiochiletv.py index b92031c8a..dc86c57c5 100644 --- a/youtube_dl/extractor/biobiochiletv.py +++ b/youtube_dl/extractor/biobiochiletv.py @@ -6,7 +6,6 @@ from ..utils import ( ExtractorError, remove_end, ) -from .rudo import RudoIE class BioBioChileTVIE(InfoExtractor): @@ -41,11 +40,15 @@ class BioBioChileTVIE(InfoExtractor): }, { 'url': 'http://www.biobiochile.cl/noticias/bbtv/comentarios-bio-bio/2016/07/08/edecanes-del-congreso-figuras-decorativas-que-le-cuestan-muy-caro-a-los-chilenos.shtml', 'info_dict': { - 'id': 'edecanes-del-congreso-figuras-decorativas-que-le-cuestan-muy-caro-a-los-chilenos', + 'id': 'b4xd0LK3SK', 'ext': 'mp4', - 'uploader': '(none)', - 'upload_date': '20160708', - 'title': 'Edecanes del Congreso: Figuras decorativas que le cuestan muy caro a los chilenos', + # TODO: fix url_transparent information overriding + # 'uploader': 'Juan Pablo Echenique', + 'title': 'Comentario Oscar Cáceres', + }, + 'params': { + # empty m3u8 manifest + 'skip_download': True, }, }, { 'url': 'http://tv.biobiochile.cl/notas/2015/10/22/ninos-transexuales-de-quien-es-la-decision.shtml', @@ -60,7 +63,9 @@ class BioBioChileTVIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - rudo_url = RudoIE._extract_url(webpage) + rudo_url = self._search_regex( + r']+src=(?P[\'"])(?P(?:https?:)?//rudo\.video/vod/[0-9a-zA-Z]+)(?P=q1)', + webpage, 'embed URL', None, group='url') if not rudo_url: raise ExtractorError('No videos found') @@ -68,7 +73,7 @@ class BioBioChileTVIE(InfoExtractor): thumbnail = self._og_search_thumbnail(webpage) uploader = self._html_search_regex( - r']+href=["\']https?://(?:busca|www)\.biobiochile\.cl/(?:lista/)?(?:author|autor)[^>]+>(.+?)', + r']+href=["\'](?:https?://(?:busca|www)\.biobiochile\.cl)?/(?:lista/)?(?:author|autor)[^>]+>(.+?)', webpage, 'uploader', fatal=False) return { diff --git a/youtube_dl/extractor/bleacherreport.py b/youtube_dl/extractor/bleacherreport.py index e829974ff..dc60224d0 100644 --- a/youtube_dl/extractor/bleacherreport.py +++ b/youtube_dl/extractor/bleacherreport.py @@ -71,7 +71,7 @@ class BleacherReportIE(InfoExtractor): video = article_data.get('video') if video: video_type = video['type'] - if video_type == 'cms.bleacherreport.com': + if video_type in ('cms.bleacherreport.com', 'vid.bleacherreport.com'): info['url'] = 'http://bleacherreport.com/video_embed?id=%s' % video['id'] elif video_type == 'ooyala.com': info['url'] = 'ooyala:%s' % video['id'] @@ -87,9 +87,9 @@ class BleacherReportIE(InfoExtractor): class BleacherReportCMSIE(AMPIE): - _VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/video_embed\?id=(?P[0-9a-f-]{36})' + _VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/video_embed\?id=(?P[0-9a-f-]{36}|\d{5})' _TESTS = [{ - 'url': 'http://bleacherreport.com/video_embed?id=8fd44c2f-3dc5-4821-9118-2c825a98c0e1', + 'url': 'http://bleacherreport.com/video_embed?id=8fd44c2f-3dc5-4821-9118-2c825a98c0e1&library=video-cms', 'md5': '2e4b0a997f9228ffa31fada5c53d1ed1', 'info_dict': { 'id': '8fd44c2f-3dc5-4821-9118-2c825a98c0e1', @@ -101,6 +101,6 @@ class BleacherReportCMSIE(AMPIE): def _real_extract(self, url): video_id = self._match_id(url) - info = self._extract_feed_info('http://cms.bleacherreport.com/media/items/%s/akamai.json' % video_id) + info = self._extract_feed_info('http://vid.bleacherreport.com/videos/%s.akamai' % video_id) info['id'] = video_id return info diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 9c3e9eec6..859786617 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -220,7 +220,7 @@ class InfoExtractor(object): * "preference" (optional, int) - quality of the image * "width" (optional, int) * "height" (optional, int) - * "resolution" (optional, string "{width}x{height"}, + * "resolution" (optional, string "{width}x{height}", deprecated) * "filesize" (optional, int) thumbnail: Full URL to a video thumbnail image. diff --git a/youtube_dl/extractor/ctsnews.py b/youtube_dl/extractor/ctsnews.py index d565335cf..679f1d92e 100644 --- a/youtube_dl/extractor/ctsnews.py +++ b/youtube_dl/extractor/ctsnews.py @@ -3,6 +3,7 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import unified_timestamp +from .youtube import YoutubeIE class CtsNewsIE(InfoExtractor): @@ -14,8 +15,8 @@ class CtsNewsIE(InfoExtractor): 'info_dict': { 'id': '201501291578109', 'ext': 'mp4', - 'title': '以色列.真主黨交火 3人死亡', - 'description': '以色列和黎巴嫩真主黨，爆發五年最嚴重衝突，雙方砲轟交火，兩名以軍死亡，還有一名西班牙籍的聯合國維和人...', + 'title': '以色列.真主黨交火 3人死亡 - 華視新聞網', + 'description': '以色列和黎巴嫩真主黨，爆發五年最嚴重衝突，雙方砲轟交火，兩名以軍死亡，還有一名西班牙籍的聯合國維和人員也不幸罹難。大陸陝西、河南、安徽、江蘇和湖北五個省份出現大暴雪，嚴重影響陸空交通，不過九華山卻出現...', 'timestamp': 1422528540, 'upload_date': '20150129', } @@ -26,7 +27,7 @@ class CtsNewsIE(InfoExtractor): 'info_dict': { 'id': '201309031304098', 'ext': 'mp4', - 'title': '韓國31歲童顏男 貌如十多歲小孩', + 'title': '韓國31歲童顏男 貌如十多歲小孩 - 華視新聞網', 'description': '越有年紀的人，越希望看起來年輕一點，而南韓卻有一位31歲的男子，看起來像是11、12歲的小孩，身...', 'thumbnail': r're:^https?://.*\.jpg$', 'timestamp': 1378205880, @@ -62,8 +63,7 @@ class CtsNewsIE(InfoExtractor): video_url = mp4_feed['source_url'] else: self.to_screen('Not CTSPlayer video, trying Youtube...') - youtube_url = self._search_regex( - r'src="(//www\.youtube\.com/embed/[^"]+)"', page, 'youtube url') + youtube_url = YoutubeIE._extract_url(page) return self.url_result(youtube_url, ie='Youtube') diff --git a/youtube_dl/extractor/dbtv.py b/youtube_dl/extractor/dbtv.py index f232f0dc5..aaedf2e3d 100644 --- a/youtube_dl/extractor/dbtv.py +++ b/youtube_dl/extractor/dbtv.py @@ -7,50 +7,51 @@ from .common import InfoExtractor class DBTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?dbtv\.no/(?:[^/]+/)?(?P[0-9]+)(?:#(?P.+))?' + _VALID_URL = r'https?://(?:www\.)?dagbladet\.no/video/(?:(?:embed|(?P[^/]+))/)?(?P[0-9A-Za-z_-]{11}|[a-zA-Z0-9]{8})' _TESTS = [{ - 'url': 'http://dbtv.no/3649835190001#Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen', - 'md5': '2e24f67936517b143a234b4cadf792ec', + 'url': 'https://www.dagbladet.no/video/PynxJnNWChE/', + 'md5': 'b8f850ba1860adbda668d367f9b77699', 'info_dict': { - 'id': '3649835190001', - 'display_id': 'Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen', + 'id': 'PynxJnNWChE', 'ext': 'mp4', 'title': 'Skulle teste ut fornøyelsespark, men kollegaen var bare opptatt av bikinikroppen', - 'description': 'md5:1504a54606c4dde3e4e61fc97aa857e0', + 'description': 'md5:49cc8370e7d66e8a2ef15c3b4631fd3f', 'thumbnail': r're:https?://.