From 311ee457314359662c975cd29f2ee58ad068db49 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 14 Oct 2019 18:36:25 +0100 Subject: [PATCH 01/65] [nbc] switch to graphql api(closes #18581)(closes #22693)(closes #22701) --- youtube_dl/extractor/nbc.py | 39 ++++++++++++++++++++++++------------- 1 file changed, 26 insertions(+), 13 deletions(-) diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py index 3282f84ee..10680b202 100644 --- a/youtube_dl/extractor/nbc.py +++ b/youtube_dl/extractor/nbc.py @@ -10,7 +10,6 @@ from .adobepass import AdobePassIE from ..compat import compat_urllib_parse_unquote from ..utils import ( smuggle_url, - try_get, update_url_query, int_or_none, ) @@ -85,27 +84,41 @@ class NBCIE(AdobePassIE): permalink, video_id = re.match(self._VALID_URL, url).groups() permalink = 'http' + compat_urllib_parse_unquote(permalink) response = self._download_json( - 'https://api.nbc.com/v3/videos', video_id, query={ - 'filter[permalink]': permalink, - 'fields[videos]': 'description,entitlement,episodeNumber,guid,keywords,seasonNumber,title,vChipRating', - 'fields[shows]': 'shortTitle', - 'include': 'show.shortTitle', + 'https://friendship.nbc.co/v2/graphql', video_id, query={ + 'query': '''{ + page(name: "%s", platform: web, type: VIDEO, userId: "0") { + data { + ... on VideoPageData { + description + episodeNumber + keywords + locked + mpxAccountId + mpxGuid + rating + seasonNumber + secondaryTitle + seriesShortTitle + } + } + } +}''' % permalink, }) - video_data = response['data'][0]['attributes'] + video_data = response['data']['page']['data'] query = { 'mbr': 'true', 'manifest': 'm3u', } - video_id = video_data['guid'] - title = video_data['title'] - if video_data.get('entitlement') == 'auth': + video_id = video_data['mpxGuid'] + title = video_data['secondaryTitle'] + if video_data.get('locked'): resource = self._get_mvpd_resource( 'nbcentertainment', title, video_id, - video_data.get('vChipRating')) + video_data.get('rating')) query['auth'] = self._extract_mvpd_auth( url, video_id, 'nbcentertainment', resource) theplatform_url = smuggle_url(update_url_query( - 'http://link.theplatform.com/s/NnzsPC/media/guid/2410887629/' + video_id, + 'http://link.theplatform.com/s/NnzsPC/media/guid/%s/%s' % (video_data.get('mpxAccountId') or '2410887629', video_id), query), {'force_smil_url': True}) return { '_type': 'url_transparent', @@ -117,7 +130,7 @@ class NBCIE(AdobePassIE): 'season_number': int_or_none(video_data.get('seasonNumber')), 'episode_number': int_or_none(video_data.get('episodeNumber')), 'episode': title, - 'series': try_get(response, lambda x: x['included'][0]['attributes']['shortTitle']), + 'series': video_data.get('seriesShortTitle'), 'ie_key': 'ThePlatform', } From a1ee23e98fe2ec80b8726829927fcae1267e76b1 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 14 Oct 2019 18:37:35 +0100 Subject: [PATCH 02/65] [vimeo] fix VHX embed extraction --- youtube_dl/extractor/vimeo.py | 97 ++++------------------------------- 1 file changed, 9 insertions(+), 88 deletions(-) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index ddf375c6c..5dc38e243 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -23,7 +23,6 @@ from ..utils import ( NO_DEFAULT, OnDemandPagedList, parse_filesize, - qualities, RegexNotFoundError, sanitized_Request, smuggle_url, @@ -211,6 +210,7 @@ class VimeoBaseInfoExtractor(InfoExtractor): video_uploader_url = owner.get('url') return { + 'id': video_id, 'title': self._live_title(video_title) if is_live else video_title, 'uploader': owner.get('name'), 'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None, @@ -730,7 +730,6 @@ class VimeoIE(VimeoBaseInfoExtractor): channel_url = 'https://vimeo.com/channels/%s' % channel_id if channel_id else None info_dict = { - 'id': video_id, 'formats': formats, 'timestamp': unified_timestamp(timestamp), 'description': video_description, @@ -1061,7 +1060,6 @@ class VimeoReviewIE(VimeoBaseInfoExtractor): if source_format: info_dict['formats'].append(source_format) self._vimeo_sort_formats(info_dict['formats']) - info_dict['id'] = video_id return info_dict @@ -1115,94 +1113,17 @@ class VimeoLikesIE(VimeoChannelIE): return self._extract_videos(user_id, 'https://vimeo.com/%s/likes' % user_id) -class VHXEmbedIE(InfoExtractor): +class VHXEmbedIE(VimeoBaseInfoExtractor): IE_NAME = 'vhx:embed' _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P\d+)' - def _call_api(self, video_id, access_token, path='', query=None): - return self._download_json( - 'https://api.vhx.tv/videos/' + video_id + path, video_id, headers={ - 'Authorization': 'Bearer ' + access_token, - }, query=query) - def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - credentials = self._parse_json(self._search_regex( - r'(?s)credentials\s*:\s*({.+?}),', webpage, - 'config'), video_id, js_to_json) - access_token = credentials['access_token'] - - query = {} - for k, v in credentials.items(): - if k in ('authorization', 'authUserToken', 'ticket') and v and v != 'undefined': - if k == 'authUserToken': - query['auth_user_token'] = v - else: - query[k] = v - files = self._call_api(video_id, access_token, '/files', query) - - formats = [] - for f in files: - href = try_get(f, lambda x: x['_links']['source']['href']) - if not href: - continue - method = f.get('method') - if method == 'hls': - formats.extend(self._extract_m3u8_formats( - href, video_id, 'mp4', 'm3u8_native', - m3u8_id='hls', fatal=False)) - elif method == 'dash': - formats.extend(self._extract_mpd_formats( - href, video_id, mpd_id='dash', fatal=False)) - else: - fmt = { - 'filesize': int_or_none(try_get(f, lambda x: x['size']['bytes'])), - 'format_id': 'http', - 'preference': 1, - 'url': href, - 'vcodec': f.get('codec'), - } - quality = f.get('quality') - if quality: - fmt.update({ - 'format_id': 'http-' + quality, - 'height': int_or_none(self._search_regex(r'(\d+)p', quality, 'height', default=None)), - }) - formats.append(fmt) - self._sort_formats(formats) - - video_data = self._call_api(video_id, access_token) - title = video_data.get('title') or video_data['name'] - - subtitles = {} - for subtitle in try_get(video_data, lambda x: x['tracks']['subtitles'], list) or []: - lang = subtitle.get('srclang') or subtitle.get('label') - for _link in subtitle.get('_links', {}).values(): - href = _link.get('href') - if not href: - continue - subtitles.setdefault(lang, []).append({ - 'url': href, - }) - - q = qualities(['small', 'medium', 'large', 'source']) - thumbnails = [] - for thumbnail_id, thumbnail_url in video_data.get('thumbnail', {}).items(): - thumbnails.append({ - 'id': thumbnail_id, - 'url': thumbnail_url, - 'preference': q(thumbnail_id), - }) - - return { - 'id': video_id, - 'title': title, - 'description': video_data.get('description'), - 'duration': int_or_none(try_get(video_data, lambda x: x['duration']['seconds'])), - 'formats': formats, - 'subtitles': subtitles, - 'thumbnails': thumbnails, - 'timestamp': unified_timestamp(video_data.get('created_at')), - 'view_count': int_or_none(video_data.get('plays_count')), - } + config_url = self._parse_json(self._search_regex( + r'window\.OTTData\s*=\s*({.+})', webpage, + 'ott data'), video_id, js_to_json)['config_url'] + config = self._download_json(config_url, video_id) + info = self._parse_config(config, video_id) + self._vimeo_sort_formats(info['formats']) + return info From 7e05df71b7d8c0e1ea9beafff48275ef3c9e27d2 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Tue, 15 Oct 2019 00:10:22 +0100 Subject: [PATCH 03/65] [nexx] handle result list(closes #22666) --- youtube_dl/extractor/nexx.py | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/nexx.py b/youtube_dl/extractor/nexx.py index 82d526c22..f9aad83c4 100644 --- a/youtube_dl/extractor/nexx.py +++ b/youtube_dl/extractor/nexx.py @@ -295,13 +295,23 @@ class NexxIE(InfoExtractor): video = None + def find_video(result): + if isinstance(result, dict): + return result + elif isinstance(result, list): + vid = int(video_id) + for v in result: + if try_get(v, lambda x: x['general']['ID'], int) == vid: + return v + return None + response = self._download_json( 'https://arc.nexx.cloud/api/video/%s.json' % video_id, video_id, fatal=False) if response and isinstance(response, dict): result = response.get('result') - if result and isinstance(result, dict): - video = result + if result: + video = find_video(result) # not all videos work via arc, e.g. nexx:741:1269984 if not video: @@ -348,7 +358,7 @@ class NexxIE(InfoExtractor): request_token = hashlib.md5( ''.join((op, domain_id, secret)).encode('utf-8')).hexdigest() - video = self._call_api( + result = self._call_api( domain_id, 'videos/%s/%s' % (op, video_id), video_id, data={ 'additionalfields': 'language,channel,actors,studio,licenseby,slug,subtitle,teaser,description', 'addInteractionOptions': '1', @@ -363,6 +373,7 @@ class NexxIE(InfoExtractor): 'X-Request-CID': cid, 'X-Request-Token': request_token, }) + video = find_video(result) general = video['general'] title = general['title'] From 2af01c0293db53dc80c552df3986d0e088b65b76 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Tue, 15 Oct 2019 15:18:51 +0100 Subject: [PATCH 04/65] [bokecc] improve player params extraction(closes #22638) --- youtube_dl/extractor/bokecc.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/bokecc.py b/youtube_dl/extractor/bokecc.py index 86a7f4d7d..6017e8344 100644 --- a/youtube_dl/extractor/bokecc.py +++ b/youtube_dl/extractor/bokecc.py @@ -11,8 +11,8 @@ from ..utils import ExtractorError class BokeCCBaseIE(InfoExtractor): def _extract_bokecc_formats(self, webpage, video_id, format_id=None): player_params_str = self._html_search_regex( - r'<(?:script|embed)[^>]+src="http://p\.bokecc\.com/player\?([^"]+)', - webpage, 'player params') + r'<(?:script|embed)[^>]+src=(?P["\'])(?:https?:)?//p\.bokecc\.com/(?:player|flash/player\.swf)\?(?P.+?)(?P=q)', + webpage, 'player params', group='query') player_params = compat_parse_qs(player_params_str) @@ -36,9 +36,9 @@ class BokeCCIE(BokeCCBaseIE): _VALID_URL = r'https?://union\.bokecc\.com/playvideo\.bo\?(?P.*)' _TESTS = [{ - 'url': 'http://union.bokecc.com/playvideo.bo?vid=E44D40C15E65EA30&uid=CD0C5D3C8614B28B', + 'url': 'http://union.bokecc.com/playvideo.bo?vid=E0ABAE9D4F509B189C33DC5901307461&uid=FE644790DE9D154A', 'info_dict': { - 'id': 'CD0C5D3C8614B28B_E44D40C15E65EA30', + 'id': 'FE644790DE9D154A_E0ABAE9D4F509B189C33DC5901307461', 'ext': 'flv', 'title': 'BokeCC Video', }, From 30eb05cb41d95a73f7baff8da9ec1d6a50b08f50 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Tue, 15 Oct 2019 19:54:53 +0100 Subject: [PATCH 05/65] [globo] extract subtitles(closes #22713) --- youtube_dl/extractor/globo.py | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/globo.py b/youtube_dl/extractor/globo.py index b9c400a57..9ad1d95fb 100644 --- a/youtube_dl/extractor/globo.py +++ b/youtube_dl/extractor/globo.py @@ -102,10 +102,18 @@ class GloboIE(InfoExtractor): title = video['title'] formats = [] + subtitles = {} for resource in video['resources']: resource_id = resource.get('_id') resource_url = resource.get('url') - if not resource_id or not resource_url: + resource_type = resource.get('type') + if not resource_url or (resource_type == 'media' and not resource_id) or resource_type not in ('subtitle', 'media'): + continue + + if resource_type == 'subtitle': + subtitles.setdefault(resource.get('language') or 'por', []).append({ + 'url': resource_url, + }) continue security = self._download_json( @@ -165,7 +173,8 @@ class GloboIE(InfoExtractor): 'duration': duration, 'uploader': uploader, 'uploader_id': uploader_id, - 'formats': formats + 'formats': formats, + 'subtitles': subtitles, } From 974311b5aa1a53564a00915b9228af30e2a5b40d Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Tue, 15 Oct 2019 21:01:59 +0100 Subject: [PATCH 06/65] [vimeo] improve album videos id extraction(closes #22599) --- youtube_dl/extractor/vimeo.py | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 5dc38e243..9abd59d98 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -938,7 +938,7 @@ class VimeoAlbumIE(VimeoChannelIE): def _fetch_page(self, album_id, authorizaion, hashed_pass, page): api_page = page + 1 query = { - 'fields': 'link', + 'fields': 'link,uri', 'page': api_page, 'per_page': self._PAGE_SIZE, } @@ -953,7 +953,9 @@ class VimeoAlbumIE(VimeoChannelIE): link = video.get('link') if not link: continue - yield self.url_result(link, VimeoIE.ie_key(), VimeoIE._match_id(link)) + uri = video.get('uri') + video_id = self._search_regex(r'/videos/(\d+)', uri, 'video_id', default=None) if uri else None + yield self.url_result(link, VimeoIE.ie_key(), video_id) def _real_extract(self, url): album_id = self._match_id(url) From 173190f5e3946173daea0539cf0e749cb14acd12 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 16 Oct 2019 03:25:13 +0700 Subject: [PATCH 07/65] [ChangeLog] Actualize [ci skip] --- ChangeLog | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) diff --git a/ChangeLog b/ChangeLog index 80681a9ae..8a59398d9 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,39 @@ +version + +Core +* [extractor/common] Make _is_valid_url more relaxed + +Extractors +* [vimeo] Improve album videos id extraction (#22599) ++ [globo] Extract subtitles (#22713) +* [bokecc] Improve player params extraction (#22638) +* [nexx] Handle result list (#22666) +* [vimeo] Fix VHX embed extraction +* [nbc] Switch to graphql API (#18581, #22693, #22701) +- [vessel] Remove extractor +- [promptfile] Remove extractor (#6239) +* [kaltura] Fix service URL extraction (#22658) +* [kaltura] Fix embed info strip (#22658) +* [globo] Fix format extraction (#20319) +* [redtube] Improve metadata extraction (#22492, #22615) +* [pornhub:uservideos:upload] Fix extraction (#22619) ++ [telequebec:squat] Add support for squat.telequebec.tv (#18503) +- [wimp] Remove extractor (#22088, #22091) ++ [gfycat] Extend URL regular expression (#22225) ++ [chaturbate] Extend URL regular expression (#22309) +* [peertube] Update instances (#22414) ++ [telequebec] Add support for coucou.telequebec.tv (#22482) ++ [xvideos] Extend URL regular expression (#22471) +- [youtube] Remove support for invidious.enkirton.net (#22543) ++ [openload] Add support for oload.monster (#22592) +* [nrktv:seriebase] Fix extraction (#22596) ++ [youtube] Add support for yt.lelux.fi (#22597) +* [orf:tvthek] Make manifest requests non fatal (#22578) +* [teachable] Skip login when already logged in (#22572) +* [viewlift] Improve extraction (#22545) +* [nonktube] Fix extraction (#22544) + + version 2019.09.28 Core From 7815d6b74373feb90d969b5fcde7df11702fa5d0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 16 Oct 2019 03:26:47 +0700 Subject: [PATCH 08/65] release 2019.10.16 --- .github/ISSUE_TEMPLATE/1_broken_site.md | 6 +++--- .github/ISSUE_TEMPLATE/2_site_support_request.md | 4 ++-- .github/ISSUE_TEMPLATE/3_site_feature_request.md | 4 ++-- .github/ISSUE_TEMPLATE/4_bug_report.md | 6 +++--- .github/ISSUE_TEMPLATE/5_feature_request.md | 4 ++-- ChangeLog | 2 +- docs/supportedsites.md | 4 +--- youtube_dl/version.py | 2 +- 8 files changed, 15 insertions(+), 17 deletions(-) diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.md b/.github/ISSUE_TEMPLATE/1_broken_site.md index 2fea0120e..5cd9f0dc0 100644 --- a/.github/ISSUE_TEMPLATE/1_broken_site.md +++ b/.github/ISSUE_TEMPLATE/1_broken_site.md @@ -18,7 +18,7 @@ title: '' - [ ] I'm reporting a broken site support -- [ ] I've verified that I'm running youtube-dl version **2019.09.28** +- [ ] I've verified that I'm running youtube-dl version **2019.10.16** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar issues including closed ones @@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.09.28 + [debug] youtube-dl version 2019.10.16 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/2_site_support_request.md b/.github/ISSUE_TEMPLATE/2_site_support_request.md index 6116acc79..6cc34796a 100644 --- a/.github/ISSUE_TEMPLATE/2_site_support_request.md +++ b/.github/ISSUE_TEMPLATE/2_site_support_request.md @@ -19,7 +19,7 @@ labels: 'site-support-request' - [ ] I'm reporting a new site support request -- [ ] I've verified that I'm running youtube-dl version **2019.09.28** +- [ ] I've verified that I'm running youtube-dl version **2019.10.16** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that none of provided URLs violate any copyrights - [ ] I've searched the bugtracker for similar site support requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/3_site_feature_request.md b/.github/ISSUE_TEMPLATE/3_site_feature_request.md index 79d1a7f3c..0b7911e79 100644 --- a/.github/ISSUE_TEMPLATE/3_site_feature_request.md +++ b/.github/ISSUE_TEMPLATE/3_site_feature_request.md @@ -18,13 +18,13 @@ title: '' - [ ] I'm reporting a site feature request -- [ ] I've verified that I'm running youtube-dl version **2019.09.28** +- [ ] I've verified that I'm running youtube-dl version **2019.10.16** - [ ] I've searched the bugtracker for similar site feature requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/4_bug_report.md b/.github/ISSUE_TEMPLATE/4_bug_report.md index 9bda3d440..a6f417d38 100644 --- a/.github/ISSUE_TEMPLATE/4_bug_report.md +++ b/.github/ISSUE_TEMPLATE/4_bug_report.md @@ -18,7 +18,7 @@ title: '' - [ ] I'm reporting a broken site support issue -- [ ] I've verified that I'm running youtube-dl version **2019.09.28** +- [ ] I've verified that I'm running youtube-dl version **2019.10.16** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar bug reports including closed ones @@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.09.28 + [debug] youtube-dl version 2019.10.16 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/5_feature_request.md b/.github/ISSUE_TEMPLATE/5_feature_request.md index 581344917..3fe753b62 100644 --- a/.github/ISSUE_TEMPLATE/5_feature_request.md +++ b/.github/ISSUE_TEMPLATE/5_feature_request.md @@ -19,13 +19,13 @@ labels: 'request' - [ ] I'm reporting a feature request -- [ ] I've verified that I'm running youtube-dl version **2019.09.28** +- [ ] I've verified that I'm running youtube-dl version **2019.10.16** - [ ] I've searched the bugtracker for similar feature requests including closed ones diff --git a/ChangeLog b/ChangeLog index 8a59398d9..dc5c32a1f 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version +version 2019.10.16 Core * [extractor/common] Make _is_valid_url more relaxed diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 35275278b..0cbad28ea 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -694,7 +694,6 @@ - **PornoXO** - **PornTube** - **PressTV** - - **PromptFile** - **prosiebensat1**: ProSiebenSat.1 Digital - **puhutv** - **puhutv:serie** @@ -884,6 +883,7 @@ - **TeleQuebec** - **TeleQuebecEmission** - **TeleQuebecLive** + - **TeleQuebecSquat** - **TeleTask** - **Telewebion** - **TennisTV** @@ -991,7 +991,6 @@ - **VeeHD** - **Veoh** - **verystream** - - **Vessel** - **Vesti**: Вести.Ru - **Vevo** - **VevoPlaylist** @@ -1090,7 +1089,6 @@ - **Weibo** - **WeiboMobile** - **WeiqiTV**: WQTV - - **Wimp** - **Wistia** - **wnl**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl - **WorldStarHipHop** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index c3eafb068..53889b7cb 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.09.28' +__version__ = '2019.10.16' From 6d394a66f54216cc2b0b68fadd958eaf455c2778 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 16 Oct 2019 12:03:46 +0100 Subject: [PATCH 09/65] [atresplayer] fix extraction(closes #16277)(closes #16716) --- youtube_dl/extractor/atresplayer.py | 213 +++++++++------------------- 1 file changed, 64 insertions(+), 149 deletions(-) diff --git a/youtube_dl/extractor/atresplayer.py b/youtube_dl/extractor/atresplayer.py index ae1c09427..b96218f6c 100644 --- a/youtube_dl/extractor/atresplayer.py +++ b/youtube_dl/extractor/atresplayer.py @@ -1,202 +1,117 @@ from __future__ import unicode_literals -import time -import hmac -import hashlib import re from .common import InfoExtractor -from ..compat import compat_str +from ..compat import compat_HTTPError from ..utils import ( ExtractorError, - float_or_none, int_or_none, - sanitized_Request, urlencode_postdata, - xpath_text, ) class AtresPlayerIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?atresplayer\.com/television/[^/]+/[^/]+/[^/]+/(?P.+?)_\d+\.html' + _VALID_URL = r'https?://(?:www\.)?atresplayer\.com/[^/]+/[^/]+/[^/]+/[^/]+/(?P.+?)_(?P[0-9a-f]{24})' _NETRC_MACHINE = 'atresplayer' _TESTS = [ { - 'url': 'http://www.atresplayer.com/television/programas/el-club-de-la-comedia/temporada-4/capitulo-10-especial-solidario-nochebuena_2014122100174.html', - 'md5': 'efd56753cda1bb64df52a3074f62e38a', + 'url': 'https://www.atresplayer.com/antena3/series/pequenas-coincidencias/temporada-1/capitulo-7-asuntos-pendientes_5d4aa2c57ed1a88fc715a615/', 'info_dict': { - 'id': 'capitulo-10-especial-solidario-nochebuena', + 'id': '5d4aa2c57ed1a88fc715a615', 'ext': 'mp4', - 'title': 'Especial Solidario de Nochebuena', - 'description': 'md5:e2d52ff12214fa937107d21064075bf1', - 'duration': 5527.6, - 'thumbnail': r're:^https?://.*\.jpg$', + 'title': 'Capítulo 7: Asuntos pendientes', + 'description': 'md5:7634cdcb4d50d5381bedf93efb537fbc', + 'duration': 3413, + }, + 'params': { + 'format': 'bestvideo', }, 'skip': 'This video is only available for registered users' }, { - 'url': 'http://www.atresplayer.com/television/especial/videoencuentros/temporada-1/capitulo-112-david-bustamante_2014121600375.html', - 'md5': '6e52cbb513c405e403dbacb7aacf8747', - 'info_dict': { - 'id': 'capitulo-112-david-bustamante', - 'ext': 'flv', - 'title': 'David Bustamante', - 'description': 'md5:f33f1c0a05be57f6708d4dd83a3b81c6', - 'duration': 1439.0, - 'thumbnail': r're:^https?://.*\.jpg$', - }, + 'url': 'https://www.atresplayer.com/lasexta/programas/el-club-de-la-comedia/temporada-4/capitulo-10-especial-solidario-nochebuena_5ad08edf986b2855ed47adc4/', + 'only_matching': True, }, { - 'url': 'http://www.atresplayer.com/television/series/el-secreto-de-puente-viejo/el-chico-de-los-tres-lunares/capitulo-977-29-12-14_2014122400174.html', + 'url': 'https://www.atresplayer.com/antena3/series/el-secreto-de-puente-viejo/el-chico-de-los-tres-lunares/capitulo-977-29-12-14_5ad51046986b2886722ccdea/', 'only_matching': True, }, ] - - _USER_AGENT = 'Dalvik/1.6.0 (Linux; U; Android 4.3; GT-I9300 Build/JSS15J' - _MAGIC = 'QWtMLXs414Yo+c#_+Q#K@NN)' - _TIMESTAMP_SHIFT = 30000 - - _TIME_API_URL = 'http://servicios.atresplayer.com/api/admin/time.json' - _URL_VIDEO_TEMPLATE = 'https://servicios.atresplayer.com/api/urlVideo/{1}/{0}/{1}|{2}|{3}.json' - _PLAYER_URL_TEMPLATE = 'https://servicios.atresplayer.com/episode/getplayer.json?episodePk=%s' - _EPISODE_URL_TEMPLATE = 'http://www.atresplayer.com/episodexml/%s' - - _LOGIN_URL = 'https://servicios.atresplayer.com/j_spring_security_check' - - _ERRORS = { - 'UNPUBLISHED': 'We\'re sorry, but this video is not yet available.', - 'DELETED': 'This video has expired and is no longer available for online streaming.', - 'GEOUNPUBLISHED': 'We\'re sorry, but this video is not available in your region due to right restrictions.', - # 'PREMIUM': 'PREMIUM', - } + _API_BASE = 'https://api.atresplayer.com/' def _real_initialize(self): self._login() + def _handle_error(self, e, code): + if isinstance(e.cause, compat_HTTPError) and e.cause.code == code: + error = self._parse_json(e.cause.read(), None) + if error.get('error') == 'required_registered': + self.raise_login_required() + raise ExtractorError(error['error_description'], expected=True) + raise + def _login(self): username, password = self._get_login_info() if username is None: return - login_form = { - 'j_username': username, - 'j_password': password, - } + self._request_webpage( + self._API_BASE + 'login', None, 'Downloading login page') - request = sanitized_Request( - self._LOGIN_URL, urlencode_postdata(login_form)) - request.add_header('Content-Type', 'application/x-www-form-urlencoded') - response = self._download_webpage( - request, None, 'Logging in') + try: + target_url = self._download_json( + 'https://account.atresmedia.com/api/login', None, + 'Logging in', headers={ + 'Content-Type': 'application/x-www-form-urlencoded' + }, data=urlencode_postdata({ + 'username': username, + 'password': password, + }))['targetUrl'] + except ExtractorError as e: + self._handle_error(e, 400) - error = self._html_search_regex( - r'(?s)]+class="[^"]*\blist_error\b[^"]*">(.+?)', - response, 'error', default=None) - if error: - raise ExtractorError( - 'Unable to login: %s' % error, expected=True) + self._request_webpage(target_url, None, 'Following Target URL') def _real_extract(self, url): - video_id = self._match_id(url) + display_id, video_id = re.match(self._VALID_URL, url).groups() - webpage = self._download_webpage(url, video_id) + try: + episode = self._download_json( + self._API_BASE + 'client/v1/player/episode/' + video_id, video_id) + except ExtractorError as e: + self._handle_error(e, 403) - episode_id = self._search_regex( - r'episode="([^"]+)"', webpage, 'episode id') - - request = sanitized_Request( - self._PLAYER_URL_TEMPLATE % episode_id, - headers={'User-Agent': self._USER_AGENT}) - player = self._download_json(request, episode_id, 'Downloading player JSON') - - episode_type = player.get('typeOfEpisode') - error_message = self._ERRORS.get(episode_type) - if error_message: - raise ExtractorError( - '%s returned error: %s' % (self.IE_NAME, error_message), expected=True) + title = episode['titulo'] formats = [] - video_url = player.get('urlVideo') - if video_url: - format_info = { - 'url': video_url, - 'format_id': 'http', - } - mobj = re.search(r'(?P\d+)K_(?P\d+)x(?P\d+)', video_url) - if mobj: - format_info.update({ - 'width': int_or_none(mobj.group('width')), - 'height': int_or_none(mobj.group('height')), - 'tbr': int_or_none(mobj.group('bitrate')), - }) - formats.append(format_info) - - timestamp = int_or_none(self._download_webpage( - self._TIME_API_URL, - video_id, 'Downloading timestamp', fatal=False), 1000, time.time()) - timestamp_shifted = compat_str(timestamp + self._TIMESTAMP_SHIFT) - token = hmac.new( - self._MAGIC.encode('ascii'), - (episode_id + timestamp_shifted).encode('utf-8'), hashlib.md5 - ).hexdigest() - - request = sanitized_Request( - self._URL_VIDEO_TEMPLATE.format('windows', episode_id, timestamp_shifted, token), - headers={'User-Agent': self._USER_AGENT}) - - fmt_json = self._download_json( - request, video_id, 'Downloading windows video JSON') - - result = fmt_json.get('resultDes') - if result.lower() != 'ok': - raise ExtractorError( - '%s returned error: %s' % (self.IE_NAME, result), expected=True) - - for format_id, video_url in fmt_json['resultObject'].items(): - if format_id == 'token' or not video_url.startswith('http'): + for source in episode.get('sources', []): + src = source.get('src') + if not src: continue - if 'geodeswowsmpra3player' in video_url: - # f4m_path = video_url.split('smil:', 1)[-1].split('free_', 1)[0] - # f4m_url = 'http://drg.antena3.com/{0}hds/es/sd.f4m'.format(f4m_path) - # this videos are protected by DRM, the f4m downloader doesn't support them - continue - video_url_hd = video_url.replace('free_es', 'es') - formats.extend(self._extract_f4m_formats( - video_url_hd[:-9] + '/manifest.f4m', video_id, f4m_id='hds', - fatal=False)) - formats.extend(self._extract_mpd_formats( - video_url_hd[:-9] + '/manifest.mpd', video_id, mpd_id='dash', - fatal=False)) + src_type = source.get('type') + if src_type == 'application/vnd.apple.mpegurl': + formats.extend(self._extract_m3u8_formats( + src, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) + elif src_type == 'application/dash+xml': + formats.extend(self._extract_mpd_formats( + src, video_id, mpd_id='dash', fatal=False)) self._sort_formats(formats) - path_data = player.get('pathData') - - episode = self._download_xml( - self._EPISODE_URL_TEMPLATE % path_data, video_id, - 'Downloading episode XML') - - duration = float_or_none(xpath_text( - episode, './media/asset/info/technical/contentDuration', 'duration')) - - art = episode.find('./media/asset/info/art') - title = xpath_text(art, './name', 'title') - description = xpath_text(art, './description', 'description') - thumbnail = xpath_text(episode, './media/asset/files/background', 'thumbnail') - - subtitles = {} - subtitle_url = xpath_text(episode, './media/asset/files/subtitle', 'subtitle') - if subtitle_url: - subtitles['es'] = [{ - 'ext': 'srt', - 'url': subtitle_url, - }] + heartbeat = episode.get('heartbeat') or {} + omniture = episode.get('omniture') or {} + get_meta = lambda x: heartbeat.get(x) or omniture.get(x) return { + 'display_id': display_id, 'id': video_id, 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'duration': duration, + 'description': episode.get('descripcion'), + 'thumbnail': episode.get('imgPoster'), + 'duration': int_or_none(episode.get('duration')), 'formats': formats, - 'subtitles': subtitles, + 'channel': get_meta('channel'), + 'season': get_meta('season'), + 'episode_number': int_or_none(get_meta('episodeNumber')), } From e29e96a9f5bc390789d176d509f592e208aa30d8 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 16 Oct 2019 15:06:48 +0100 Subject: [PATCH 10/65] [dumpert] fix extraction(closes #22428)(closes #22564) --- youtube_dl/extractor/dumpert.py | 83 +++++++++++++++++++-------------- 1 file changed, 47 insertions(+), 36 deletions(-) diff --git a/youtube_dl/extractor/dumpert.py b/youtube_dl/extractor/dumpert.py index be2e3d378..d9d9afdec 100644 --- a/youtube_dl/extractor/dumpert.py +++ b/youtube_dl/extractor/dumpert.py @@ -1,20 +1,17 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..compat import compat_b64decode from ..utils import ( + int_or_none, qualities, - sanitized_Request, ) class DumpertIE(InfoExtractor): - _VALID_URL = r'(?Phttps?)://(?:www\.)?dumpert\.nl/(?:mediabase|embed)/(?P[0-9]+/[0-9a-zA-Z]+)' + _VALID_URL = r'(?Phttps?)://(?:(?:www|legacy)\.)?dumpert\.nl/(?:mediabase|embed|item)/(?P[0-9]+[/_][0-9a-zA-Z]+)' _TESTS = [{ - 'url': 'http://www.dumpert.nl/mediabase/6646981/951bc60f/', + 'url': 'https://www.dumpert.nl/item/6646981_951bc60f', 'md5': '1b9318d7d5054e7dcb9dc7654f21d643', 'info_dict': { 'id': '6646981/951bc60f', @@ -24,46 +21,60 @@ class DumpertIE(InfoExtractor): 'thumbnail': r're:^https?://.*\.jpg$', } }, { - 'url': 'http://www.dumpert.nl/embed/6675421/dc440fe7/', + 'url': 'https://www.dumpert.nl/embed/6675421_dc440fe7', + 'only_matching': True, + }, { + 'url': 'http://legacy.dumpert.nl/mediabase/6646981/951bc60f', + 'only_matching': True, + }, { + 'url': 'http://legacy.dumpert.nl/embed/6675421/dc440fe7', 'only_matching': True, }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - protocol = mobj.group('protocol') - - url = '%s://www.dumpert.nl/mediabase/%s' % (protocol, video_id) - req = sanitized_Request(url) - req.add_header('Cookie', 'nsfw=1; cpc=10') - webpage = self._download_webpage(req, video_id) - - files_base64 = self._search_regex( - r'data-files="([^"]+)"', webpage, 'data files') - - files = self._parse_json( - compat_b64decode(files_base64).decode('utf-8'), - video_id) + video_id = self._match_id(url).replace('_', '/') + item = self._download_json( + 'http://api-live.dumpert.nl/mobile_api/json/info/' + video_id.replace('/', '_'), + video_id)['items'][0] + title = item['title'] + media = next(m for m in item['media'] if m.get('mediatype') == 'VIDEO') quality = qualities(['flv', 'mobile', 'tablet', '720p']) - - formats = [{ - 'url': video_url, - 'format_id': format_id, - 'quality': quality(format_id), - } for format_id, video_url in files.items() if format_id != 'still'] + formats = [] + for variant in media.get('variants', []): + uri = variant.get('uri') + if not uri: + continue + version = variant.get('version') + formats.append({ + 'url': uri, + 'format_id': version, + 'quality': quality(version), + }) self._sort_formats(formats) - title = self._html_search_meta( - 'title', webpage) or self._og_search_title(webpage) - description = self._html_search_meta( - 'description', webpage) or self._og_search_description(webpage) - thumbnail = files.get('still') or self._og_search_thumbnail(webpage) + thumbnails = [] + stills = item.get('stills') or {} + for t in ('thumb', 'still'): + for s in ('', '-medium', '-large'): + still_id = t + s + still_url = stills.get(still_id) + if not still_url: + continue + thumbnails.append({ + 'id': still_id, + 'url': still_url, + }) + + stats = item.get('stats') or {} return { 'id': video_id, 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'formats': formats + 'description': item.get('description'), + 'thumbnails': thumbnails, + 'formats': formats, + 'duration': int_or_none(media.get('duration')), + 'like_count': int_or_none(stats.get('kudos_total')), + 'view_count': int_or_none(stats.get('views_total')), } From 2b115b9460502944d6088cf42810c440495128a3 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 16 Oct 2019 15:41:58 +0100 Subject: [PATCH 11/65] [servingsys] Remove extractor(closes #22639) --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/servingsys.py | 72 ------------------------------ 2 files changed, 73 deletions(-) delete mode 100644 youtube_dl/extractor/servingsys.