*\.jpg', - 'timestamp': 1404039863, - 'upload_date': '20140629', - 'duration': 69.544, - 'uploader_id': '1027729757001', + 'upload_date': '20160916', + 'duration': 69, + 'uploader_id': 'UCk5pvsyZJoYJBd7_oFPTlRQ', + 'uploader': 'Dagbladet', }, - 'add_ie': ['BrightcoveNew'] + 'add_ie': ['Youtube'] }, { - 'url': 'http://dbtv.no/3649835190001', + 'url': 'https://www.dagbladet.no/video/embed/xlGmyIeN9Jo/?autoplay=false', 'only_matching': True, }, { - 'url': 'http://www.dbtv.no/lazyplayer/4631135248001', - 'only_matching': True, - }, { - 'url': 'http://dbtv.no/vice/5000634109001', - 'only_matching': True, - }, { - 'url': 'http://dbtv.no/filmtrailer/3359293614001', + 'url': 'https://www.dagbladet.no/video/truer-iran-bor-passe-dere/PalfB2Cw', 'only_matching': True, }] @staticmethod def _extract_urls(webpage): return [url for _, url in re.findall( - r']+src=(["\'])((?:https?:)?//(?:www\.)?dbtv\.no/(?:lazy)?player/\d+.*?)\1', + r']+src=(["\'])((?:https?:)?//(?:www\.)?dagbladet\.no/video/embed/(?:[0-9A-Za-z_-]{11}|[a-zA-Z0-9]{8}).*?)\1', webpage)] def _real_extract(self, url): - video_id, display_id = re.match(self._VALID_URL, url).groups() - - return { + display_id, video_id = re.match(self._VALID_URL, url).groups() + info = { '_type': 'url_transparent', - 'url': 'http://players.brightcove.net/1027729757001/default_default/index.html?videoId=%s' % video_id, 'id': video_id, 'display_id': display_id, - 'ie_key': 'BrightcoveNew', } + if len(video_id) == 11: + info.update({ + 'url': video_id, + 'ie_key': 'Youtube', + }) + else: + info.update({ + 'url': 'jwplatform:' + video_id, + 'ie_key': 'JWPlatform', + }) + return info diff --git a/youtube_dl/extractor/discovery.py b/youtube_dl/extractor/discovery.py index b70c307a7..9003545ce 100644 --- a/youtube_dl/extractor/discovery.py +++ b/youtube_dl/extractor/discovery.py @@ -19,9 +19,9 @@ from ..compat import compat_HTTPError class DiscoveryIE(DiscoveryGoBaseIE): _VALID_URL = r'''(?x)https?:// (?P + (?:(?:www|go)\.)?discovery| (?:www\.)? (?: - discovery| investigationdiscovery| discoverylife| animalplanet| @@ -56,6 +56,9 @@ class DiscoveryIE(DiscoveryGoBaseIE): }, { 'url': 'https://www.investigationdiscovery.com/tv-shows/final-vision/full-episodes/final-vision', 'only_matching': True, + }, { + 'url': 'https://go.discovery.com/tv-shows/alaskan-bush-people/videos/follow-your-own-road', + 'only_matching': True, }] _GEO_COUNTRIES = ['US'] _GEO_BYPASS = False diff --git a/youtube_dl/extractor/dlive.py b/youtube_dl/extractor/dlive.py new file mode 100644 index 000000000..8787f15a6 --- /dev/null +++ b/youtube_dl/extractor/dlive.py @@ -0,0 +1,94 @@ +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import int_or_none + + +class DLiveVODIE(InfoExtractor): + IE_NAME = 'dlive:vod' + _VALID_URL = r'https?://(?:www\.)?dlive\.tv/p/(?P.+?)\+(?P[a-zA-Z0-9]+)' + _TEST = { + 'url': 'https://dlive.tv/p/pdp+3mTzOl4WR', + 'info_dict': { + 'id': '3mTzOl4WR', + 'ext': 'mp4', + 'title': 'Minecraft with james charles epic', + 'upload_date': '20190701', + 'timestamp': 1562011015, + 'uploader_id': 'pdp', + } + } + + def _real_extract(self, url): + uploader_id, vod_id = re.match(self._VALID_URL, url).groups() + broadcast = self._download_json( + 'https://graphigo.prd.dlive.tv/', vod_id, + data=json.dumps({'query': '''query { + pastBroadcast(permlink:"%s+%s") { + content + createdAt + length + playbackUrl + title + thumbnailUrl + viewCount + } +}''' % (uploader_id, vod_id)}).encode())['data']['pastBroadcast'] + title = broadcast['title'] + formats = self._extract_m3u8_formats( + broadcast['playbackUrl'], vod_id, 'mp4', 'm3u8_native') + self._sort_formats(formats) + return { + 'id': vod_id, + 'title': title, + 'uploader_id': uploader_id, + 'formats': formats, + 'description': broadcast.get('content'), + 'thumbnail': broadcast.get('thumbnailUrl'), + 'timestamp': int_or_none(broadcast.get('createdAt'), 1000), + 'view_count': int_or_none(broadcast.get('viewCount')), + } + + +class DLiveStreamIE(InfoExtractor): + IE_NAME = 'dlive:stream' + _VALID_URL = r'https?://(?:www\.)?dlive\.tv/(?!p/)(?P[\w.-]+)' + + def _real_extract(self, url): + display_name = self._match_id(url) + user = self._download_json( + 'https://graphigo.prd.dlive.tv/', display_name, + data=json.dumps({'query': '''query { + userByDisplayName(displayname:"%s") { + livestream { + content + createdAt + title + thumbnailUrl + watchingCount + } + username + } +}''' % display_name}).encode())['data']['userByDisplayName'] + livestream = user['livestream'] + title = livestream['title'] + username = user['username'] + formats = self._extract_m3u8_formats( + 'https://live.prd.dlive.tv/hls/live/%s.m3u8' % username, + display_name, 'mp4') + self._sort_formats(formats) + return { + 'id': display_name, + 'title': self._live_title(title), + 'uploader': display_name, + 'uploader_id': username, + 'formats': formats, + 'description': livestream.get('content'), + 'thumbnail': livestream.get('thumbnailUrl'), + 'is_live': True, + 'timestamp': int_or_none(livestream.get('createdAt'), 1000), + 'view_count': int_or_none(livestream.get('watchingCount')), + } diff --git a/youtube_dl/extractor/einthusan.py b/youtube_dl/extractor/einthusan.py index 4485bf8c1..1fb00c9b0 100644 --- a/youtube_dl/extractor/einthusan.py +++ b/youtube_dl/extractor/einthusan.py @@ -2,6 +2,7 @@ from __future__ import unicode_literals import json +import re from .common import InfoExtractor from ..compat import ( @@ -18,7 +19,7 @@ from ..utils import ( class EinthusanIE(InfoExtractor): - _VALID_URL = r'https?://einthusan\.tv/movie/watch/(?P[^/?#&]+)' + _VALID_URL = r'https?://(?Peinthusan\.(?:tv|com))/movie/watch/(?P[^/?#&]+)' _TESTS = [{ 'url': 'https://einthusan.tv/movie/watch/9097/', 'md5': 'ff0f7f2065031b8a2cf13a933731c035', @@ -32,6 +33,9 @@ class EinthusanIE(InfoExtractor): }, { 'url': 'https://einthusan.tv/movie/watch/51MZ/?lang=hindi', 'only_matching': True, + }, { + 'url': 'https://einthusan.com/movie/watch/9097/', + 'only_matching': True, }] # reversed from jsoncrypto.prototype.decrypt() in einthusan-PGMovieWatcher.js @@ -41,7 +45,9 @@ class EinthusanIE(InfoExtractor): )).decode('utf-8'), video_id) def _real_extract(self, url): - video_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + host = mobj.group('host') + video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) @@ -53,7 +59,7 @@ class EinthusanIE(InfoExtractor): 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, + 'https://%s/ajax/movie/watch/%s/' % (host, video_id), video_id, data=urlencode_postdata({ 'xEvent': 'UIVideoPlayer.PingOutcome', 'xJson': json.dumps({ diff --git a/youtube_dl/extractor/espn.py b/youtube_dl/extractor/espn.py index 8cc9bd165..6cf05e6da 100644 --- a/youtube_dl/extractor/espn.py +++ b/youtube_dl/extractor/espn.py @@ -216,17 +216,14 @@ class FiveThirtyEightIE(InfoExtractor): _TEST = { 'url': 'http://fivethirtyeight.com/features/how-the-6-8-raiders-can-still-make-the-playoffs/', 'info_dict': { - 'id': '21846851', - 'ext': 'mp4', + 'id': '56032156', + 'ext': 'flv', 'title': 'FiveThirtyEight: The Raiders can still make the playoffs', 'description': 