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 7a1e0dad6..53d527440 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -995,7 +995,6 @@ from .scrippsnetworks import ScrippsNetworksWatchIE from .seeker import SeekerIE from .senateisvp import SenateISVPIE from .sendtonews import SendtoNewsIE -from .servingsys import ServingSysIE from .servus import ServusIE from .sevenplus import SevenPlusIE from .sexu import SexuIE diff --git a/youtube_dl/extractor/servingsys.py b/youtube_dl/extractor/servingsys.py deleted file mode 100644 index c013d678f..000000000 --- a/youtube_dl/extractor/servingsys.py +++ /dev/null @@ -1,72 +0,0 @@ -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..utils import ( - int_or_none, -) - - -class ServingSysIE(InfoExtractor): - _VALID_URL = r'https?://(?:[^.]+\.)?serving-sys\.com/BurstingPipe/adServer\.bs\?.*?&pli=(?P[0-9]+)' - - _TEST = { - 'url': 'http://bs.serving-sys.com/BurstingPipe/adServer.bs?cn=is&c=23&pl=VAST&pli=5349193&PluID=0&pos=7135&ord=[timestamp]&cim=1?', - 'info_dict': { - 'id': '5349193', - 'title': 'AdAPPter_Hyundai_demo', - }, - 'playlist': [{ - 'md5': 'baed851342df6846eb8677a60a011a0f', - 'info_dict': { - 'id': '29955898', - 'ext': 'flv', - 'title': 'AdAPPter_Hyundai_demo (1)', - 'duration': 74, - 'tbr': 1378, - 'width': 640, - 'height': 400, - }, - }, { - 'md5': '979b4da2655c4bc2d81aeb915a8c5014', - 'info_dict': { - 'id': '29907998', - 'ext': 'flv', - 'title': 'AdAPPter_Hyundai_demo (2)', - 'duration': 34, - 'width': 854, - 'height': 480, - 'tbr': 516, - }, - }], - 'params': { - 'playlistend': 2, - }, - '_skip': 'Blocked in the US [sic]', - } - - def _real_extract(self, url): - pl_id = self._match_id(url) - vast_doc = self._download_xml(url, pl_id) - - title = vast_doc.find('.//AdTitle').text - media = vast_doc.find('.//MediaFile').text - info_url = self._search_regex(r'&adData=([^&]+)&', media, 'info URL') - - doc = self._download_xml(info_url, pl_id, 'Downloading video info') - entries = [{ - '_type': 'video', - 'id': a.attrib['id'], - 'title': '%s (%s)' % (title, a.attrib['assetID']), - 'url': a.attrib['URL'], - 'duration': int_or_none(a.attrib.get('length')), - 'tbr': int_or_none(a.attrib.get('bitrate')), - 'height': int_or_none(a.attrib.get('height')), - 'width': int_or_none(a.attrib.get('width')), - } for a in doc.findall('.//AdditionalAssets/asset')] - - return { - '_type': 'playlist', - 'id': pl_id, - 'title': title, - 'entries': entries, - } From d07866f13efac39bf3f0b331870a15e0f5e98057 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 16 Oct 2019 15:45:45 +0100 Subject: [PATCH 12/65] [mit] Remove support for video.mit.edu(closes #22403) --- youtube_dl/extractor/extractors.py | 2 +- youtube_dl/extractor/mit.py | 24 ------------------------ 2 files changed, 1 insertion(+), 25 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 53d527440..ea47b99f6 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -644,7 +644,7 @@ from .minhateca import MinhatecaIE from .ministrygrid import MinistryGridIE from .minoto import MinotoIE from .miomio import MioMioIE -from .mit import TechTVMITIE, MITIE, OCWMITIE +from .mit import TechTVMITIE, OCWMITIE from .mitele import MiTeleIE from .mixcloud import ( MixcloudIE, diff --git a/youtube_dl/extractor/mit.py b/youtube_dl/extractor/mit.py index 1aea78d11..e1506a745 100644 --- a/youtube_dl/extractor/mit.py +++ b/youtube_dl/extractor/mit.py @@ -65,30 +65,6 @@ class TechTVMITIE(InfoExtractor): } -class MITIE(TechTVMITIE): - IE_NAME = 'video.mit.edu' - _VALID_URL = r'https?://video\.mit\.edu/watch/(?P[^/]+)' - - _TEST = { - 'url': 'http://video.mit.edu/watch/the-government-is-profiling-you-13222/', - 'md5': '7db01d5ccc1895fc5010e9c9e13648da', - 'info_dict': { - 'id': '21783', - 'ext': 'mp4', - 'title': 'The Government is Profiling You', - 'description': 'md5:ad5795fe1e1623b73620dbfd47df9afd', - }, - } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - page_title = mobj.group('title') - webpage = self._download_webpage(url, page_title) - embed_url = self._search_regex( - r'<iframe .*?src="(.+?)"', webpage, 'embed url') - return self.url_result(embed_url) - - class OCWMITIE(InfoExtractor): IE_NAME = 'ocw.mit.edu' _VALID_URL = r'^https?://ocw\.mit\.edu/courses/(?P<topic>[a-z0-9\-]+)' From bc48773ed4c068adfe67078714814035660e5ca4 Mon Sep 17 00:00:00 2001 From: MobiDotS <msaad615@gmail.com> Date: Wed, 16 Oct 2019 10:13:35 -0500 Subject: [PATCH 13/65] [twitch] update VOD URL matching (closes #22395) (#22727) --- youtube_dl/extractor/twitch.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py index 0500e33a6..ca7676fe2 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -248,7 +248,7 @@ class TwitchVodIE(TwitchItemBaseIE): https?:// (?: (?:(?:www|go|m)\.)?twitch\.tv/(?:[^/]+/v(?:ideo)?|videos)/| - player\.twitch\.tv/\?.*?\bvideo=v + player\.twitch\.tv/\?.*?\bvideo=v? ) (?P<id>\d+) ''' @@ -306,6 +306,9 @@ class TwitchVodIE(TwitchItemBaseIE): }, { 'url': 'https://www.twitch.tv/northernlion/video/291940395', 'only_matching': True, + }, { + 'url': 'https://player.twitch.tv/?video=480452374', + 'only_matching': True, }] def _real_extract(self, url): From 000115759485797be719c71716c1ac35f003ba6c Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Wed, 16 Oct 2019 23:57:40 +0100 Subject: [PATCH 14/65] [atresplayer] Add coding cookie --- youtube_dl/extractor/atresplayer.py | 1 + 1 file changed, 1 insertion(+) diff --git a/youtube_dl/extractor/atresplayer.py b/youtube_dl/extractor/atresplayer.py index b96218f6c..c2cec9845 100644 --- a/youtube_dl/extractor/atresplayer.py +++ b/youtube_dl/extractor/atresplayer.py @@ -1,3 +1,4 @@ +# coding: utf-8 from __future__ import unicode_literals import re From 86f63633c8e7c62ce245d1352d4d381efb614466 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Thu, 17 Oct 2019 13:20:16 +0100 Subject: [PATCH 15/65] [audioboom] improve metadata extraction --- youtube_dl/extractor/audioboom.py | 34 +++++++++++++++++-------------- 1 file changed, 19 insertions(+), 15 deletions(-) diff --git a/youtube_dl/extractor/audioboom.py b/youtube_dl/extractor/audioboom.py index 393f381c6..c51837b40 100644 --- a/youtube_dl/extractor/audioboom.py +++ b/youtube_dl/extractor/audioboom.py @@ -2,22 +2,25 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import float_or_none +from ..utils import ( + clean_html, + float_or_none, +) class AudioBoomIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?audioboom\.com/(?:boos|posts)/(?P<id>[0-9]+)' _TESTS = [{ - 'url': 'https://audioboom.com/boos/4279833-3-09-2016-czaban-hour-3?t=0', - 'md5': '63a8d73a055c6ed0f1e51921a10a5a76', + 'url': 'https://audioboom.com/posts/7398103-asim-chaudhry', + 'md5': '7b00192e593ff227e6a315486979a42d', 'info_dict': { - 'id': '4279833', + 'id': '7398103', 'ext': 'mp3', - 'title': '3/09/2016 Czaban Hour 3', - 'description': 'Guest: Nate Davis - NFL free agency, Guest: Stan Gans', - 'duration': 2245.72, - 'uploader': 'SB Nation A.M.', - 'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channel/steveczabanyahoosportsradio', + 'title': 'Asim Chaudhry', + 'description': 'md5:2f3fef17dacc2595b5362e1d7d3602fc', + 'duration': 4000.99, + 'uploader': 'Sue Perkins: An hour or so with...', + 'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channel/perkins', } }, { 'url': 'https://audioboom.com/posts/4279833-3-09-2016-czaban-hour-3?t=0', @@ -32,8 +35,8 @@ class AudioBoomIE(InfoExtractor): clip = None clip_store = self._parse_json( - self._search_regex( - r'data-new-clip-store=(["\'])(?P<json>{.*?"clipId"\s*:\s*%s.*?})\1' % video_id, + self._html_search_regex( + r'data-new-clip-store=(["\'])(?P<json>{.+?})\1', webpage, 'clip store', default='{}', group='json'), video_id, fatal=False) if clip_store: @@ -47,14 +50,15 @@ class AudioBoomIE(InfoExtractor): audio_url = from_clip('clipURLPriorToLoading') or self._og_search_property( 'audio', webpage, 'audio url') - title = from_clip('title') or self._og_search_title(webpage) - description = from_clip('description') or self._og_search_description(webpage) + title = from_clip('title') or self._html_search_meta( + ['og:title', 'og:audio:title', 'audio_title'], webpage) + description = from_clip('description') or clean_html(from_clip('formattedDescription')) or self._og_search_description(webpage) duration = float_or_none(from_clip('duration') or self._html_search_meta( 'weibo:audio:duration', webpage)) - uploader = from_clip('author') or self._og_search_property( - 'audio:artist', webpage, 'uploader', fatal=False) + uploader = from_clip('author') or self._html_search_meta( + ['og:audio:artist', 'twitter:audio:artist_name', 'audio_artist'], webpage, 'uploader') uploader_url = from_clip('author_url') or self._html_search_meta( 'audioboo:channel', webpage, 'uploader url') From 755541a4c8ac3dd4e8b9abd0c7df95182a1f3fd4 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Thu, 17 Oct 2019 13:21:44 +0100 Subject: [PATCH 16/65] [mangomolo] fix video format extraction and add support for player URLs --- youtube_dl/extractor/generic.py | 8 ++++++-- youtube_dl/extractor/mangomolo.py | 17 +++++++++++------ 2 files changed, 17 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index ec43c5ae4..5ed952b29 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -2962,10 +2962,14 @@ class GenericIE(InfoExtractor): # Look for Mangomolo embeds mobj = re.search( - r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/ + r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?// + (?: + admin\.mangomolo\.com/analytics/index\.php/customers/embed| + player\.mangomolo\.com/v1 + )/ (?: video\?.*?\bid=(?P<video_id>\d+)| - index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+) + (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+) ).+?)\1''', webpage) if mobj is not None: info = { diff --git a/youtube_dl/extractor/mangomolo.py b/youtube_dl/extractor/mangomolo.py index 482175a34..acee370e9 100644 --- a/youtube_dl/extractor/mangomolo.py +++ b/youtube_dl/extractor/mangomolo.py @@ -10,18 +10,21 @@ from ..utils import int_or_none class MangomoloBaseIE(InfoExtractor): + _BASE_REGEX = r'https?://(?:admin\.mangomolo\.com/analytics/index\.php/customers/embed/|player\.mangomolo\.com/v1/)' + def _get_real_id(self, page_id): return page_id def _real_extract(self, url): page_id = self._get_real_id(self._match_id(url)) - webpage = self._download_webpage(url, page_id) + webpage = self._download_webpage( + 'https://player.mangomolo.com/v1/%s?%s' % (self._TYPE, url.split('?')[1]), page_id) hidden_inputs = self._hidden_inputs(webpage) m3u8_entry_protocol = 'm3u8' if self._IS_LIVE else 'm3u8_native' format_url = self._html_search_regex( [ - r'file\s*:\s*"(https?://[^"]+?/playlist\.m3u8)', + r'(?:file|src)\s*:\s*"(https?://[^"]+?/playlist\.m3u8)', r'<a[^>]+href="(rtsp://[^"]+)"' ], webpage, 'format url') formats = self._extract_wowza_formats( @@ -39,14 +42,16 @@ class MangomoloBaseIE(InfoExtractor): class MangomoloVideoIE(MangomoloBaseIE): - IE_NAME = 'mangomolo:video' - _VALID_URL = r'https?://admin\.mangomolo\.com/analytics/index\.php/customers/embed/video\?.*?\bid=(?P<id>\d+)' + _TYPE = 'video' + IE_NAME = 'mangomolo:' + _TYPE + _VALID_URL = MangomoloBaseIE._BASE_REGEX + r'video\?.*?\bid=(?P<id>\d+)' _IS_LIVE = False class MangomoloLiveIE(MangomoloBaseIE): - IE_NAME = 'mangomolo:live' - _VALID_URL = r'https?://admin\.mangomolo\.com/analytics/index\.php/customers/embed/index\?.*?\bchannelid=(?P<id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)' + _TYPE = 'live' + IE_NAME = 'mangomolo:' + _TYPE + _VALID_URL = MangomoloBaseIE._BASE_REGEX + r'(live|index)\?.*?\bchannelid=(?P<id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)' _IS_LIVE = True def _get_real_id(self, page_id): From 59296bae7ec6d15b0df37dce34bdd96381c0e743 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Thu, 17 Oct 2019 13:26:45 +0100 Subject: [PATCH 17/65] [xfileshare] clean extractor - update the list of domains - add support for aa-encoded video data - improve jwplayer format extraction - add support for Clappr sources closes #17032 closes #17906 closes #18237 closes #18239 --- youtube_dl/extractor/xfileshare.py | 192 +++++++++++++---------------- 1 file changed, 86 insertions(+), 106 deletions(-) diff --git a/youtube_dl/extractor/xfileshare.py b/youtube_dl/extractor/xfileshare.py index b38c7a7b3..48ef07ed1 100644 --- a/youtube_dl/extractor/xfileshare.py +++ b/youtube_dl/extractor/xfileshare.py @@ -4,37 +4,64 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_chr from ..utils import ( decode_packed_codes, determine_ext, ExtractorError, int_or_none, - NO_DEFAULT, + js_to_json, urlencode_postdata, ) +# based on openload_decode from 2bfeee69b976fe049761dd3012e30b637ee05a58 +def aa_decode(aa_code): + symbol_table = [ + ('7', '((ﾟｰﾟ) + (o^_^o))'), + ('6', '((o^_^o) +(o^_^o))'), + ('5', '((ﾟｰﾟ) + (ﾟΘﾟ))'), + ('2', '((o^_^o) - (ﾟΘﾟ))'), + ('4', '(ﾟｰﾟ)'), + ('3', '(o^_^o)'), + ('1', '(ﾟΘﾟ)'), + ('0', '(c^_^o)'), + ] + delim = '(ﾟДﾟ)[ﾟεﾟ]+' + ret = '' + for aa_char in aa_code.split(delim): + for val, pat in symbol_table: + aa_char = aa_char.replace(pat, val) + aa_char = aa_char.replace('+ ', '') + m = re.match(r'^\d+', aa_char) + if m: + ret += compat_chr(int(m.group(0), 8)) + else: + m = re.match(r'^u([\da-f]+)', aa_char) + if m: + ret += compat_chr(int(m.group(1), 16)) + return ret + + class XFileShareIE(InfoExtractor): _SITES = ( - (r'daclips\.(?:in|com)', 'DaClips'), - (r'filehoot\.com', 'FileHoot'), - (r'gorillavid\.(?:in|com)', 'GorillaVid'), - (r'movpod\.in', 'MovPod'), - (r'powerwatch\.pw', 'PowerWatch'), - (r'rapidvideo\.ws', 'Rapidvideo.ws'), + (r'clipwatching\.com', 'ClipWatching'), + (r'gounlimited\.to', 'GoUnlimited'), + (r'govid\.me', 'GoVid'), + (r'holavid\.com', 'HolaVid'), + (r'streamty\.com', 'Streamty'), (r'thevideobee\.to', 'TheVideoBee'), - (r'vidto\.(?:me|se)', 'Vidto'), - (r'streamin\.to', 'Streamin.To'), - (r'xvidstage\.com', 'XVIDSTAGE'), - (r'vidabc\.com', 'Vid ABC'), + (r'uqload\.com', 'Uqload'), (r'vidbom\.com', 'VidBom'), (r'vidlo\.us', 'vidlo'), - (r'rapidvideo\.(?:cool|org)', 'RapidVideo.TV'), - (r'fastvideo\.me', 'FastVideo.me'), + (r'vidlocker\.xyz', 'VidLocker'), + (r'vidshare\.tv', 'VidShare'), + (r'vup\.to', 'VUp'), + (r'xvideosharing\.com', 'XVideoSharing'), ) IE_DESC = 'XFileShare based sites: %s' % ', '.join(list(zip(*_SITES))[1]) - _VALID_URL = (r'https?://(?P<host>(?:www\.)?(?:%s))/(?:embed-)?(?P<id>[0-9a-zA-Z]+)' + _VALID_URL = (r'https?://(?:www\.)?(?P<host>%s)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)' % '|'.join(site for site in list(zip(*_SITES))[0])) _FILE_NOT_FOUND_REGEXES = ( @@ -43,82 +70,14 @@ class XFileShareIE(InfoExtractor): ) _TESTS = [{ - 'url': 'http://gorillavid.in/06y9juieqpmi', - 'md5': '5ae4a3580620380619678ee4875893ba', + 'url': 'http://xvideosharing.com/fq65f94nd2ve', + 'md5': '4181f63957e8fe90ac836fa58dc3c8a6', 'info_dict': { - 'id': '06y9juieqpmi', + 'id': 'fq65f94nd2ve', 'ext': 'mp4', - 'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ', + 'title': 'sample', 'thumbnail': r're:http://.*\.jpg', }, - }, { - 'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html', - 'only_matching': True, - }, { - 'url': 'http://daclips.in/3rso4kdn6f9m', - 'md5': '1ad8fd39bb976eeb66004d3a4895f106', - 'info_dict': { - 'id': '3rso4kdn6f9m', - 'ext': 'mp4', - 'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc', - 'thumbnail': r're:http://.*\.jpg', - } - }, { - 'url': 'http://movpod.in/0wguyyxi1yca', - 'only_matching': True, - }, { - 'url': 'http://filehoot.com/3ivfabn7573c.html', - 'info_dict': { - 'id': '3ivfabn7573c', - 'ext': 'mp4', - 'title': 'youtube-dl test video \'äBaW_jenozKc.mp4.mp4', - 'thumbnail': r're:http://.*\.jpg', - }, - 'skip': 'Video removed', - }, { - 'url': 'http://vidto.me/ku5glz52nqe1.html', - 'info_dict': { - 'id': 'ku5glz52nqe1', - 'ext': 'mp4', - 'title': 'test' - } - }, { - 'url': 'http://powerwatch.pw/duecjibvicbu', - 'info_dict': { - 'id': 'duecjibvicbu', - 'ext': 'mp4', - 'title': 'Big Buck Bunny trailer', - }, - }, { - 'url': 'http://xvidstage.com/e0qcnl03co6z', - 'info_dict': { - 'id': 'e0qcnl03co6z', - 'ext': 'mp4', - 'title': 'Chucky Prank 2015.mp4', - }, - }, { - # removed by administrator - 'url': 'http://xvidstage.com/amfy7atlkx25', - 'only_matching': True, - }, { - 'url': 'http://vidabc.com/i8ybqscrphfv', - 'info_dict': { - 'id': 'i8ybqscrphfv', - 'ext': 'mp4', - 'title': 're:Beauty and the Beast 2017', - }, - 'params': { - 'skip_download': True, - }, - }, { - 'url': 'http://www.rapidvideo.cool/b667kprndr8w', - 'only_matching': True, - }, { - 'url': 'http://www.fastvideo.me/k8604r8nk8sn/FAST_FURIOUS_8_-_Trailer_italiano_ufficiale.mp4.html', - 'only_matching': True, - }, { - 'url': 'http://vidto.se/1tx1pf6t12cg.html', - 'only_matching': True, }] @staticmethod @@ -131,10 +90,9 @@ class XFileShareIE(InfoExtractor): webpage)] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + host, video_id = re.match(self._VALID_URL, url).groups() - url = 'http://%s/%s' % (mobj.group('host'), video_id) + url = 'https://%s/' % host + ('embed-%s.html' % video_id if host in ('govid.me', 'vidlo.us') else video_id) webpage = self._download_webpage(url, video_id) if any(re.search(p, webpage) for p in self._FILE_NOT_FOUND_REGEXES): @@ -142,7 +100,7 @@ class XFileShareIE(InfoExtractor): fields = self._hidden_inputs(webpage) - if fields['op'] == 'download1': + if fields.get('op') == 'download1': countdown = int_or_none(self._search_regex( r'<span id="countdown_str">(?:[Ww]ait)?\s*<span id="cxc">(\d+)</span>\s*(?:seconds?)?</span>', webpage, 'countdown', default=None)) @@ -160,13 +118,37 @@ class XFileShareIE(InfoExtractor): (r'style="z-index: [0-9]+;">([^<]+)</span>', r'<td nowrap>([^<]+)</td>', r'h4-fine[^>]*>([^<]+)<', - r'>Watch (.+) ', + r'>Watch (.+)[ <]', r'<h2 class="video-page-head">([^<]+)</h2>', - r'<h2 style="[^"]*color:#403f3d[^"]*"[^>]*>([^<]+)<'), # streamin.to + r'<h2 style="[^"]*color:#403f3d[^"]*"[^>]*>([^<]+)<', # streamin.to + r'title\s*:\s*"([^"]+)"'), # govid.me webpage, 'title', default=None) or self._og_search_title( webpage, default=None) or video_id).strip() - def extract_formats(default=NO_DEFAULT): + for regex, func in ( + (r'(eval\(function\(p,a,c,k,e,d\){.+)', decode_packed_codes), + (r'(ﾟ.+)', aa_decode)): + obf_code = self._search_regex(regex, webpage, 'obfuscated code', default=None) + if obf_code: + webpage = webpage.replace(obf_code, func(obf_code)) + + formats = [] + + jwplayer_data = self._search_regex( + [ + r'jwplayer\("[^"]+"\)\.load\(\[({.+?})\]\);', + r'jwplayer\("[^"]+"\)\.setup\(({.+?})\);', + ], webpage, + 'jwplayer data', default=None) + if jwplayer_data: + jwplayer_data = self._parse_json( + jwplayer_data.replace(r"\'", "'"), video_id, js_to_json) + if jwplayer_data: + formats = self._parse_jwplayer_data( + jwplayer_data, video_id, False, + m3u8_id='hls', mpd_id='dash')['formats'] + + if not formats: urls = [] for regex in ( r'(?:file|src)\s*:\s*(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1', @@ -177,6 +159,12 @@ class XFileShareIE(InfoExtractor): video_url = mobj.group('url') if video_url not in urls: urls.append(video_url) + + sources = self._search_regex( + r'sources\s*:\s*(\[(?!{)[^\]]+\])', webpage, 'sources', default=None) + if sources: + urls.extend(self._parse_json(sources, video_id)) + formats = [] for video_url in urls: if determine_ext(video_url) == 'm3u8': @@ -189,21 +177,13 @@ class XFileShareIE(InfoExtractor): 'url': video_url, 'format_id': 'sd', }) - if not formats and default is not NO_DEFAULT: - return default - self._sort_formats(formats) - return formats - - formats = extract_formats(default=None) - - if not formats: - webpage = decode_packed_codes(self._search_regex( - r"(}\('(.+)',(\d+),(\d+),'[^']*\b(?:file|embed)\b[^']*'\.split\('\|'\))", - webpage, 'packed code')) - formats = extract_formats() + self._sort_formats(formats) thumbnail = self._search_regex( - r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', default=None) + [ + r'<video[^>]+poster="([^"]+)"', + r'(?:image|poster)\s*:\s*["\'](http[^"\']+)["\'],', + ], webpage, 'thumbnail', default=None) return { 'id': video_id, From 34e3885bc9e3aecab104b96eabce03854ac8f7a2 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Thu, 17 Oct 2019 15:55:44 +0100 Subject: [PATCH 18/65] [viewster->contv] remove viewster extractor and add support for contv.com --- youtube_dl/extractor/contv.py | 118 ++++++++++++++++ youtube_dl/extractor/extractors.py | 2 +- youtube_dl/extractor/viewster.py | 217 ----------------------------- 3 files changed, 119 insertions(+), 218 deletions(-) create mode 100644 youtube_dl/extractor/contv.py delete mode 100644 youtube_dl/extractor/viewster.py diff --git a/youtube_dl/extractor/contv.py b/youtube_dl/extractor/contv.py new file mode 100644 index 000000000..84b462d40 --- /dev/null +++ b/youtube_dl/extractor/contv.py @@ -0,0 +1,118 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + float_or_none, + int_or_none, +) + + +class CONtvIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?contv\.com/details-movie/(?P<id>[^/]+)' + _TESTS = [{ + 'url': 'https://www.contv.com/details-movie/CEG10022949/days-of-thrills-&-laughter', + 'info_dict': { + 'id': 'CEG10022949', + 'ext': 'mp4', + 'title': 'Days Of Thrills & Laughter', + 'description': 'md5:5d6b3d0b1829bb93eb72898c734802eb', + 'upload_date': '20180703', + 'timestamp': 1530634789.61, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + 'url': 'https://www.contv.com/details-movie/CLIP-show_fotld_bts/fight-of-the-living-dead:-behind-the-scenes-bites', + 'info_dict': { + 'id': 'CLIP-show_fotld_bts', + 'title': 'Fight of the Living Dead: Behind the Scenes Bites', + }, + 'playlist_mincount': 7, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + details = self._download_json( + 'http://metax.contv.live.junctiontv.net/metax/2.5/details/' + video_id, + video_id, query={'device': 'web'}) + + if details.get('type') == 'episodic': + seasons = self._download_json( + 'http://metax.contv.live.junctiontv.net/metax/2.5/seriesfeed/json/' + video_id, + video_id) + entries = [] + for season in seasons: + for episode in season.get('episodes', []): + episode_id = episode.get('id') + if not episode_id: + continue + entries.append(self.url_result( + 'https://www.contv.com/details-movie/' + episode_id, + CONtvIE.ie_key(), episode_id)) + return self.playlist_result(entries, video_id, details.get('title')) + + m_details = details['details'] + title = details['title'] + + formats = [] + + media_hls_url = m_details.get('media_hls_url') + if media_hls_url: + formats.extend(self._extract_m3u8_formats( + media_hls_url, video_id, 'mp4', + m3u8_id='hls', fatal=False)) + + media_mp4_url = m_details.get('media_mp4_url') + if media_mp4_url: + formats.append({ + 'format_id': 'http', + 'url': media_mp4_url, + }) + + self._sort_formats(formats) + + subtitles = {} + captions = m_details.get('captions') or {} + for caption_url in captions.values(): + subtitles.setdefault('en', []).append({ + 'url': caption_url + }) + + thumbnails = [] + for image in m_details.get('images', []): + image_url = image.get('url') + if not image_url: + continue + thumbnails.append({ + 'url': image_url, + 'width': int_or_none(image.get('width')), + 'height': int_or_none(image.get('height')), + }) + + description = None + for p in ('large_', 'medium_', 'small_', ''): + d = m_details.get(p + 'description') + if d: + description = d + break + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnails': thumbnails, + 'description': description, + 'timestamp': float_or_none(details.get('metax_added_on'), 1000), + 'subtitles': subtitles, + 'duration': float_or_none(m_details.get('duration'), 1000), + 'view_count': int_or_none(details.get('num_watched')), + 'like_count': int_or_none(details.get('num_fav')), + 'categories': details.get('category'), + 'tags': details.get('tags'), + 'season_number': int_or_none(details.get('season')), + 'episode_number': int_or_none(details.get('episode')), + 'release_year': int_or_none(details.get('pub_year')), + } diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index ea47b99f6..1db21529f 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -231,6 +231,7 @@ from .commonprotocols import ( RtmpIE, ) from .condenast import CondeNastIE +from .contv import CONtvIE from .corus import CorusIE from .cracked import CrackedIE from .crackle import CrackleIE @@ -1322,7 +1323,6 @@ from .viewlift import ( ViewLiftIE, ViewLiftEmbedIE, ) -from .viewster import ViewsterIE from .viidea import ViideaIE from .vimeo import ( VimeoIE, diff --git a/youtube_dl/extractor/viewster.py b/youtube_dl/extractor/viewster.py deleted file mode 100644 index 6e318479c..000000000 --- a/youtube_dl/extractor/viewster.py +++ /dev/null @@ -1,217 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..compat import ( - compat_HTTPError, - compat_urllib_parse_unquote, -) -from ..utils import ( - determine_ext, - ExtractorError, - int_or_none, - parse_iso8601, - sanitized_Request, - HEADRequest, - url_basename, -) - - -class ViewsterIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?viewster\.com/(?:serie|movie)/(?P<id>\d+-\d+-\d+)' - _TESTS = [{ - # movie, Type=Movie - 'url': 'http://www.viewster.com/movie/1140-11855-000/the-listening-project/', - 'md5': 'e642d1b27fcf3a4ffa79f194f5adde36', - 'info_dict': { - 'id': '1140-11855-000', - 'ext': 'mp4', - 'title': 'The listening Project', - 'description': 'md5:bac720244afd1a8ea279864e67baa071', - 'timestamp': 1214870400, - 'upload_date': '20080701', - 'duration': 4680, - }, - }, { - # series episode, Type=Episode - 'url': 'http://www.viewster.com/serie/1284-19427-001/the-world-and-a-wall/', - 'md5': '9243079a8531809efe1b089db102c069', - 'info_dict': { - 'id': '1284-19427-001', - 'ext': 'mp4', - 'title': 'The World and a Wall', - 'description': 'md5:24814cf74d3453fdf5bfef9716d073e3', - 'timestamp': 1428192000, - 'upload_date': '20150405', - 'duration': 1500, - }, - }, { - # serie, Type=Serie - 'url': 'http://www.viewster.com/serie/1303-19426-000/', - 'info_dict': { - 'id': '1303-19426-000', - 'title': 'Is It Wrong to Try to Pick up Girls in a Dungeon?', - 'description': 'md5:eeda9bef25b0d524b3a29a97804c2f11', - }, - 'playlist_count': 13, - }, { - # unfinished serie, no Type - 'url': 'http://www.viewster.com/serie/1284-19427-000/baby-steps-season-2/', - 'info_dict': { - 'id': '1284-19427-000', - 'title': 'Baby Steps—Season 2', - 'description': 'md5:e7097a8fc97151e25f085c9eb7a1cdb1', - }, - 'playlist_mincount': 16, - }, { - # geo restricted series - 'url': 'https://www.viewster.com/serie/1280-18794-002/', - 'only_matching': True, - }, { - # geo restricted video - 'url': 'https://www.viewster.com/serie/1280-18794-002/what-is-extraterritoriality-lawo/', - 'only_matching': True, - }] - - _ACCEPT_HEADER = 'application/json, text/javascript, */*; q=0.01' - - def _download_json(self, url, video_id, note='Downloading JSON metadata', fatal=True, query={}): - request = sanitized_Request(url) - request.add_header('Accept', self._ACCEPT_HEADER) - request.add_header('Auth-token', self._AUTH_TOKEN) - return super(ViewsterIE, self)._download_json(request, video_id, note, fatal=fatal, query=query) - - def _real_extract(self, url): - video_id = self._match_id(url) - # Get 'api_token' cookie - self._request_webpage( - HEADRequest('http://www.viewster.com/'), - video_id, headers=self.geo_verification_headers()) - cookies = self._get_cookies('http://www.viewster.com/') - self._AUTH_TOKEN = compat_urllib_parse_unquote(cookies['api_token'].value) - - info = self._download_json( - 'https://public-api.viewster.com/search/%s' % video_id, - video_id, 'Downloading entry JSON') - - entry_id = info.get('Id') or info['id'] - - # unfinished serie has no Type - if info.get('Type') in ('Serie', None): - try: - episodes = self._download_json( - 'https://public-api.viewster.com/series/%s/episodes' % entry_id, - video_id, 'Downloading series JSON') - except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404: - self.raise_geo_restricted() - else: - raise - entries = [ - self.url_result( - 'http://www.viewster.com/movie/%s' % episode['OriginId'], 'Viewster') - for episode in episodes] - title = (info.get('Title') or info['Synopsis']['Title']).strip() - description = info.get('Synopsis', {}).get('Detailed') - return self.playlist_result(entries, video_id, title, description) - - formats = [] - for language_set in info.get('LanguageSets', []): - manifest_url = None - m3u8_formats = [] - audio = language_set.get('Audio') or '' - subtitle = language_set.get('Subtitle') or '' - base_format_id = audio - if subtitle: - base_format_id += '-%s' % subtitle - - def concat(suffix, sep='-'): - return (base_format_id + '%s%s' % (sep, suffix)) if base_format_id else suffix - - medias = self._download_json( - 'https://public-api.viewster.com/movies/%s/videos' % entry_id, - video_id, fatal=False, query={ - 'mediaTypes': ['application/f4m+xml', 'application/x-mpegURL', 'video/mp4'], - 'language': audio, - 'subtitle': subtitle, - }) - if not medias: - continue - for media in medias: - video_url = media.get('Uri') - if not video_url: - continue - ext = determine_ext(video_url) - if ext == 'f4m': - manifest_url = video_url - video_url += '&' if '?' in video_url else '?' - video_url += 'hdcore=3.2.0&plugin=flowplayer-3.2.0.1' - formats.extend(self._extract_f4m_formats( - video_url, video_id, f4m_id=concat('hds'))) - elif ext == 'm3u8': - manifest_url = video_url - m3u8_formats = self._extract_m3u8_formats( - video_url, video_id, 'mp4', m3u8_id=concat('hls'), - fatal=False) # m3u8 sometimes fail - if m3u8_formats: - formats.extend(m3u8_formats) - else: - qualities_basename = self._search_regex( - r'/([^/]+)\.csmil/', - manifest_url, 'qualities basename', default=None) - if not qualities_basename: - continue - QUALITIES_RE = r'((,\d+k)+,?)' - qualities = self._search_regex( - QUALITIES_RE, qualities_basename, - 'qualities', default=None) - if not qualities: - continue - qualities = list(map(lambda q: int(q[:-1]), qualities.strip(',').split(','))) - qualities.sort() - http_template = re.sub(QUALITIES_RE, r'%dk', qualities_basename) - http_url_basename = url_basename(video_url) - if m3u8_formats: - self._sort_formats(m3u8_formats) - m3u8_formats = list(filter( - lambda f: f.get('vcodec') != 'none', m3u8_formats)) - if len(qualities) == len(m3u8_formats): - for q, m3u8_format in zip(qualities, m3u8_formats): - f = m3u8_format.copy() - f.update({ - 'url': video_url.replace(http_url_basename, http_template % q), - 'format_id': f['format_id'].replace('hls', 'http'), - 'protocol': 'http', - }) - formats.append(f) - else: - for q in qualities: - formats.append({ - 'url': video_url.replace(http_url_basename, http_template % q), - 'ext': 'mp4', - 'format_id': 'http-%d' % q, - 'tbr': q, - }) - - if not formats and not info.get('VODSettings'): - self.raise_geo_restricted() - - self._sort_formats(formats) - - synopsis = info.get('Synopsis') or {} - # Prefer title outside synopsis since it's less messy - title = (info.get('Title') or synopsis['Title']).strip() - description = synopsis.get('Detailed') or (info.get('Synopsis') or {}).get('Short') - duration = int_or_none(info.get('Duration')) - timestamp = parse_iso8601(info.get('ReleaseDate')) - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'timestamp': timestamp, - 'duration': duration, - 'formats': formats, - } From 824fa51165d92ceee01589bf995ebbf009df328c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Fri, 18 Oct 2019 04:03:53 +0700 Subject: [PATCH 19/65] [utils] Improve subtitles_filename (closes #22753) --- test/test_utils.py | 6 ++++++ youtube_dl/YoutubeDL.py | 2 +- youtube_dl/postprocessor/ffmpeg.py | 8 ++++---- youtube_dl/utils.py | 4 ++-- 4 files changed, 13 insertions(+), 7 deletions(-) diff --git a/test/test_utils.py b/test/test_utils.py index 659c6ece5..3920542bb 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -74,6 +74,7 @@ from youtube_dl.utils import ( str_to_int, strip_jsonp, strip_or_none, + subtitles_filename, timeconvert, unescapeHTML, unified_strdate, @@ -261,6 +262,11 @@ class TestUtil(unittest.TestCase): self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp') self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp') + def test_subtitles_filename(self): + self.assertEqual(subtitles_filename('abc.ext', 'en', 'vtt'), 'abc.en.vtt') + self.assertEqual(subtitles_filename('abc.ext', 'en', 'vtt', 'ext'), 'abc.en.vtt') + self.assertEqual(subtitles_filename('abc.unexpected_ext', 'en', 'vtt', 'ext'), 'abc.unexpected_ext.en.vtt') + def test_remove_start(self): self.assertEqual(remove_start(None, 'A - '), None) self.assertEqual(remove_start('A - B', 'A - '), 'B') diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index c3d1407f9..f5cb46308 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -1814,7 +1814,7 @@ class YoutubeDL(object): ie = self.get_info_extractor(info_dict['extractor_key']) for sub_lang, sub_info in subtitles.items(): sub_format = sub_info['ext'] - sub_filename = subtitles_filename(filename, sub_lang, sub_format) + sub_filename = subtitles_filename(filename, sub_lang, sub_format, info_dict.get('ext')) if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(sub_filename)): self.to_screen('[info] Video subtitle %s.