'Neil Paine breaks down the simplest scenario that will put the Raiders into the playoffs at 8-8.', - 'timestamp': 1513960621, - 'upload_date': '20171222', }, 'params': { 'skip_download': True, }, - 'expected_warnings': ['Unable to download f4m manifest'], } def _real_extract(self, url): @@ -234,9 +231,8 @@ class FiveThirtyEightIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - video_id = self._search_regex( - r'data-video-id=["\'](?P\d+)', - webpage, 'video id', group='id') + embed_url = self._search_regex( + r']+src=["\'](https?://fivethirtyeight\.abcnews\.go\.com/video/embed/\d+/\d+)', + webpage, 'embed url') - return self.url_result( - 'http://espn.go.com/video/clip?id=%s' % video_id, ESPNIE.ie_key()) + return self.url_result(embed_url, 'AbcNewsVideo') diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 02f17cf0d..06de556b7 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -395,11 +395,7 @@ from .frontendmasters import ( FrontendMastersCourseIE ) from .funimation import FunimationIE -from .funk import ( - FunkMixIE, - FunkChannelIE, -) -from .funnyordie import FunnyOrDieIE +from .funk import FunkIE from .fusion import FusionIE from .fxnetworks import FXNetworksIE from .gaia import GaiaIE @@ -583,6 +579,7 @@ from .linkedin import ( ) from .linuxacademy import LinuxAcademyIE from .litv import LiTVIE +from .livejournal import LiveJournalIE from .liveleak import ( LiveLeakIE, LiveLeakEmbedIE, @@ -971,7 +968,6 @@ from .rts import RTSIE from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE, RTVELiveIE, RTVETelevisionIE from .rtvnh import RTVNHIE from .rtvs import RTVSIE -from .rudo import RudoIE from .ruhd import RUHDIE from .rutube import ( RutubeIE, @@ -1259,6 +1255,10 @@ from .udn import UDNEmbedIE from .ufctv import UFCTVIE from .uktvplay import UKTVPlayIE from .digiteka import DigitekaIE +from .dlive import ( + DLiveVODIE, + DLiveStreamIE, +) from .umg import UMGDeIE from .unistra import UnistraIE from .unity import UnityIE @@ -1448,6 +1448,7 @@ from .yahoo import ( YahooSearchIE, YahooGyaOPlayerIE, YahooGyaOIE, + YahooJapanNewsIE, ) from .yandexdisk import YandexDiskIE from .yandexmusic import ( diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index 789dd79d5..a3dcdca3e 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -428,7 +428,7 @@ class FacebookIE(InfoExtractor): timestamp = int_or_none(self._search_regex( r']+data-utime=["\'](\d+)', webpage, 'timestamp', default=None)) - thumbnail = self._og_search_thumbnail(webpage) + thumbnail = self._html_search_meta(['og:image', 'twitter:image'], webpage) view_count = parse_count(self._search_regex( r'\bviewCount\s*:\s*["\']([\d,.]+)', webpage, 'view count', diff --git a/youtube_dl/extractor/fivetv.py b/youtube_dl/extractor/fivetv.py index 9f9863746..c4c0f1b3d 100644 --- a/youtube_dl/extractor/fivetv.py +++ b/youtube_dl/extractor/fivetv.py @@ -9,7 +9,7 @@ from ..utils import int_or_none class FiveTVIE(InfoExtractor): _VALID_URL = r'''(?x) - http:// + https?:// (?:www\.)?5-tv\.ru/ (?: (?:[^/]+/)+(?P\d+)| @@ -39,6 +39,7 @@ class FiveTVIE(InfoExtractor): 'duration': 180, }, }, { + # redirect to https://www.5-tv.ru/projects/1000095/izvestia-glavnoe/ 'url': 'http://www.5-tv.ru/glavnoe/#itemDetails', 'info_dict': { 'id': 'glavnoe', @@ -46,6 +47,7 @@ class FiveTVIE(InfoExtractor): 'title': r're:^Итоги недели с \d+ по \d+ \w+ \d{4} года$', 'thumbnail': r're:^https?://.*\.jpg$', }, + 'skip': 'redirect to «Известия. Главное» project page', }, { 'url': 'http://www.5-tv.ru/glavnoe/broadcasts/508645/', 'only_matching': True, @@ -70,7 +72,7 @@ class FiveTVIE(InfoExtractor): webpage = self._download_webpage(url, video_id) video_url = self._search_regex( - [r']+?class="flowplayer[^>]+?data-href="([^"]+)"', + [r']+?class="(?:flow)?player[^>]+?data-href="([^"]+)"', r']+?href="([^"]+)"[^>]+?class="videoplayer"'], webpage, 'video url') diff --git a/youtube_dl/extractor/funk.py b/youtube_dl/extractor/funk.py index 7e1af95e0..81d1949fd 100644 --- a/youtube_dl/extractor/funk.py +++ b/youtube_dl/extractor/funk.py @@ -1,89 +1,21 @@ # coding: utf-8 from __future__ import unicode_literals -import itertools import re from .common import InfoExtractor from .nexx import NexxIE -from ..compat import compat_str from ..utils import ( int_or_none, - try_get, + str_or_none, ) -class FunkBaseIE(InfoExtractor): - _HEADERS = { - 'Accept': '*/*', - 'Accept-Language': 'en-US,en;q=0.9,ru;q=0.8', - 'authorization': 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJjbGllbnROYW1lIjoid2ViYXBwLXYzMSIsInNjb3BlIjoic3RhdGljLWNvbnRlbnQtYXBpLGN1cmF0aW9uLWFwaSxuZXh4LWNvbnRlbnQtYXBpLXYzMSx3ZWJhcHAtYXBpIn0.mbuG9wS9Yf5q6PqgR4fiaRFIagiHk9JhwoKES7ksVX4', - } - _AUTH = 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJjbGllbnROYW1lIjoid2ViYXBwLXYzMSIsInNjb3BlIjoic3RhdGljLWNvbnRlbnQtYXBpLGN1cmF0aW9uLWFwaSxuZXh4LWNvbnRlbnQtYXBpLXYzMSx3ZWJhcHAtYXBpIn0.mbuG9wS9Yf5q6PqgR4fiaRFIagiHk9JhwoKES7ksVX4' - - @staticmethod - def _make_headers(referer): - headers = FunkBaseIE._HEADERS.copy() - headers['Referer'] = referer - return headers - - def _make_url_result(self, video): - return { - '_type': 'url_transparent', - 'url': 'nexx:741:%s' % video['sourceId'], - 'ie_key': NexxIE.ie_key(), - 'id': video['sourceId'], - 'title': video.get('title'), - 'description': video.get('description'), - 'duration': int_or_none(video.get('duration')), - 'season_number': int_or_none(video.get('seasonNr')), - 'episode_number': int_or_none(video.get('episodeNr')), - } - - -class FunkMixIE(FunkBaseIE): - _VALID_URL = r'https?://(?:www\.)?funk\.net/mix/(?P[^/]+)/(?P[^/?#&]+)' +class FunkIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?funk\.net/(?:channel|playlist)/[^/]+/(?P[0-9a-z-]+)-(?P\d+)' _TESTS = [{ - 'url': 'https://www.funk.net/mix/59d65d935f8b160001828b5b/die-realste-kifferdoku-aller-zeiten', - 'md5': '8edf617c2f2b7c9847dfda313f199009', - 'info_dict': { - 'id': '123748', - 'ext': 'mp4', - 'title': '"Die realste Kifferdoku aller Zeiten"', - 'description': 'md5:c97160f5bafa8d47ec8e2e461012aa9d', - 'timestamp': 1490274721, - 'upload_date': '20170323', - }, - }] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - mix_id = mobj.group('id') - alias = mobj.group('alias') - - lists = self._download_json( - 'https://www.funk.net/api/v3.1/curation/curatedLists/', - mix_id, headers=self._make_headers(url), query={ - 'size': 100, - })['_embedded']['curatedListList'] - - metas = next( - l for l in lists - if mix_id in (l.get('entityId'), l.get('alias')))['videoMetas'] - video = next( - meta['videoDataDelegate'] - for meta in metas - if try_get( - meta, lambda x: x['videoDataDelegate']['alias'], - compat_str) == alias) - - return self._make_url_result(video) - - -class FunkChannelIE(FunkBaseIE): - _VALID_URL = r'https?://(?:www\.)