%s is already present' % (sub_lang, sub_format)) else: diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index 70416c25e..fd3f921a8 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -393,7 +393,7 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor): sub_ext = sub_info['ext'] if ext != 'webm' or ext == 'webm' and sub_ext == 'vtt': sub_langs.append(lang) - sub_filenames.append(subtitles_filename(filename, lang, sub_ext)) + sub_filenames.append(subtitles_filename(filename, lang, sub_ext, ext)) else: if not webm_vtt_warn and ext == 'webm' and sub_ext != 'vtt': webm_vtt_warn = True @@ -606,9 +606,9 @@ class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor): self._downloader.to_screen( '[ffmpeg] Subtitle file for %s is already in the requested format' % new_ext) continue - old_file = subtitles_filename(filename, lang, ext) + old_file = subtitles_filename(filename, lang, ext, info.get('ext')) sub_filenames.append(old_file) - new_file = subtitles_filename(filename, lang, new_ext) + new_file = subtitles_filename(filename, lang, new_ext, info.get('ext')) if ext in ('dfxp', 'ttml', 'tt'): self._downloader.report_warning( @@ -616,7 +616,7 @@ class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor): 'which results in style information loss') dfxp_file = old_file - srt_file = subtitles_filename(filename, lang, 'srt') + srt_file = subtitles_filename(filename, lang, 'srt', info.get('ext')) with open(dfxp_file, 'rb') as f: srt_data = dfxp2srt(f.read()) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 798757241..53117ea90 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -2906,8 +2906,8 @@ def determine_ext(url, default_ext='unknown_video'): return default_ext -def subtitles_filename(filename, sub_lang, sub_format): - return filename.rsplit('.', 1)[0] + '.' + sub_lang + '.' + sub_format +def subtitles_filename(filename, sub_lang, sub_format, expected_real_ext=None): + return replace_extension(filename, sub_lang + '.' + sub_format, expected_real_ext) def date_from_str(date_str): From 2297c0d7d977921dca865e6c9cbc7ee5282ba8ef Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 19 Oct 2019 23:56:36 +0700 Subject: [PATCH 20/65] [facebook] Bypass download rate limits (closes #21018) --- youtube_dl/extractor/facebook.py | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index a3dcdca3e..a56f85c21 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -405,6 +405,11 @@ class FacebookIE(InfoExtractor): if not formats: raise ExtractorError('Cannot find video formats') + # Downloads with browser's User-Agent are rate limited. Working around + # with non-browser User-Agent. + for f in formats: + f.setdefault('http_headers', {})['User-Agent'] = 'facebookexternalhit/1.1' + self._sort_formats(formats) video_title = self._html_search_regex( From b4818e3c7a718428d3366c34da8e21e2f416f5e0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 22 Oct 2019 00:02:22 +0700 Subject: [PATCH 21/65] [ChangeLog] Actualize [ci skip] --- ChangeLog | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/ChangeLog b/ChangeLog index dc5c32a1f..045349b05 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,26 @@ +version <unreleased> + +Core +* [utils] Improve subtitles_filename (#22753) + +Extractors +* [facebook] Bypass download rate limits (#21018) ++ [contv] Add support for contv.com +- [viewster] Remove extractor +* [xfileshare] Improve extractor (#17032, #17906, #18237, #18239) + * Update the list of domains + + Add support for aa-encoded video data + * Improve jwplayer format extraction + + Add support for Clappr sources +* [mangomolo] Fix video format extraction and add support for player URLs +* [audioboom] Improve metadata extraction +* [twitch] Update VOD URL matching (#22395, #22727) +- [mit] Remove support for video.mit.edu (#22403) +- [servingsys] Remove extractor (#22639) +* [dumpert] Fix extraction (#22428, #22564) +* [atresplayer] Fix extraction (#16277, #16716) + + version 2019.10.16 Core From 820215f0e34813089d559fed24a398d9e91810e0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Tue, 22 Oct 2019 00:09:02 +0700 Subject: [PATCH 22/65] release 2019.10.22 --- .github/ISSUE_TEMPLATE/1_broken_site.md | 6 +++--- .github/ISSUE_TEMPLATE/2_site_support_request.md | 4 ++-- .github/ISSUE_TEMPLATE/3_site_feature_request.md | 4 ++-- .github/ISSUE_TEMPLATE/4_bug_report.md | 6 +++--- .github/ISSUE_TEMPLATE/5_feature_request.md | 4 ++-- ChangeLog | 2 +- docs/supportedsites.md | 6 ++---- youtube_dl/version.py | 2 +- 8 files changed, 16 insertions(+), 18 deletions(-) diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.md b/.github/ISSUE_TEMPLATE/1_broken_site.md index 5cd9f0dc0..f1afe704c 100644 --- a/.github/ISSUE_TEMPLATE/1_broken_site.md +++ b/.github/ISSUE_TEMPLATE/1_broken_site.md @@ -18,7 +18,7 @@ title: '' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.16. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.22. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape. - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates. @@ -26,7 +26,7 @@ Carefully read and work through this check list in order to prevent the most com --> - [ ] I'm reporting a broken site support -- [ ] I've verified that I'm running youtube-dl version **2019.10.16** +- [ ] I've verified that I'm running youtube-dl version **2019.10.22** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar issues including closed ones @@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.10.16 + [debug] youtube-dl version 2019.10.22 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/2_site_support_request.md b/.github/ISSUE_TEMPLATE/2_site_support_request.md index 6cc34796a..a4dc9b005 100644 --- a/.github/ISSUE_TEMPLATE/2_site_support_request.md +++ b/.github/ISSUE_TEMPLATE/2_site_support_request.md @@ -19,7 +19,7 @@ labels: 'site-support-request' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.16. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.22. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that site you are requesting is not dedicated to copyright infringement, see https://yt-dl.org/copyright-infringement. youtube-dl does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights. - Search the bugtracker for similar site support requests: http://yt-dl.org/search-issues. DO NOT post duplicates. @@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com --> - [ ] I'm reporting a new site support request -- [ ] I've verified that I'm running youtube-dl version **2019.10.16** +- [ ] I've verified that I'm running youtube-dl version **2019.10.22** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that none of provided URLs violate any copyrights - [ ] I've searched the bugtracker for similar site support requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/3_site_feature_request.md b/.github/ISSUE_TEMPLATE/3_site_feature_request.md index 0b7911e79..5bf86adce 100644 --- a/.github/ISSUE_TEMPLATE/3_site_feature_request.md +++ b/.github/ISSUE_TEMPLATE/3_site_feature_request.md @@ -18,13 +18,13 @@ title: '' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.16. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.22. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Search the bugtracker for similar site feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates. - Finally, put x into all relevant boxes (like this [x]) --> - [ ] I'm reporting a site feature request -- [ ] I've verified that I'm running youtube-dl version **2019.10.16** +- [ ] I've verified that I'm running youtube-dl version **2019.10.22** - [ ] I've searched the bugtracker for similar site feature requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/4_bug_report.md b/.github/ISSUE_TEMPLATE/4_bug_report.md index a6f417d38..7aa5534e5 100644 --- a/.github/ISSUE_TEMPLATE/4_bug_report.md +++ b/.github/ISSUE_TEMPLATE/4_bug_report.md @@ -18,7 +18,7 @@ title: '' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.16. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.22. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser. - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape. - Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates. @@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com --> - [ ] I'm reporting a broken site support issue -- [ ] I've verified that I'm running youtube-dl version **2019.10.16** +- [ ] I've verified that I'm running youtube-dl version **2019.10.22** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar bug reports including closed ones @@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.10.16 + [debug] youtube-dl version 2019.10.22 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/5_feature_request.md b/.github/ISSUE_TEMPLATE/5_feature_request.md index 3fe753b62..5d3645e3d 100644 --- a/.github/ISSUE_TEMPLATE/5_feature_request.md +++ b/.github/ISSUE_TEMPLATE/5_feature_request.md @@ -19,13 +19,13 @@ labels: 'request' <!-- Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl: -- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.16. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. +- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.22. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED. - Search the bugtracker for similar feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates. - Finally, put x into all relevant boxes (like this [x]) --> - [ ] I'm reporting a feature request -- [ ] I've verified that I'm running youtube-dl version **2019.10.16** +- [ ] I've verified that I'm running youtube-dl version **2019.10.22** - [ ] I've searched the bugtracker for similar feature requests including closed ones diff --git a/ChangeLog b/ChangeLog index 045349b05..64233b03b 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version <unreleased> +version 2019.10.22 Core * [utils] Improve subtitles_filename (#22753) diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 0cbad28ea..a1b0edeeb 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -183,6 +183,7 @@ - **ComedyCentralShortname** - **ComedyCentralTV** - **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED + - **CONtv** - **Corus** - **Coub** - **Cracked** @@ -784,7 +785,6 @@ - **Seeker** - **SenateISVP** - **SendtoNews** - - **ServingSys** - **Servus** - **Sexu** - **SeznamZpravy** @@ -1005,7 +1005,6 @@ - **Viddler** - **Videa** - **video.google:search**: Google Video search - - **video.mit.edu** - **VideoDetective** - **videofy.me** - **videomore** @@ -1023,7 +1022,6 @@ - **vier:videos** - **ViewLift** - **ViewLiftEmbed** - - **Viewster** - **Viidea** - **viki** - **viki:channel** @@ -1097,7 +1095,7 @@ - **WWE** - **XBef** - **XboxClips** - - **XFileShare**: XFileShare based sites: DaClips, FileHoot, GorillaVid, MovPod, PowerWatch, Rapidvideo.ws, TheVideoBee, Vidto, Streamin.To, XVIDSTAGE, Vid ABC, VidBom, vidlo, RapidVideo.TV, FastVideo.me + - **XFileShare**: XFileShare based sites: ClipWatching, GoUnlimited, GoVid, HolaVid, Streamty, TheVideoBee, Uqload, VidBom, vidlo, VidLocker, VidShare, VUp, XVideoSharing - **XHamster** - **XHamsterEmbed** - **XHamsterUser** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 53889b7cb..39b355b9e 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.10.16' +__version__ = '2019.10.22' From 0c2d10d225f61ac1fb534d8ed1788250401465b2 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Tue, 22 Oct 2019 17:49:50 +0100 Subject: [PATCH 23/65] [globo] handle alternative hash signing method --- youtube_dl/extractor/globo.py | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/globo.py b/youtube_dl/extractor/globo.py index 9ad1d95fb..60d842d3a 100644 --- a/youtube_dl/extractor/globo.py +++ b/youtube_dl/extractor/globo.py @@ -132,18 +132,24 @@ class GloboIE(InfoExtractor): '%s returned error: %s' % (self.IE_NAME, message), expected=True) continue - assert security_hash[:2] in ('04', '14') - received_time = security_hash[3:13] - received_md5 = security_hash[24:] - - sign_time = compat_str(int(received_time) + 86400) + hash_code = security_hash[:2] padding = '%010d' % random.randint(1, 10000000000) + if hash_code in ('04', '14'): + received_time = security_hash[3:13] + received_md5 = security_hash[24:] + hash_prefix = security_hash[:23] + elif hash_code in ('02', '12', '03', '13'): + received_time = security_hash[2:12] + received_md5 = security_hash[22:] + padding += '1' + hash_prefix = '05' + security_hash[:22] - md5_data = (received_md5 + sign_time + padding + '0xAC10FD').encode() + padded_sign_time = compat_str(int(received_time) + 86400) + padding + md5_data = (received_md5 + padded_sign_time + '0xAC10FD').encode() signed_md5 = base64.urlsafe_b64encode(hashlib.md5(md5_data).digest()).decode().strip('=') - signed_hash = security_hash[:23] + sign_time + padding + signed_md5 - + signed_hash = hash_prefix + padded_sign_time + signed_md5 signed_url = '%s?h=%s&k=html5&a=%s&u=%s' % (resource_url, signed_hash, 'F' if video.get('subscriber_only') else 'A', security.get('user') or '') + if resource_id.endswith('m3u8') or resource_url.endswith('.m3u8'): formats.extend(self._extract_m3u8_formats( signed_url, resource_id, 'mp4', entry_protocol='m3u8_native', From 07154c793065bca816793186590d8d6461e07478 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Tue, 22 Oct 2019 17:53:47 +0100 Subject: [PATCH 24/65] [facebook] extract subtitles(closes #22777) --- youtube_dl/extractor/ceskatelevize.py | 2 ++ youtube_dl/extractor/facebook.py | 5 +++++ 2 files changed, 7 insertions(+) diff --git a/youtube_dl/extractor/ceskatelevize.py b/youtube_dl/extractor/ceskatelevize.py index 1ec58f7d8..7cb4efb74 100644 --- a/youtube_dl/extractor/ceskatelevize.py +++ b/youtube_dl/extractor/ceskatelevize.py @@ -147,6 +147,8 @@ class CeskaTelevizeIE(InfoExtractor): is_live = item.get('type') == 'LIVE' formats = [] for format_id, stream_url in item.get('streamUrls', {}).items(): + if 'drmOnly=true' in stream_url: + continue if 'playerType=flash' in stream_url: stream_formats = self._extract_m3u8_formats( stream_url, playlist_id, 'mp4', 'm3u8_native', diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index a56f85c21..c723726b7 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -379,6 +379,7 @@ class FacebookIE(InfoExtractor): if not video_data: raise ExtractorError('Cannot parse data') + subtitles = {} formats = [] for f in video_data: format_id = f['stream_type'] @@ -402,6 +403,9 @@ class FacebookIE(InfoExtractor): if dash_manifest: formats.extend(self._parse_mpd_formats( compat_etree_fromstring(compat_urllib_parse_unquote_plus(dash_manifest)))) + subtitles_src = f[0].get('subtitles_src') + if subtitles_src: + subtitles.setdefault('en', []).append({'url': subtitles_src}) if not formats: raise ExtractorError('Cannot find video formats') @@ -447,6 +451,7 @@ class FacebookIE(InfoExtractor): 'timestamp': timestamp, 'thumbnail': thumbnail, 'view_count': view_count, + 'subtitles': subtitles, } return webpage, info_dict From 162bcc68dc73706699b559fffdd8bed3db6643b9 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Thu, 24 Oct 2019 12:53:33 +0100 Subject: [PATCH 25/65] [puhutv] improve extraction - fix subtitles extraction - transform HLS URLs to http URLs - improve metadata extraction --- youtube_dl/extractor/puhutv.py | 90 ++++++++++++++++++---------------- 1 file changed, 49 insertions(+), 41 deletions(-) diff --git a/youtube_dl/extractor/puhutv.py b/youtube_dl/extractor/puhutv.py index 5465e8ab7..fb704a3c4 100644 --- a/youtube_dl/extractor/puhutv.py +++ b/youtube_dl/extractor/puhutv.py @@ -25,21 +25,21 @@ class PuhuTVIE(InfoExtractor): _TESTS = [{ # film 'url': 'https://puhutv.com/sut-kardesler-izle', - 'md5': 'fbd8f2d8e7681f8bcd51b592475a6ae7', + 'md5': 'a347470371d56e1585d1b2c8dab01c96', 'info_dict': { 'id': '5085', 'display_id': 'sut-kardesler', 'ext': 'mp4', 'title': 'Süt Kardeşler', - 'description': 'md5:405fd024df916ca16731114eb18e511a', + 'description': 'md5:ca09da25b7e57cbb5a9280d6e48d17aa', 'thumbnail': r're:^https?://.*\.jpg$', 'duration': 4832.44, 'creator': 'Arzu Film', - 'timestamp': 1469778212, - 'upload_date': '20160729', + 'timestamp': 1561062602, + 'upload_date': '20190620', 'release_year': 1976, 'view_count': int, - 'tags': ['Aile', 'Komedi', 'Klasikler'], + 'tags': list, }, }, { # episode, geo restricted, bypassable with --geo-verification-proxy @@ -64,9 +64,10 @@ class PuhuTVIE(InfoExtractor): display_id)['data'] video_id = compat_str(info['id']) - title = info.get('name') or info['title']['name'] + show = info.get('title') or {} + title = info.get('name') or show['name'] if info.get('display_name'): - title = '%s %s' % (title, info.get('display_name')) + title = '%s %s' % (title, info['display_name']) try: videos = self._download_json( @@ -78,17 +79,36 @@ class PuhuTVIE(InfoExtractor): self.raise_geo_restricted() raise + urls = [] formats = [] + + def add_http_from_hls(m3u8_f): + http_url = m3u8_f['url'].replace('/hls/', '/mp4/').replace('/chunklist.m3u8', '.mp4') + if http_url != m3u8_f['url']: + f = m3u8_f.copy() + f.update({ + 'format_id': f['format_id'].replace('hls', 'http'), + 'protocol': 'http', + 'url': http_url, + }) + formats.append(f) + for video in videos['data']['videos']: media_url = url_or_none(video.get('url')) - if not media_url: + if not media_url or media_url in urls: continue + urls.append(media_url) + playlist = video.get('is_playlist') - if video.get('stream_type') == 'hls' and playlist is True: - formats.extend(self._extract_m3u8_formats( + if (video.get('stream_type') == 'hls' and playlist is True) or 'playlist.m3u8' in media_url: + m3u8_formats = self._extract_m3u8_formats( media_url, video_id, 'mp4', entry_protocol='m3u8_native', - m3u8_id='hls', fatal=False)) + m3u8_id='hls', fatal=False) + for m3u8_f in m3u8_formats: + formats.append(m3u8_f) + add_http_from_hls(m3u8_f) continue + quality = int_or_none(video.get('quality')) f = { 'url': media_url, @@ -96,34 +116,29 @@ class PuhuTVIE(InfoExtractor): 'height': quality } video_format = video.get('video_format') - if video_format == 'hls' and playlist is False: + is_hls = (video_format == 'hls' or '/hls/' in media_url or '/chunklist.m3u8' in media_url) and playlist is False + if is_hls: format_id = 'hls' f['protocol'] = 'm3u8_native' elif video_format == 'mp4': format_id = 'http' - else: continue if quality: format_id += '-%sp' % quality f['format_id'] = format_id formats.append(f) + if is_hls: + add_http_from_hls(f) self._sort_formats(formats) - description = try_get( - info, lambda x: x['title']['description'], - compat_str) or info.get('description') - timestamp = unified_timestamp(info.get('created_at')) creator = try_get( - info, lambda x: x['title']['producer']['name'], compat_str) + show, lambda x: x['producer']['name'], compat_str) - duration = float_or_none( - try_get(info, lambda x: x['content']['duration_in_ms'], int), - scale=1000) - view_count = try_get(info, lambda x: x['content']['watch_count'], int) + content = info.get('content') or {} images = try_get( - info, lambda x: x['content']['images']['wide'], dict) or {} + content, lambda x: x['images']['wide'], dict) or {} thumbnails = [] for image_id, image_url in images.items(): if not isinstance(image_url, compat_str): @@ -137,14 +152,8 @@ class PuhuTVIE(InfoExtractor): }) thumbnails.append(t) - release_year = try_get(info, lambda x: x['title']['released_at'], int) - - season_number = int_or_none(info.get('season_number')) - season_id = str_or_none(info.get('season_id')) - episode_number = int_or_none(info.get('episode_number')) - tags = [] - for genre in try_get(info, lambda x: x['title']['genres'], list) or []: + for genre in show.get('genres') or []: if not isinstance(genre, dict): continue genre_name = genre.get('name') @@ -152,12 +161,11 @@ class PuhuTVIE(InfoExtractor): tags.append(genre_name) subtitles = {} - for subtitle in try_get( - info, lambda x: x['content']['subtitles'], list) or []: + for subtitle in content.get('subtitles') or []: if not isinstance(subtitle, dict): continue lang = subtitle.get('language') - sub_url = url_or_none(subtitle.get('url')) + sub_url = url_or_none(subtitle.get('url') or subtitle.get('file')) if not lang or not isinstance(lang, compat_str) or not sub_url: continue subtitles[self._SUBTITLE_LANGS.get(lang, lang)] = [{ @@ -168,15 +176,15 @@ class PuhuTVIE(InfoExtractor): 'id': video_id, 'display_id': display_id, 'title': title, - 'description': description, - 'season_id': season_id, - 'season_number': season_number, - 'episode_number': episode_number, - 'release_year': release_year, - 'timestamp': timestamp, + 'description': info.get('description') or show.get('description'), + 'season_id': str_or_none(info.get('season_id')), + 'season_number': int_or_none(info.get('season_number')), + 'episode_number': int_or_none(info.get('episode_number')), + 'release_year': int_or_none(show.get('released_at')), + 'timestamp': unified_timestamp(info.get('created_at')), 'creator': creator, - 'view_count': view_count, - 'duration': duration, + 'view_count': int_or_none(content.get('watch_count')), + 'duration': float_or_none(content.get('duration_in_ms'), 1000), 'tags': tags, 'subtitles': subtitles, 'thumbnails': thumbnails, From 416c3ca7f53dab76b9e5ec46a0c0335698252c2d Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Fri, 25 Oct 2019 19:27:28 +0100 Subject: [PATCH 26/65] [odnoklassniki] add support for Schemeless embed extraction --- youtube_dl/extractor/generic.py | 7 ++++--- youtube_dl/extractor/odnoklassniki.py | 9 +++++++++ 2 files changed, 13 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 5ed952b29..f66cae0eb 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -118,6 +118,7 @@ from .foxnews import FoxNewsIE from .viqeo import ViqeoIE from .expressen import ExpressenIE from .zype import ZypeIE +from .odnoklassniki import OdnoklassnikiIE class GenericIE(InfoExtractor): @@ -2627,9 +2628,9 @@ class GenericIE(InfoExtractor): return self.url_result(mobj.group('url'), 'VK') # Look for embedded Odnoklassniki player - mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage) - if mobj is not None: - return self.url_result(mobj.group('url'), 'Odnoklassniki') + odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage) + if odnoklassniki_url: + return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key()) # Look for embedded ivi player mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage) diff --git a/youtube_dl/extractor/odnoklassniki.py b/youtube_dl/extractor/odnoklassniki.py index 114b93c07..7ed9fac55 100644 --- a/youtube_dl/extractor/odnoklassniki.py +++ b/youtube_dl/extractor/odnoklassniki.py @@ -1,6 +1,8 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..compat import ( compat_etree_fromstring, @@ -121,6 +123,13 @@ class OdnoklassnikiIE(InfoExtractor): 'only_matching': True, }] + @staticmethod + def _extract_url(webpage): + mobj = re.search( + r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage) + if mobj: + return mobj.group('url') + def _real_extract(self, url): start_time = int_or_none(compat_parse_qs( compat_urllib_parse_urlparse(url).query).get('fromTime', [None])[0]) From 3c989818e7dc7706da069312bbdd040165a97517 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Fri, 25 Oct 2019 19:35:07 +0100 Subject: [PATCH 27/65] [vk] improve extraction - add support for Odnoklassniki embeds - update tests - extract more video from user lists(closes #4470) - fix wall post audio extraction(closes #18332) - improve error detection(closes #22568) --- youtube_dl/extractor/vk.py | 329 +++++++++++++++++++------------------ 1 file changed, 173 insertions(+), 156 deletions(-) diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index 8b6dc0e24..c289fcad3 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -12,7 +12,6 @@ from ..utils import ( get_element_by_class, int_or_none, orderedSet, - remove_start, str_or_none, str_to_int, unescapeHTML, @@ -21,6 +20,7 @@ from ..utils import ( urlencode_postdata, ) from .dailymotion import DailymotionIE +from .odnoklassniki import OdnoklassnikiIE from .pladform import PladformIE from .vimeo import VimeoIE from .youtube import YoutubeIE @@ -60,6 +60,18 @@ class VKBaseIE(InfoExtractor): def _real_initialize(self): self._login() + def _download_payload(self, path, video_id, data, fatal=True): + data['al'] = 1 + code, payload = self._download_json( + 'https://vk.com/%s.php' % path, video_id, + data=urlencode_postdata(data), fatal=fatal, + headers={'X-Requested-With': 'XMLHttpRequest'})['payload'] + if code == '3': + self.raise_login_required() + elif code == '8': + raise ExtractorError(clean_html(payload[0][1:-1]), expected=True) + return payload + class VKIE(VKBaseIE): IE_NAME = 'vk' @@ -96,7 +108,6 @@ class VKIE(VKBaseIE): }, { 'url': 'http://vk.com/video205387401_165548505', - 'md5': '6c0aeb2e90396ba97035b9cbde548700', 'info_dict': { 'id': '205387401_165548505', 'ext': 'mp4', @@ -110,18 +121,18 @@ class VKIE(VKBaseIE): }, { 'note': 'Embedded video', - 'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1', - 'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a', + 'url': 'https://vk.com/video_ext.php?oid=-77521&id=162222515&hash=87b046504ccd8bfa', + 'md5': '7babad3b85ea2e91948005b1b8b0cb84', 'info_dict': { - 'id': '32194266_162925554', + 'id': '-77521_162222515', 'ext': 'mp4', - 'uploader': 'Vladimir Gavrin', - 'title': 'Lin Dan', - 'duration': 101, - 'upload_date': '20120730', - 'view_count': int, + 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*', + 'title': 'ProtivoGunz - Хуёвая песня', + 'duration': 195, + 'upload_date': '20120212', + 'timestamp': 1329049880, + 'uploader_id': '-77521', }, - 'skip': 'This video has been removed from public access.', }, { # VIDEO NOW REMOVED @@ -138,18 +149,19 @@ class VKIE(VKBaseIE): 'upload_date': '20121218', 'view_count': int, }, - 'skip': 'Requires vk account credentials', + 'skip': 'Removed', }, { 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d', - 'md5': '4d7a5ef8cf114dfa09577e57b2993202', 'info_dict': { 'id': '-43215063_168067957', 'ext': 'mp4', - 'uploader': 'Киномания - лучшее из мира кино', + 'uploader': 'Bro Mazter', 'title': ' ', 'duration': 7291, 'upload_date': '20140328', + 'uploader_id': '223413403', + 'timestamp': 1396018030, }, 'skip': 'Requires vk account credentials', }, @@ -165,7 +177,7 @@ class VKIE(VKBaseIE): 'upload_date': '20140626', 'view_count': int, }, - 'skip': 'Only works from Russia', + 'skip': 'Removed', }, { # video (removed?) only available with list id @@ -247,6 +259,9 @@ class VKIE(VKBaseIE): 'uploader_id': '-387766', 'timestamp': 1475137527, }, + 'params': { + 'skip_download': True, + }, }, { # live stream, hls and rtmp links, most likely already finished live @@ -288,80 +303,94 @@ class VKIE(VKBaseIE): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('videoid') + mv_data = {} if video_id: - info_url = 'https://vk.com/al_video.php?act=show_inline&al=1&video=' + video_id + data = { + 'act': 'show_inline', + 'video': video_id, + } # Some videos (removed?) can only be downloaded with list id specified list_id = mobj.group('list_id') if list_id: - info_url += '&list=%s' % list_id + data['list'] = list_id + + payload = self._download_payload('al_video', video_id, data) + info_page = payload[1] + opts = payload[-1] + mv_data = opts.get('mvData') or {} + player = opts.get('player') or {} else: - info_url = 'http://vk.com/video_ext.php?' + mobj.group('embed_query') video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id')) - info_page = self._download_webpage(info_url, video_id) + info_page = self._download_webpage( + 'http://vk.com/video_ext.php?' + mobj.group('embed_query'), video_id) - error_message = self._html_search_regex( - [r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>', - r'(?s)<div[^>]+id="video_ext_msg"[^>]*>(.+?)</div>'], - info_page, 'error message', default=None) - if error_message: - raise ExtractorError(error_message, expected=True) + error_message = self._html_search_regex( + [r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>', + r'(?s)<div[^>]+id="video_ext_msg"[^>]*>(.+?)</div>'], + info_page, 'error message', default=None) + if error_message: + raise ExtractorError(error_message, expected=True) - if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page): - raise ExtractorError( - 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.', - expected=True) + if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page): + raise ExtractorError( + 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.', + expected=True) - ERROR_COPYRIGHT = 'Video %s has been removed from public access due to rightholder complaint.' + ERROR_COPYRIGHT = 'Video %s has been removed from public access due to rightholder complaint.' - ERRORS = { - r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<': - ERROR_COPYRIGHT, + ERRORS = { + r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<': + ERROR_COPYRIGHT, - r'>The video .*? was removed from public access by request of the copyright holder.<': - ERROR_COPYRIGHT, + r'>The video .*? was removed from public access by request of the copyright holder.<': + ERROR_COPYRIGHT, - r'<!>Please log in or <': - 'Video %s is only available for registered users, ' - 'use --username and --password options to provide account credentials.', + r'<!>Please log in or <': + 'Video %s is only available for registered users, ' + 'use --username and --password options to provide account credentials.', - r'<!>Unknown error': - 'Video %s does not exist.', + r'<!>Unknown error': + 'Video %s does not exist.', - r'<!>Видео временно недоступно': - 'Video %s is temporarily unavailable.', + r'<!>Видео временно недоступно': + 'Video %s is temporarily unavailable.', - r'<!