?funk\.net/channel/(?P[^/]+)/(?P[^/?#&]+)' - _TESTS = [{ - 'url': 'https://www.funk.net/channel/ba/die-lustigsten-instrumente-aus-dem-internet-teil-2', + 'url': 'https://www.funk.net/channel/ba-793/die-lustigsten-instrumente-aus-dem-internet-teil-2-1155821', + 'md5': '8dd9d9ab59b4aa4173b3197f2ea48e81', 'info_dict': { 'id': '1155821', 'ext': 'mp4', @@ -92,83 +24,26 @@ class FunkChannelIE(FunkBaseIE): 'timestamp': 1514507395, 'upload_date': '20171229', }, - 'params': { - 'skip_download': True, - }, + }, { - # only available via byIdList API - 'url': 'https://www.funk.net/channel/informr/martin-sonneborn-erklaert-die-eu', - 'info_dict': { - 'id': '205067', - 'ext': 'mp4', - 'title': 'Martin Sonneborn erklärt die EU', - 'description': 'md5:050f74626e4ed87edf4626d2024210c0', - 'timestamp': 1494424042, - 'upload_date': '20170510', - }, - 'params': { - 'skip_download': True, - }, - }, { - 'url': 'https://www.funk.net/channel/59d5149841dca100012511e3/mein-erster-job-lovemilla-folge-1/lovemilla/', + 'url': 'https://www.funk.net/playlist/neuesteVideos/kameras-auf-dem-fusion-festival-1618699', 'only_matching': True, }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - channel_id = mobj.group('id') - alias = mobj.group('alias') - - headers = self._make_headers(url) - - video = None - - # Id-based channels are currently broken on their side: webplayer - # tries to process them via byChannelAlias endpoint and fails - # predictably. - for page_num in itertools.count(): - by_channel_alias = self._download_json( - 'https://www.funk.net/api/v3.1/webapp/videos/byChannelAlias/%s' - % channel_id, - 'Downloading byChannelAlias JSON page %d' % (page_num + 1), - headers=headers, query={ - 'filterFsk': 'false', - 'sort': 'creationDate,desc', - 'size': 100, - 'page': page_num, - }, fatal=False) - if not by_channel_alias: - break - video_list = try_get( - by_channel_alias, lambda x: x['_embedded']['videoList'], list) - if not video_list: - break - try: - video = next(r for r in video_list if r.get('alias') == alias) - break - except StopIteration: - pass - if not try_get( - by_channel_alias, lambda x: x['_links']['next']): - break - - if not video: - by_id_list = self._download_json( - 'https://www.funk.net/api/v3.0/content/videos/byIdList', - channel_id, 'Downloading byIdList JSON', headers=headers, - query={ - 'ids': alias, - }, fatal=False) - if by_id_list: - video = try_get(by_id_list, lambda x: x['result'][0], dict) - - if not video: - results = self._download_json( - 'https://www.funk.net/api/v3.0/content/videos/filter', - channel_id, 'Downloading filter JSON', headers=headers, query={ - 'channelId': channel_id, - 'size': 100, - })['result'] - video = next(r for r in results if r.get('alias') == alias) - - return self._make_url_result(video) + display_id, nexx_id = re.match(self._VALID_URL, url).groups() + video = self._download_json( + 'https://www.funk.net/api/v4.0/videos/' + nexx_id, nexx_id) + return { + '_type': 'url_transparent', + 'url': 'nexx:741:' + nexx_id, + 'ie_key': NexxIE.ie_key(), + 'id': nexx_id, + 'title': video.get('title'), + 'description': video.get('description'), + 'duration': int_or_none(video.get('duration')), + 'channel_id': str_or_none(video.get('channelId')), + 'display_id': display_id, + 'tags': video.get('tags'), + 'thumbnail': video.get('imageUrlLandscape'), + } diff --git a/youtube_dl/extractor/funnyordie.py b/youtube_dl/extractor/funnyordie.py deleted file mode 100644 index f85e7de14..000000000 --- a/youtube_dl/extractor/funnyordie.py +++ /dev/null @@ -1,162 +0,0 @@ -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..utils import ( - ExtractorError, - float_or_none, - int_or_none, - unified_timestamp, -) - - -class FunnyOrDieIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?funnyordie\.com/(?Pembed|articles|videos)/(?P[0-9a-f]+)(?:$|[?#/])' - _TESTS = [{ - 'url': 'http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version', - 'md5': 'bcd81e0c4f26189ee09be362ad6e6ba9', - 'info_dict': { - 'id': '0732f586d7', - 'ext': 'mp4', - 'title': 'Heart-Shaped Box: Literal Video Version', - 'description': 'md5:ea09a01bc9a1c46d9ab696c01747c338', - 'thumbnail': r're:^http:.*\.jpg$', - 'uploader': 'DASjr', - 'timestamp': 1317904928, - 'upload_date': '20111006', - 'duration': 318.3, - }, - }, { - 'url': 'http://www.funnyordie.com/embed/e402820827', - 'info_dict': { - 'id': 'e402820827', - 'ext': 'mp4', - 'title': 'Please Use This Song (Jon Lajoie)', - 'description': 'Please use this to sell something. www.jonlajoie.com', - 'thumbnail': r're:^http:.*\.jpg$', - 'timestamp': 1398988800, - 'upload_date': '20140502', - }, - 'params': { - 'skip_download': True, - }, - }, { - 'url': 'http://www.funnyordie.com/articles/ebf5e34fc8/10-hours-of-walking-in-nyc-as-a-man', - 'only_matching': True, - }] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - - video_id = mobj.group('id') - webpage = self._download_webpage(url, video_id) - - links = re.findall(r']+src=(["\'])(?P.+?/master\.m3u8[^"\']*)\1', - webpage, 'm3u8 url', group='url') - - formats = [] - - m3u8_formats = self._extract_m3u8_formats( - m3u8_url, video_id, 'mp4', 'm3u8_native', - m3u8_id='hls', fatal=False) - source_formats = list(filter( - lambda f: f.get('vcodec') != 'none', m3u8_formats)) - - bitrates = [int(bitrate) for bitrate in re.findall(r'[,/]v(\d+)(?=[,/])', m3u8_url)] - bitrates.sort() - - if source_formats: - self._sort_formats(source_formats) - - for bitrate, f in zip(bitrates, source_formats or [{}] * len(bitrates)): - for path, ext in links: - ff = f.copy() - if ff: - if ext != 'mp4': - ff = dict( - [(k, v) for k, v in ff.items() - if k in ('height', 'width', 'format_id')]) - ff.update({ - 'format_id': ff['format_id'].replace('hls', ext), - 'ext': ext, - 'protocol': 'http', - }) - else: - ff.update({ - 'format_id': '%s-%d' % (ext, bitrate), - 'vbr': bitrate, - }) - ff['url'] = self._proto_relative_url( - '%s%d.%s' % (path, bitrate, ext)) - formats.append(ff) - self._check_formats(formats, video_id) - - formats.extend(m3u8_formats) - self._sort_formats( - formats, field_preference=('height', 'width', 'tbr', 'format_id')) - - subtitles = {} - for src, src_lang in re.findall(r']+\bclass=["\']channel-preview-name[^>]+>(.+?).+)\.aspx' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?gameinformer\.com/(?:[^/]+/)*(?P[^.?