>Access denied': - 'Access denied to video %s.', + r'<!>Access denied': + 'Access denied to video %s.', - r'<!>Видеозапись недоступна, так как её автор был заблокирован.': - 'Video %s is no longer available, because its author has been blocked.', + r'<!>Видеозапись недоступна, так как её автор был заблокирован.': + 'Video %s is no longer available, because its author has been blocked.', - r'<!>This video is no longer available, because its author has been blocked.': - 'Video %s is no longer available, because its author has been blocked.', + r'<!>This video is no longer available, because its author has been blocked.': + 'Video %s is no longer available, because its author has been blocked.', - r'<!>This video is no longer available, because it has been deleted.': - 'Video %s is no longer available, because it has been deleted.', + r'<!>This video is no longer available, because it has been deleted.': + 'Video %s is no longer available, because it has been deleted.', - r'<!>The video .+? is not available in your region.': - 'Video %s is not available in your region.', - } + r'<!>The video .+? is not available in your region.': + 'Video %s is not available in your region.', + } - for error_re, error_msg in ERRORS.items(): - if re.search(error_re, info_page): - raise ExtractorError(error_msg % video_id, expected=True) + for error_re, error_msg in ERRORS.items(): + if re.search(error_re, info_page): + raise ExtractorError(error_msg % video_id, expected=True) + + player = self._parse_json(self._search_regex( + r'var\s+playerParams\s*=\s*({.+?})\s*;\s*\n', + info_page, 'player params'), video_id) youtube_url = YoutubeIE._extract_url(info_page) if youtube_url: - return self.url_result(youtube_url, ie=YoutubeIE.ie_key()) + return self.url_result(youtube_url, YoutubeIE.ie_key()) vimeo_url = VimeoIE._extract_url(url, info_page) if vimeo_url is not None: - return self.url_result(vimeo_url) + return self.url_result(vimeo_url, VimeoIE.ie_key()) pladform_url = PladformIE._extract_url(info_page) if pladform_url: - return self.url_result(pladform_url) + return self.url_result(pladform_url, PladformIE.ie_key()) m_rutube = re.search( r'\ssrc="((?:https?:)?//rutube\.ru\\?/(?:video|play)\\?/embed(?:.*?))\\?"', info_page) @@ -374,6 +403,10 @@ class VKIE(VKBaseIE): if dailymotion_urls: return self.url_result(dailymotion_urls[0], DailymotionIE.ie_key()) + odnoklassniki_url = OdnoklassnikiIE._extract_url(info_page) + if odnoklassniki_url: + return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key()) + m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page) if m_opts: m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1)) @@ -383,38 +416,7 @@ class VKIE(VKBaseIE): opts_url = 'http:' + opts_url return self.url_result(opts_url) - # vars does not look to be served anymore since 24.10.2016 - data = self._parse_json( - self._search_regex( - r'var\s+vars\s*=\s*({.+?});', info_page, 'vars', default='{}'), - video_id, fatal=False) - - # <!json> is served instead - if not data: - data = self._parse_json( - self._search_regex( - [r'<!json>\s*({.+?})\s*<!>', r'<!json>\s*({.+})'], - info_page, 'json', default='{}'), - video_id) - if data: - data = data['player']['params'][0] - - if not data: - data = self._parse_json( - self._search_regex( - r'var\s+playerParams\s*=\s*({.+?})\s*;\s*\n', info_page, - 'player params', default='{}'), - video_id) - if data: - data = data['params'][0] - - # <!--{...} - if not data: - data = self._parse_json( - self._search_regex( - r'<!--\s*({.+})', info_page, 'payload'), - video_id)['payload'][-1][-1]['player']['params'][0] - + data = player['params'][0] title = unescapeHTML(data['md_title']) # 2 = live @@ -463,12 +465,12 @@ class VKIE(VKBaseIE): 'title': title, 'thumbnail': data.get('jpg'), 'uploader': data.get('md_author'), - 'uploader_id': str_or_none(data.get('author_id')), - 'duration': data.get('duration'), + 'uploader_id': str_or_none(data.get('author_id') or mv_data.get('authorId')), + 'duration': int_or_none(data.get('duration') or mv_data.get('duration')), 'timestamp': timestamp, 'view_count': view_count, - 'like_count': int_or_none(data.get('liked')), - 'dislike_count': int_or_none(data.get('nolikes')), + 'like_count': int_or_none(mv_data.get('likes')), + 'comment_count': int_or_none(mv_data.get('commcount')), 'is_live': is_live, } @@ -482,7 +484,6 @@ class VKUserVideosIE(VKBaseIE): 'url': 'http://vk.com/videos205387401', 'info_dict': { 'id': '205387401', - 'title': "Tom Cruise's Videos", }, 'playlist_mincount': 4, }, { @@ -498,22 +499,25 @@ class VKUserVideosIE(VKBaseIE): 'url': 'http://new.vk.com/videos205387401', 'only_matching': True, }] + _VIDEO = collections.namedtuple( + 'Video', ['owner_id', 'id', 'thumb', 'title', 'flags', 'duration', 'hash', 'moder_acts', 'owner', 'date', 'views', 'platform', 'blocked', 'music_video_meta']) def _real_extract(self, url): page_id = self._match_id(url) - webpage = self._download_webpage(url, page_id) + l = self._download_payload('al_video', page_id, { + 'act': 'load_videos_silent', + 'oid': page_id, + })[0]['']['list'] - entries = [ - self.url_result( - 'http://vk.com/video' + video_id, 'VK', video_id=video_id) - for video_id in orderedSet(re.findall(r'href="/video(-?[0-9_]+)"', webpage))] + entries = [] + for video in l: + v = self._VIDEO._make(video) + video_id = '%d_%d' % (v.owner_id, v.id) + entries.append(self.url_result( + 'http://vk.com/video' + video_id, 'VK', video_id=video_id)) - title = unescapeHTML(self._search_regex( - r'<title>\s*([^<]+?)\s+\|\s+\d+\s+videos', - webpage, 'title', default=page_id)) - - return self.playlist_result(entries, page_id, title) + return self.playlist_result(entries, page_id) class VKWallPostIE(VKBaseIE): @@ -523,15 +527,15 @@ class VKWallPostIE(VKBaseIE): # public page URL, audio playlist 'url': 'https://vk.com/bs.official?w=wall-23538238_35', 'info_dict': { - 'id': '23538238_35', - 'title': 'Black Shadow - Wall post 23538238_35', + 'id': '-23538238_35', + 'title': 'Black Shadow - Wall post -23538238_35', 'description': 'md5:3f84b9c4f9ef499731cf1ced9998cc0c', }, 'playlist': [{ 'md5': '5ba93864ec5b85f7ce19a9af4af080f6', 'info_dict': { 'id': '135220665_111806521', - 'ext': 'mp3', + 'ext': 'mp4', 'title': 'Black Shadow - Слепое Верование', 'duration': 370, 'uploader': 'Black Shadow', @@ -542,18 +546,16 @@ class VKWallPostIE(VKBaseIE): 'md5': '4cc7e804579122b17ea95af7834c9233', 'info_dict': { 'id': '135220665_111802303', - 'ext': 'mp3', + 'ext': 'mp4', 'title': 'Black Shadow - Война - Негасимое Бездны Пламя!', 'duration': 423, 'uploader': 'Black Shadow', 'artist': 'Black Shadow', 'track': 'Война - Негасимое Бездны Пламя!', }, - 'params': { - 'skip_download': True, - }, }], 'params': { + 'skip_download': True, 'usenetrc': True, }, 'skip': 'Requires vk account credentials', @@ -562,7 +564,7 @@ class VKWallPostIE(VKBaseIE): 'url': 'https://vk.com/wall85155021_6319', 'info_dict': { 'id': '85155021_6319', - 'title': 'Sergey Gorbunov - Wall post 85155021_6319', + 'title': 'Сергей Горбунов - Wall post 85155021_6319', }, 'playlist_count': 1, 'params': { @@ -578,58 +580,73 @@ class VKWallPostIE(VKBaseIE): 'url': 'https://m.vk.com/wall-23538238_35', 'only_matching': True, }] + _BASE64_CHARS = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMN0PQRSTUVWXYZO123456789+/=' + _AUDIO = collections.namedtuple( + 'Audio', ['id', 'owner_id', 'url', 'title', 'performer', 'duration', 'album_id', 'unk', 'author_link', 'lyrics', 'flags', 'context', 'extra', 'hashes', 'cover_url', 'ads', 'subtitle', 'main_artists', 'feat_artists', 'album', 'track_code', 'restriction', 'album_part', 'new_stats', 'access_key']) + + def _decode(self, enc): + dec = '' + e = n = 0 + for c in enc: + r = self._BASE64_CHARS.index(c) + cond = n % 4 + e = 64 * e + r if cond else r + n += 1 + if cond: + dec += chr(255 & e >> (-2 * n & 6)) + return dec + + def _unmask_url(self, mask_url, vk_id): + if 'audio_api_unavailable' in mask_url: + extra = mask_url.split('?extra=')[1].split('#') + func, base = self._decode(extra[1]).split(chr(11)) + assert (func == 'i') + mask_url = list(self._decode(extra[0])) + url_len = len(mask_url) + indexes = [None] * url_len + index = int(base) ^ vk_id + for n in range(url_len - 1, -1, -1): + index = (url_len * (n + 1) ^ index + n) % url_len + indexes[n] = index + for n in range(1, url_len): + c = mask_url[n] + index = indexes[url_len - 1 - n] + mask_url[n] = mask_url[index] + mask_url[index] = c + mask_url = ''.join(mask_url) + return mask_url def _real_extract(self, url): post_id = self._match_id(url) - wall_url = 'https://vk.com/wall%s' % post_id - - post_id = remove_start(post_id, '-') - - webpage = self._download_webpage(wall_url, post_id) - - error = self._html_search_regex( - r'>Error</div>\s*<div[^>]+class=["\']body["\'][^>]*>([^<]+)', - webpage, 'error', default=None) - if error: - raise ExtractorError('VK said: %s' % error, expected=True) + webpage = self._download_payload('wkview', post_id, { + 'act': 'show', + 'w': 'wall' + post_id, + })[1] description = clean_html(get_element_by_class('wall_post_text', webpage)) uploader = clean_html(get_element_by_class('author', webpage)) - thumbnail = self._og_search_thumbnail(webpage) entries = [] - audio_ids = re.findall(r'data-full-id=["\'](\d+_\d+)', webpage) - if audio_ids: - al_audio = self._download_webpage( - 'https://vk.com/al_audio.php', post_id, - note='Downloading audio info', fatal=False, - data=urlencode_postdata({ - 'act': 'reload_audio', - 'al': '1', - 'ids': ','.join(audio_ids) - })) - if al_audio: - Audio = collections.namedtuple( - 'Audio', ['id', 'user_id', 'url', 'track', 'artist', 'duration']) - audios = self._parse_json( - self._search_regex( - r'<!json>(.+?)<!>', al_audio, 'audios', default='[]'), - post_id, fatal=False, transform_source=unescapeHTML) - if isinstance(audios, list): - for audio in audios: - a = Audio._make(audio[:6]) - entries.append({ - 'id': '%s_%s' % (a.user_id, a.id), - 'url': a.url, - 'title': '%s - %s' % (a.artist, a.track) if a.artist and a.track else a.id, - 'thumbnail': thumbnail, - 'duration': a.duration, - 'uploader': uploader, - 'artist': a.artist, - 'track': a.track, - }) + for audio in re.findall(r'data-audio="([^"]+)', webpage): + audio = self._parse_json(unescapeHTML(audio), post_id) + a = self._AUDIO._make(audio) + if not a.url: + continue + title = unescapeHTML(a.title) + entries.append({ + 'id': '%s_%s' % (a.owner_id, a.id), + 'url': self._unmask_url(a.url, a.ads['vk_id']), + 'title': '%s - %s' % (a.performer, title) if a.performer else title, + 'thumbnail': a.cover_url.split(',') if a.cover_url else None, + 'duration': a.duration, + 'uploader': uploader, + 'artist': a.performer, + 'track': title, + 'ext': 'mp4', + 'protocol': 'm3u8', + }) for video in re.finditer( r'<a[^>]+href=(["\'])(?P<url>/video(?:-?[\d_]+).*?)\1', webpage): From 42cd0824b3975e6ce500d8cecd60e1fc077a758b Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sat, 26 Oct 2019 00:06:05 +0100 Subject: [PATCH 28/65] [vk] remove assert statement --- youtube_dl/extractor/vk.py | 1 - 1 file changed, 1 deletion(-) diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index c289fcad3..4c8ca4f41 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -600,7 +600,6 @@ class VKWallPostIE(VKBaseIE): if 'audio_api_unavailable' in mask_url: extra = mask_url.split('?extra=')[1].split('#') func, base = self._decode(extra[1]).split(chr(11)) - assert (func == 'i') mask_url = list(self._decode(extra[0])) url_len = len(mask_url) indexes = [None] * url_len From 235dbb434bfa724718c37d8af0a61baf93b775be Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sat, 26 Oct 2019 14:57:42 +0100 Subject: [PATCH 29/65] [discoverynetworks] add support for dplay.co.uk --- youtube_dl/extractor/discoverynetworks.py | 63 +++++++---------------- 1 file changed, 19 insertions(+), 44 deletions(-) diff --git a/youtube_dl/extractor/discoverynetworks.py b/youtube_dl/extractor/discoverynetworks.py index fba1ef221..607a54948 100644 --- a/youtube_dl/extractor/discoverynetworks.py +++ b/youtube_dl/extractor/discoverynetworks.py @@ -3,63 +3,38 @@ from __future__ import unicode_literals import re -from .brightcove import BrightcoveLegacyIE from .dplay import DPlayIE -from ..compat import ( - compat_parse_qs, - compat_urlparse, -) -from ..utils import smuggle_url class DiscoveryNetworksDeIE(DPlayIE): - _VALID_URL = r'''(?x)https?://(?:www\.)?(?P<site>discovery|tlc|animalplanet|dmax)\.de/ - (?: - .*\#(?P<id>\d+)| - (?:[^/]+/)*videos/(?P<display_id>[^/?#]+)| - programme/(?P<programme>[^/]+)/video/(?P<alternate_id>[^/]+) - )''' + _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:tlc|dmax)\.de|dplay\.co\.uk)/(?:programme|show)/(?P<programme>[^/]+)/video/(?P<alternate_id>[^/]+)' _TESTS = [{ - 'url': 'http://www.tlc.de/sendungen/breaking-amish/videos/#3235167922001', + 'url': 'https://www.tlc.de/programme/breaking-amish/video/die-welt-da-drauen/DCB331270001100', 'info_dict': { - 'id': '3235167922001', + 'id': '78867', 'ext': 'mp4', - 'title': 'Breaking Amish: Die Welt da draußen', - 'description': ( - 'Vier Amische und eine Mennonitin wagen in New York' - ' den Sprung in ein komplett anderes Leben. Begleitet sie auf' - ' ihrem spannenden Weg.'), - 'timestamp': 1396598084, - 'upload_date': '20140404', - 'uploader_id': '1659832546', + 'title': 'Die Welt da draußen', + 'description': 'md5:61033c12b73286e409d99a41742ef608', + 'timestamp': 1554069600, + 'upload_date': '20190331', + }, + 'params': { + 'format': 'bestvideo', + 'skip_download': True, }, }, { - 'url': 'http://www.dmax.de/programme/storage-hunters-uk/videos/storage-hunters-uk-episode-6/', + 'url': 'https://www.dmax.de/programme/dmax-highlights/video/tuning-star-sidney-hoffmann-exklusiv-bei-dmax/191023082312316', 'only_matching': True, }, { - 'url': 'http://www.discovery.de/#5332316765001', + 'url': 'https://www.dplay.co.uk/show/ghost-adventures/video/hotel-leger-103620/EHD_280313B', 'only_matching': True, }] - BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1659832546/default_default/index.html?videoId=%s' def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - alternate_id = mobj.group('alternate_id') - if alternate_id: - self._initialize_geo_bypass({ - 'countries': ['DE'], - }) - return self._get_disco_api_info( - url, '%s/%s' % (mobj.group('programme'), alternate_id), - 'sonic-eu1-prod.disco-api.com', mobj.group('site') + 'de') - brightcove_id = mobj.group('id') - if not brightcove_id: - title = mobj.group('title') - webpage = self._download_webpage(url, title) - brightcove_legacy_url = BrightcoveLegacyIE._extract_brightcove_url(webpage) - brightcove_id = compat_parse_qs(compat_urlparse.urlparse( - brightcove_legacy_url).query)['@videoPlayer'][0] - return self.url_result(smuggle_url( - self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, {'geo_countries': ['DE']}), - 'BrightcoveNew', brightcove_id) + domain, programme, alternate_id = re.match(self._VALID_URL, url).groups() + country = 'GB' if domain == 'dplay.co.uk' else 'DE' + realm = 'questuk' if country == 'GB' else domain.replace('.', '') + return self._get_disco_api_info( + url, '%s/%s' % (programme, alternate_id), + 'sonic-eu1-prod.disco-api.com', realm, country) From 0b98f3a7517601b7d2aabc789997016b9c3c24f2 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sat, 26 Oct 2019 14:58:29 +0100 Subject: [PATCH 30/65] [dplay] improve extraction - add support for dplay.fi, dplay.jp and es.dplay.com(closes #16969) - fix it.dplay.com extraction(closes #22826) - update tests - extract creator, tags and thumbnails - handle playback API call errors --- youtube_dl/extractor/dplay.py | 397 ++++++++++------------------- youtube_dl/extractor/extractors.py | 5 +- 2 files changed, 133 insertions(+), 269 deletions(-) diff --git a/youtube_dl/extractor/dplay.py b/youtube_dl/extractor/dplay.py index ebf59512c..d9c3d59cd 100644 --- a/youtube_dl/extractor/dplay.py +++ b/youtube_dl/extractor/dplay.py @@ -1,74 +1,68 @@ # coding: utf-8 from __future__ import unicode_literals -import json import re -import time from .common import InfoExtractor -from ..compat import ( - compat_HTTPError, - compat_str, - compat_urlparse, -) +from ..compat import compat_HTTPError from ..utils import ( determine_ext, ExtractorError, float_or_none, int_or_none, - remove_end, - try_get, - unified_strdate, unified_timestamp, - update_url_query, - urljoin, - USER_AGENTS, ) class DPlayIE(InfoExtractor): - _VALID_URL = r'https?://(?P<domain>www\.(?P<host>dplay\.(?P<country>dk|se|no)))/(?:video(?:er|s)/)?(?P<id>[^/]+/[^/?#]+)' + _VALID_URL = r'''(?x)https?:// + (?P<domain> + (?:www\.)?(?P<host>dplay\.(?P<country>dk|fi|jp|se|no))| + (?P<subdomain_country>es|it)\.dplay\.com + )/[^/]+/(?P<id>[^/]+/[^/?#]+)''' _TESTS = [{ # non geo restricted, via secure api, unsigned download hls URL - 'url': 'http://www.dplay.se/nugammalt-77-handelser-som-format-sverige/season-1-svensken-lar-sig-njuta-av-livet/', + 'url': 'https://www.dplay.se/videos/nugammalt-77-handelser-som-format-sverige/nugammalt-77-handelser-som-format-sverige-101', 'info_dict': { - 'id': '3172', - 'display_id': 'nugammalt-77-handelser-som-format-sverige/season-1-svensken-lar-sig-njuta-av-livet', + 'id': '13628', + 'display_id': 'nugammalt-77-handelser-som-format-sverige/nugammalt-77-handelser-som-format-sverige-101', 'ext': 'mp4', 'title': 'Svensken lär sig njuta av livet', 'description': 'md5:d3819c9bccffd0fe458ca42451dd50d8', - 'duration': 2650, - 'timestamp': 1365454320, + 'duration': 2649.856, + 'timestamp': 1365453720, 'upload_date': '20130408', - 'creator': 'Kanal 5 (Home)', + 'creator': 'Kanal 5', 'series': 'Nugammalt - 77 händelser som format Sverige', 'season_number': 1, 'episode_number': 1, - 'age_limit': 0, + }, + 'params': { + 'format': 'bestvideo', + 'skip_download': True, }, }, { # geo restricted, via secure api, unsigned download hls URL - 'url': 'http://www.dplay.dk/mig-og-min-mor/season-6-episode-12/', + 'url': 'http://www.dplay.dk/videoer/ted-bundy-mind-of-a-monster/ted-bundy-mind-of-a-monster', 'info_dict': { - 'id': '70816', - 'display_id': 'mig-og-min-mor/season-6-episode-12', + 'id': '104465', + 'display_id': 'ted-bundy-mind-of-a-monster/ted-bundy-mind-of-a-monster', 'ext': 'mp4', - 'title': 'Episode 12', - 'description': 'md5:9c86e51a93f8a4401fc9641ef9894c90', - 'duration': 2563, - 'timestamp': 1429696800, - 'upload_date': '20150422', - 'creator': 'Kanal 4 (Home)', - 'series': 'Mig og min mor', - 'season_number': 6, - 'episode_number': 12, - 'age_limit': 0, + 'title': 'Ted Bundy: Mind Of A Monster', + 'description': 'md5:8b780f6f18de4dae631668b8a9637995', + 'duration': 5290.027, + 'timestamp': 1570694400, + 'upload_date': '20191010', + 'creator': 'ID - Investigation Discovery', + 'series': 'Ted Bundy: Mind Of A Monster', + 'season_number': 1, + 'episode_number': 1, + }, + 'params': { + 'format': 'bestvideo', + 'skip_download': True, }, - }, { - # geo restricted, via direct unsigned hls URL - 'url': 'http://www.dplay.no/pga-tour/season-1-hoydepunkter-18-21-februar/', - 'only_matching': True, }, { # disco-api 'url': 'https://www.dplay.no/videoer/i-kongens-klr/sesong-1-episode-7', @@ -89,19 +83,59 @@ class DPlayIE(InfoExtractor): 'format': 'bestvideo', 'skip_download': True, }, + 'skip': 'Available for Premium users', }, { - - 'url': 'https://www.dplay.dk/videoer/singleliv/season-5-episode-3', + 'url': 'http://it.dplay.com/nove/biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij/', + 'md5': '2b808ffb00fc47b884a172ca5d13053c', + 'info_dict': { + 'id': '6918', + 'display_id': 'biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij', + 'ext': 'mp4', + 'title': 'Luigi Di Maio: la psicosi di Stanislawskij', + 'description': 'md5:3c7a4303aef85868f867a26f5cc14813', + 'thumbnail': r're:^https?://.*\.jpe?g', + 'upload_date': '20160524', + 'timestamp': 1464076800, + 'series': 'Biografie imbarazzanti', + 'season_number': 1, + 'episode': 'Episode 1', + 'episode_number': 1, + }, + }, { + 'url': 'https://es.dplay.com/dmax/la-fiebre-del-oro/temporada-8-episodio-1/', + 'info_dict': { + 'id': '21652', + 'display_id': 'la-fiebre-del-oro/temporada-8-episodio-1', + 'ext': 'mp4', + 'title': 'Episodio 1', + 'description': 'md5:b9dcff2071086e003737485210675f69', + 'thumbnail': r're:^https?://.*\.png', + 'upload_date': '20180709', + 'timestamp': 1531173540, + 'series': 'La fiebre del oro', + 'season_number': 8, + 'episode': 'Episode 1', + 'episode_number': 1, + }, + 'params': { + 'skip_download': True, + }, + }, { + 'url': 'https://www.dplay.fi/videot/shifting-gears-with-aaron-kaufman/episode-16', 'only_matching': True, }, { - 'url': 'https://www.dplay.se/videos/sofias-anglar/sofias-anglar-1001', + 'url': 'https://www.dplay.jp/video/gold-rush/24086', 'only_matching': True, }] - def _get_disco_api_info(self, url, display_id, disco_host, realm): - disco_base = 'https://' + disco_host + def _get_disco_api_info(self, url, display_id, disco_host, realm, country): + geo_countries = [country.upper()] + self._initialize_geo_bypass({ + 'countries': geo_countries, + }) + disco_base = 'https://%s/' % disco_host token = self._download_json( - '%s/token' % disco_base, display_id, 'Downloading token', + disco_base + 'token', display_id, 'Downloading token', query={ 'realm': realm, })['data']['attributes']['token'] @@ -110,17 +144,30 @@ class DPlayIE(InfoExtractor): 'Authorization': 'Bearer ' + token, } video = self._download_json( - '%s/content/videos/%s' % (disco_base, display_id), display_id, + disco_base + 'content/videos/' + display_id, display_id, headers=headers, query={ - 'include': 'show' + 'include': 'images,primaryChannel,show,tags' }) video_id = video['data']['id'] info = video['data']['attributes'] - title = info['name'] + title = info['name'].strip() formats = [] - for format_id, format_dict in self._download_json( - '%s/playback/videoPlaybackInfo/%s' % (disco_base, video_id), - display_id, headers=headers)['data']['attributes']['streaming'].items(): + try: + streaming = self._download_json( + disco_base + 'playback/videoPlaybackInfo/' + video_id, + display_id, headers=headers)['data']['attributes']['streaming'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + info = self._parse_json(e.cause.read().decode('utf-8'), display_id) + error = info['errors'][0] + error_code = error.get('code') + if error_code == 'access.denied.geoblocked': + self.raise_geo_restricted(countries=geo_countries) + elif error_code == 'access.denied.missingpackage': + self.raise_login_required() + raise ExtractorError(info['errors'][0]['detail'], expected=True) + raise + for format_id, format_dict in streaming.items(): if not isinstance(format_dict, dict): continue format_url = format_dict.get('url') @@ -142,235 +189,55 @@ class DPlayIE(InfoExtractor): }) self._sort_formats(formats) - series = None - try: - included = video.get('included') - if isinstance(included, list): - show = next(e for e in included if e.get('type') == 'show') - series = try_get( - show, lambda x: x['attributes']['name'], compat_str) - except StopIteration: - pass + creator = series = None + tags = [] + thumbnails = [] + included = video.get('included') or [] + if isinstance(included, list): + for e in included: + attributes = e.get('attributes') + if not attributes: + continue + e_type = e.get('type') + if e_type == 'channel': + creator = attributes.get('name') + elif e_type == 'image': + src = attributes.get('src') + if src: + thumbnails.append({ + 'url': src, + 'width': int_or_none(attributes.get('width')), + 'height': int_or_none(attributes.get('height')), + }) + if e_type == 'show': + series = attributes.get('name') + elif e_type == 'tag': + name = attributes.get('name') + if name: + tags.append(name) return { 'id': video_id, 'display_id': display_id, 'title': title, 'description': info.get('description'), - 'duration': float_or_none( - info.get('videoDuration'), scale=1000), + 'duration': float_or_none(info.get('videoDuration'), 1000), 'timestamp': unified_timestamp(info.get('publishStart')), 'series': series, 'season_number': int_or_none(info.get('seasonNumber')), 'episode_number': int_or_none(info.get('episodeNumber')), 'age_limit': int_or_none(info.get('minimum_age')), + 'creator': creator, + 'tags': tags, + 'thumbnails': thumbnails, 'formats': formats, } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) display_id = mobj.group('id') - domain = mobj.group('domain') - - self._initialize_geo_bypass({ - 'countries': [mobj.group('country').upper()], - }) - - webpage = self._download_webpage(url, display_id) - - video_id = self._search_regex( - r'data-video-id=["\'](\d+)', webpage, 'video id', default=None) - - if not video_id: - host = mobj.group('host') - return self._get_disco_api_info( - url, display_id, 'disco-api.' + host, host.replace('.', '')) - - info = self._download_json( - 'http://%s/api/v2/ajax/videos?video_id=%s' % (domain, video_id), - video_id)['data'][0] - - title = info['title'] - - PROTOCOLS = ('hls', 'hds') - formats = [] - - def extract_formats(protocol, manifest_url): - if protocol == 'hls': - m3u8_formats = self._extract_m3u8_formats( - manifest_url, video_id, ext='mp4', - entry_protocol='m3u8_native', m3u8_id=protocol, fatal=False) - # Sometimes final URLs inside m3u8 are unsigned, let's fix this - # ourselves. Also fragments' URLs are only served signed for - # Safari user agent. - query = compat_urlparse.parse_qs(compat_urlparse.urlparse(manifest_url).query) - for m3u8_format in m3u8_formats: - m3u8_format.update({ - 'url': update_url_query(m3u8_format['url'], query), - 'http_headers': { - 'User-Agent': USER_AGENTS['Safari'], - }, - }) - formats.extend(m3u8_formats) - elif protocol == 'hds': - formats.extend(self._extract_f4m_formats( - manifest_url + '&hdcore=3.8.0&plugin=flowplayer-3.8.0.0', - video_id, f4m_id=protocol, fatal=False)) - - domain_tld = domain.split('.')[-1] - if domain_tld in ('se', 'dk', 'no'): - for protocol in PROTOCOLS: - # Providing dsc-geo allows to bypass geo restriction in some cases - self._set_cookie( - 'secure.dplay.%s' % domain_tld, 'dsc-geo', - json.dumps({ - 'countryCode': domain_tld.upper(), - 'expiry': (time.time() + 20 * 60) * 1000, - })) - stream = self._download_json( - 'https://secure.dplay.%s/secure/api/v2/user/authorization/stream/%s?stream_type=%s' - % (domain_tld, video_id, protocol), video_id, - 'Downloading %s stream JSON' % protocol, fatal=False) - if stream and stream.get(protocol): - extract_formats(protocol, stream[protocol]) - - # The last resort is to try direct unsigned hls/hds URLs from info dictionary. - # Sometimes this does work even when secure API with dsc-geo has failed (e.g. - # http://www.dplay.no/pga-tour/season-1-hoydepunkter-18-21-februar/). - if not formats: - for protocol in PROTOCOLS: - if info.get(protocol): - extract_formats(protocol, info[protocol]) - - self._sort_formats(formats) - - subtitles = {} - for lang in ('se', 'sv', 'da', 'nl', 'no'): - for format_id in ('web_vtt', 'vtt', 'srt'): - subtitle_url = info.get('subtitles_%s_%s' % (lang, format_id)) - if subtitle_url: - subtitles.setdefault(lang, []).append({'url': subtitle_url}) - - return { - 'id': video_id, - 'display_id': display_id, - 'title': title, - 'description': info.get('video_metadata_longDescription'), - 'duration': int_or_none(info.get('video_metadata_length'), scale=1000), - 'timestamp': int_or_none(info.get('video_publish_date')), - 'creator': info.get('video_metadata_homeChannel'), - 'series': info.get('video_metadata_show'), - 'season_number': int_or_none(info.get('season')), - 'episode_number': int_or_none(info.get('episode')), - 'age_limit': int_or_none(info.get('minimum_age')), - 'formats': formats, - 'subtitles': subtitles, - } - - -class DPlayItIE(InfoExtractor): - _VALID_URL = r'https?://it\.dplay\.com/[^/]+/[^/]+/(?P<id>[^/?#]+)' - _GEO_COUNTRIES = ['IT'] - _TEST = { - 'url': 'http://it.dplay.com/nove/biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij/', - 'md5': '2b808ffb00fc47b884a172ca5d13053c', - 'info_dict': { - 'id': '6918', - 'display_id': 'luigi-di-maio-la-psicosi-di-stanislawskij', - 'ext': 'mp4', - 'title': 'Biografie imbarazzanti: Luigi Di Maio: la psicosi di Stanislawskij', - 'description': 'md5:3c7a4303aef85868f867a26f5cc14813', - 'thumbnail': r're:^https?://.*\.jpe?g', - 'upload_date': '20160524', - 'series': 'Biografie imbarazzanti', - 'season_number': 1, - 'episode': 'Luigi Di Maio: la psicosi di Stanislawskij', - 'episode_number': 1, - }, - } - - def _real_extract(self, url): - display_id = self._match_id(url) - - webpage = self._download_webpage(url, display_id) - - title = remove_end(self._og_search_title(webpage), ' | Dplay') - - video_id = None - - info = self._search_regex( - r'playback_json\s*:\s*JSON\.parse\s*\(\s*("(?:\\.|[^"\\])+?")', - webpage, 'playback JSON', default=None) - if info: - for _ in range(2): - info = self._parse_json(info, display_id, fatal=False) - if not info: - break - else: - video_id = try_get(info, lambda x: x['data']['id']) - - if not info: - info_url = self._search_regex( - (r'playback_json_url\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', - r'url\s*[:=]\s*["\'](?P<url>(?:https?:)?//[^/]+/playback/videoPlaybackInfo/\d+)'), - webpage, 'info url', group='url') - - info_url = urljoin(url, info_url) - video_id = info_url.rpartition('/')[-1] - - try: - info = self._download_json( - info_url, display_id, headers={ - 'Authorization': 'Bearer %s' % self._get_cookies(url).get( - 'dplayit_token').value, - 'Referer': url, - }) - if isinstance(info, compat_str): - info = self._parse_json(info, display_id) - except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 403): - info = self._parse_json(e.cause.read().decode('utf-8'), display_id) - error = info['errors'][0] - if error.get('code') == 'access.denied.geoblocked': - self.raise_geo_restricted( - msg=error.get('detail'), countries=self._GEO_COUNTRIES) - raise ExtractorError(info['errors'][0]['detail'], expected=True) - raise - - hls_url = info['data']['attributes']['streaming']['hls']['url'] - - formats = self._extract_m3u8_formats( - hls_url, display_id, ext='mp4', entry_protocol='m3u8_native', - m3u8_id='hls') - self._sort_formats(formats) - - series = self._html_search_regex( - r'(?s)<h1[^>]+class=["\'].*?\bshow_title\b.*?["\'][^>]*>(.+?)</h1>', - webpage, 'series', fatal=False) - episode = self._search_regex( - r'<p[^>]+class=["\'].*?\bdesc_ep\b.*?["\'][^>]*>\s*<br/>\s*<b>([^<]+)', - webpage, 'episode', fatal=False) - - mobj = re.search( - r'(?s)<span[^>]+class=["\']dates["\'][^>]*>.+?\bS\.(?P<season_number>\d+)\s+E\.(?P<episode_number>\d+)\s*-\s*(?P<upload_date>\d{2}/\d{2}/\d{4})', - webpage) - if mobj: - season_number = int(mobj.group('season_number')) - episode_number = int(mobj.group('episode_number')) - upload_date = unified_strdate(mobj.group('upload_date')) - else: - season_number = episode_number = upload_date = None - - return { - 'id': compat_str(video_id or display_id), - 'display_id': display_id, - 'title': title, - 'description': self._og_search_description(webpage), - 'thumbnail': self._og_search_thumbnail(webpage), - 'series': series, - 'season_number': season_number, - 'episode': episode, - 'episode_number': episode_number, - 'upload_date': upload_date, - 'formats': formats, - } + domain = mobj.group('domain').lstrip('www.') + country = mobj.group('country') or mobj.group('subdomain_country') + host = 'disco-api.' + domain if domain.startswith('dplay.') else 'eu2-prod.disco-api.com' + return self._get_disco_api_info( + url, display_id, host, 'dplay' + country, country) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 1db21529f..a8fe0de1a 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -277,10 +277,7 @@ from .douyutv import ( DouyuShowIE, DouyuTVIE, ) -from .dplay import ( - DPlayIE, - DPlayItIE, -) +from .dplay import DPlayIE from .dreisat import DreiSatIE from .drbonanza import DRBonanzaIE from .drtuber import DrTuberIE From 548c395716b1d5aa215e526fcb052a03926c1573 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 27 Oct 2019 17:52:46 +0100 Subject: [PATCH 31/65] [soundcloud] improve extraction - improve format extraction(closes #22123) - extract uploader_id and uploader_url(closes #21916) - extract all known thumbnails(closes #19071)(closes #20659) - fix extration for private playlists(closes #20976) - add support for playlist embeds(#20976) - skip preview formats(closes #22806) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/generic.py | 6 +- youtube_dl/extractor/soundcloud.py | 497 ++++++++++++++--------------- 3 files changed, 248 insertions(+), 256 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index a8fe0de1a..388c1ebe6 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1033,6 +1033,7 @@ from .snotr import SnotrIE from .sohu import SohuIE from .sonyliv import SonyLIVIE from .soundcloud import ( + SoundcloudEmbedIE, SoundcloudIE, SoundcloudSetIE, SoundcloudUserIE, diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index f66cae0eb..1c0780e98 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -80,7 +80,7 @@ from .theplatform import ThePlatformIE from .kaltura import KalturaIE from .eagleplatform import EaglePlatformIE from .facebook import FacebookIE -from .soundcloud import SoundcloudIE +from .soundcloud import SoundcloudEmbedIE from .tunein import TuneInBaseIE from .vbox7 import Vbox7IE from .dbtv import DBTVIE @@ -2749,9 +2749,9 @@ class GenericIE(InfoExtractor): return self.url_result(myvi_url) # Look for embedded soundcloud player - soundcloud_urls = SoundcloudIE._extract_urls(webpage) + soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage) if soundcloud_urls: - return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key()) + return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML) # Look for tunein player tunein_urls = TuneInBaseIE._extract_urls(webpage) diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 05538f3d6..875b9d887 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -11,14 +11,13 @@ from .common import ( from ..compat import ( compat_str, compat_urlparse, - compat_urllib_parse_urlencode, ) from ..utils import ( ExtractorError, float_or_none, + HEADRequest, int_or_none, KNOWN_EXTENSIONS, - merge_dicts, mimetype2ext, str_or_none, try_get, @@ -28,6 +27,20 @@ from ..utils import ( ) +class SoundcloudEmbedIE(InfoExtractor): + _VALID_URL = r'https?://(?:w|player|p)\.soundcloud\.com/player/?.*?url=(?P<id>.*)' + + @staticmethod + def _extract_urls(webpage): + return [m.group('url') for m in re.finditer( + r'<iframe[^>]+src=(["\'])(?P<url>(?:https?://)?(?:w\.)?soundcloud\.com/player.+?)\1', + webpage)] + + def _real_extract(self, url): + return self.url_result(compat_urlparse.parse_qs( + compat_urlparse.urlparse(url).query)['url'][0]) + + class SoundcloudIE(InfoExtractor): """Information extractor for soundcloud.com To access the media, the uid of the song and a stream token @@ -44,9 +57,8 @@ class SoundcloudIE(InfoExtractor): (?!(?:tracks|albums|sets(?:/.+?)?|reposts|likes|spotlight)/?(?:$|[?#])) (?P<title>[\w\d-]+)/? (?P<token>[^?]+?)?(?:[?].*)?$) - |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+) + |(?:api(?:-v2)?\.soundcloud\.com/tracks/(?P<track_id>\d+) (?:/?\?secret_token=(?P<secret_token>[^&]+))?) - |(?P<player>(?:w|player|p.)\.soundcloud\.com/player/?.*?url=.*) ) ''' IE_NAME = 'soundcloud' @@ -60,6 +72,7 @@ class SoundcloudIE(InfoExtractor): 'title': 'Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1', 'description': 'No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o\'d', 'uploader': 'E.T. ExTerrestrial Music', + 'uploader_id': '1571244', 'timestamp': 1349920598, 'upload_date': '20121011', 'duration': 143.216, @@ -79,6 +92,7 @@ class SoundcloudIE(InfoExtractor): 'title': 'Goldrushed', 'description': 'From Stockholm Sweden\r\nPovel / Magnus / Filip / David\r\nwww.theroyalconcept.com', 'uploader': 'The Royal Concept', + 'uploader_id': '9615865', 'timestamp': 1337635207, 'upload_date': '20120521', 'duration': 30, @@ -92,6 +106,7 @@ class SoundcloudIE(InfoExtractor): # rtmp 'skip_download': True, }, + 'skip': 'Preview', }, # private link { @@ -103,6 +118,7 @@ class SoundcloudIE(InfoExtractor): 'title': 'Youtube - Dl Test Video \'\' Ä↭', 'description': 'test chars: \"\'/\\ä↭', 'uploader': 'jaimeMF', + 'uploader_id': '69767071', 'timestamp': 1386604920, 'upload_date': '20131209', 'duration': 9.927, @@ -123,6 +139,7 @@ class SoundcloudIE(InfoExtractor): 'title': 'Youtube - Dl Test Video \'\' Ä↭', 'description': 'test chars: \"\'/\\ä↭', 'uploader': 'jaimeMF', + 'uploader_id': '69767071', 'timestamp': 1386604920, 'upload_date': '20131209', 'duration': 9.927, @@ -143,6 +160,7 @@ class SoundcloudIE(InfoExtractor): 'title': 'Bus Brakes', 'description': 'md5:0053ca6396e8d2fd7b7e1595ef12ab66', 'uploader': 'oddsamples', + 'uploader_id': '73680509', 'timestamp': 1389232924, 'upload_date': '20140109', 'duration': 17.346, @@ -163,6 +181,7 @@ class SoundcloudIE(InfoExtractor): 'title': 'Uplifting Only 238 [No Talking] (incl. Alex Feed Guestmix) (Aug 31, 2017) [wav]', 'description': 'md5:fa20ee0fca76a3d6df8c7e57f3715366', 'uploader': 'Ori Uplift Music', + 'uploader_id': '12563093', 'timestamp': 1504206263, 'upload_date': '20170831', 'duration': 7449.096, @@ -183,6 +202,7 @@ class SoundcloudIE(InfoExtractor): 'title': 'Sideways (Prod. Mad Real)', 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', 'uploader': 'garyvee', + 'uploader_id': '2366352', 'timestamp': 1488152409, 'upload_date': '20170226', 'duration': 207.012, @@ -207,6 +227,7 @@ class SoundcloudIE(InfoExtractor): 'title': 'Mezzo Valzer', 'description': 'md5:4138d582f81866a530317bae316e8b61', 'uploader': 'Giovanni Sarani', + 'uploader_id': '3352531', 'timestamp': 1551394171, 'upload_date': '20190228', 'duration': 180.157, @@ -221,114 +242,81 @@ class SoundcloudIE(InfoExtractor): } ] + _API_BASE = 'https://api.soundcloud.com/' + _API_V2_BASE = 'https://api-v2.soundcloud.com/' + _BASE_URL = 'https://soundcloud.com/' _CLIENT_ID = 'BeGVhOrGmfboy1LtiHTQF6Ejpt9ULJCI' + _IMAGE_REPL_RE = r'-([0-9a-z]+)\.jpg' - @staticmethod - def _extract_urls(webpage): - return [m.group('url') for m in re.finditer( - r'<iframe[^>]+src=(["\'])(?P<url>(?:https?://)?(?:w\.)?soundcloud\.com/player.+?)\1', - webpage)] + _ARTWORK_MAP = { + 'mini': 16, + 'tiny': 20, + 'small': 32, + 'badge': 47, + 't67x67': 67, + 'large': 100, + 't300x300': 300, + 'crop': 400, + 't500x500': 500, + 'original': 0, + } @classmethod def _resolv_url(cls, url): - return 'https://api.soundcloud.com/resolve.json?url=' + url + '&client_id=' + cls._CLIENT_ID + return SoundcloudIE._API_V2_BASE + 'resolve?url=' + url + '&client_id=' + cls._CLIENT_ID - def _extract_info_dict(self, info, full_title=None, quiet=False, secret_token=None): + def _extract_info_dict(self, info, full_title=None, secret_token=None, version=2): track_id = compat_str(info['id']) title = info['title'] - name = full_title or track_id - if quiet: - self.report_extraction(name) - thumbnail = info.get('artwork_url') or info.get('user', {}).get('avatar_url') - if isinstance(thumbnail, compat_str): - thumbnail = thumbnail.replace('-large', '-t500x500') - username = try_get(info, lambda x: x['user']['username'], compat_str) - - def extract_count(key): - return int_or_none(info.get('%s_count' % key)) - - like_count = extract_count('favoritings') - if like_count is None: - like_count = extract_count('likes') - - result = { - 'id': track_id, - 'uploader': username, - 'timestamp': unified_timestamp(info.get('created_at')), - 'title': title, - 'description': info.get('description'), - 'thumbnail': thumbnail, - 'duration': float_or_none(info.get('duration'), 1000), - 'webpage_url': info.get('permalink_url'), - 'license': info.get('license'), - 'view_count': extract_count('playback'), - 'like_count': like_count, - 'comment_count': extract_count('comment'), - 'repost_count': extract_count('reposts'), - 'genre': info.get('genre'), - } + track_base_url = self._API_BASE + 'tracks/%s' % track_id format_urls = set() formats = [] query = {'client_id': self._CLIENT_ID} - if secret_token is not None: + if secret_token: query['secret_token'] = secret_token - if info.get('downloadable', False): - # We can build a direct link to the song + + if info.get('downloadable'): format_url = update_url_query( - 'https://api.soundcloud.com/tracks/%s/download' % track_id, query) + info.get('download_url') or track_base_url + '/download', query) format_urls.add(format_url) + if version == 2: + v1_info = self._download_json( + track_base_url, track_id, query=query, fatal=False) or {} + else: + v1_info = info formats.append({ 'format_id': 'download', - 'ext': info.get('original_format', 'mp3'), + 'ext': v1_info.get('original_format') or 'mp3', + 'filesize': int_or_none(v1_info.get('original_content_size')), 'url': format_url, - 'vcodec': 'none', 'preference': 10, }) - # Old API, does not work for some tracks (e.g. - # https://soundcloud.com/giovannisarani/mezzo-valzer) - format_dict = self._download_json( - 'https://api.soundcloud.com/i1/tracks/%s/streams' % track_id, - track_id, 'Downloading track url', query=query, fatal=False) + def invalid_url(url): + return not url or url in format_urls or re.search(r'/(?:preview|playlist)/0/30/', url) - if format_dict: - for key, stream_url in format_dict.items(): - if stream_url in format_urls: - continue - format_urls.add(stream_url) - ext, abr = 'mp3', None - mobj = re.search(r'_([^_]+)_(\d+)_url', key) - if mobj: - ext, abr = mobj.groups() - abr = int(abr) - if key.startswith('http'): - stream_formats = [{ - 'format_id': key, - 'ext': ext, - 'url': stream_url, - }] - elif key.startswith('rtmp'): - # The url doesn't have an rtmp app, we have to extract the playpath - url, path = stream_url.split('mp3:', 1) - stream_formats = [{ - 'format_id': key, - 'url': url, - 'play_path': 'mp3:' + path, - 'ext': 'flv', - }] - elif key.startswith('hls'): - stream_formats = self._extract_m3u8_formats( - stream_url, track_id, ext, entry_protocol='m3u8_native', - m3u8_id=key, fatal=False) - else: - continue - - if abr: - for f in stream_formats: - f['abr'] = abr - - formats.extend(stream_formats) + def add_format(f, protocol): + mobj = re.search(r'\.(?P<abr>\d+)\.(?P<ext>[0-9a-z]{3,4})(?=[/?])', stream_url) + if mobj: + for k, v in mobj.groupdict().items(): + if not f.get(k): + f[k] = v + format_id_list = [] + if protocol: + format_id_list.append(protocol) + for k in ('ext', 'abr'): + v = f.get(k) + if v: + format_id_list.append(v) + abr = f.get('abr') + if abr: + f['abr'] = int(abr) + f.update({ + 'format_id': '_'.join(format_id_list), + 'protocol': 'm3u8_native' if protocol == 'hls' else 'http', + }) + formats.append(f) # New API transcodings = try_get( @@ -337,129 +325,165 @@ class SoundcloudIE(InfoExtractor): if not isinstance(t, dict): continue format_url = url_or_none(t.get('url')) - if not format_url: + if not format_url or t.get('snipped') or '/preview/' in format_url: continue stream = self._download_json( - update_url_query(format_url, query), track_id, fatal=False) + format_url, track_id, query=query, fatal=False) if not isinstance(stream, dict): continue stream_url = url_or_none(stream.get('url')) - if not stream_url: - continue - if stream_url in format_urls: + if invalid_url(stream_url): continue format_urls.add(stream_url) - protocol = try_get(t, lambda x: x['format']['protocol'], compat_str) + stream_format = t.get('format') or {} + protocol = stream_format.get('protocol') if protocol != 'hls' and '/hls' in format_url: protocol = 'hls' ext = None preset = str_or_none(t.get('preset')) if preset: ext = preset.split('_')[0] - if ext not in KNOWN_EXTENSIONS: - mimetype = try_get( - t, lambda x: x['format']['mime_type'], compat_str) - ext = mimetype2ext(mimetype) or 'mp3' - format_id_list = [] - if protocol: - format_id_list.append(protocol) - format_id_list.append(ext) - format_id = '_'.join(format_id_list) - formats.append({ + if ext not in KNOWN_EXTENSIONS: + ext = mimetype2ext(stream_format.get('mime_type')) + add_format({ 'url': stream_url, - 'format_id': format_id, 'ext': ext, - 'protocol': 'm3u8_native' if protocol == 'hls' else 'http', - }) + }, 'http' if protocol == 'progressive' else protocol) + + if not formats: + # Old API, does not work for some tracks (e.g. + # https://soundcloud.com/giovannisarani/mezzo-valzer) + # and might serve preview URLs (e.g. + # http://www.soundcloud.com/snbrn/ele) + format_dict = self._download_json( + track_base_url + '/streams', track_id, + 'Downloading track url', query=query, fatal=False) or {} + + for key, stream_url in format_dict.items(): + if invalid_url(stream_url): + continue + format_urls.add(stream_url) + mobj = re.search(r'(http|hls)_([^_]+)_(\d+)_url', key) + if mobj: + protocol, ext, abr = mobj.groups() + add_format({ + 'abr': abr, + 'ext': ext, + 'url': stream_url, + }, protocol) if not formats: # We fallback to the stream_url in the original info, this # cannot be always used, sometimes it can give an HTTP 404 error - formats.append({ - 'format_id': 'fallback', - 'url': update_url_query(info['stream_url'], query), - 'ext': 'mp3', - }) - self._check_formats(formats, track_id) + urlh = self._request_webpage( + HEADRequest(info.get('stream_url') or track_base_url + '/stream'), + track_id, query=query, fatal=False) + if urlh: + stream_url = urlh.geturl() + if not invalid_url(stream_url): + add_format({'url': stream_url}, 'http') for f in formats: f['vcodec'] = 'none' self._sort_formats(formats) - result['formats'] = formats - return result + user = info.get('user') or {} + + thumbnails = [] + artwork_url = info.get('artwork_url') + thumbnail = artwork_url or user.get('avatar_url') + if isinstance(thumbnail, compat_str): + if re.search(self._IMAGE_REPL_RE, thumbnail): + for image_id, size in self._ARTWORK_MAP.items(): + i = { + 'id': image_id, + 'url': re.sub(self._IMAGE_REPL_RE, '-%s.jpg' % image_id, thumbnail), + } + if image_id == 'tiny' and not artwork_url: + size = 18 + elif image_id == 'original': + i['preference'] = 10 + if size: + i.update({ + 'width': size, + 'height': size, + }) + thumbnails.append(i) + else: + thumbnails = [{'url': thumbnail}] + + def extract_count(key): + return int_or_none(info.get('%s_count' % key)) + + return { + 'id': track_id, + 'uploader': user.get('username'), + 'uploader_id': str_or_none(user.get('id')) or user.get('permalink'), + 'uploader_url': user.get('permalink_url'), + 'timestamp': unified_timestamp(info.get('created_at')), + 'title': title, + 'description': info.get('description'), + 'thumbnails': thumbnails, + 'duration': float_or_none(info.get('duration'), 1000), + 'webpage_url': info.get('permalink_url'), + 'license': info.get('license'), + 'view_count': extract_count('playback'), + 'like_count': extract_count('favoritings') or extract_count('likes'), + 'comment_count': extract_count('comment'), + 'repost_count': extract_count('reposts'), + 'genre': info.get('genre'), + 'formats': formats + } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE) - if mobj is None: - raise ExtractorError('Invalid URL: %s' % url) + mobj = re.match(self._VALID_URL, url) track_id = mobj.group('track_id') - new_info = {} - if track_id is not None: - info_json_url = 'https://api.soundcloud.com/tracks/' + track_id + '.json?client_id=' + self._CLIENT_ID + query = { + 'client_id': self._CLIENT_ID, + } + if track_id: + info_json_url = self._API_V2_BASE + 'tracks/' + track_id full_title = track_id token = mobj.group('secret_token') if token: - info_json_url += '&secret_token=' + token - elif mobj.group('player'): - query = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) - real_url = query['url'][0] - # If the token is in the query of the original url we have to - # manually add it - if 'secret_token' in query: - real_url += '?secret_token=' + query['secret_token'][0] - return self.url_result(real_url) + query['secret_token'] = token else: - # extract uploader (which is in the url) - uploader = mobj.group('uploader') - # extract simple title (uploader + slug of song title) - slug_title = mobj.group('title') + full_title = resolve_title = '%s/%s' % mobj.group('uploader', 'title') token = mobj.group('token') - full_title = resolve_title = '%s/%s' % (uploader, slug_title) if token: resolve_title += '/%s' % token + info_json_url = self._resolv_url(self._BASE_URL + resolve_title) - webpage = self._download_webpage(url, full_title, fatal=False) - if webpage: - entries = self._parse_json( - self._search_regex( - r'var\s+c\s*=\s*(\[.+?\])\s*,\s*o\s*=Date\b', webpage, - 'data', default='[]'), full_title, fatal=False) - if entries: - for e in entries: - if not isinstance(e, dict): - continue - if e.get('id') != 67: - continue - data = try_get(e, lambda x: x['data'][0], dict) - if data: - new_info = data - break - info_json_url = self._resolv_url( - 'https://soundcloud.com/%s' % resolve_title) - - # Contains some additional info missing from new_info + version = 2 info = self._download_json( - info_json_url, full_title, 'Downloading info JSON') + info_json_url, full_title, 'Downloading info JSON', query=query, fatal=False) + if not info: + info = self._download_json( + info_json_url.replace(self._API_V2_BASE, self._API_BASE), + full_title, 'Downloading info JSON', query=query) + version = 1 - return self._extract_info_dict( - merge_dicts(info, new_info), full_title, secret_token=token) + return self._extract_info_dict(info, full_title, token, version) class SoundcloudPlaylistBaseIE(SoundcloudIE): - @staticmethod - def _extract_id(e): - return compat_str(e['id']) if e.get('id') else None - - def _extract_track_entries(self, tracks): - return [ - self.url_result( - track['permalink_url'], SoundcloudIE.ie_key(), - video_id=self._extract_id(track)) - for track in tracks if track.get('permalink_url')] + def _extract_track_entries(self, tracks, token=None): + entries = [] + for track in tracks: + track_id = str_or_none(track.get('id')) + url = track.get('permalink_url') + if not url: + if not track_id: + continue + url = self._API_V2_BASE + 'tracks/' + track_id + if token: + url += '?secret_token=' + token + entries.append(self.url_result( + url, SoundcloudIE.ie_key(), track_id)) + return entries class SoundcloudSetIE(SoundcloudPlaylistBaseIE): @@ -480,41 +504,28 @@ class SoundcloudSetIE(SoundcloudPlaylistBaseIE): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - # extract uploader (which is in the url) - uploader = mobj.group('uploader') - # extract simple title (uploader + slug of song title) - slug_title = mobj.group('slug_title') - full_title = '%s/sets/%s' % (uploader, slug_title) - url = 'https://soundcloud.com/%s/sets/%s' % (uploader, slug_title) - + full_title = '%s/sets/%s' % mobj.group('uploader', 'slug_title') token = mobj.group('token') if token: full_title += '/' + token - url += '/' + token - resolv_url = self._resolv_url(url) - info = self._download_json(resolv_url, full_title) + info = self._download_json(self._resolv_url( + self._BASE_URL + full_title), full_title) if 'errors' in info: msgs = (compat_str(err['error_message']) for err in info['errors']) raise ExtractorError('unable to download video webpage: %s' % ','.join(msgs)) - entries = self._extract_track_entries(info['tracks']) + entries = self._extract_track_entries(info['tracks'], token) - return { - '_type': 'playlist', - 'entries': entries, - 'id': '%s' % info['id'], - 'title': info['title'], - } + return self.playlist_result( + entries, str_or_none(info.get('id')), info.get('title')) class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE): - _API_V2_BASE = 'https://api-v2.soundcloud.com' - def _extract_playlist(self, base_url, playlist_id, playlist_title): COMMON_QUERY = { - 'limit': 50, + 'limit': 2000000000, 'client_id': self._CLIENT_ID, 'linked_partitioning': '1', } @@ -522,12 +533,13 @@ class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE): query = COMMON_QUERY.copy() query['offset'] = 0 - next_href = base_url + '?' + compat_urllib_parse_urlencode(query) + next_href = base_url entries = [] for i in itertools.count(): response = self._download_json( - next_href, playlist_id, 'Downloading track page %s' % (i + 1)) + next_href, playlist_id, + 'Downloading track page %s' % (i + 1), query=query) collection = response['collection'] @@ -546,9 +558,8 @@ class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE): continue return self.url_result( permalink_url, - ie=SoundcloudIE.ie_key() if SoundcloudIE.suitable(permalink_url) else None, - video_id=self._extract_id(cand), - video_title=cand.get('title')) + SoundcloudIE.ie_key() if SoundcloudIE.suitable(permalink_url) else None, + str_or_none(cand.get('id')), cand.get('title')) for e in collection: entry = resolve_entry((e, e.get('track'), e.get('playlist'))) @@ -559,11 +570,10 @@ class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE): if not next_href: break - parsed_next_href = compat_urlparse.urlparse(response['next_href']) - qs = compat_urlparse.parse_qs(parsed_next_href.query) - qs.update(COMMON_QUERY) - next_href = compat_urlparse.urlunparse( - parsed_next_href._replace(query=compat_urllib_parse_urlencode(qs, True))) + next_href = response['next_href'] + parsed_next_href = compat_urlparse.urlparse(next_href) + query = compat_urlparse.parse_qs(parsed_next_href.query) + query.update(COMMON_QUERY) return { '_type': 'playlist', @@ -609,7 +619,7 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE): 'url': 'https://soundcloud.com/jcv246/sets', 'info_dict': { 'id': '12982173', - 'title': 'Jordi / cv (Playlists)', + 'title': 'Jordi / cv (Sets)', }, 'playlist_mincount': 2, }, { @@ -636,39 +646,29 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE): }] _BASE_URL_MAP = { - 'all': '%s/stream/users/%%s' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, - 'tracks': '%s/users/%%s/tracks' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, - 'albums': '%s/users/%%s/albums' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, - 'sets': '%s/users/%%s/playlists' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, - 'reposts': '%s/stream/users/%%s/reposts' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, - 'likes': '%s/users/%%s/likes' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, - 'spotlight': '%s/users/%%s/spotlight' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE, - } - - _TITLE_MAP = { - 'all': 'All', - 'tracks': 'Tracks', - 'albums': 'Albums', - 'sets': 'Playlists', - 'reposts': 'Reposts', - 'likes': 'Likes', - 'spotlight': 'Spotlight', + 'all': 'stream/users/%s', + 'tracks': 'users/%s/tracks', + 'albums': 'users/%s/albums', + 'sets': 'users/%s/playlists', + 'reposts': 'stream/users/%s/reposts', + 'likes': 'users/%s/likes', + 'spotlight': 'users/%s/spotlight', } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) uploader = mobj.group('user') - url = 'https://soundcloud.com/%s/' % uploader - resolv_url = self._resolv_url(url) user = self._download_json( - resolv_url, uploader, 'Downloading user info') + self._resolv_url(self._BASE_URL + uploader), + uploader, 'Downloading user info') resource = mobj.group('rsrc') or 'all' return self._extract_playlist( - self._BASE_URL_MAP[resource] % user['id'], compat_str(user['id']), - '%s (%s)' % (user['username'], self._TITLE_MAP[resource])) + self._API_V2_BASE + self._BASE_URL_MAP[resource] % user['id'], + str_or_none(user.get('id')), + '%s (%s)' % (user['username'], resource.capitalize())) class SoundcloudTrackStationIE(SoundcloudPagedPlaylistBaseIE): @@ -678,7 +678,7 @@ class SoundcloudTrackStationIE(SoundcloudPagedPlaylistBaseIE): 'url': 'https://soundcloud.com/stations/track/officialsundial/your-text', 'info_dict': { 'id': '286017854', - 'title': 'Track station: your-text', + 'title': 'Track station: your text', }, 'playlist_mincount': 47, }] @@ -686,19 +686,17 @@ class SoundcloudTrackStationIE(SoundcloudPagedPlaylistBaseIE): def _real_extract(self, url): track_name = self._match_id(url) - webpage = self._download_webpage(url, track_name) - + track = self._download_json(self._resolv_url(url), track_name) track_id = self._search_regex( - r'soundcloud:track-stations:(\d+)', webpage, 'track id') + r'soundcloud:track-stations:(\d+)', track['id'], 'track id') return self._extract_playlist( - '%s/stations/soundcloud:track-stations:%s/tracks' - % (self._API_V2_BASE, track_id), - track_id, 'Track station: %s' % track_name) + self._API_V2_BASE + 'stations/%s/tracks' % track['id'], + track_id, 'Track station: %s' % track['title']) class SoundcloudPlaylistIE(SoundcloudPlaylistBaseIE): - _VALID_URL = r'https?://api\.soundcloud\.com/playlists/(?P<id>[0-9]+)(?:/?\?secret_token=(?P<token>[^&]+?))?$' + _VALID_URL = r'https?://api(?:-v2)?\.soundcloud\.com/playlists/(?P<id>[0-9]+)(?:/?\?secret_token=(?P<token>[^&]+?))?$' IE_NAME = 'soundcloud:playlist' _TESTS = [{ 'url': 'https://api.soundcloud.com/playlists/4110309', @@ -713,29 +711,22 @@ class SoundcloudPlaylistIE(SoundcloudPlaylistBaseIE): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) playlist_id = mobj.group('id') - base_url = '%s//api.soundcloud.com/playlists/%s.json?' % (self.http_scheme(), playlist_id) - data_dict = { + query = { 'client_id': self._CLIENT_ID, } token = mobj.group('token') - if token: - data_dict['secret_token'] = token + query['secret_token'] = token - data = compat_urllib_parse_urlencode(data_dict) data = self._download_json( - base_url + data, playlist_id, 'Downloading playlist') + self._API_V2_BASE + 'playlists/' + playlist_id, + playlist_id, 'Downloading playlist', query=query) - entries = self._extract_track_entries(data['tracks']) + entries = self._extract_track_entries(data['tracks'], token) - return { - '_type': 'playlist', - 'id': playlist_id, - 'title': data.get('title'), - 'description': data.get('description'), - 'entries': entries, - } + return self.playlist_result( + entries, playlist_id, data.get('title'), data.get('description')) class SoundcloudSearchIE(SearchInfoExtractor, SoundcloudIE): @@ -753,18 +744,18 @@ class SoundcloudSearchIE(SearchInfoExtractor, SoundcloudIE): _SEARCH_KEY = 'scsearch' _MAX_RESULTS_PER_PAGE = 200 _DEFAULT_RESULTS_PER_PAGE = 50 - _API_V2_BASE = 'https://api-v2.soundcloud.com' def _get_collection(self, endpoint, collection_id, **query): limit = min( query.get('limit', self._DEFAULT_RESULTS_PER_PAGE), self._MAX_RESULTS_PER_PAGE) - query['limit'] = limit - query['client_id'] = self._CLIENT_ID - query['linked_partitioning'] = '1' - query['offset'] = 0 - data = compat_urllib_parse_urlencode(query) - next_url = '{0}{1}?{2}'.format(self._API_V2_BASE, endpoint, data) + query.update({ + 'limit': limit, + 'client_id': self._CLIENT_ID, + 'linked_partitioning': 1, + 'offset': 0, + }) + next_url = update_url_query(self._API_V2_BASE + endpoint, query) collected_results = 0 @@ -791,5 +782,5 @@ class SoundcloudSearchIE(SearchInfoExtractor, SoundcloudIE): break def _get_n_results(self, query, n): - tracks = self._get_collection('/search/tracks', query, limit=n, q=query) + tracks = self._get_collection('search/tracks', query, limit=n, q=query) return self.playlist_result(tracks, playlist_title=query) From dd90451f0f4867480c5ed8cb3588b30312204e3f Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sun, 27 Oct 2019 22:02:46 +0100 Subject: [PATCH 32/65] [tenplay] Add new extractor(closes #21446) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/tenplay.py | 55 ++++++++++++++++++++++++++++++ 2 files changed, 56 insertions(+) create mode 100644 youtube_dl/extractor/tenplay.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 388c1ebe6..339a141a5 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1133,6 +1133,7 @@ from .telequebec import ( from .teletask import TeleTaskIE from .telewebion import TelewebionIE from .tennistv import TennisTVIE +from .tenplay import TenPlayIE from .testurl import TestURLIE from .tf1 import TF1IE from .tfo import TFOIE diff --git a/youtube_dl/extractor/tenplay.py b/youtube_dl/extractor/tenplay.py new file mode 100644 index 000000000..dff44a4e2 --- /dev/null +++ b/youtube_dl/extractor/tenplay.py @@ -0,0 +1,55 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + parse_age_limit, + parse_iso8601, + smuggle_url, +) + + +class TenPlayIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?10play\.com\.au/[^/]+/episodes/[^/]+/[^/]+/(?P<id>tpv\d{6}[a-z]{5})' + _TEST = { + 'url': 'https://10play.com.au/masterchef/episodes/season-1/masterchef-s1-ep-1/tpv190718kwzga', + 'info_dict': { + 'id': '6060533435001', + 'ext': 'mp4', + 'title': 'MasterChef - S1 Ep. 1', + 'description': 'md5:4fe7b78e28af8f2d900cd20d900ef95c', + 'age_limit': 10, + 'timestamp': 1240828200, + 'upload_date': '20090427', + 'uploader_id': '2199827728001', + }, + 'params': { + 'format': 'bestvideo', + 'skip_download': True, + } + } + BRIGHTCOVE_URL_TEMPLATE = 'https://players.brightcove.net/2199827728001/cN6vRtRQt_default/index.html?videoId=%s' + + def _real_extract(self, url): + content_id = self._match_id(url) + data = self._download_json( + 'https://10play.com.au/api/video/' + content_id, content_id) + video = data.get('video') or {} + metadata = data.get('metaData') or {} + brightcove_id = video.get('videoId') or metadata['showContentVideoId'] + brightcove_url = smuggle_url( + self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, + {'geo_countries': ['AU']}) + + return { + '_type': 'url_transparent', + 'url': brightcove_url, + 'id': content_id, + 'title': video.get('title') or metadata.get('pageContentName') or metadata.get('showContentName'), + 'description': video.get('description'), + 'age_limit': parse_age_limit(video.get('showRatingClassification') or metadata.get('showProgramClassification')), + 'series': metadata.get('showName'), + 'season': metadata.get('showContentSeason'), + 'timestamp': parse_iso8601(metadata.get('contentPublishDate') or metadata.get('pageContentPublishDate')), + 'ie_key': 'BrightcoveNew', + } From 71fa0b04f9099090f43f6747632a9bdc3a4b1015 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Mon, 28 Oct 2019 13:30:30 +0100 Subject: [PATCH 33/65] [makertv] remove extractor --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/makertv.py | 32 ------------------------------ 2 files changed, 33 deletions(-) delete mode 100644 youtube_dl/extractor/makertv.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 339a141a5..4229518fd 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -604,7 +604,6 @@ from .mailru import ( MailRuMusicIE, MailRuMusicSearchIE, ) -from .makertv import MakerTVIE from .malltv import MallTVIE from .mangomolo import ( MangomoloVideoIE, diff --git a/youtube_dl/extractor/makertv.py b/youtube_dl/extractor/makertv.py deleted file mode 100644 index 8eda69cfc..000000000 --- a/youtube_dl/extractor/makertv.py +++ /dev/null @@ -1,32 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor - - -class MakerTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:(?:www\.)?maker\.tv/(?:[^/]+/)*video|makerplayer\.com/embed/maker)/(?P<id>[a-zA-Z0-9]{12})' - _TEST = { - 'url': 'http://www.maker.tv/video/Fh3QgymL9gsc', - 'md5': 'ca237a53a8eb20b6dc5bd60564d4ab3e', - 'info_dict': { - 'id': 'Fh3QgymL9gsc', - 'ext': 'mp4', - 'title': 'Maze Runner: The Scorch Trials Official Movie Review', - 'description': 'md5:11ff3362d7ef1d679fdb649f6413975a', - 'upload_date': '20150918', - 'timestamp': 1442549540, - } - } - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - jwplatform_id = self._search_regex(r'jw_?id="([^"]+)"', webpage, 'jwplatform id') - - return { - '_type': 'url_transparent', - 'id': video_id, - 'url': 'jwplatform:%s' % jwplatform_id, - 'ie_key': 'JWPlatform', - } From 80c2126e80bc41f7b66d325c4c67c61887c58fb0 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Mon, 28 Oct 2019 13:32:35 +0100 Subject: [PATCH 34/65] [thesun] fix extraction(closes #16966) --- youtube_dl/extractor/thesun.py | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/thesun.py b/youtube_dl/extractor/thesun.py index 22d003776..15d4a6932 100644 --- a/youtube_dl/extractor/thesun.py +++ b/youtube_dl/extractor/thesun.py @@ -3,7 +3,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from .ooyala import OoyalaIE +from ..utils import extract_attributes class TheSunIE(InfoExtractor): @@ -16,6 +16,7 @@ class TheSunIE(InfoExtractor): }, 'playlist_count': 2, } + BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' def _real_extract(self, url): article_id = self._match_id(url) @@ -23,10 +24,15 @@ class TheSunIE(InfoExtractor): webpage = self._download_webpage(url, article_id) entries = [] - for ooyala_id in re.findall( - r'<[^>]+\b(?:id\s*=\s*"thesun-ooyala-player-|data-content-id\s*=\s*")([^"]+)', + for video in re.findall( + r'<video[^>]+data-video-id-pending=[^>]+>', webpage): - entries.append(OoyalaIE._build_url_result(ooyala_id)) + attrs = extract_attributes(video) + video_id = attrs['data-video-id-pending'] + account_id = attrs.get('data-account', '5067014667001') + entries.append(self.url_result( + self.BRIGHTCOVE_URL_TEMPLATE % (account_id, video_id), + 'BrightcoveNew', video_id)) return self.playlist_result( entries, article_id, self._og_search_title(webpage, fatal=False)) From 0f9d53566a5956854af77173c0e910ed7454aadf Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Mon, 28 Oct 2019 15:17:06 +0100 Subject: [PATCH 35/65] [la7] update Kaltura service URL(closes #22358) --- youtube_dl/extractor/la7.