&#]+)' + _TESTS = [{ + # normal Brightcove embed code extracted with BrightcoveNewIE._extract_url 'url': 'http://www.gameinformer.com/b/features/archive/2015/09/26/replay-animal-crossing.aspx', 'md5': '292f26da1ab4beb4c9099f1304d2b071', 'info_dict': { @@ -18,16 +25,25 @@ class GameInformerIE(InfoExtractor): 'upload_date': '20150928', 'uploader_id': '694940074001', }, - } + }, { + # Brightcove id inside unique element with field--name-field-brightcove-video-id class + 'url': 'https://www.gameinformer.com/video-feature/new-gameplay-today/2019/07/09/new-gameplay-today-streets-of-rogue', + 'info_dict': { + 'id': '6057111913001', + 'ext': 'mp4', + 'title': 'New Gameplay Today – Streets Of Rogue', + 'timestamp': 1562699001, + 'upload_date': '20190709', + 'uploader_id': '694940074001', + + }, + }] BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/694940074001/default_default/index.html?videoId=%s' def _real_extract(self, url): display_id = self._match_id(url) webpage = self._download_webpage( url, display_id, headers=self.geo_verification_headers()) - brightcove_id = self._search_regex( - [r'<[^>]+\bid=["\']bc_(\d+)', r"getVideo\('[^']+video_id=(\d+)"], - webpage, 'brightcove id') - return self.url_result( - self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', - brightcove_id) + brightcove_id = clean_html(get_element_by_class('field--name-field-brightcove-video-id', webpage) or get_element_by_id('video-source-content', webpage)) + brightcove_url = self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id if brightcove_id else BrightcoveNewIE._extract_url(self, webpage) + return self.url_result(brightcove_url, 'BrightcoveNew', brightcove_id) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 77e217460..d34fc4b15 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -2226,7 +2226,7 @@ class GenericIE(InfoExtractor): default_search = 'fixup_error' if default_search in ('auto', 'auto_warning', 'fixup_error'): - if '/' in url: + if re.match(r'^[^\s/]+\.[^\s/]+/', url): self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http') return self.url_result('http://' + url) elif default_search != 'fixup_error': diff --git a/youtube_dl/extractor/gfycat.py b/youtube_dl/extractor/gfycat.py index eb6f85836..bbe3cb283 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/(?:ifr/|gifs/detail/)?(?P[^-/?#]+)' + _VALID_URL = r'https?://(?:www\.)?gfycat\.com/(?:ru/|ifr/|gifs/detail/)?(?P[^-/?#]+)' _TESTS = [{ 'url': 'http://gfycat.com/DeadlyDecisiveGermanpinscher', 'info_dict': { @@ -44,6 +44,9 @@ class GfycatIE(InfoExtractor): 'categories': list, 'age_limit': 0, } + }, { + 'url': 'https://gfycat.com/ru/RemarkableDrearyAmurstarfish', + 'only_matching': True }, { 'url': 'https://gfycat.com/gifs/detail/UnconsciousLankyIvorygull', 'only_matching': True diff --git a/youtube_dl/extractor/kaltura.py b/youtube_dl/extractor/kaltura.py index 639d73837..0a733424c 100644 --- a/youtube_dl/extractor/kaltura.py +++ b/youtube_dl/extractor/kaltura.py @@ -103,6 +103,11 @@ class KalturaIE(InfoExtractor): { 'url': 'https://www.kaltura.com:443/index.php/extwidget/preview/partner_id/1770401/uiconf_id/37307382/entry_id/0_58u8kme7/embed/iframe?&flashvars[streamerType]=auto', 'only_matching': True, + }, + { + # unavailable source format + 'url': 'kaltura:513551:1_66x4rg7o', + 'only_matching': True, } ] @@ -306,12 +311,17 @@ class KalturaIE(InfoExtractor): f['fileExt'] = 'mp4' video_url = sign_url( '%s/flavorId/%s' % (data_url, f['id'])) + format_id = '%(fileExt)s-%(bitrate)s' % f + # Source format may not be available (e.g. kaltura:513551:1_66x4rg7o) + if f.get('isOriginal') is True and not self._is_valid_url( + video_url, entry_id, format_id): + continue # audio-only has no videoCodecId (e.g. kaltura:1926081:0_c03e1b5g # -f mp4-56) vcodec = 'none' if 'videoCodecId' not in f and f.get( 'frameRate') == 0 else f.get('videoCodecId') formats.append({ - 'format_id': '%(fileExt)s-%(bitrate)s' % f, + 'format_id': format_id, 'ext': f.get('fileExt'), 'tbr': int_or_none(f['bitrate']), 'fps': int_or_none(f.get('frameRate')), diff --git a/youtube_dl/extractor/leeco.py b/youtube_dl/extractor/leeco.py index 8dd1ce0d0..7dc0ad794 100644 --- a/youtube_dl/extractor/leeco.py +++ b/youtube_dl/extractor/leeco.py @@ -326,7 +326,7 @@ class LetvCloudIE(InfoExtractor): elif play_json.get('code'): raise ExtractorError('Letv cloud returned error %d' % play_json['code'], expected=True) else: - raise ExtractorError('Letv cloud returned an unknwon error') + raise ExtractorError('Letv cloud returned an unknown error') def b64decode(s): return compat_b64decode(s).decode('utf-8') diff --git a/youtube_dl/extractor/livejournal.py b/youtube_dl/extractor/livejournal.py new file mode 100644 index 000000000..3a9f4553f --- /dev/null +++ b/youtube_dl/extractor/livejournal.py @@ -0,0 +1,42 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import int_or_none + + +class LiveJournalIE(InfoExtractor): + _VALID_URL = r'https?://(?:[^.]+\.)?livejournal\.com/video/album/\d+.+?\bid=(?P\d+)' + _TEST = { + 'url': 'https://andrei-bt.livejournal.com/video/album/407/?mode=view&id=51272', + 'md5': 'adaf018388572ced8a6f301ace49d4b2', + 'info_dict': { + 'id': '1263729', + 'ext': 'mp4', + 'title': 'Истребители против БПЛА', + 'upload_date': '20190624', + 'timestamp': 1561406715, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + record = self._parse_json(self._search_regex( + r'Site\.page\s*=\s*({.+?});', webpage, + 'page data'), video_id)['video']['record'] + storage_id = compat_str(record['storageid']) + title = record.get('name') + if title: + # remove filename extension(.mp4, .mov, etc...) + title = title.rsplit('.', 1)[0] + return { + '_type': 'url_transparent', + 'id': video_id, + 'title': title, + 'thumbnail': record.get('thumbnail'), + 'timestamp': int_or_none(record.get('timecreate')), + 'url': 'eagleplatform:vc.videos.livejournal.com:' + storage_id, + 'ie_key': 'EaglePlatform', + } diff --git a/youtube_dl/extractor/lynda.py b/youtube_dl/extractor/lynda.py index 3084c6dff..b3d8653d0 100644 --- a/youtube_dl/extractor/lynda.py +++ b/youtube_dl/extractor/lynda.py @@ -117,6 +117,10 @@ class LyndaIE(LyndaBaseIE): }, { 'url': 'https://www.lynda.com/de/Graphic-Design-tutorials/Willkommen-Grundlagen-guten-Gestaltung/393570/393572-4.html', 'only_matching': True, + }, { + # Status="NotFound", Message="Transcript not found" + 'url': 'https://www.lynda.com/ASP-NET-tutorials/What-you-should-know/5034180/2811512-4.html', + 'only_matching': True, }] def _raise_unavailable(self, video_id): @@ -247,12 +251,17 @@ class LyndaIE(LyndaBaseIE): def _get_subtitles(self, video_id): url = 'https://www.lynda.com/ajax/player?videoId=%s&type=transcript' % video_id - subs = self._download_json(url, None, False) + subs = self._download_webpage( + url, video_id, 'Downloading subtitles JSON', fatal=False) + if not subs or 'Status="NotFound"' in subs: + return {} + subs = self._parse_json(subs, video_id, fatal=False) + if not subs: + return {} fixed_subs = self._fix_subtitles(subs) if fixed_subs: return {'en': [{'ext': 'srt', 'data': fixed_subs}]} - else: - return {} + return {} class LyndaCourseIE(LyndaBaseIE): diff --git a/youtube_dl/extractor/mgtv.py b/youtube_dl/extractor/mgtv.py index 84137df50..7ae2e3c3b 100644 --- a/youtube_dl/extractor/mgtv.py +++ b/youtube_dl/extractor/mgtv.py @@ -79,6 +79,9 @@ class MGTVIE(InfoExtractor): 'ext': 'mp4', 'tbr': tbr, 'protocol': 'm3u8_native', + 'http_headers': { + 'Referer': url, + }, }) self._sort_formats(formats) diff --git a/youtube_dl/extractor/porn91.py b/youtube_dl/extractor/porn91.py index 24c3600fe..20eac647a 100644 --- a/youtube_dl/extractor/porn91.py +++ b/youtube_dl/extractor/porn91.py @@ -39,7 +39,12 @@ class Porn91IE(InfoExtractor): r'