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/la7.py b/youtube_dl/extractor/la7.py index 6373268c4..c3b4ffa7e 100644 --- a/youtube_dl/extractor/la7.py +++ b/youtube_dl/extractor/la7.py @@ -20,7 +20,7 @@ class LA7IE(InfoExtractor): 'url': 'http://www.la7.it/crozza/video/inccool8-02-10-2015-163722', 'md5': '8b613ffc0c4bf9b9e377169fc19c214c', 'info_dict': { - 'id': 'inccool8-02-10-2015-163722', + 'id': '0_42j6wd36', 'ext': 'mp4', 'title': 'Inc.Cool8', 'description': 'Benvenuti nell\'incredibile mondo della INC. COOL. 8. dove “INC.” sta per “Incorporated” “COOL” sta per “fashion” ed Eight sta per il gesto atletico', @@ -57,7 +57,7 @@ class LA7IE(InfoExtractor): return { '_type': 'url_transparent', 'url': smuggle_url('kaltura:103:%s' % player_data['vid'], { - 'service_url': 'http://kdam.iltrovatore.it', + 'service_url': 'http://nkdam.iltrovatore.it', }), 'id': video_id, 'title': player_data['title'], From 3e252cca0e81aef55b0288f86991bb566878a9fc Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Mon, 28 Oct 2019 17:39:01 +0100 Subject: [PATCH 36/65] [macgamestore] remove extractor Covered by generic extractor --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/macgamestore.py | 42 ---------------------------- 2 files changed, 43 deletions(-) delete mode 100644 youtube_dl/extractor/macgamestore.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 4229518fd..1807744be 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -598,7 +598,6 @@ from .lynda import ( LyndaCourseIE ) from .m6 import M6IE -from .macgamestore import MacGameStoreIE from .mailru import ( MailRuIE, MailRuMusicIE, diff --git a/youtube_dl/extractor/macgamestore.py b/youtube_dl/extractor/macgamestore.py deleted file mode 100644 index 43db9929c..000000000 --- a/youtube_dl/extractor/macgamestore.py +++ /dev/null @@ -1,42 +0,0 @@ -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..utils import ExtractorError - - -class MacGameStoreIE(InfoExtractor): - IE_NAME = 'macgamestore' - IE_DESC = 'MacGameStore trailers' - _VALID_URL = r'https?://(?:www\.)?macgamestore\.com/mediaviewer\.php\?trailer=(?P<id>\d+)' - - _TEST = { - 'url': 'http://www.macgamestore.com/mediaviewer.php?trailer=2450', - 'md5': '8649b8ea684b6666b4c5be736ecddc61', - 'info_dict': { - 'id': '2450', - 'ext': 'm4v', - 'title': 'Crow', - } - } - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage( - url, video_id, 'Downloading trailer page') - - if '>Missing Media<' in webpage: - raise ExtractorError( - 'Trailer %s does not exist' % video_id, expected=True) - - video_title = self._html_search_regex( - r'<title>MacGameStore: (.*?) Trailer', webpage, 'title') - - video_url = self._html_search_regex( - r'(?s)', - webpage, 'video URL') - - return { - 'id': video_id, - 'url': video_url, - 'title': video_title - } From 831b732da1d0796a1927af8767d76af780cc90f0 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 28 Oct 2019 17:41:17 +0100 Subject: [PATCH 37/65] [learnr] remove extractor --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/learnr.py | 33 ------------------------------ 2 files changed, 34 deletions(-) delete mode 100644 youtube_dl/extractor/learnr.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 1807744be..9f3a5f8a5 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -546,7 +546,6 @@ from .lcp import ( LcpPlayIE, LcpIE, ) -from .learnr import LearnrIE from .lecture2go import Lecture2GoIE from .lecturio import ( LecturioIE, diff --git a/youtube_dl/extractor/learnr.py b/youtube_dl/extractor/learnr.py deleted file mode 100644 index 1435e090e..000000000 --- a/youtube_dl/extractor/learnr.py +++ /dev/null @@ -1,33 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor - - -class LearnrIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?learnr\.pro/view/video/(?P[0-9]+)' - _TEST = { - 'url': 'http://www.learnr.pro/view/video/51624-web-development-tutorial-for-beginners-1-how-to-build-webpages-with-html-css-javascript', - 'md5': '3719fdf0a68397f49899e82c308a89de', - 'info_dict': { - 'id': '51624', - 'ext': 'mp4', - 'title': 'Web Development Tutorial for Beginners (#1) - How to build webpages with HTML, CSS, Javascript', - 'description': 'md5:b36dbfa92350176cdf12b4d388485503', - 'uploader': 'LearnCode.academy', - 'uploader_id': 'learncodeacademy', - 'upload_date': '20131021', - }, - 'add_ie': ['Youtube'], - } - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - return { - '_type': 'url_transparent', - 'url': self._search_regex( - r"videoId\s*:\s*'([^']+)'", webpage, 'youtube id'), - 'id': video_id, - } From b3c2fa6dad607da6455a13d232461d4380e4b53c Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 28 Oct 2019 17:42:33 +0100 Subject: [PATCH 38/65] [tutv] remove extractor --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/tutv.py | 36 ------------------------------ 2 files changed, 37 deletions(-) delete mode 100644 youtube_dl/extractor/tutv.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 9f3a5f8a5..39282b785 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1183,7 +1183,6 @@ from .tunein import ( ) from .tunepk import TunePkIE from .turbo import TurboIE -from .tutv import TutvIE from .tv2 import ( TV2IE, TV2ArticleIE, diff --git a/youtube_dl/extractor/tutv.py b/youtube_dl/extractor/tutv.py deleted file mode 100644 index 362318b24..000000000 --- a/youtube_dl/extractor/tutv.py +++ /dev/null @@ -1,36 +0,0 @@ -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..compat import ( - compat_b64decode, - compat_parse_qs, -) - - -class TutvIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?tu\.tv/videos/(?P[^/?]+)' - _TEST = { - 'url': 'http://tu.tv/videos/robots-futbolistas', - 'md5': '0cd9e28ad270488911b0d2a72323395d', - 'info_dict': { - 'id': '2973058', - 'ext': 'mp4', - 'title': 'Robots futbolistas', - }, - } - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - - internal_id = self._search_regex(r'codVideo=([0-9]+)', webpage, 'internal video ID') - - data_content = self._download_webpage( - 'http://tu.tv/flvurl.php?codVideo=%s' % internal_id, video_id, 'Downloading video info') - video_url = compat_b64decode(compat_parse_qs(data_content)['kpt'][0]).decode('utf-8') - - return { - 'id': internal_id, - 'url': video_url, - 'title': self._og_search_title(webpage), - } From 702984eca955f61811078c33337faf9eebeb48c8 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 28 Oct 2019 17:49:05 +0100 Subject: [PATCH 39/65] [hark] remove extractor --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/hark.py | 33 ------------------------------ 2 files changed, 34 deletions(-) delete mode 100644 youtube_dl/extractor/hark.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 39282b785..114ede8b9 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -428,7 +428,6 @@ from .googlesearch import GoogleSearchIE from .goshgay import GoshgayIE from .gputechconf import GPUTechConfIE from .groupon import GrouponIE -from .hark import HarkIE from .hbo import HBOIE from .hearthisat import HearThisAtIE from .heise import HeiseIE diff --git a/youtube_dl/extractor/hark.py b/youtube_dl/extractor/hark.py deleted file mode 100644 index 342a6130e..000000000 --- a/youtube_dl/extractor/hark.py +++ /dev/null @@ -1,33 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor - - -class HarkIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?hark\.com/clips/(?P.+?)-.+' - _TEST = { - 'url': 'http://www.hark.com/clips/mmbzyhkgny-obama-beyond-the-afghan-theater-we-only-target-al-qaeda-on-may-23-2013', - 'md5': '6783a58491b47b92c7c1af5a77d4cbee', - 'info_dict': { - 'id': 'mmbzyhkgny', - 'ext': 'mp3', - 'title': 'Obama: \'Beyond The Afghan Theater, We Only Target Al Qaeda\' on May 23, 2013', - 'description': 'President Barack Obama addressed the nation live on May 23, 2013 in a speech aimed at addressing counter-terrorism policies including the use of drone strikes, detainees at Guantanamo Bay prison facility, and American citizens who are terrorists.', - 'duration': 11, - } - } - - def _real_extract(self, url): - video_id = self._match_id(url) - data = self._download_json( - 'http://www.hark.com/clips/%s.json' % video_id, video_id) - - return { - 'id': video_id, - 'url': data['url'], - 'title': data['name'], - 'description': data.get('description'), - 'thumbnail': data.get('image_original'), - 'duration': data.get('duration'), - } From 895e5c03db310ee97d585360ef8e6ae117e4cbd6 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 28 Oct 2019 19:31:20 +0100 Subject: [PATCH 40/65] [nbcnews] fix extraction closes #12569 closes #12576 closes #21703 closes #21923 --- youtube_dl/extractor/nbc.py | 86 +++++++++++++++++++++++++++---------- 1 file changed, 63 insertions(+), 23 deletions(-) diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py index 10680b202..5bc39d002 100644 --- a/youtube_dl/extractor/nbc.py +++ b/youtube_dl/extractor/nbc.py @@ -9,9 +9,13 @@ from .theplatform import ThePlatformIE from .adobepass import AdobePassIE from ..compat import compat_urllib_parse_unquote from ..utils import ( - smuggle_url, - update_url_query, int_or_none, + js_to_json, + parse_duration, + smuggle_url, + try_get, + unified_timestamp, + update_url_query, ) @@ -285,13 +289,12 @@ class NBCNewsIE(ThePlatformIE): _TESTS = [ { 'url': 'http://www.nbcnews.com/watch/nbcnews-com/how-twitter-reacted-to-the-snowden-interview-269389891880', - 'md5': 'af1adfa51312291a017720403826bb64', + 'md5': 'cf4bc9e6ce0130f00f545d80ecedd4bf', 'info_dict': { 'id': '269389891880', 'ext': 'mp4', 'title': 'How Twitter Reacted To The Snowden Interview', 'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64', - 'uploader': 'NBCU-NEWS', 'timestamp': 1401363060, 'upload_date': '20140529', }, @@ -309,28 +312,26 @@ class NBCNewsIE(ThePlatformIE): }, { 'url': 'http://www.nbcnews.com/nightly-news/video/nightly-news-with-brian-williams-full-broadcast-february-4-394064451844', - 'md5': '73135a2e0ef819107bbb55a5a9b2a802', + 'md5': '8eb831eca25bfa7d25ddd83e85946548', 'info_dict': { 'id': '394064451844', 'ext': 'mp4', 'title': 'Nightly News with Brian Williams Full Broadcast (February 4)', 'description': 'md5:1c10c1eccbe84a26e5debb4381e2d3c5', 'timestamp': 1423104900, - 'uploader': 'NBCU-NEWS', 'upload_date': '20150205', }, }, { 'url': 'http://www.nbcnews.com/business/autos/volkswagen-11-million-vehicles-could-have-suspect-software-emissions-scandal-n431456', - 'md5': 'a49e173825e5fcd15c13fc297fced39d', + 'md5': '4a8c4cec9e1ded51060bdda36ff0a5c0', 'info_dict': { - 'id': '529953347624', + 'id': 'n431456', 'ext': 'mp4', - 'title': 'Volkswagen U.S. Chief:\xa0 We Have Totally Screwed Up', - 'description': 'md5:c8be487b2d80ff0594c005add88d8351', + 'title': "Volkswagen U.S. Chief: We 'Totally Screwed Up'", + 'description': 'md5:d22d1281a24f22ea0880741bb4dd6301', 'upload_date': '20150922', 'timestamp': 1442917800, - 'uploader': 'NBCU-NEWS', }, }, { @@ -343,7 +344,6 @@ class NBCNewsIE(ThePlatformIE): 'description': 'md5:74752b7358afb99939c5f8bb2d1d04b1', 'upload_date': '20160420', 'timestamp': 1461152093, - 'uploader': 'NBCU-NEWS', }, }, { @@ -357,7 +357,6 @@ class NBCNewsIE(ThePlatformIE): 'thumbnail': r're:^https?://.*\.jpg$', 'timestamp': 1406937606, 'upload_date': '20140802', - 'uploader': 'NBCU-NEWS', }, }, { @@ -373,20 +372,61 @@ class NBCNewsIE(ThePlatformIE): def _real_extract(self, url): video_id = self._match_id(url) - if not video_id.isdigit(): - webpage = self._download_webpage(url, video_id) + webpage = self._download_webpage(url, video_id) - data = self._parse_json(self._search_regex( - r'window\.__data\s*=\s*({.+});', webpage, - 'bootstrap json'), video_id) - video_id = data['article']['content'][0]['primaryMedia']['video']['mpxMetadata']['id'] + data = self._parse_json(self._search_regex( + r'window\.__data\s*=\s*({.+});', webpage, + 'bootstrap json'), video_id, js_to_json) + video_data = try_get(data, lambda x: x['video']['current'], dict) + if not video_data: + video_data = data['article']['content'][0]['primaryMedia']['video'] + title = video_data['headline']['primary'] + + formats = [] + for va in video_data.get('videoAssets', []): + public_url = va.get('publicUrl') + if not public_url: + continue + if '://link.theplatform.com/' in public_url: + public_url = update_url_query(public_url, {'format': 'redirect'}) + format_id = va.get('format') + if format_id == 'M3U': + formats.extend(self._extract_m3u8_formats( + public_url, video_id, 'mp4', 'm3u8_native', + m3u8_id=format_id, fatal=False)) + continue + tbr = int_or_none(va.get('bitrate'), 1000) + if tbr: + format_id += '-%d' % tbr + formats.append({ + 'format_id': format_id, + 'url': public_url, + 'width': int_or_none(va.get('width')), + 'height': int_or_none(va.get('height')), + 'tbr': tbr, + 'ext': 'mp4', + }) + self._sort_formats(formats) + + subtitles = {} + closed_captioning = video_data.get('closedCaptioning') + if closed_captioning: + for cc_url in closed_captioning.values(): + if not cc_url: + continue + subtitles.setdefault('en', []).append({ + 'url': cc_url, + }) return { - '_type': 'url_transparent', 'id': video_id, - # http://feed.theplatform.com/f/2E2eJC/nbcnews also works - 'url': update_url_query('http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews', {'byId': video_id}), - 'ie_key': 'ThePlatformFeed', + 'title': title, + 'description': try_get(video_data, lambda x: x['description']['primary']), + 'thumbnail': try_get(video_data, lambda x: x['primaryImage']['url']['primary']), + 'duration': parse_duration(video_data.get('duration')), + 'timestamp': unified_timestamp(video_data.get('datePublished')), + 'formats': formats, + 'subtitles': subtitles, } From 83e49259bfd4e0b54a4b53c30742109555087e3a Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 28 Oct 2019 19:45:42 +0100 Subject: [PATCH 41/65] [internetvideoarchive] fix extraction --- youtube_dl/extractor/internetvideoarchive.py | 92 ++++++-------------- 1 file changed, 28 insertions(+), 64 deletions(-) diff --git a/youtube_dl/extractor/internetvideoarchive.py b/youtube_dl/extractor/internetvideoarchive.py index 76cc5ec3e..59b0a90c3 100644 --- a/youtube_dl/extractor/internetvideoarchive.py +++ b/youtube_dl/extractor/internetvideoarchive.py @@ -1,15 +1,13 @@ from __future__ import unicode_literals +import json +import re + from .common import InfoExtractor from ..compat import ( compat_parse_qs, compat_urlparse, ) -from ..utils import ( - determine_ext, - int_or_none, - xpath_text, -) class InternetVideoArchiveIE(InfoExtractor): @@ -20,7 +18,7 @@ class InternetVideoArchiveIE(InfoExtractor): 'info_dict': { 'id': '194487', 'ext': 'mp4', - 'title': 'KICK-ASS 2', + 'title': 'Kick-Ass 2', 'description': 'md5:c189d5b7280400630a1d3dd17eaa8d8a', }, 'params': { @@ -33,68 +31,34 @@ class InternetVideoArchiveIE(InfoExtractor): def _build_json_url(query): return 'http://video.internetvideoarchive.net/player/6/configuration.ashx?' + query - @staticmethod - def _build_xml_url(query): - return 'http://video.internetvideoarchive.net/flash/players/flashconfiguration.aspx?' + query - def _real_extract(self, url): - query = compat_urlparse.urlparse(url).query - query_dic = compat_parse_qs(query) - video_id = query_dic['publishedid'][0] - - if '/player/' in url: - configuration = self._download_json(url, video_id) - - # There are multiple videos in the playlist whlie only the first one - # matches the video played in browsers - video_info = configuration['playlist'][0] - title = video_info['title'] - - formats = [] - for source in video_info['sources']: - file_url = source['file'] - if determine_ext(file_url) == 'm3u8': - m3u8_formats = self._extract_m3u8_formats( - file_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False) - if m3u8_formats: - formats.extend(m3u8_formats) - file_url = m3u8_formats[0]['url'] - formats.extend(self._extract_f4m_formats( - file_url.replace('.m3u8', '.f4m'), - video_id, f4m_id='hds', fatal=False)) - formats.extend(self._extract_mpd_formats( - file_url.replace('.m3u8', '.mpd'), - video_id, mpd_id='dash', fatal=False)) - else: - a_format = { - 'url': file_url, - } - - if source.get('label') and source['label'][-4:] == ' kbs': - tbr = int_or_none(source['label'][:-4]) - a_format.update({ - 'tbr': tbr, - 'format_id': 'http-%d' % tbr, - }) - formats.append(a_format) - - self._sort_formats(formats) - - description = video_info.get('description') - thumbnail = video_info.get('image') - else: - configuration = self._download_xml(url, video_id) - formats = [{ - 'url': xpath_text(configuration, './file', 'file URL', fatal=True), - }] - thumbnail = xpath_text(configuration, './image', 'thumbnail') - title = 'InternetVideoArchive video %s' % video_id - description = None + query = compat_parse_qs(compat_urlparse.urlparse(url).query) + video_id = query['publishedid'][0] + data = self._download_json( + 'https://video.internetvideoarchive.net/videojs7/videojs7.ivasettings.ashx', + video_id, data=json.dumps({ + 'customerid': query['customerid'][0], + 'publishedid': video_id, + }).encode()) + title = data['Title'] + formats = self._extract_m3u8_formats( + data['VideoUrl'], video_id, 'mp4', + 'm3u8_native', m3u8_id='hls', fatal=False) + file_url = formats[0]['url'] + if '.ism/' in file_url: + replace_url = lambda x: re.sub(r'\.ism/[^?]+', '.ism/' + x, file_url) + formats.extend(self._extract_f4m_formats( + replace_url('.f4m'), video_id, f4m_id='hds', fatal=False)) + formats.extend(self._extract_mpd_formats( + replace_url('.mpd'), video_id, mpd_id='dash', fatal=False)) + formats.extend(self._extract_ism_formats( + replace_url('Manifest'), video_id, ism_id='mss', fatal=False)) + self._sort_formats(formats) return { 'id': video_id, 'title': title, 'formats': formats, - 'thumbnail': thumbnail, - 'description': description, + 'thumbnail': data.get('PosterUrl'), + 'description': data.get('Description'), } From 0086726e8674e9edec0682e7a84275c3c25ce646 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 28 Oct 2019 19:48:34 +0100 Subject: [PATCH 42/65] [videodetective] fix extraction --- youtube_dl/extractor/videodetective.py | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/videodetective.py b/youtube_dl/extractor/videodetective.py index a19411a05..fe70db713 100644 --- a/youtube_dl/extractor/videodetective.py +++ b/youtube_dl/extractor/videodetective.py @@ -1,7 +1,6 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import compat_urlparse from .internetvideoarchive import InternetVideoArchiveIE @@ -13,7 +12,7 @@ class VideoDetectiveIE(InfoExtractor): 'info_dict': { 'id': '194487', 'ext': 'mp4', - 'title': 'KICK-ASS 2', + 'title': 'Kick-Ass 2', 'description': 'md5:c189d5b7280400630a1d3dd17eaa8d8a', }, 'params': { @@ -24,7 +23,7 @@ class VideoDetectiveIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - og_video = self._og_search_video_url(webpage) - query = compat_urlparse.urlparse(og_video).query - return self.url_result(InternetVideoArchiveIE._build_json_url(query), ie=InternetVideoArchiveIE.ie_key()) + query = 'customerid=69249&publishedid=' + video_id + return self.url_result( + InternetVideoArchiveIE._build_json_url(query), + ie=InternetVideoArchiveIE.ie_key()) From cfabc505984acb3830aeac7759d913bb885d64b6 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 28 Oct 2019 22:55:01 +0100 Subject: [PATCH 43/65] [mtv] fix extraction for mtv.de (closes #22113) --- youtube_dl/extractor/mtv.py | 51 ++++++++++++++----------------------- 1 file changed, 19 insertions(+), 32 deletions(-) diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py index 7a3b57abd..7e95ca18e 100644 --- a/youtube_dl/extractor/mtv.py +++ b/youtube_dl/extractor/mtv.py @@ -425,14 +425,14 @@ class MTVVideoIE(MTVServicesInfoExtractor): class MTVDEIE(MTVServicesInfoExtractor): IE_NAME = 'mtv.de' - _VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:artists|shows|news)/(?:[^/]+/)*(?P\d+)-[^/#?]+/*(?:[#?].*)?$' + _VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:musik/videoclips|folgen|news)/(?P[0-9a-z]+)' _TESTS = [{ - 'url': 'http://www.mtv.de/artists/10571-cro/videos/61131-traum', + 'url': 'http://www.mtv.de/musik/videoclips/2gpnv7/Traum', 'info_dict': { - 'id': 'music_video-a50bc5f0b3aa4b3190aa', - 'ext': 'flv', - 'title': 'MusicVideo_cro-traum', - 'description': 'Cro - Traum', + 'id': 'd5d472bc-f5b7-11e5-bffd-a4badb20dab5', + 'ext': 'mp4', + 'title': 'Traum', + 'description': 'Traum', }, 'params': { # rtmp download @@ -441,11 +441,12 @@ class MTVDEIE(MTVServicesInfoExtractor): 'skip': 'Blocked at Travis CI', }, { # mediagen URL without query (e.g. http://videos.mtvnn.com/mediagen/e865da714c166d18d6f80893195fcb97) - 'url': 'http://www.mtv.de/shows/933-teen-mom-2/staffeln/5353/folgen/63565-enthullungen', + 'url': 'http://www.mtv.de/folgen/6b1ylu/teen-mom-2-enthuellungen-S5-F1', 'info_dict': { - 'id': 'local_playlist-f5ae778b9832cc837189', - 'ext': 'flv', - 'title': 'Episode_teen-mom-2_shows_season-5_episode-1_full-episode_part1', + 'id': '1e5a878b-31c5-11e7-a442-0e40cf2fc285', + 'ext': 'mp4', + 'title': 'Teen Mom 2', + 'description': 'md5:dc65e357ef7e1085ed53e9e9d83146a7', }, 'params': { # rtmp download @@ -453,7 +454,7 @@ class MTVDEIE(MTVServicesInfoExtractor): }, 'skip': 'Blocked at Travis CI', }, { - 'url': 'http://www.mtv.de/news/77491-mtv-movies-spotlight-pixels-teil-3', + 'url': 'http://www.mtv.de/news/glolix/77491-mtv-movies-spotlight--pixels--teil-3', 'info_dict': { 'id': 'local_playlist-4e760566473c4c8c5344', 'ext': 'mp4', @@ -466,25 +467,11 @@ class MTVDEIE(MTVServicesInfoExtractor): }, 'skip': 'Das Video kann zur Zeit nicht abgespielt werden.', }] + _GEO_COUNTRIES = ['DE'] + _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed' - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - playlist = self._parse_json( - self._search_regex( - r'window\.pagePlaylist\s*=\s*(\[.+?\]);\n', webpage, 'page playlist'), - video_id) - - def _mrss_url(item): - return item['mrss'] + item.get('mrssvars', '') - - # news pages contain single video in playlist with different id - if len(playlist) == 1: - return self._get_videos_info_from_url(_mrss_url(playlist[0]), video_id) - - for item in playlist: - item_id = item.get('id') - if item_id and compat_str(item_id) == video_id: - return self._get_videos_info_from_url(_mrss_url(item), video_id) + def _get_feed_query(self, uri): + return { + 'arcEp': 'mtv.de', + 'mgid': uri, + } From 3cdcebf5470a56df7d52e6f8acbcde5b4b9f0241 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 28 Oct 2019 23:31:14 +0100 Subject: [PATCH 44/65] [mtv] add support for mtvjapan.com --- youtube_dl/extractor/mtv.py | 37 +++++++++++++++++-------------------- 1 file changed, 17 insertions(+), 20 deletions(-) diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py index 7e95ca18e..fedd5f46b 100644 --- a/youtube_dl/extractor/mtv.py +++ b/youtube_dl/extractor/mtv.py @@ -1,3 +1,4 @@ +# coding: utf-8 from __future__ import unicode_literals import re @@ -349,33 +350,29 @@ class MTVIE(MTVServicesInfoExtractor): }] -class MTV81IE(InfoExtractor): - IE_NAME = 'mtv81' - _VALID_URL = r'https?://(?:www\.)?mtv81\.com/videos/(?P[^/?#.]+)' +class MTVJapanIE(MTVServicesInfoExtractor): + IE_NAME = 'mtvjapan' + _VALID_URL = r'https?://(?:www\.)?mtvjapan\.com/videos/(?P[0-9a-z]+)' _TEST = { - 'url': 'http://www.mtv81.com/videos/artist-to-watch/the-godfather-of-japanese-hip-hop-segment-1/', - 'md5': '1edbcdf1e7628e414a8c5dcebca3d32b', + 'url': 'http://www.mtvjapan.com/videos/prayht/fresh-info-cadillac-escalade', 'info_dict': { - 'id': '5e14040d-18a4-47c4-a582-43ff602de88e', + 'id': 'bc01da03-6fe5-4284-8880-f291f4e368f5', 'ext': 'mp4', - 'title': 'Unlocking The Truth|July 18, 2016|1|101|Trailer', - 'description': '"Unlocking the Truth" premieres August 17th at 11/10c.', - 'timestamp': 1468846800, - 'upload_date': '20160718', + 'title': '【Fresh Info】Cadillac ESCALADE Sport Edition', + }, + 'params': { + 'skip_download': True, }, } + _GEO_COUNTRIES = ['JP'] + _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed' - def _extract_mgid(self, webpage): - return self._search_regex( - r'getTheVideo\((["\'])(?Pmgid:.+?)\1', webpage, - 'mgid', group='id') - - def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - mgid = self._extract_mgid(webpage) - return self.url_result('http://media.mtvnservices.com/embed/%s' % mgid) + def _get_feed_query(self, uri): + return { + 'arcEp': 'mtvjapan.com', + 'mgid': uri, + } class MTVVideoIE(MTVServicesInfoExtractor): From 01358b9fc198cafb619a03ed5ad7865a74805611 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 28 Oct 2019 23:34:31 +0100 Subject: [PATCH 45/65] [extractors] add import for MTVJapanIE --- youtube_dl/extractor/extractors.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 114ede8b9..c10bcbcc1 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -666,7 +666,7 @@ from .mtv import ( MTVVideoIE, MTVServicesEmbeddedIE, MTVDEIE, - MTV81IE, + MTVJapanIE, ) from .muenchentv import MuenchenTVIE from .musicplayon import MusicPlayOnIE From dd90a21c28cb1ec592e5961a5f67556edfb3ce87 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 29 Oct 2019 05:49:36 +0700 Subject: [PATCH 46/65] [go] Add support for abc.com and freeform.com (closes #22823, closes #22864) --- youtube_dl/extractor/go.py | 44 ++++++++++++++++++++++++++++++++------ 1 file changed, 38 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/go.py b/youtube_dl/extractor/go.py index 03e48f4ea..107059023 100644 --- a/youtube_dl/extractor/go.py +++ b/youtube_dl/extractor/go.py @@ -40,8 +40,8 @@ class GoIE(AdobePassIE): 'resource_id': 'Disney', } } - _VALID_URL = r'https?://(?:(?:(?P%s)\.)?go|(?Pdisneynow))\.com/(?:(?:[^/]+/)*(?Pvdka\w+)|(?:[^/]+/)*(?P[^/?#]+))'\ - % '|'.join(list(_SITE_INFO.keys()) + ['disneynow']) + _VALID_URL = r'https?://(?:(?:(?P%s)\.)?go|(?Pabc|freeform|disneynow))\.com/(?:(?:[^/]+/)*(?Pvdka\w+)|(?:[^/]+/)*(?P[^/?#]+))'\ + % '|'.join(list(_SITE_INFO.keys())) _TESTS = [{ 'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643', 'info_dict': { @@ -54,6 +54,7 @@ class GoIE(AdobePassIE): # m3u8 download 'skip_download': True, }, + 'skip': 'This content is no longer available.', }, { 'url': 'http://watchdisneyxd.go.com/doraemon', 'info_dict': { @@ -61,6 +62,34 @@ class GoIE(AdobePassIE): 'id': 'SH55574025', }, 'playlist_mincount': 51, + }, { + 'url': 'http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood', + 'info_dict': { + 'id': 'VDKA3609139', + 'ext': 'mp4', + 'title': 'This Guilty Blood', + 'description': 'md5:f18e79ad1c613798d95fdabfe96cd292', + 'age_limit': 14, + }, + 'params': { + 'geo_bypass_ip_block': '3.244.239.0/24', + # m3u8 download + 'skip_download': True, + }, + }, { + 'url': 'https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet', + 'info_dict': { + 'id': 'VDKA13435179', + 'ext': 'mp4', + 'title': 'The Bet', + 'description': 'md5:c66de8ba2e92c6c5c113c3ade84ab404', + 'age_limit': 14, + }, + 'params': { + 'geo_bypass_ip_block': '3.244.239.0/24', + # m3u8 download + 'skip_download': True, + }, }, { 'url': 'http://abc.go.com/shows/the-catch/episode-guide/season-01/10-the-wedding', 'only_matching': True, @@ -95,10 +124,13 @@ class GoIE(AdobePassIE): if not video_id or not site_info: webpage = self._download_webpage(url, display_id or video_id) video_id = self._search_regex( - # There may be inner quotes, e.g. data-video-id="'VDKA3609139'" - # from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood - r'data-video-id=["\']*(VDKA\w+)', webpage, 'video id', - default=video_id) + ( + # There may be inner quotes, e.g. data-video-id="'VDKA3609139'" + # from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood + r'data-video-id=["\']*(VDKA\w+)', + # https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet + r'\b(?:video)?id["\']\s*:\s*["\'](VDKA\w+)' + ), webpage, 'video id', default=video_id) if not site_info: brand = self._search_regex( (r'data-brand=\s*["\']\s*(\d+)', From aef9f87ea4dcfe483c5b776f1c37310766ad818d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 29 Oct 2019 05:52:15 +0700 Subject: [PATCH 47/65] [go] Improve and beautify _VALID_URL --- youtube_dl/extractor/go.py | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/go.py b/youtube_dl/extractor/go.py index 107059023..03cfba91f 100644 --- a/youtube_dl/extractor/go.py +++ b/youtube_dl/extractor/go.py @@ -40,8 +40,17 @@ class GoIE(AdobePassIE): 'resource_id': 'Disney', } } - _VALID_URL = r'https?://(?:(?:(?P%s)\.)?go|(?Pabc|freeform|disneynow))\.com/(?:(?:[^/]+/)*(?Pvdka\w+)|(?:[^/]+/)*(?P[^/?#]+))'\ - % '|'.join(list(_SITE_INFO.keys())) + _VALID_URL = r'''(?x) + https?:// + (?: + (?:(?P%s)\.)?go| + (?Pabc|freeform|disneynow) + )\.com/ + (?: + (?:[^/]+/)*(?P[Vv][Dd][Kk][Aa]\w+)| + (?:[^/]+/)*(?P[^/?