([^<]+)
', webpage, 'title') title = title.replace('\n', '') - info_dict = self._parse_html5_media_entries(url, webpage, video_id)[0] + video_link_url = self._search_regex( + r']+id=["\']fm-video_link[^>]+>([^<]+)', + webpage, 'video link') + videopage = self._download_webpage(video_link_url, video_id) + + info_dict = self._parse_html5_media_entries(url, videopage, video_id)[0] duration = parse_duration(self._search_regex( r'时长:\s*\s*(\d+:\d+)', webpage, 'duration', fatal=False)) diff --git a/youtube_dl/extractor/roosterteeth.py b/youtube_dl/extractor/roosterteeth.py index 857434540..d3eeeba62 100644 --- a/youtube_dl/extractor/roosterteeth.py +++ b/youtube_dl/extractor/roosterteeth.py @@ -4,11 +4,14 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import ( + compat_HTTPError, + compat_str, +) from ..utils import ( ExtractorError, int_or_none, - strip_or_none, - unescapeHTML, + str_or_none, urlencode_postdata, ) @@ -21,15 +24,14 @@ class RoosterTeethIE(InfoExtractor): 'url': 'http://roosterteeth.com/episode/million-dollars-but-season-2-million-dollars-but-the-game-announcement', 'md5': 'e2bd7764732d785ef797700a2489f212', 'info_dict': { - 'id': '26576', + 'id': '9156', 'display_id': 'million-dollars-but-season-2-million-dollars-but-the-game-announcement', 'ext': 'mp4', - 'title': 'Million Dollars, But...: Million Dollars, But... The Game Announcement', - 'description': 'md5:0cc3b21986d54ed815f5faeccd9a9ca5', + 'title': 'Million Dollars, But... The Game Announcement', + 'description': 'md5:168a54b40e228e79f4ddb141e89fe4f5', 'thumbnail': r're:^https?://.*\.png$', 'series': 'Million Dollars, But...', 'episode': 'Million Dollars, But... The Game Announcement', - 'comment_count': int, }, }, { 'url': 'http://achievementhunter.roosterteeth.com/episode/off-topic-the-achievement-hunter-podcast-2016-i-didn-t-think-it-would-pass-31', @@ -89,60 +91,55 @@ class RoosterTeethIE(InfoExtractor): 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 - webpage = self._download_webpage(url, display_id) - - episode = strip_or_none(unescapeHTML(self._search_regex( - (r'videoTitle\s*=\s*(["\'])(?P(?:(?!\1).)+)\1', - r'<title>(?P<title>[^<]+)'), webpage, 'title', - default=None, group='title'))) - - title = strip_or_none(self._og_search_title( - webpage, default=None)) or episode - - m3u8_url = self._search_regex( - r'file\s*:\s*(["\'])(?Phttp.+?\.m3u8.*?)\1', - webpage, 'm3u8 url', default=None, group='url') - - if not m3u8_url: - if re.search(r']+class=["\']non-sponsor', webpage): - self.raise_login_required( - '%s is only available for FIRST members' % display_id) - - if re.search(r']+class=["\']golive-gate', webpage): - self.raise_login_required('%s is not available yet' % display_id) - - raise ExtractorError('Unable to extract m3u8 URL') + try: + m3u8_url = self._download_json( + api_episode_url + '/videos', display_id, + 'Downloading video JSON metadata')['data'][0]['attributes']['url'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + if self._parse_json(e.cause.read().decode(), display_id).get('access') is False: + self.raise_login_required( + '%s is only available for FIRST members' % display_id) + raise formats = self._extract_m3u8_formats( - m3u8_url, display_id, ext='mp4', - entry_protocol='m3u8_native', m3u8_id='hls') + m3u8_url, display_id, 'mp4', 'm3u8_native', m3u8_id='hls') self._sort_formats(formats) - description = strip_or_none(self._og_search_description(webpage)) - thumbnail = self._proto_relative_url(self._og_search_thumbnail(webpage)) + episode = self._download_json( + api_episode_url, display_id, + 'Downloading episode JSON metadata')['data'][0] + attributes = episode['attributes'] + title = attributes.get('title') or attributes['display_title'] + video_id = compat_str(episode['id']) - series = self._search_regex( - (r'

More ([^<]+)

', r']+>See All ([^<]+) Videos<'), - webpage, 'series', fatal=False) - - comment_count = int_or_none(self._search_regex( - r'>Comments \((\d+)\)<', webpage, - 'comment count', fatal=False)) - - video_id = self._search_regex( - (r'containerId\s*=\s*["\']episode-(\d+)\1', - r'[0-9a-zA-Z]+)' - - _TEST = { - 'url': 'http://rudo.video/vod/oTzw0MGnyG', - 'md5': '2a03a5b32dd90a04c83b6d391cf7b415', - 'info_dict': { - 'id': 'oTzw0MGnyG', - 'ext': 'mp4', - 'title': 'Comentario Tomás Mosciatti', - 'upload_date': '20160617', - }, - } - - @classmethod - def _extract_url(cls, webpage): - mobj = re.search( - r']+src=(?P[\'"])(?P(?:https?:)?//rudo\.video/vod/[0-9a-zA-Z]+)(?P=q1)', - webpage) - if mobj: - return mobj.group('url') - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id, encoding='iso-8859-1') - - jwplayer_data = self._parse_json(self._search_regex( - r'(?s)playerInstance\.setup\(({.+?})\)', webpage, 'jwplayer data'), video_id, - transform_source=lambda s: js_to_json(re.sub(r'encodeURI\([^)]+\)', '""', s))) - - info_dict = self._parse_jwplayer_data( - jwplayer_data, video_id, require_title=False, m3u8_id='hls', mpd_id='dash') - - info_dict.update({ - 'title': self._og_search_title(webpage), - 'upload_date': unified_strdate(get_element_by_class('date', webpage)), - }) - - return info_dict diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 3a8626e02..05538f3d6 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -197,7 +197,7 @@ class SoundcloudIE(InfoExtractor): 'skip_download': True, }, }, - # not avaialble via api.soundcloud.com/i1/tracks/id/streams + # not available via api.soundcloud.com/i1/tracks/id/streams { 'url': 'https://soundcloud.com/giovannisarani/mezzo-valzer', 'md5': 'e22aecd2bc88e0e4e432d7dcc0a1abf7', diff --git a/youtube_dl/extractor/spankbang.py b/youtube_dl/extractor/spankbang.py index f11d728ca..e040ada29 100644 --- a/youtube_dl/extractor/spankbang.py +++ b/youtube_dl/extractor/spankbang.py @@ -5,6 +5,7 @@ import re from .common import InfoExtractor from ..utils import ( ExtractorError, + merge_dicts, orderedSet, parse_duration, parse_resolution, @@ -26,6 +27,8 @@ class SpankBangIE(InfoExtractor): 'description': 'dillion harper masturbates on a bed', 'thumbnail': r're:^https?://.*\.jpg$', 'uploader': 'silly2587', + 'timestamp': 1422571989, + 'upload_date': '20150129', 'age_limit': 18, } }, { @@ -106,31 +109,36 @@ class SpankBangIE(InfoExtractor): for format_id, format_url in stream.items(): if format_id.startswith(STREAM_URL_PREFIX): + if format_url and isinstance(format_url, list): + format_url = format_url[0] extract_format( format_id[len(STREAM_URL_PREFIX):], format_url) self._sort_formats(formats) + info = self._search_json_ld(webpage, video_id, default={}) + title = self._html_search_regex( - r'(?s)]*>(.+?)', webpage, 'title') + r'(?s)]*>(.+?)', webpage, 'title', default=None) description = self._search_regex( r']+\bclass=["\']bottom[^>]+>\s*

[^<]*

\s*

([^<]+)', - webpage, 'description', fatal=False) - thumbnail = self._og_search_thumbnail(webpage) - uploader = self._search_regex( - r'class="user"[^>]*>]+>([^<]+)', + webpage, 'description', default=None) + thumbnail = self._og_search_thumbnail(webpage, default=None) + uploader = self._html_search_regex( + (r'(?s)]+class=["\']profile[^>]+>(.+?)', + r'class="user"[^>]*>]+>([^<]+)'), webpage, 'uploader', default=None) duration = parse_duration(self._search_regex( r']+\bclass=["\']right_side[^>]+>\s*([^<]+)', - webpage, 'duration', fatal=False)) + webpage, 'duration', default=None)) view_count = str_to_int(self._search_regex( - r'([\d,.]+)\s+plays', webpage, 'view count', fatal=False)) + r'([\d,.]+)\s+plays', webpage, 'view count', default=None)) age_limit = self._rta_search(webpage) - return { + return merge_dicts({ 'id': video_id, - 'title': title, + 'title': title or video_id, 'description': description, 'thumbnail': thumbnail, 'uploader': uploader, @@ -138,7 +146,8 @@ class SpankBangIE(InfoExtractor): 'view_count': view_count, 'formats': formats, 'age_limit': age_limit, - } + }, info + ) class SpankBangPlaylistIE(InfoExtractor): diff --git a/youtube_dl/extractor/spike.py b/youtube_dl/extractor/spike.py index 21b93a5b3..7c11ea7aa 100644 --- a/youtube_dl/extractor/spike.py +++ b/youtube_dl/extractor/spike.py @@ -22,7 +22,7 @@ class BellatorIE(MTVServicesInfoExtractor): 'only_matching': True, }] - _FEED_URL = 'http://www.spike.com/feeds/mrss/' + _FEED_URL = 'http://www.bellator.com/feeds/mrss/' _GEO_COUNTRIES = ['US'] diff --git a/youtube_dl/extractor/twitter.py b/youtube_dl/extractor/twitter.py index 41d0b6be8..cebb6238c 100644 --- a/youtube_dl/extractor/twitter.py +++ b/youtube_dl/extractor/twitter.py @@ -428,11 +428,22 @@ class TwitterIE(InfoExtractor): 'params': { 'skip_download': True, # requires ffmpeg }, + }, { + 'url': 'https://twitter.com/foobar/status/1087791357756956680', + 'info_dict': { + 'id': '1087791357756956680', + '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', + 'uploader': 'Twitter', + 'uploader_id': 'Twitter', + 'duration': 61.567, + }, }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - user_id = mobj.group('user_id') twid = mobj.group('id') webpage, urlh = self._download_webpage_handle( @@ -441,8 +452,13 @@ class TwitterIE(InfoExtractor): if 'twitter.com/account/suspended' in urlh.geturl(): raise ExtractorError('Account suspended by Twitter.', expected=True) - if user_id is None: - mobj = re.match(self._VALID_URL, urlh.geturl()) + 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') diff --git a/youtube_dl/extractor/voxmedia.py b/youtube_dl/extractor/voxmedia.py index c7a0a88fe..b318e15d4 100644 --- a/youtube_dl/extractor/voxmedia.py +++ b/youtube_dl/extractor/voxmedia.py @@ -4,7 +4,10 @@ from __future__ import unicode_literals from .common import InfoExtractor from .once import OnceIE from ..compat import compat_urllib_parse_unquote -from ..utils import ExtractorError +from ..utils import ( + ExtractorError, + int_or_none, +) class VoxMediaVolumeIE(OnceIE): @@ -13,18 +16,43 @@ class VoxMediaVolumeIE(OnceIE): 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'Volume\.createVideo\(({.+})\s*,\s*{.*}\s*,\s*\[.*\]\s*,\s*{.*}\);', webpage, 'video data'), video_id) + + setup = self._parse_json(self._search_regex( + r'setup\s*=\s*({.+});', webpage, 'setup'), video_id) + video_data = setup.get('video') or {} + info = { + 'id': video_id, + 'title': video_data.get('title_short'), + 'description': video_data.get('description_long') or video_data.get('description_short'), + 'thumbnail': video_data.get('brightcove_thumbnail') + } + asset = setup.get('asset') or setup.get('params') or {} + + formats = [] + hls_url = asset.get('hls_url') + if hls_url: + formats.extend(self._extract_m3u8_formats( + hls_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) + mp4_url = asset.get('mp4_url') + if mp4_url: + tbr = self._search_regex(r'-(\d+)k\.', mp4_url, 'bitrate', default=None) + format_id = 'http' + if tbr: + format_id += '-' + tbr + formats.append({ + 'format_id': format_id, + 'url': mp4_url, + 'tbr': int_or_none(tbr), + }) + if formats: + self._sort_formats(formats) + info['formats'] = formats + return info + for provider_video_type in ('ooyala', 'youtube', 'brightcove'): provider_video_id = video_data.get('%s_id' % provider_video_type) if not provider_video_id: continue - info = { - 'id': video_id, - 'title': video_data.get('title_short'), - 'description': video_data.get('description_long') or video_data.get('description_short'), - 'thumbnail': video_data.get('brightcove_thumbnail') - } if provider_video_type == 'brightcove': info['formats'] = self._extract_once_formats(provider_video_id) self._sort_formats(info['formats']) @@ -39,46 +67,49 @@ class VoxMediaVolumeIE(OnceIE): class VoxMediaIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?:(?:theverge|vox|sbnation|eater|polygon|curbed|racked)\.com|recode\.net)/(?:[^/]+/)*(?P[^/?]+)' + _VALID_URL = r'https?://(?:www\.)?(?:(?:theverge|vox|sbnation|eater|polygon|curbed|racked|funnyordie)\.com|recode\.net)/(?:[^/]+/)*(?P[^/?]+)' _TESTS = [{ + # Volume embed, Youtube 'url': 'http://www.theverge.com/2014/6/27/5849272/material-world-how-google-discovered-what-software-is-made-of', 'info_dict': { - 'id': '11eXZobjrG8DCSTgrNjVinU-YmmdYjhe', + 'id': 'j4mLW6x17VM', 'ext': 'mp4', - 'title': 'Google\'s new material design direction', - 'description': 'md5:2f44f74c4d14a1f800ea73e1c6832ad2', + 'title': 'Material world: how Google discovered what software is made of', + 'description': 'md5:dfc17e7715e3b542d66e33a109861382', + 'upload_date': '20190710', + 'uploader_id': 'TheVerge', + 'uploader': 'The Verge', }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - 'add_ie': ['Ooyala'], + 'add_ie': ['Youtube'], }, { - # data-ooyala-id + # Volume embed, Youtube 'url': 'http://www.theverge.com/2014/10/21/7025853/google-nexus-6-hands-on-photos-video-android-phablet', - 'md5': 'd744484ff127884cd2ba09e3fa604e4b', + 'md5': '4c8f4a0937752b437c3ebc0ed24802b5', 'info_dict': { - 'id': 'RkZXU4cTphOCPDMZg5oEounJyoFI0g-B', + 'id': 'Gy8Md3Eky38', 'ext': 'mp4', 'title': 