\#]+) + ) + ''' % '|'.join(list(_SITE_INFO.keys())) _TESTS = [{ 'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643', 'info_dict': { From 0d7392e68b7ebb7215651da0784e859d7bdff826 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 29 Oct 2019 05:54:32 +0700 Subject: [PATCH 48/65] [ChangeLog] Actualize [ci skip] --- ChangeLog | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) diff --git a/ChangeLog b/ChangeLog index 64233b03b..b664368a1 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,48 @@ +version + +Extractors ++ [go] Add support for abc.com and freeform.com (#22823, #22864) ++ [mtv] Add support for mtvjapan.com +* [mtv] Fix extraction for mtv.de (#22113) +* [videodetective] Fix extraction +* [internetvideoarchive] Fix extraction +* [nbcnews] Fix extraction (#12569, #12576, #21703, #21923) +- [hark] Remove extractor +- [tutv] Remove extractor +- [learnr] Remove extractor +- [macgamestore] Remove extractor +* [la7] Update Kaltura service URL (#22358) +* [thesun] Fix extraction (#16966) +- [makertv] Remove extractor ++ [tenplay] Add support for 10play.com.au (#21446) +* [soundcloud] Improve extraction + * Improve format extraction (#22123) + + Extract uploader_id and uploader_url (#21916) + + Extract all known thumbnails (#19071, #20659) + * Fix extration for private playlists (#20976) + + Add support for playlist embeds (#20976) + * Skip preview formats (#22806) +* [dplay] Improve extraction + + Add support for dplay.fi, dplay.jp and es.dplay.com (#16969) + * Fix it.dplay.com extraction (#22826) + + Extract creator, tags and thumbnails + * Handle playback API call errors ++ [discoverynetworks] Add support for dplay.co.uk +* [vk] Improve extraction + + Add support for Odnoklassniki embeds + + Extract more videos from user lists (#4470) + + Fix wall post audio extraction (#18332) + * Improve error detection (#22568) ++ [odnoklassniki] Add support for embeds +* [puhutv] Improve extraction + * Fix subtitles extraction + * Transform HLS URLs to HTTP URLs + * Improve metadata extraction +* [ceskatelevize] Skip DRM media ++ [facebook] Extract subtitles (#22777) +* [globo] Handle alternative hash signing method + + version 2019.10.22 Core From 53896ca5be9a629c2cbaceb3fe43c707bb217437 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 29 Oct 2019 06:10:20 +0700 Subject: [PATCH 49/65] [utils] Actualize major IPv4 address blocks per country --- youtube_dl/utils.py | 71 +++++++++++++++++++++++---------------------- 1 file changed, 37 insertions(+), 34 deletions(-) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 53117ea90..aed988b88 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -4979,7 +4979,7 @@ class ISO3166Utils(object): class GeoUtils(object): # Major IPv4 address blocks per country _country_ip_map = { - 'AD': '85.94.160.0/19', + 'AD': '46.172.224.0/19', 'AE': '94.200.0.0/13', 'AF': '149.54.0.0/17', 'AG': '209.59.64.0/18', @@ -4987,28 +4987,30 @@ class GeoUtils(object): 'AL': '46.99.0.0/16', 'AM': '46.70.0.0/15', 'AO': '105.168.0.0/13', - 'AP': '159.117.192.0/21', + 'AP': '182.50.184.0/21', + 'AQ': '23.154.160.0/24', 'AR': '181.0.0.0/12', 'AS': '202.70.112.0/20', - 'AT': '84.112.0.0/13', + 'AT': '77.116.0.0/14', 'AU': '1.128.0.0/11', 'AW': '181.41.0.0/18', - 'AZ': '5.191.0.0/16', + 'AX': '185.217.4.0/22', + 'AZ': '5.197.0.0/16', 'BA': '31.176.128.0/17', 'BB': '65.48.128.0/17', 'BD': '114.130.0.0/16', 'BE': '57.0.0.0/8', - 'BF': '129.45.128.0/17', + 'BF': '102.178.0.0/15', 'BG': '95.42.0.0/15', 'BH': '37.131.0.0/17', 'BI': '154.117.192.0/18', 'BJ': '137.255.0.0/16', - 'BL': '192.131.134.0/24', + 'BL': '185.212.72.0/23', 'BM': '196.12.64.0/18', 'BN': '156.31.0.0/16', 'BO': '161.56.0.0/16', 'BQ': '161.0.80.0/20', - 'BR': '152.240.0.0/12', + 'BR': '191.128.0.0/12', 'BS': '24.51.64.0/18', 'BT': '119.2.96.0/19', 'BW': '168.167.0.0/16', @@ -5016,20 +5018,20 @@ class GeoUtils(object): 'BZ': '179.42.192.0/18', 'CA': '99.224.0.0/11', 'CD': '41.243.0.0/16', - 'CF': '196.32.200.0/21', - 'CG': '197.214.128.0/17', + 'CF': '197.242.176.0/21', + 'CG': '160.113.0.0/16', 'CH': '85.0.0.0/13', - 'CI': '154.232.0.0/14', + 'CI': '102.136.0.0/14', 'CK': '202.65.32.0/19', 'CL': '152.172.0.0/14', - 'CM': '165.210.0.0/15', + 'CM': '102.244.0.0/14', 'CN': '36.128.0.0/10', 'CO': '181.240.0.0/12', 'CR': '201.192.0.0/12', 'CU': '152.206.0.0/15', 'CV': '165.90.96.0/19', 'CW': '190.88.128.0/17', - 'CY': '46.198.0.0/15', + 'CY': '31.153.0.0/16', 'CZ': '88.100.0.0/14', 'DE': '53.0.0.0/8', 'DJ': '197.241.0.0/17', @@ -5046,6 +5048,7 @@ class GeoUtils(object): 'EU': '2.16.0.0/13', 'FI': '91.152.0.0/13', 'FJ': '144.120.0.0/16', + 'FK': '80.73.208.0/21', 'FM': '119.252.112.0/20', 'FO': '88.85.32.0/19', 'FR': '90.0.0.0/9', @@ -5055,8 +5058,8 @@ class GeoUtils(object): 'GE': '31.146.0.0/16', 'GF': '161.22.64.0/18', 'GG': '62.68.160.0/19', - 'GH': '45.208.0.0/14', - 'GI': '85.115.128.0/19', + 'GH': '154.160.0.0/12', + 'GI': '95.164.0.0/16', 'GL': '88.83.0.0/19', 'GM': '160.182.0.0/15', 'GN': '197.149.192.0/18', @@ -5085,13 +5088,13 @@ class GeoUtils(object): 'JE': '87.244.64.0/18', 'JM': '72.27.0.0/17', 'JO': '176.29.0.0/16', - 'JP': '126.0.0.0/8', + 'JP': '133.0.0.0/8', 'KE': '105.48.0.0/12', 'KG': '158.181.128.0/17', 'KH': '36.37.128.0/17', 'KI': '103.25.140.0/22', 'KM': '197.255.224.0/20', - 'KN': '198.32.32.0/19', + 'KN': '198.167.192.0/19', 'KP': '175.45.176.0/22', 'KR': '175.192.0.0/10', 'KW': '37.36.0.0/14', @@ -5099,10 +5102,10 @@ class GeoUtils(object): 'KZ': '2.72.0.0/13', 'LA': '115.84.64.0/18', 'LB': '178.135.0.0/16', - 'LC': '192.147.231.0/24', + 'LC': '24.92.144.0/20', 'LI': '82.117.0.0/19', 'LK': '112.134.0.0/15', - 'LR': '41.86.0.0/19', + 'LR': '102.183.0.0/16', 'LS': '129.232.0.0/17', 'LT': '78.56.0.0/13', 'LU': '188.42.0.0/16', @@ -5127,7 +5130,7 @@ class GeoUtils(object): 'MT': '46.11.0.0/16', 'MU': '105.16.0.0/12', 'MV': '27.114.128.0/18', - 'MW': '105.234.0.0/16', + 'MW': '102.70.0.0/15', 'MX': '187.192.0.0/11', 'MY': '175.136.0.0/13', 'MZ': '197.218.0.0/15', @@ -5158,23 +5161,23 @@ class GeoUtils(object): 'PW': '202.124.224.0/20', 'PY': '181.120.0.0/14', 'QA': '37.210.0.0/15', - 'RE': '139.26.0.0/16', + 'RE': '102.35.0.0/16', 'RO': '79.112.0.0/13', - 'RS': '178.220.0.0/14', + 'RS': '93.86.0.0/15', 'RU': '5.136.0.0/13', - 'RW': '105.178.0.0/15', + 'RW': '41.186.0.0/16', 'SA': '188.48.0.0/13', 'SB': '202.1.160.0/19', 'SC': '154.192.0.0/11', - 'SD': '154.96.0.0/13', + 'SD': '102.120.0.0/13', 'SE': '78.64.0.0/12', - 'SG': '152.56.0.0/14', + 'SG': '8.128.0.0/10', 'SI': '188.196.0.0/14', 'SK': '78.98.0.0/15', - 'SL': '197.215.0.0/17', + 'SL': '102.143.0.0/17', 'SM': '89.186.32.0/19', 'SN': '41.82.0.0/15', - 'SO': '197.220.64.0/19', + 'SO': '154.115.192.0/18', 'SR': '186.179.128.0/17', 'SS': '105.235.208.0/21', 'ST': '197.159.160.0/19', @@ -5197,15 +5200,15 @@ class GeoUtils(object): 'TV': '202.2.96.0/19', 'TW': '120.96.0.0/11', 'TZ': '156.156.0.0/14', - 'UA': '93.72.0.0/13', - 'UG': '154.224.0.0/13', - 'US': '3.0.0.0/8', + 'UA': '37.52.0.0/14', + 'UG': '102.80.0.0/13', + 'US': '6.0.0.0/8', 'UY': '167.56.0.0/13', - 'UZ': '82.215.64.0/18', + 'UZ': '84.54.64.0/18', 'VA': '212.77.0.0/19', - 'VC': '24.92.144.0/20', + 'VC': '207.191.240.0/21', 'VE': '186.88.0.0/13', - 'VG': '172.103.64.0/18', + 'VG': '66.81.192.0/20', 'VI': '146.226.0.0/16', 'VN': '14.160.0.0/11', 'VU': '202.80.32.0/20', @@ -5214,8 +5217,8 @@ class GeoUtils(object): 'YE': '134.35.0.0/16', 'YT': '41.242.116.0/22', 'ZA': '41.0.0.0/11', - 'ZM': '165.56.0.0/13', - 'ZW': '41.85.192.0/19', + 'ZM': '102.144.0.0/13', + 'ZW': '102.177.192.0/18', } @classmethod From cae0bbc53831eed38c4af3755de43e223c503270 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 29 Oct 2019 06:11:09 +0700 Subject: [PATCH 50/65] [ChangeLog] Actualize [ci skip] --- ChangeLog | 3 +++ 1 file changed, 3 insertions(+) diff --git a/ChangeLog b/ChangeLog index b664368a1..2957b7ced 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,5 +1,8 @@ version +Core +* [utils] Actualize major IPv4 address blocks per country + Extractors + [go] Add support for abc.com and freeform.com (#22823, #22864) + [mtv] Add support for mtvjapan.com From c4bd9cb7bb57c6e4bbc04fb054dfea14d4ecb171 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 29 Oct 2019 06:12:33 +0700 Subject: [PATCH 51/65] release 2019.10.29 --- .github/ISSUE_TEMPLATE/1_broken_site.md | 6 +++--- .github/ISSUE_TEMPLATE/2_site_support_request.md | 4 ++-- .github/ISSUE_TEMPLATE/3_site_feature_request.md | 4 ++-- .github/ISSUE_TEMPLATE/4_bug_report.md | 6 +++--- .github/ISSUE_TEMPLATE/5_feature_request.md | 4 ++-- ChangeLog | 2 +- docs/supportedsites.md | 10 +++------- youtube_dl/version.py | 2 +- 8 files changed, 17 insertions(+), 21 deletions(-) diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.md b/.github/ISSUE_TEMPLATE/1_broken_site.md index f1afe704c..f82502bd1 100644 --- a/.github/ISSUE_TEMPLATE/1_broken_site.md +++ b/.github/ISSUE_TEMPLATE/1_broken_site.md @@ -18,7 +18,7 @@ title: '' - [ ] I'm reporting a broken site support -- [ ] I've verified that I'm running youtube-dl version **2019.10.22** +- [ ] I've verified that I'm running youtube-dl version **2019.10.29** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar issues including closed ones @@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.10.22 + [debug] youtube-dl version 2019.10.29 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/2_site_support_request.md b/.github/ISSUE_TEMPLATE/2_site_support_request.md index a4dc9b005..5ef983d43 100644 --- a/.github/ISSUE_TEMPLATE/2_site_support_request.md +++ b/.github/ISSUE_TEMPLATE/2_site_support_request.md @@ -19,7 +19,7 @@ labels: 'site-support-request' - [ ] I'm reporting a new site support request -- [ ] I've verified that I'm running youtube-dl version **2019.10.22** +- [ ] I've verified that I'm running youtube-dl version **2019.10.29** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that none of provided URLs violate any copyrights - [ ] I've searched the bugtracker for similar site support requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/3_site_feature_request.md b/.github/ISSUE_TEMPLATE/3_site_feature_request.md index 5bf86adce..8f05aa79f 100644 --- a/.github/ISSUE_TEMPLATE/3_site_feature_request.md +++ b/.github/ISSUE_TEMPLATE/3_site_feature_request.md @@ -18,13 +18,13 @@ title: '' - [ ] I'm reporting a site feature request -- [ ] I've verified that I'm running youtube-dl version **2019.10.22** +- [ ] I've verified that I'm running youtube-dl version **2019.10.29** - [ ] I've searched the bugtracker for similar site feature requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/4_bug_report.md b/.github/ISSUE_TEMPLATE/4_bug_report.md index 7aa5534e5..e90900d8d 100644 --- a/.github/ISSUE_TEMPLATE/4_bug_report.md +++ b/.github/ISSUE_TEMPLATE/4_bug_report.md @@ -18,7 +18,7 @@ title: '' - [ ] I'm reporting a broken site support issue -- [ ] I've verified that I'm running youtube-dl version **2019.10.22** +- [ ] I've verified that I'm running youtube-dl version **2019.10.29** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar bug reports including closed ones @@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.10.22 + [debug] youtube-dl version 2019.10.29 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/5_feature_request.md b/.github/ISSUE_TEMPLATE/5_feature_request.md index 5d3645e3d..7021d7397 100644 --- a/.github/ISSUE_TEMPLATE/5_feature_request.md +++ b/.github/ISSUE_TEMPLATE/5_feature_request.md @@ -19,13 +19,13 @@ labels: 'request' - [ ] I'm reporting a feature request -- [ ] I've verified that I'm running youtube-dl version **2019.10.22** +- [ ] I've verified that I'm running youtube-dl version **2019.10.29** - [ ] I've searched the bugtracker for similar feature requests including closed ones diff --git a/ChangeLog b/ChangeLog index 2957b7ced..fcab1102c 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version +version 2019.10.29 Core * [utils] Actualize major IPv4 address blocks per country diff --git a/docs/supportedsites.md b/docs/supportedsites.md index a1b0edeeb..af905db5a 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -232,7 +232,6 @@ - **DouyuShow** - **DouyuTV**: 斗鱼 - **DPlay** - - **DPlayIt** - **DRBonanza** - **Dropbox** - **DrTuber** @@ -339,7 +338,6 @@ - **Goshgay** - **GPUTechConf** - **Groupon** - - **Hark** - **hbo** - **HearThisAt** - **Heise** @@ -432,7 +430,6 @@ - **Lcp** - **LcpPlay** - **Le**: 乐视网 - - **Learnr** - **Lecture2Go** - **Lecturio** - **LecturioCourse** @@ -466,11 +463,9 @@ - **lynda**: lynda.com videos - **lynda:course**: lynda.com online courses - **m6** - - **macgamestore**: MacGameStore trailers - **mailru**: Видео@Mail.Ru - **mailru:music**: Музыка@Mail.Ru - **mailru:music:search**: Музыка@Mail.Ru - - **MakerTV** - **MallTV** - **mangomolo:live** - **mangomolo:video** @@ -526,8 +521,8 @@ - **mtg**: MTG services - **mtv** - **mtv.de** - - **mtv81** - **mtv:video** + - **mtvjapan** - **mtvservices:embedded** - **MuenchenTV**: münchen.tv - **MusicPlayOn** @@ -815,6 +810,7 @@ - **soundcloud:set** - **soundcloud:trackstation** - **soundcloud:user** + - **SoundcloudEmbed** - **soundgasm** - **soundgasm:profile** - **southpark.cc.com** @@ -887,6 +883,7 @@ - **TeleTask** - **Telewebion** - **TennisTV** + - **TenPlay** - **TF1** - **TFO** - **TheIntercept** @@ -925,7 +922,6 @@ - **tunein:topic** - **TunePk** - **Turbo** - - **Tutv** - **tv.dfb.de** - **TV2** - **tv2.hu** diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 39b355b9e..924f26ca8 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.10.22' +__version__ = '2019.10.29' From 7455832f311843663b416968b9e5a0a0c6134d8d Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Tue, 29 Oct 2019 09:43:17 +0100 Subject: [PATCH 52/65] [fox9] fix extraction --- youtube_dl/extractor/extractors.py | 5 +++- youtube_dl/extractor/fox9.py | 43 +++++++++++++++--------------- 2 files changed, 25 insertions(+), 23 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index c10bcbcc1..15f96fb8f 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -367,7 +367,10 @@ from .fourtube import ( FuxIE, ) from .fox import FOXIE -from .fox9 import FOX9IE +from .fox9 import ( + FOX9IE, + FOX9NewsIE, +) from .foxgay import FoxgayIE from .foxnews import ( FoxNewsIE, diff --git a/youtube_dl/extractor/fox9.py b/youtube_dl/extractor/fox9.py index 17dfffa7b..91f8f7b8a 100644 --- a/youtube_dl/extractor/fox9.py +++ b/youtube_dl/extractor/fox9.py @@ -1,13 +1,23 @@ # coding: utf-8 from __future__ import unicode_literals -from .anvato import AnvatoIE +from .common import InfoExtractor -class FOX9IE(AnvatoIE): - _VALID_URL = r'https?://(?:www\.)?fox9\.com/(?:[^/]+/)+(?P\d+)-story' - _TESTS = [{ - 'url': 'http://www.fox9.com/news/215123287-story', +class FOX9IE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?fox9\.com/video/(?P\d+)' + + def _real_extract(self, url): + video_id = self._match_id(url) + return self.url_result( + 'anvato:anvato_epfox_app_web_prod_b3373168e12f423f41504f207000188daf88251b:' + video_id, + 'Anvato', video_id) + + +class FOX9NewsIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?fox9\.com/news/(?P[^/?&#]+)' + _TEST = { + 'url': 'https://www.fox9.com/news/black-bear-in-tree-draws-crowd-in-downtown-duluth-minnesota', 'md5': 'd6e1b2572c3bab8a849c9103615dd243', 'info_dict': { 'id': '314473', @@ -21,22 +31,11 @@ class FOX9IE(AnvatoIE): 'categories': ['News', 'Sports'], 'tags': ['news', 'video'], }, - }, { - 'url': 'http://www.fox9.com/news/investigators/214070684-story', - 'only_matching': True, - }] + } def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - video_id = self._parse_json( - self._search_regex( - r"this\.videosJson\s*=\s*'(\[.+?\])';", - webpage, 'anvato playlist'), - video_id)[0]['video'] - - return self._get_anvato_videos( - 'anvato_epfox_app_web_prod_b3373168e12f423f41504f207000188daf88251b', - video_id) + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + anvato_id = self._search_regex( + r'anvatoId\s*:\s*[\'"](\d+)', webpage, 'anvato id') + return self.url_result('https://www.fox9.com/video/' + anvato_id, 'FOX9') From 8989349e6dcaa98204f77fb9f1e15a86eecb823d Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Tue, 29 Oct 2019 09:44:07 +0100 Subject: [PATCH 53/65] [onet] improve extraction - add support for onet100.vod.pl domain - extract m3u8 formats - correct audio only format info --- youtube_dl/extractor/onet.py | 54 ++++++++++++++++++++++++------------ 1 file changed, 36 insertions(+), 18 deletions(-) diff --git a/youtube_dl/extractor/onet.py b/youtube_dl/extractor/onet.py index 58da1bc27..e55b2ac89 100644 --- a/youtube_dl/extractor/onet.py +++ b/youtube_dl/extractor/onet.py @@ -20,6 +20,8 @@ from ..utils import ( class OnetBaseIE(InfoExtractor): + _URL_BASE_RE = r'https?://(?:(?:www\.)?onet\.tv|onet100\.vod\.pl)/[a-z]/' + def _search_mvp_id(self, webpage): return self._search_regex( r'id=(["\'])mvp:(?P.+?)\1', webpage, 'mvp id', group='id') @@ -45,7 +47,7 @@ class OnetBaseIE(InfoExtractor): video = response['result'].get('0') formats = [] - for _, formats_dict in video['formats'].items(): + for format_type, formats_dict in video['formats'].items(): if not isinstance(formats_dict, dict): continue for format_id, format_list in formats_dict.items(): @@ -56,21 +58,31 @@ class OnetBaseIE(InfoExtractor): if not video_url: continue ext = determine_ext(video_url) - if format_id == 'ism': + if format_id.startswith('ism'): formats.extend(self._extract_ism_formats( video_url, video_id, 'mss', fatal=False)) elif ext == 'mpd': formats.extend(self._extract_mpd_formats( video_url, video_id, mpd_id='dash', fatal=False)) + elif format_id.startswith('hls'): + formats.extend(self._extract_m3u8_formats( + video_url, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) else: - formats.append({ + http_f = { 'url': video_url, 'format_id': format_id, - 'height': int_or_none(f.get('vertical_resolution')), - 'width': int_or_none(f.get('horizontal_resolution')), 'abr': float_or_none(f.get('audio_bitrate')), - 'vbr': float_or_none(f.get('video_bitrate')), - }) + } + if format_type == 'audio': + http_f['vcodec'] = 'none' + else: + http_f.update({ + 'height': int_or_none(f.get('vertical_resolution')), + 'width': int_or_none(f.get('horizontal_resolution')), + 'vbr': float_or_none(f.get('video_bitrate')), + }) + formats.append(http_f) self._sort_formats(formats) meta = video.get('meta', {}) @@ -105,12 +117,12 @@ class OnetMVPIE(OnetBaseIE): class OnetIE(OnetBaseIE): - _VALID_URL = r'https?://(?:www\.)?onet\.tv/[a-z]/[a-z]+/(?P[0-9a-z-]+)/(?P[0-9a-z]+)' + _VALID_URL = OnetBaseIE._URL_BASE_RE + r'[a-z]+/(?P[0-9a-z-]+)/(?P[0-9a-z]+)' IE_NAME = 'onet.tv' - _TEST = { + _TESTS = [{ 'url': 'http://onet.tv/k/openerfestival/open-er-festival-2016-najdziwniejsze-wymagania-gwiazd/qbpyqc', - 'md5': 'e3ffbf47590032ac3f27249204173d50', + 'md5': '436102770fb095c75b8bb0392d3da9ff', 'info_dict': { 'id': 'qbpyqc', 'display_id': 'open-er-festival-2016-najdziwniejsze-wymagania-gwiazd', @@ -120,7 +132,10 @@ class OnetIE(OnetBaseIE): 'upload_date': '20160705', 'timestamp': 1467721580, }, - } + }, { + 'url': 'https://onet100.vod.pl/k/openerfestival/open-er-festival-2016-najdziwniejsze-wymagania-gwiazd/qbpyqc', + 'only_matching': True, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -140,18 +155,21 @@ class OnetIE(OnetBaseIE): class OnetChannelIE(OnetBaseIE): - _VALID_URL = r'https?://(?:www\.)?onet\.tv/[a-z]/(?P[a-z]+)(?:[?#]|$)' + _VALID_URL = OnetBaseIE._URL_BASE_RE + r'(?P[a-z]+)(?:[?#]|$)' IE_NAME = 'onet.tv:channel' - _TEST = { + _TESTS = [{ 'url': 'http://onet.tv/k/openerfestival', 'info_dict': { 'id': 'openerfestival', - 'title': 'Open\'er Festival Live', - 'description': 'Dziękujemy, że oglądaliście transmisje. Zobaczcie nasze relacje i wywiady z artystami.', + 'title': "Open'er Festival", + 'description': "Tak było na Open'er Festival 2016! Oglądaj nasze reportaże i wywiady z artystami.", }, - 'playlist_mincount': 46, - } + 'playlist_mincount': 35, + }, { + 'url': 'https://onet100.vod.pl/k/openerfestival', + 'only_matching': True, + }] def _real_extract(self, url): channel_id = self._match_id(url) @@ -173,7 +191,7 @@ class OnetChannelIE(OnetBaseIE): 'Downloading channel %s - add --no-playlist to just download video %s' % ( channel_id, video_name)) matches = re.findall( - r']+href=[\'"](https?://(?:www\.)?onet\.tv/[a-z]/[a-z]+/[0-9a-z-]+/[0-9a-z]+)', + r']+href=[\'"](%s[a-z]+/[0-9a-z-]+/[0-9a-z]+)' % self._URL_BASE_RE, webpage) entries = [ self.url_result(video_link, OnetIE.ie_key()) From c56b2ac43ca27b32fb4f7b230d851a61b5fc7cbd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 30 Oct 2019 02:21:03 +0700 Subject: [PATCH 54/65] [tv2dk] Add extractor --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/tv2dk.py | 82 ++++++++++++++++++++++++++++++ 2 files changed, 83 insertions(+) create mode 100644 youtube_dl/extractor/tv2dk.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 15f96fb8f..5d20ba863 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1189,6 +1189,7 @@ from .tv2 import ( TV2IE, TV2ArticleIE, ) +from .tv2dk import TV2DKIE from .tv2hu import TV2HuIE from .tv4 import TV4IE from .tv5mondeplus import TV5MondePlusIE diff --git a/youtube_dl/extractor/tv2dk.py b/youtube_dl/extractor/tv2dk.py new file mode 100644 index 000000000..eb39424df --- /dev/null +++ b/youtube_dl/extractor/tv2dk.py @@ -0,0 +1,82 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import extract_attributes + + +class TV2DKIE(InfoExtractor): + _VALID_URL = r'''(?x) + https?:// + (?:www\.)? + (?: + tvsyd| + tv2ostjylland| + tvmidtvest| + tv2fyn| + tv2east| + tv2lorry| + tv2nord + )\.dk/ + (:[^/]+/)* + (?P[^/?\#&]+) + ''' + _TESTS = [{ + 'url': 'https://www.tvsyd.dk/nyheder/28-10-2019/1930/1930-28-okt-2019?autoplay=1#player', + 'info_dict': { + 'id': '0_52jmwa0p', + 'ext': 'mp4', + 'title': '19:30 - 28. okt. 2019', + 'timestamp': 1572290248, + 'upload_date': '20191028', + 'uploader_id': 'tvsyd', + 'duration': 1347, + 'view_count': int, + }, + 'params': { + 'skip_download': True, + }, + 'add_ie': ['Kaltura'], + }, { + 'url': 'https://www.tv2ostjylland.dk/artikel/minister-gaar-ind-i-sag-om-diabetes-teknologi', + 'only_matching': True, + }, { + 'url': 'https://www.tv2ostjylland.dk/nyheder/28-10-2019/22/2200-nyhederne-mandag-d-28-oktober-2019?autoplay=1#player', + 'only_matching': True, + }, { + 'url': 'https://www.tvmidtvest.dk/nyheder/27-10-2019/1930/1930-27-okt-2019', + 'only_matching': True, + }, { + 'url': 'https://www.tv2fyn.dk/artikel/fyn-kan-faa-landets-foerste-fabrik-til-groent-jetbraendstof', + 'only_matching': True, + }, { + 'url': 'https://www.tv2east.dk/artikel/gods-faar-indleveret-tonsvis-af-aebler-100-kilo-aebler-gaar-til-en-aeblebrandy', + 'only_matching': True, + }, { + 'url': 'https://www.tv2lorry.dk/koebenhavn/rasmus-paludan-evakueret-til-egen-demonstration#player', + 'only_matching': True, + }, { + 'url': 'https://www.tv2nord.dk/artikel/dybt-uacceptabelt', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + entries = [] + for video_el in re.findall(r'(?s)<[^>]+\bdata-entryid\s*=[^>]*>', webpage): + video = extract_attributes(video_el) + kaltura_id = video.get('data-entryid') + if not kaltura_id: + continue + partner_id = video.get('data-partnerid') + if not partner_id: + continue + entries.append(self.url_result( + 'kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura', + video_id=kaltura_id)) + return self.playlist_result(entries) From 9a621ddc3a42769f107f8bd0d67b2c7073ea8256 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 30 Oct 2019 02:21:52 +0700 Subject: [PATCH 55/65] [tv2] Fix and improve extraction (closes #22787) --- youtube_dl/extractor/tv2.py | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/tv2.py b/youtube_dl/extractor/tv2.py index d5071e8a5..1b6590767 100644 --- a/youtube_dl/extractor/tv2.py +++ b/youtube_dl/extractor/tv2.py @@ -11,6 +11,7 @@ from ..utils import ( js_to_json, parse_iso8601, remove_end, + try_get, ) @@ -44,7 +45,14 @@ class TV2IE(InfoExtractor): data = self._download_json( 'http://sumo.tv2.no/api/web/asset/%s/play.json?protocol=%s&videoFormat=SMIL+ISMUSP' % (video_id, protocol), video_id, 'Downloading play JSON')['playback'] - for item in data['items']['item']: + items = try_get(data, lambda x: x['items']['item']) + if not items: + continue + if not isinstance(items, list): + items = [items] + for item in items: + if not isinstance(item, dict): + continue video_url = item.get('url') if not video_url or video_url in format_urls: continue From 45f4a433894556301204b704caca7d6a14286287 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 30 Oct 2019 23:07:35 +0100 Subject: [PATCH 56/65] [yahoo] improve extraction - add support for live streams(closes #3597)(closes #3779)(closes #22178) - bypass cookie consent page for european domains(closes #16948)(closes #22576) - add generic support for embeds(closes #20332) --- youtube_dl/extractor/yahoo.py | 672 +++++++++++++--------------------- 1 file changed, 264 insertions(+), 408 deletions(-) diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index e5ebdd180..ee68096d0 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -3,453 +3,309 @@ from __future__ import unicode_literals import hashlib import itertools -import json import re from .common import InfoExtractor, SearchInfoExtractor from ..compat import ( compat_str, compat_urllib_parse, - compat_urlparse, ) from ..utils import ( clean_html, - determine_ext, - ExtractorError, - extract_attributes, int_or_none, mimetype2ext, + parse_iso8601, smuggle_url, try_get, - unescapeHTML, url_or_none, ) -from .brightcove import ( - BrightcoveLegacyIE, - BrightcoveNewIE, -) -from .nbc import NBCSportsVPlayerIE +from .brightcove import BrightcoveNewIE class YahooIE(InfoExtractor): IE_DESC = 'Yahoo screen and movies' - _VALID_URL = r'(?Phttps?://(?:(?P[a-zA-Z]{2})\.)?[\da-zA-Z_-]+\.yahoo\.com)/(?:[^/]+/)*(?:(?P.+)?-)?(?P[0-9]+)(?:-[a-z]+)?(?:\.html)?' - _TESTS = [ - { - 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html', - 'info_dict': { - 'id': '2d25e626-2378-391f-ada0-ddaf1417e588', - 'ext': 'mp4', - 'title': 'Julian Smith & Travis Legg Watch Julian Smith', - 'description': 'Julian and Travis watch Julian Smith', - 'duration': 6863, - }, + _VALID_URL = r'(?Phttps?://(?:(?P[a-zA-Z]{2}(?:-[a-zA-Z]{2})?|malaysia)\.)?(?:[\da-zA-Z_-]+\.)?yahoo\.com/(?:[^/]+/)*(?P[^?&#]*-[0-9]+)\.html)' + _TESTS = [{ + 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html', + 'info_dict': { + 'id': '2d25e626-2378-391f-ada0-ddaf1417e588', + 'ext': 'mp4', + 'title': 'Julian Smith & Travis Legg Watch Julian Smith', + 'description': 'Julian and Travis watch Julian Smith', + 'duration': 6863, + 'timestamp': 1369812016, + 'upload_date': '20130529', }, - { - 'url': 'http://screen.yahoo.com/wired/codefellas-s1-ep12-cougar-lies-103000935.html', - 'md5': '251af144a19ebc4a033e8ba91ac726bb', - 'info_dict': { - 'id': 'd1dedf8c-d58c-38c3-8963-e899929ae0a9', - 'ext': 'mp4', - 'title': 'Codefellas - The Cougar Lies with Spanish Moss', - 'description': 'md5:66b627ab0a282b26352136ca96ce73c1', - 'duration': 151, - }, - 'skip': 'HTTP Error 404', + }, { + 'url': 'https://screen.yahoo.com/community/community-sizzle-reel-203225340.html?format=embed', + 'md5': '7993e572fac98e044588d0b5260f4352', + 'info_dict': { + 'id': '4fe78544-8d48-39d8-97cd-13f205d9fcdb', + 'ext': 'mp4', + 'title': "Yahoo Saves 'Community'", + 'description': 'md5:4d4145af2fd3de00cbb6c1d664105053', + 'duration': 170, + 'timestamp': 1406838636, + 'upload_date': '20140731', }, - { - 'url': 'https://screen.yahoo.com/community/community-sizzle-reel-203225340.html?format=embed', - 'md5': '7993e572fac98e044588d0b5260f4352', - 'info_dict': { - 'id': '4fe78544-8d48-39d8-97cd-13f205d9fcdb', - 'ext': 'mp4', - 'title': "Yahoo Saves 'Community'", - 'description': 'md5:4d4145af2fd3de00cbb6c1d664105053', - 'duration': 170, - } - }, - { - 'url': 'https://tw.news.yahoo.com/%E6%95%A2%E5%95%8F%E5%B8%82%E9%95%B7%20%E9%BB%83%E7%A7%80%E9%9C%9C%E6%89%B9%E8%B3%B4%E6%B8%85%E5%BE%B7%20%E9%9D%9E%E5%B8%B8%E9%AB%98%E5%82%B2-034024051.html', - 'md5': '45c024bad51e63e9b6f6fad7a43a8c23', - 'info_dict': { - 'id': 'cac903b3-fcf4-3c14-b632-643ab541712f', - 'ext': 'mp4', - 'title': '敢問市長／黃秀霜批賴清德「非常高傲」', - 'description': '直言台南沒捷運 交通居五都之末', - 'duration': 396, - }, - }, - { - 'url': 'https://uk.screen.yahoo.com/editor-picks/cute-raccoon-freed-drain-using-091756545.html', - 'md5': '71298482f7c64cbb7fa064e4553ff1c1', - 'info_dict': { - 'id': 'b3affa53-2e14-3590-852b-0e0db6cd1a58', - 'ext': 'webm', - 'title': 'Cute Raccoon Freed From Drain\u00a0Using Angle Grinder', - 'description': 'md5:f66c890e1490f4910a9953c941dee944', - 'duration': 97, - } - }, - { - 'url': 'https://ca.sports.yahoo.com/video/program-makes-hockey-more-affordable-013127711.html', - 'md5': '57e06440778b1828a6079d2f744212c4', - 'info_dict': { - 'id': 'c9fa2a36-0d4d-3937-b8f6-cc0fb1881e73', - 'ext': 'mp4', - 'title': 'Program that makes hockey more affordable not offered in Manitoba', - 'description': 'md5:c54a609f4c078d92b74ffb9bf1f496f4', - 'duration': 121, - }, - 'skip': 'Video gone', - }, { - 'url': 'https://ca.finance.yahoo.com/news/hackers-sony-more-trouble-well-154609075.html', - 'info_dict': { - 'id': '154609075', - }, - 'playlist': [{ - 'md5': '000887d0dc609bc3a47c974151a40fb8', - 'info_dict': { - 'id': 'e624c4bc-3389-34de-9dfc-025f74943409', - 'ext': 'mp4', - 'title': '\'The Interview\' TV Spot: War', - 'description': 'The Interview', - 'duration': 30, - }, - }, { - 'md5': '81bc74faf10750fe36e4542f9a184c66', - 'info_dict': { - 'id': '1fc8ada0-718e-3abe-a450-bf31f246d1a9', - 'ext': 'mp4', - 'title': '\'The Interview\' TV Spot: Guys', - 'description': 'The Interview', - 'duration': 30, - }, - }], - }, { - 'url': 'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html', - 'md5': '88e209b417f173d86186bef6e4d1f160', - 'info_dict': { - 'id': 'f885cf7f-43d4-3450-9fac-46ac30ece521', - 'ext': 'mp4', - 'title': 'China Moses Is Crazy About the Blues', - 'description': 'md5:9900ab8cd5808175c7b3fe55b979bed0', - 'duration': 128, - } - }, { - 'url': 'https://in.lifestyle.yahoo.com/video/connect-dots-dark-side-virgo-090247395.html', - 'md5': 'd9a083ccf1379127bf25699d67e4791b', - 'info_dict': { - 'id': '52aeeaa3-b3d1-30d8-9ef8-5d0cf05efb7c', - 'ext': 'mp4', - 'title': 'Connect the Dots: Dark Side of Virgo', - 'description': 'md5:1428185051cfd1949807ad4ff6d3686a', - 'duration': 201, - }, - 'skip': 'Domain name in.lifestyle.yahoo.com gone', - }, { - 'url': 'https://www.yahoo.com/movies/v/true-story-trailer-173000497.html', - 'md5': '989396ae73d20c6f057746fb226aa215', - 'info_dict': { - 'id': '071c4013-ce30-3a93-a5b2-e0413cd4a9d1', - 'ext': 'mp4', - 'title': '\'True Story\' Trailer', - 'description': 'True Story', - 'duration': 150, - }, - }, { - 'url': 'https://gma.yahoo.com/pizza-delivery-man-surprised-huge-tip-college-kids-195200785.html', - 'only_matching': True, - }, { - 'note': 'NBC Sports embeds', - 'url': 'http://sports.yahoo.com/blogs/ncaab-the-dagger/tyler-kalinoski-s-buzzer-beater-caps-davidson-s-comeback-win-185609842.html?guid=nbc_cbk_davidsonbuzzerbeater_150313', - 'info_dict': { - 'id': '9CsDKds0kvHI', - 'ext': 'flv', - 'description': 'md5:df390f70a9ba7c95ff1daace988f0d8d', - 'title': 'Tyler Kalinoski hits buzzer-beater to lift Davidson', - 'upload_date': '20150313', - 'uploader': 'NBCU-SPORTS', - 'timestamp': 1426270238, - } - }, { - 'url': 'https://tw.news.yahoo.com/-100120367.html', - 'only_matching': True, - }, { - # Query result is embedded in webpage, but explicit request to video API fails with geo restriction - 'url': 'https://screen.yahoo.com/community/communitary-community-episode-1-ladders-154501237.html', - 'md5': '4fbafb9c9b6f07aa8f870629f6671b35', - 'info_dict': { - 'id': '1f32853c-a271-3eef-8cb6-f6d6872cb504', - 'ext': 'mp4', - 'title': 'Communitary - Community Episode 1: Ladders', - 'description': 'md5:8fc39608213295748e1e289807838c97', - 'duration': 1646, - }, - }, { - # it uses an alias to get the video_id - 'url': 'https://www.yahoo.com/movies/the-stars-of-daddys-home-have-very-different-212843197.html', - 'info_dict': { - 'id': '40eda9c8-8e5f-3552-8745-830f67d0c737', - 'ext': 'mp4', - 'title': 'Will Ferrell & Mark Wahlberg Are Pro-Spanking', - 'description': 'While they play feuding fathers in \'Daddy\'s Home,\' star Will Ferrell & Mark Wahlberg share their true feelings on parenthood.', - }, - }, - { - # config['models']['applet_model']['data']['sapi'] has no query - 'url': 'https://www.yahoo.com/music/livenation/event/galactic-2016', - 'md5': 'dac0c72d502bc5facda80c9e6d5c98db', - 'info_dict': { - 'id': 'a6015640-e9e5-3efb-bb60-05589a183919', - 'ext': 'mp4', - 'description': 'Galactic', - 'title': 'Dolla Diva (feat. Maggie Koerner)', - }, - 'skip': 'redirect to https://www.yahoo.com/music', - }, - { - # yahoo://article/ - 'url': 'https://www.yahoo.com/movies/video/true-story-trailer-173000497.html', - 'info_dict': { - 'id': '071c4013-ce30-3a93-a5b2-e0413cd4a9d1', - 'ext': 'mp4', - 'title': "'True Story' Trailer", - 'description': 'True Story', - }, - 'params': { - 'skip_download': True, - }, - }, - { - # ytwnews://cavideo/ - 'url': 'https://tw.video.yahoo.com/movie-tw/單車天使-中文版預-092316541.html', - 'info_dict': { - 'id': 'ba133ff2-0793-3510-b636-59dfe9ff6cff', - 'ext': 'mp4', - 'title': '單車天使 - 中文版預', - 'description': '中文版預', - }, - 'params': { - 'skip_download': True, - }, - }, - { - # custom brightcove - 'url': 'https://au.tv.yahoo.com/plus7/sunrise/-/watch/37083565/clown-entertainers-say-it-is-hurting-their-business/', - 'info_dict': { - 'id': '5575377707001', - 'ext': 'mp4', - 'title': "Clown entertainers say 'It' is hurting their business", - 'description': 'Stephen King s horror film has much to answer for. Jelby and Mr Loopy the Clowns join us.', - 'timestamp': 1505341164, - 'upload_date': '20170913', - 'uploader_id': '2376984109001', - }, - 'params': { - 'skip_download': True, - }, - }, - { - # custom brightcove, geo-restricted to Australia, bypassable - 'url': 'https://au.tv.yahoo.com/plus7/sunrise/-/watch/37263964/sunrise-episode-wed-27-sep/', - 'only_matching': True, + }, { + 'url': 'https://uk.screen.yahoo.com/editor-picks/cute-raccoon-freed-drain-using-091756545.html', + 'md5': '0b51660361f0e27c9789e7037ef76f4b', + 'info_dict': { + 'id': 'b3affa53-2e14-3590-852b-0e0db6cd1a58', + 'ext': 'mp4', + 'title': 'Cute Raccoon Freed From Drain\u00a0Using Angle Grinder', + 'description': 'md5:f66c890e1490f4910a9953c941dee944', + 'duration': 97, + 'timestamp': 1414489862, + 'upload_date': '20141028', } - ] + }, { + 'url': 'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html', + 'md5': '88e209b417f173d86186bef6e4d1f160', + 'info_dict': { + 'id': 'f885cf7f-43d4-3450-9fac-46ac30ece521', + 'ext': 'mp4', + 'title': 'China Moses Is Crazy About the Blues', + 'description': 'md5:9900ab8cd5808175c7b3fe55b979bed0', + 'duration': 128, + 'timestamp': 1385722202, + 'upload_date': '20131129', + } + }, { + 'url': 'https://www.yahoo.com/movies/v/true-story-trailer-173000497.html', + 'md5': '2a9752f74cb898af5d1083ea9f661b58', + 'info_dict': { + 'id': '071c4013-ce30-3a93-a5b2-e0413cd4a9d1', + 'ext': 'mp4', + 'title': '\'True Story\' Trailer', + 'description': 'True Story', + 'duration': 150, + 'timestamp': 1418919206, + 'upload_date': '20141218', + }, + }, { + 'url': 'https://gma.yahoo.com/pizza-delivery-man-surprised-huge-tip-college-kids-195200785.html', + 'only_matching': True, + }, { + 'note': 'NBC Sports embeds', + 'url': 'http://sports.yahoo.com/blogs/ncaab-the-dagger/tyler-kalinoski-s-buzzer-beater-caps-davidson-s-comeback-win-185609842.html?guid=nbc_cbk_davidsonbuzzerbeater_150313', + 'info_dict': { + 'id': '9CsDKds0kvHI', + 'ext': 'flv', + 'description': 'md5:df390f70a9ba7c95ff1daace988f0d8d', + 'title': 'Tyler Kalinoski hits buzzer-beater to lift Davidson', + 'upload_date': '20150313', + 'uploader': 'NBCU-SPORTS', + 'timestamp': 1426270238, + }, + }, { + 'url': 'https://tw.news.yahoo.com/-100120367.html', + 'only_matching': True, + }, { + # Query result is embedded in webpage, but explicit request to video API fails with geo restriction + 'url': 'https://screen.yahoo.com/community/communitary-community-episode-1-ladders-154501237.html', + 'md5': '4fbafb9c9b6f07aa8f870629f6671b35', + 'info_dict': { + 'id': '1f32853c-a271-3eef-8cb6-f6d6872cb504', + 'ext': 'mp4', + 'title': 'Communitary - Community Episode 1: Ladders', + 'description': 'md5:8fc39608213295748e1e289807838c97', + 'duration': 1646, + 'timestamp': 1440436550, + 'upload_date': '20150824', + 'series': 'Communitary', + 'season_number': 6, + 'episode_number': 1, + }, + }, { + # ytwnews://cavideo/ + 'url': 'https://tw.video.yahoo.com/movie-tw/單車天使-中文版預-092316541.html', + 'info_dict': { + 'id': 'ba133ff2-0793-3510-b636-59dfe9ff6cff', + 'ext': 'mp4', + 'title': '單車天使 - 中文版預', + 'description': '中文版預', + 'timestamp': 1476696196, + 'upload_date': '20161017', + }, + 'params': { + 'skip_download': True, + }, + }, { + # Contains both a Yahoo hosted video and multiple Youtube embeds + 'url': 'https://www.yahoo.com/entertainment/gwen-stefani-reveals-the-pop-hit-she-passed-on-assigns-it-to-her-voice-contestant-instead-033045672.html', + 'info_dict': { + 'id': '46c5d95a-528f-3d03-b732-732fcadd51de', + 'title': 'Gwen Stefani reveals the pop hit she passed on, assigns it to her \'Voice\' contestant instead', + 'description': 'Gwen decided not to record this hit herself, but she decided it was the perfect fit for Kyndall Inskeep.', + }, + 'playlist': [{ + 'info_dict': { + 'id': '966d4262-4fd1-3aaa-b45b-049ca6e38ba6', + 'ext': 'mp4', + 'title': 'Gwen Stefani reveals she turned down one of Sia\'s best songs', + 'description': 'On "The Voice" Tuesday, Gwen Stefani told Taylor Swift which Sia hit was almost hers.', + 'timestamp': 1572406500, + 'upload_date': '20191030', + }, + }, { + 'info_dict': { + 'id': '352CFDOQrKg', + 'ext': 'mp4', + 'title': 'Kyndal Inskeep "Performs the Hell Out of" Sia\'s "Elastic Heart" - The Voice Knockouts 2019', + 'description': 'md5:35b61e94c2ae214bc965ff4245f80d11', + 'uploader': 'The Voice', + 'uploader_id': 'NBCTheVoice', + 'upload_date': '20191029', + }, + }], + 'params': { + 'playlistend': 2, + }, + }, { + 'url': 'https://malaysia.news.yahoo.com/video/bystanders-help-ontario-policeman-bust-190932818.html', + 'only_matching': True, + }, { + 'url': 'https://es-us.noticias.yahoo.com/es-la-puerta-irrompible-que-110539379.html', + 'only_matching': True, + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - page_id = mobj.group('id') - display_id = mobj.group('display_id') or page_id - host = mobj.group('host') - webpage, urlh = self._download_webpage_handle(url, display_id) - if 'err=404' in urlh.geturl(): - raise ExtractorError('Video gone', expected=True) - - # Look for iframed media first - entries = [] - iframe_urls = re.findall(r']+src="(/video/.