'The Nexus 6: hands-on with Google\'s phablet', - 'description': 'md5:87a51fe95ff8cea8b5bdb9ac7ae6a6af', + 'description': 'md5:d9f0216e5fb932dd2033d6db37ac3f1d', + 'uploader_id': 'TheVerge', + 'upload_date': '20141021', + 'uploader': 'The Verge', }, - 'add_ie': ['Ooyala'], - 'skip': 'Video Not Found', + 'add_ie': ['Youtube'], + 'skip': 'similar to the previous test', }, { - # volume embed + # Volume embed, Youtube 'url': 'http://www.vox.com/2016/3/31/11336640/mississippi-lgbt-religious-freedom-bill', 'info_dict': { - 'id': 'wydzk3dDpmRz7PQoXRsTIX6XTkPjYL0b', + 'id': 'YCjDnX-Xzhg', 'ext': 'mp4', - 'title': 'The new frontier of LGBTQ civil rights, explained', - 'description': 'md5:0dc58e94a465cbe91d02950f770eb93f', + 'title': "Mississippi's laws are so bad that its anti-LGBTQ law isn't needed to allow discrimination", + 'description': 'md5:fc1317922057de31cd74bce91eb1c66c', + 'uploader_id': 'voxdotcom', + 'upload_date': '20150915', + 'uploader': 'Vox', }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - 'add_ie': ['Ooyala'], + 'add_ie': ['Youtube'], + 'skip': 'similar to the previous test', }, { # youtube embed 'url': 'http://www.vox.com/2016/3/24/11291692/robot-dance', @@ -93,6 +124,7 @@ class VoxMediaIE(InfoExtractor): 'uploader': 'Vox', }, 'add_ie': ['Youtube'], + 'skip': 'Page no longer contain videos', }, { # SBN.VideoLinkset.entryGroup multiple ooyala embeds 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok', @@ -118,10 +150,11 @@ class VoxMediaIE(InfoExtractor): 'description': 'md5:e02d56b026d51aa32c010676765a690d', }, }], + 'skip': 'Page no longer contain videos', }, { # volume embed, Brightcove Once 'url': 'https://www.recode.net/2014/6/17/11628066/post-post-pc-ceo-the-full-code-conference-video-of-microsofts-satya', - 'md5': '01571a896281f77dc06e084138987ea2', + 'md5': '2dbc77b8b0bff1894c2fce16eded637d', 'info_dict': { 'id': '1231c973d', 'ext': 'mp4', diff --git a/youtube_dl/extractor/vrv.py b/youtube_dl/extractor/vrv.py index c814a8a4a..6e51469b0 100644 --- a/youtube_dl/extractor/vrv.py +++ b/youtube_dl/extractor/vrv.py @@ -64,7 +64,15 @@ class VRVBaseIE(InfoExtractor): def _call_cms(self, path, video_id, note): if not self._CMS_SIGNING: - self._CMS_SIGNING = self._call_api('index', video_id, 'CMS Signing')['cms_signing'] + index = self._call_api('index', video_id, 'CMS Signing') + self._CMS_SIGNING = index.get('cms_signing') or {} + if not self._CMS_SIGNING: + for signing_policy in index.get('signing_policies', []): + signing_path = signing_policy.get('path') + if signing_path and signing_path.startswith('/cms/'): + name, value = signing_policy.get('name'), signing_policy.get('value') + if name and value: + self._CMS_SIGNING[name] = value return self._download_json( self._API_DOMAIN + path, video_id, query=self._CMS_SIGNING, note='Downloading %s JSON metadata' % note, headers=self.geo_verification_headers()) diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index a3b5f00c8..e5ebdd180 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -1,12 +1,14 @@ # coding: utf-8 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, ) @@ -18,7 +20,9 @@ from ..utils import ( int_or_none, mimetype2ext, smuggle_url, + try_get, unescapeHTML, + url_or_none, ) from .brightcove import ( @@ -556,3 +560,130 @@ class YahooGyaOIE(InfoExtractor): 'https://gyao.yahoo.co.jp/player/%s/' % video_id.replace(':', '/'), YahooGyaOPlayerIE.ie_key(), video_id)) return self.playlist_result(entries, program_id) + + +class YahooJapanNewsIE(InfoExtractor): + IE_NAME = 'yahoo:japannews' + IE_DESC = 'Yahoo! Japan News' + _VALID_URL = r'https?://(?P(?:news|headlines)\.yahoo\.co\.jp)[^\d]*(?P\d[\d-]*\d)?' + _GEO_COUNTRIES = ['JP'] + _TESTS = [{ + 'url': 'https://headlines.yahoo.co.jp/videonews/ann?a=20190716-00000071-ann-int', + 'info_dict': { + 'id': '1736242', + 'ext': 'mp4', + 'title': 'ムン大統領が対日批判を強化“現金化”効果は？（テレビ朝日系（ANN）） - Yahoo!ニュース', + 'description': '韓国の元徴用工らを巡る裁判の原告が弁護士が差し押さえた三菱重工業の資産を売却して - Yahoo!ニュース(テレビ朝日系（ANN）)', + 'thumbnail': r're:^https?://.*\.[a-zA-Z\d]{3,4}$', + }, + 'params': { + 'skip_download': True, + }, + }, { + # geo restricted + 'url': 'https://headlines.yahoo.co.jp/hl?a=20190721-00000001-oxv-l04', + 'only_matching': True, + }, { + 'url': 'https://headlines.yahoo.co.jp/videonews/', + 'only_matching': True, + }, { + 'url': 'https://news.yahoo.co.jp', + 'only_matching': True, + }, { + 'url': 'https://news.yahoo.co.jp/byline/hashimotojunji/20190628-00131977/', + 'only_matching': True, + }, { + 'url': 'https://news.yahoo.co.jp/feature/1356', + 'only_matching': True + }] + + def _extract_formats(self, json_data, content_id): + formats = [] + + video_data = try_get( + json_data, + lambda x: x['ResultSet']['Result'][0]['VideoUrlSet']['VideoUrl'], + list) + for vid in video_data or []: + delivery = vid.get('delivery') + url = url_or_none(vid.get('Url')) + if not delivery or not url: + continue + elif delivery == 'hls': + formats.extend( + self._extract_m3u8_formats( + url, content_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) + else: + formats.append({ + 'url': url, + 'format_id': 'http-%s' % compat_str(vid.get('bitrate', '')), + 'height': int_or_none(vid.get('height')), + 'width': int_or_none(vid.get('width')), + 'tbr': int_or_none(vid.get('bitrate')), + }) + self._remove_duplicate_formats(formats) + self._sort_formats(formats) + + return formats + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + host = mobj.group('host') + display_id = mobj.group('id') or host + + webpage = self._download_webpage(url, display_id) + + title = self._html_search_meta( + ['og:title', 'twitter:title'], webpage, 'title', default=None + ) or self._html_search_regex('([^<]+)', webpage, 'title') + + if display_id == host: + # Headline page (w/ multiple BC playlists) ('news.yahoo.co.jp', 'headlines.yahoo.co.jp/videonews/', ...) + stream_plists = re.findall(r'plist=(\d+)', webpage) or re.findall(r'plist["\']:\s*["\']([^"\']+)', webpage) + entries = [ + self.url_result( + smuggle_url( + 'http://players.brightcove.net/5690807595001/HyZNerRl7_default/index.html?playlistId=%s' % plist_id, + {'geo_countries': ['JP']}), + ie='BrightcoveNew', video_id=plist_id) + for plist_id in stream_plists] + return self.playlist_result(entries, playlist_title=title) + + # Article page + description = self._html_search_meta( + ['og:description', 'description', 'twitter:description'], + webpage, 'description', default=None) + thumbnail = self._og_search_thumbnail( + webpage, default=None) or self._html_search_meta( + 'twitter:image', webpage, 'thumbnail', default=None) + space_id = self._search_regex([ + r']+class=["\']yvpub-player["\'][^>]+spaceid=([^&"\']+)', + r'YAHOO\.JP\.srch\.\w+link\.onLoad[^;]+spaceID["\' ]*:["\' ]+([^"\']+)', + r'