+?-\d+\.html\?format=embed.*?)"', webpage) - for idx, iframe_url in enumerate(iframe_urls): - entries.append(self.url_result(host + iframe_url, 'Yahoo')) - if entries: - return self.playlist_result(entries, page_id) - - # Look for NBCSports iframes - nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage) - if nbc_sports_url: - return self.url_result(nbc_sports_url, NBCSportsVPlayerIE.ie_key()) - - # Look for Brightcove Legacy Studio embeds - bc_url = BrightcoveLegacyIE._extract_brightcove_url(webpage) - if bc_url: - return self.url_result(bc_url, BrightcoveLegacyIE.ie_key()) - - def brightcove_url_result(bc_url): - return self.url_result( - smuggle_url(bc_url, {'geo_countries': [mobj.group('country')]}), - BrightcoveNewIE.ie_key()) - - # Look for Brightcove New Studio embeds - bc_url = BrightcoveNewIE._extract_url(self, webpage) - if bc_url: - return brightcove_url_result(bc_url) - - brightcove_iframe = self._search_regex( - r'(]+data-video-id=["\']\d+[^>]+>)', webpage, - 'brightcove iframe', default=None) - if brightcove_iframe: - attr = extract_attributes(brightcove_iframe) - src = attr.get('src') - if src: - parsed_src = compat_urlparse.urlparse(src) - qs = compat_urlparse.parse_qs(parsed_src.query) - account_id = qs.get('accountId', ['2376984109001'])[0] - brightcove_id = attr.get('data-video-id') or qs.get('videoId', [None])[0] - if account_id and brightcove_id: - return brightcove_url_result( - 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' - % (account_id, brightcove_id)) - - # Query result is often embedded in webpage as JSON. Sometimes explicit requests - # to video API results in a failure with geo restriction reason therefore using - # embedded query result when present sounds reasonable. - config_json = self._search_regex( - r'window\.Af\.bootstrap\[[^\]]+\]\s*=\s*({.*?"applet_type"\s*:\s*"td-applet-videoplayer".*?});(?:|$)', - webpage, 'videoplayer applet', default=None) - if config_json: - config = self._parse_json(config_json, display_id, fatal=False) - if config: - sapi = config.get('models', {}).get('applet_model', {}).get('data', {}).get('sapi') - if sapi and 'query' in sapi: - info = self._extract_info(display_id, sapi, webpage) - self._sort_formats(info['formats']) - return info - - items_json = self._search_regex( - r'mediaItems: ({.*?})$', webpage, 'items', flags=re.MULTILINE, - default=None) - if items_json is None: - alias = self._search_regex( - r'"aliases":{"video":"(.*?)"', webpage, 'alias', default=None) - if alias is not None: - alias_info = self._download_json( - 'https://www.yahoo.com/_td/api/resource/VideoService.videos;video_aliases=["%s"]' % alias, - display_id, 'Downloading alias info') - video_id = alias_info[0]['id'] - else: - CONTENT_ID_REGEXES = [ - r'YUI\.namespace\("Media"\)\.CONTENT_ID\s*=\s*"([^"]+)"', - r'root\.App\.Cache\.context\.videoCache\.curVideo = \{"([^"]+)"', - r'"first_videoid"\s*:\s*"([^"]+)"', - r'%s[^}]*"ccm_id"\s*:\s*"([^"]+)"' % re.escape(page_id), - r']data-uuid=["\']([^"\']+)', - r']+yahoo://article/view\?.*\buuid=([^&"\']+)', - r']+["\']ytwnews://cavideo/(?:[^/]+/)+([\da-fA-F-]+)[&"\']', - ] - video_id = self._search_regex( - CONTENT_ID_REGEXES, webpage, 'content ID') + url, country, display_id = re.match(self._VALID_URL, url).groups() + if not country: + country = 'us' else: - items = json.loads(items_json) - info = items['mediaItems']['query']['results']['mediaObj'][0] - # The 'meta' field is not always in the video webpage, we request it - # from another page - video_id = info['id'] - return self._get_info(video_id, display_id, webpage) + country = country.split('-')[0] + api_base = 'https://%s.yahoo.com/_td/api/resource/' % country - def _extract_info(self, display_id, query, webpage): - info = query['query']['results']['mediaObj'][0] - meta = info.get('meta') - video_id = info.get('id') + for i, uuid in enumerate(['url=' + url, 'ymedia-alias=' + display_id]): + content = self._download_json( + api_base + 'content;getDetailView=true;uuids=["%s"]' % uuid, + display_id, 'Downloading content JSON metadata', fatal=i == 1) + if content: + item = content['items'][0] + break - if not meta: - msg = info['status'].get('msg') - if msg: - raise ExtractorError( - '%s returned error: %s' % (self.IE_NAME, msg), expected=True) - raise ExtractorError('Unable to extract media object meta') + if item.get('type') != 'video': + entries = [] + cover = item.get('cover') or {} + if cover.get('type') == 'yvideo': + cover_url = cover.get('url') + if cover_url: + entries.append(self.url_result( + cover_url, 'Yahoo', cover.get('uuid'))) + + for e in item.get('body', []): + if e.get('type') == 'videoIframe': + iframe_url = e.get('url') + if not iframe_url: + continue + entries.append(self.url_result(iframe_url)) + + return self.playlist_result( + entries, item.get('uuid'), + item.get('title'), item.get('summary')) + + video_id = item['uuid'] + video = self._download_json( + api_base + 'VideoService.videos;view=full;video_ids=["%s"]' % video_id, + video_id, 'Downloading video JSON metadata')[0] + title = video['title'] + + if country == 'malaysia': + country = 'my' + + is_live = video.get('live_state') == 'live' + fmts = ('m3u8',) if is_live else ('web', 'mp4') + + urls = [] formats = [] - for s in info['streams']: - tbr = int_or_none(s.get('bitrate')) - format_info = { - 'width': int_or_none(s.get('width')), - 'height': int_or_none(s.get('height')), - 'tbr': tbr, - } - - host = s['host'] - path = s['path'] - if host.startswith('rtmp'): - fmt = 'rtmp' - format_info.update({ - 'url': host, - 'play_path': path, - 'ext': 'flv', - }) - else: - if s.get('format') == 'm3u8_playlist': - fmt = 'hls' - format_info.update({ - 'protocol': 'm3u8_native', - 'ext': 'mp4', - }) - else: - fmt = format_info['ext'] = determine_ext(path) - format_url = compat_urlparse.urljoin(host, path) - format_info['url'] = format_url - format_info['format_id'] = fmt + ('-%d' % tbr if tbr else '') - formats.append(format_info) - - closed_captions = self._html_search_regex( - r'"closedcaptions":(\[[^\]]+\])', webpage, 'closed captions', - default='[]') - - cc_json = self._parse_json(closed_captions, video_id, fatal=False) subtitles = {} - if cc_json: - for closed_caption in cc_json: - lang = closed_caption['lang'] - if lang not in subtitles: - subtitles[lang] = [] - subtitles[lang].append({ - 'url': closed_caption['url'], - 'ext': mimetype2ext(closed_caption['content_type']), + for fmt in fmts: + media_obj = self._download_json( + 'https://video-api.yql.yahoo.com/v1/video/sapi/streams/' + video_id, + video_id, 'Downloading %s JSON metadata' % fmt, + headers=self.geo_verification_headers(), query={ + 'format': fmt, + 'region': country.upper(), + })['query']['results']['mediaObj'][0] + msg = media_obj.get('status', {}).get('msg') + + for s in media_obj.get('streams', []): + host = s.get('host') + path = s.get('path') + if not host or not path: + continue + s_url = host + path + if s.get('format') == 'm3u8': + formats.extend(self._extract_m3u8_formats( + s_url, video_id, 'mp4', m3u8_id='hls', fatal=False)) + continue + tbr = int_or_none(s.get('bitrate')) + formats.append({ + 'url': s_url, + 'format_id': fmt + ('-%d' % tbr if tbr else ''), + 'width': int_or_none(s.get('width')), + 'height': int_or_none(s.get('height')), + 'tbr': tbr, + 'fps': int_or_none(s.get('framerate')), }) + for cc in media_obj.get('closedcaptions', []): + cc_url = cc.get('url') + if not cc_url or cc_url in urls: + continue + urls.append(cc_url) + subtitles.setdefault(cc.get('lang') or 'en-US', []).append({ + 'url': cc_url, + 'ext': mimetype2ext(cc.get('content_type')), + }) + + streaming_url = video.get('streaming_url') + if streaming_url and not is_live: + formats.extend(self._extract_m3u8_formats( + streaming_url, video_id, 'mp4', + 'm3u8_native', m3u8_id='hls', fatal=False)) + + if not formats and msg == 'geo restricted': + self.raise_geo_restricted() + + self._sort_formats(formats) + + thumbnails = [] + for thumb in video.get('thumbnails', []): + thumb_url = thumb.get('url') + if not thumb_url: + continue + thumbnails.append({ + 'id': thumb.get('tag'), + 'url': thumb.get('url'), + 'width': int_or_none(thumb.get('width')), + 'height': int_or_none(thumb.get('height')), + }) + + series_info = video.get('series_info') or {} + return { 'id': video_id, - 'display_id': display_id, - 'title': unescapeHTML(meta['title']), + 'title': self._live_title(title) if is_live else title, 'formats': formats, - 'description': clean_html(meta['description']), - 'thumbnail': meta['thumbnail'] if meta.get('thumbnail') else self._og_search_thumbnail(webpage), - 'duration': int_or_none(meta.get('duration')), + 'display_id': display_id, + 'thumbnails': thumbnails, + 'description': clean_html(video.get('description')), + 'timestamp': parse_iso8601(video.get('publish_time')), 'subtitles': subtitles, + 'duration': int_or_none(video.get('duration')), + 'view_count': int_or_none(video.get('view_count')), + 'is_live': is_live, + 'series': video.get('show_name'), + 'season_number': int_or_none(series_info.get('season_number')), + 'episode_number': int_or_none(series_info.get('episode_number')), } - def _get_info(self, video_id, display_id, webpage): - region = self._search_regex( - r'\\?"region\\?"\s*:\s*\\?"([^"]+?)\\?"', - webpage, 'region', fatal=False, default='US').upper() - formats = [] - info = {} - for fmt in ('webm', 'mp4'): - query_result = self._download_json( - 'https://video.media.yql.yahoo.com/v1/video/sapi/streams/' + video_id, - display_id, 'Downloading %s video info' % fmt, query={ - 'protocol': 'http', - 'region': region, - 'format': fmt, - }) - info = self._extract_info(display_id, query_result, webpage) - formats.extend(info['formats']) - formats.extend(self._extract_m3u8_formats( - 'http://video.media.yql.yahoo.com/v1/hls/%s?region=%s' % (video_id, region), - video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) - self._sort_formats(formats) - info['formats'] = formats - return info - class YahooSearchIE(SearchInfoExtractor): IE_DESC = 'Yahoo screen search' From 8040a0d35e11f7b2bf6d698175ab0b12424d696f Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 30 Oct 2019 23:52:09 +0100 Subject: [PATCH 57/65] [yahoo] fix typo --- youtube_dl/extractor/yahoo.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index ee68096d0..6c6bd76e8 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -51,10 +51,10 @@ class YahooIE(InfoExtractor): }, }, { 'url': 'https://uk.screen.yahoo.com/editor-picks/cute-raccoon-freed-drain-using-091756545.html', - 'md5': '0b51660361f0e27c9789e7037ef76f4b', + 'md5': '71298482f7c64cbb7fa064e4553ff1c1', 'info_dict': { 'id': 'b3affa53-2e14-3590-852b-0e0db6cd1a58', - 'ext': 'mp4', + 'ext': 'webm', 'title': 'Cute Raccoon Freed From Drain\u00a0Using Angle Grinder', 'description': 'md5:f66c890e1490f4910a9953c941dee944', 'duration': 97, @@ -164,6 +164,7 @@ class YahooIE(InfoExtractor): 'params': { 'playlistend': 2, }, + 'expected_warnings': ['HTTP Error 404'], }, { 'url': 'https://malaysia.news.yahoo.com/video/bystanders-help-ontario-policeman-bust-190932818.html', 'only_matching': True, @@ -219,7 +220,7 @@ class YahooIE(InfoExtractor): country = 'my' is_live = video.get('live_state') == 'live' - fmts = ('m3u8',) if is_live else ('web', 'mp4') + fmts = ('m3u8',) if is_live else ('webm', 'mp4') urls = [] formats = [] From 237513e801671a51cc45d6a2fe5e7df69517958e Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Thu, 31 Oct 2019 07:38:53 +0100 Subject: [PATCH 58/65] [yahoo] restore support for cbs suffixed URLs --- test/test_all_urls.py | 6 ------ youtube_dl/extractor/yahoo.py | 5 ++++- 2 files changed, 4 insertions(+), 7 deletions(-) diff --git a/test/test_all_urls.py b/test/test_all_urls.py index 465ce0050..81056a999 100644 --- a/test/test_all_urls.py +++ b/test/test_all_urls.py @@ -123,12 +123,6 @@ class TestAllURLsMatching(unittest.TestCase): self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['pbs']) self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['pbs']) - def test_yahoo_https(self): - # https://github.com/ytdl-org/youtube-dl/issues/2701 - self.assertMatch( - 'https://screen.yahoo.com/smartwatches-latest-wearable-gadgets-163745379-cbs.html', - ['Yahoo']) - def test_no_duplicated_ie_names(self): name_accu = collections.defaultdict(list) for ie in self.ies: diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index 6c6bd76e8..f041cf5de 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -25,7 +25,7 @@ from .brightcove import BrightcoveNewIE class YahooIE(InfoExtractor): IE_DESC = 'Yahoo screen and movies' - _VALID_URL = r'(?Phttps?://(?:(?P[a-zA-Z]{2}(?:-[a-zA-Z]{2})?|malaysia)\.)?(?:[\da-zA-Z_-]+\.)?yahoo\.com/(?:[^/]+/)*(?P[^?&#]*-[0-9]+)\.html)' + _VALID_URL = r'(?Phttps?://(?:(?P[a-zA-Z]{2}(?:-[a-zA-Z]{2})?|malaysia)\.)?(?:[\da-zA-Z_-]+\.)?yahoo\.com/(?:[^/]+/)*(?P[^?&#]*-[0-9]+)(?:-[a-z]+)?\.html)' _TESTS = [{ 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html', 'info_dict': { @@ -171,6 +171,9 @@ class YahooIE(InfoExtractor): }, { 'url': 'https://es-us.noticias.yahoo.com/es-la-puerta-irrompible-que-110539379.html', 'only_matching': True, + }, { + 'url': 'https://www.yahoo.com/entertainment/v/longtime-cbs-news-60-minutes-032036500-cbs.html', + 'only_matching': True, }] def _real_extract(self, url): From 3cf70bf1590ce364dc223197ba804cb70e704760 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Thu, 31 Oct 2019 07:44:21 +0100 Subject: [PATCH 59/65] [yahoo] make cbs URL suffix part of the media alias --- youtube_dl/extractor/yahoo.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index f041cf5de..b9a9e88a0 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -25,7 +25,7 @@ from .brightcove import BrightcoveNewIE class YahooIE(InfoExtractor): IE_DESC = 'Yahoo screen and movies' - _VALID_URL = r'(?Phttps?://(?:(?P[a-zA-Z]{2}(?:-[a-zA-Z]{2})?|malaysia)\.)?(?:[\da-zA-Z_-]+\.)?yahoo\.com/(?:[^/]+/)*(?P[^?&#]*-[0-9]+)(?:-[a-z]+)?\.html)' + _VALID_URL = r'(?Phttps?://(?:(?P[a-zA-Z]{2}(?:-[a-zA-Z]{2})?|malaysia)\.)?(?:[\da-zA-Z_-]+\.)?yahoo\.com/(?:[^/]+/)*(?P[^?&#]*-[0-9]+(?:-[a-z]+)?)\.html)' _TESTS = [{ 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html', 'info_dict': { From e993f1a0959fc04507b1cb2efeb610ae628d6d98 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Thu, 31 Oct 2019 08:13:10 +0100 Subject: [PATCH 60/65] [mixcloud] fix cloudcast data extraction(closes #22821) --- youtube_dl/extractor/mixcloud.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index bf5353ef9..e5f631506 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -86,9 +86,10 @@ class MixcloudIE(InfoExtractor): r'', webpage, 'play info'), 'play info') for item in full_info_json: - item_data = try_get( - item, lambda x: x['cloudcast']['data']['cloudcastLookup'], - dict) + item_data = try_get(item, [ + lambda x: x['cloudcast']['data']['cloudcastLookup'], + lambda x: x['cloudcastLookup']['data']['cloudcastLookup'], + ], dict) if try_get(item_data, lambda x: x['streamInfo']['url']): info_json = item_data break From 274bf5e4c58bceed4ff8c283d77457bf1cb76d3e Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Fri, 1 Nov 2019 11:37:41 +0100 Subject: [PATCH 61/65] [kakao] improve extraction - support embed URLs - support Kakao Legacy vid based embed URLs - only extract fields used for extraction - strip description and extract tags --- youtube_dl/extractor/kakao.py | 45 +++++++++++++++++++---------------- 1 file changed, 24 insertions(+), 21 deletions(-) diff --git a/youtube_dl/extractor/kakao.py b/youtube_dl/extractor/kakao.py index 7fa140b0c..96f918b75 100644 --- a/youtube_dl/extractor/kakao.py +++ b/youtube_dl/extractor/kakao.py @@ -6,14 +6,15 @@ from .common import InfoExtractor from ..compat import compat_str from ..utils import ( int_or_none, + strip_or_none, unified_timestamp, update_url_query, ) class KakaoIE(InfoExtractor): - _VALID_URL = r'https?://tv\.kakao\.com/channel/(?P\d+)/cliplink/(?P\d+)' - _API_BASE = 'http://tv.kakao.com/api/v1/ft/cliplinks' + _VALID_URL = r'https?://(?:play-)?tv\.kakao\.com/(?:channel/\d+|embed/player)/cliplink/(?P\d+|[^?#&]+@my)' + _API_BASE_TMPL = 'http://tv.kakao.com/api/v1/ft/cliplinks/%s/' _TESTS = [{ 'url': 'http://tv.kakao.com/channel/2671005/cliplink/301965083', @@ -36,7 +37,7 @@ class KakaoIE(InfoExtractor): 'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\r\n\r\n[쇼! 음악중심] 20160611, 507회', 'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)', 'uploader_id': 2653210, - 'uploader': '쇼 음악중심', + 'uploader': '쇼! 음악중심', 'timestamp': 1485684628, 'upload_date': '20170129', } @@ -44,6 +45,8 @@ class KakaoIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) + display_id = video_id.rstrip('@my') + api_base = self._API_BASE_TMPL % video_id player_header = { 'Referer': update_url_query( @@ -55,20 +58,22 @@ class KakaoIE(InfoExtractor): }) } - QUERY_COMMON = { + query = { 'player': 'monet_html5', 'referer': url, 'uuid': '', 'service': 'kakao_tv', 'section': '', 'dteType': 'PC', + 'fields': ','.join([ + '-*', 'tid', 'clipLink', 'displayTitle', 'clip', 'title', + 'description', 'channelId', 'createTime', 'duration', 'playCount', + 'likeCount', 'commentCount', 'tagList', 'channel', 'name', + 'clipChapterThumbnailList', 'thumbnailUrl', 'timeInSec', 'isDefault']) } - query = QUERY_COMMON.copy() - query['fields'] = 'clipLink,clip,channel,hasPlusFriend,-service,-tagList' impress = self._download_json( - '%s/%s/impress' % (self._API_BASE, video_id), - video_id, 'Downloading video info', + api_base + 'impress', display_id, 'Downloading video info', query=query, headers=player_header) clip_link = impress['clipLink'] @@ -78,30 +83,27 @@ class KakaoIE(InfoExtractor): tid = impress.get('tid', '') - query = QUERY_COMMON.copy() query.update({ + 'fields': '-*,outputList,profile,width,height,label,filesize', 'tid': tid, 'profile': 'HIGH', }) raw = self._download_json( - '%s/%s/raw' % (self._API_BASE, video_id), - video_id, 'Downloading video formats info', + api_base + 'raw', display_id, 'Downloading video formats info', query=query, headers=player_header) formats = [] for fmt in raw.get('outputList', []): try: profile_name = fmt['profile'] + query.update({ + 'profile': profile_name, + 'fields': '-*,url', + }) fmt_url_json = self._download_json( - '%s/%s/raw/videolocation' % (self._API_BASE, video_id), - video_id, + api_base + 'raw/videolocation', display_id, 'Downloading video URL for profile %s' % profile_name, - query={ - 'service': 'kakao_tv', - 'section': '', - 'tid': tid, - 'profile': profile_name - }, headers=player_header, fatal=False) + query=query, headers=player_header, fatal=False) if fmt_url_json is None: continue @@ -134,9 +136,9 @@ class KakaoIE(InfoExtractor): }) return { - 'id': video_id, + 'id': display_id, 'title': title, - 'description': clip.get('description'), + 'description': strip_or_none(clip.get('description')), 'uploader': clip_link.get('channel', {}).get('name'), 'uploader_id': clip_link.get('channelId'), 'thumbnails': thumbs, @@ -146,4 +148,5 @@ class KakaoIE(InfoExtractor): 'like_count': int_or_none(clip.get('likeCount')), 'comment_count': int_or_none(clip.get('commentCount')), 'formats': formats, + 'tags': clip.get('tagList'), } From d439989215fcb1672bc2ac18d4fb6206e12c387a Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Fri, 1 Nov 2019 11:43:18 +0100 Subject: [PATCH 62/65] [daum] fix VOD and Clip extracton(closes #15015) --- youtube_dl/extractor/daum.py | 106 +++++++++++------------------------ 1 file changed, 32 insertions(+), 74 deletions(-) diff --git a/youtube_dl/extractor/daum.py b/youtube_dl/extractor/daum.py index 76f021892..137095577 100644 --- a/youtube_dl/extractor/daum.py +++ b/youtube_dl/extractor/daum.py @@ -2,25 +2,21 @@ from __future__ import unicode_literals -import re import itertools from .common import InfoExtractor from ..compat import ( compat_parse_qs, compat_urllib_parse_unquote, - compat_urllib_parse_urlencode, compat_urlparse, ) -from ..utils import ( - int_or_none, - str_to_int, - xpath_text, - unescapeHTML, -) -class DaumIE(InfoExtractor): +class DaumBaseIE(InfoExtractor): + _KAKAO_EMBED_BASE = 'http://tv.kakao.com/embed/player/cliplink/' + + +class DaumIE(DaumBaseIE): _VALID_URL = r'https?://(?:(?:m\.)?tvpot\.daum\.net/v/|videofarm\.daum\.net/controller/player/VodPlayer\.swf\?vid=)(?P[^?#&]+)' IE_NAME = 'daum.net' @@ -36,6 +32,9 @@ class DaumIE(InfoExtractor): 'duration': 2117, 'view_count': int, 'comment_count': int, + 'uploader_id': 186139, + 'uploader': '콘간지', + 'timestamp': 1387310323, }, }, { 'url': 'http://m.tvpot.daum.net/v/65139429', @@ -44,11 +43,14 @@ class DaumIE(InfoExtractor): 'ext': 'mp4', 'title': '1297회, \'아빠 아들로 태어나길 잘 했어\' 민수, 감동의 눈물[아빠 어디가] 20150118', 'description': 'md5:79794514261164ff27e36a21ad229fc5', - 'upload_date': '20150604', + 'upload_date': '20150118', 'thumbnail': r're:^https?://.*\.(?:jpg|png)', 'duration': 154, 'view_count': int, 'comment_count': int, + 'uploader': 'MBC 예능', + 'uploader_id': 132251, + 'timestamp': 1421604228, }, }, { 'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24', @@ -59,12 +61,15 @@ class DaumIE(InfoExtractor): 'id': 'vwIpVpCQsT8$', 'ext': 'flv', 'title': '01-Korean War ( Trouble on the horizon )', - 'description': '\nKorean War 01\nTrouble on the horizon\n전쟁의 먹구름', + 'description': 'Korean War 01\r\nTrouble on the horizon\r\n전쟁의 먹구름', 'upload_date': '20080223', 'thumbnail': r're:^https?://.*\.(?:jpg|png)', 'duration': 249, 'view_count': int, 'comment_count': int, + 'uploader': '까칠한 墮落始祖 황비홍님의', + 'uploader_id': 560824, + 'timestamp': 1203770745, }, }, { # Requires dte_type=WEB (#9972) @@ -73,60 +78,24 @@ class DaumIE(InfoExtractor): 'info_dict': { 'id': 's3794Uf1NZeZ1qMpGpeqeRU', 'ext': 'mp4', - 'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny) [쇼! 음악중심] 508회 20160611', - 'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\n\n[쇼! 음악중심] 20160611, 507회', - 'upload_date': '20160611', + 'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)', + 'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\r\n\r\n[쇼! 음악중심] 20160611, 507회', + 'upload_date': '20170129', + 'uploader': '쇼! 음악중심', + 'uploader_id': 2653210, + 'timestamp': 1485684628, }, }] def _real_extract(self, url): video_id = compat_urllib_parse_unquote(self._match_id(url)) - movie_data = self._download_json( - 'http://videofarm.daum.net/controller/api/closed/v1_2/IntegratedMovieData.json', - video_id, 'Downloading video formats info', query={'vid': video_id, 'dte_type': 'WEB'}) - - # For urls like http://m.tvpot.daum.net/v/65139429, where the video_id is really a clipid - if not movie_data.get('output_list', {}).get('output_list') and re.match(r'^\d+$', video_id): - return self.url_result('http://tvpot.daum.net/clip/ClipView.do?clipid=%s' % video_id) - - info = self._download_xml( - 'http://tvpot.daum.net/clip/ClipInfoXml.do', video_id, - 'Downloading video info', query={'vid': video_id}) - - formats = [] - for format_el in movie_data['output_list']['output_list']: - profile = format_el['profile'] - format_query = compat_urllib_parse_urlencode({ - 'vid': video_id, - 'profile': profile, - }) - url_doc = self._download_xml( - 'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query, - video_id, note='Downloading video data for %s format' % profile) - format_url = url_doc.find('result/url').text - formats.append({ - 'url': format_url, - 'format_id': profile, - 'width': int_or_none(format_el.get('width')), - 'height': int_or_none(format_el.get('height')), - 'filesize': int_or_none(format_el.get('filesize')), - }) - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': info.find('TITLE').text, - 'formats': formats, - 'thumbnail': xpath_text(info, 'THUMB_URL'), - 'description': xpath_text(info, 'CONTENTS'), - 'duration': int_or_none(xpath_text(info, 'DURATION')), - 'upload_date': info.find('REGDTTM').text[:8], - 'view_count': str_to_int(xpath_text(info, 'PLAY_CNT')), - 'comment_count': str_to_int(xpath_text(info, 'COMMENT_CNT')), - } + if not video_id.isdigit(): + video_id += '@my' + return self.url_result( + self._KAKAO_EMBED_BASE + video_id, 'Kakao', video_id) -class DaumClipIE(InfoExtractor): +class DaumClipIE(DaumBaseIE): _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:clip/ClipView.(?:do|tv)|mypot/View.do)\?.*?clipid=(?P\d+)' IE_NAME = 'daum.net:clip' _URL_TEMPLATE = 'http://tvpot.daum.net/clip/ClipView.do?clipid=%s' @@ -142,6 +111,9 @@ class DaumClipIE(InfoExtractor): 'thumbnail': r're:^https?://.*\.(?:jpg|png)', 'duration': 3868, 'view_count': int, + 'uploader': 'GOMeXP', + 'uploader_id': 6667, + 'timestamp': 1377911092, }, }, { 'url': 'http://m.tvpot.daum.net/clip/ClipView.tv?clipid=54999425', @@ -154,22 +126,8 @@ class DaumClipIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - clip_info = self._download_json( - 'http://tvpot.daum.net/mypot/json/GetClipInfo.do?clipid=%s' % video_id, - video_id, 'Downloading clip info')['clip_bean'] - - return { - '_type': 'url_transparent', - 'id': video_id, - 'url': 'http://tvpot.daum.net/v/%s' % clip_info['vid'], - 'title': unescapeHTML(clip_info['title']), - 'thumbnail': clip_info.get('thumb_url'), - 'description': clip_info.get('contents'), - 'duration': int_or_none(clip_info.get('duration')), - 'upload_date': clip_info.get('up_date')[:8], - 'view_count': int_or_none(clip_info.get('play_count')), - 'ie_key': 'Daum', - } + return self.url_result( + self._KAKAO_EMBED_BASE + video_id, 'Kakao', video_id) class DaumListIE(InfoExtractor): From e987ce4bda476a387937e4af5b46f4a412a67830 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Fri, 1 Nov 2019 12:40:41 +0100 Subject: [PATCH 63/65] [kakao] remove raw request and extract format total bitrate --- youtube_dl/extractor/kakao.py | 21 ++++++++------------- 1 file changed, 8 insertions(+), 13 deletions(-) diff --git a/youtube_dl/extractor/kakao.py b/youtube_dl/extractor/kakao.py index 96f918b75..32935bb28 100644 --- a/youtube_dl/extractor/kakao.py +++ b/youtube_dl/extractor/kakao.py @@ -69,7 +69,8 @@ class KakaoIE(InfoExtractor): '-*', 'tid', 'clipLink', 'displayTitle', 'clip', 'title', 'description', 'channelId', 'createTime', 'duration', 'playCount', 'likeCount', 'commentCount', 'tagList', 'channel', 'name', - 'clipChapterThumbnailList', 'thumbnailUrl', 'timeInSec', 'isDefault']) + 'clipChapterThumbnailList', 'thumbnailUrl', 'timeInSec', 'isDefault', + 'videoOutputList', 'width', 'height', 'kbps', 'profile', 'label']) } impress = self._download_json( @@ -81,21 +82,14 @@ class KakaoIE(InfoExtractor): title = clip.get('title') or clip_link.get('displayTitle') - tid = impress.get('tid', '') - - query.update({ - 'fields': '-*,outputList,profile,width,height,label,filesize', - 'tid': tid, - 'profile': 'HIGH', - }) - raw = self._download_json( - api_base + 'raw', display_id, 'Downloading video formats info', - query=query, headers=player_header) + query['tid'] = impress.get('tid', '') formats = [] - for fmt in raw.get('outputList', []): + for fmt in clip.get('videoOutputList', []): try: profile_name = fmt['profile'] + if profile_name == 'AUDIO': + continue query.update({ 'profile': profile_name, 'fields': '-*,url', @@ -115,7 +109,8 @@ class KakaoIE(InfoExtractor): 'width': int_or_none(fmt.get('width')), 'height': int_or_none(fmt.get('height')), 'format_note': fmt.get('label'), - 'filesize': int_or_none(fmt.get('filesize')) + 'filesize': int_or_none(fmt.get('filesize')), + 'tbr': int_or_none(fmt.get('kbps')), }) except KeyError: pass From 20cc7c082b82e82050a4e1f1bb815fee51f6c1c2 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Fri, 1 Nov 2019 16:36:35 +0100 Subject: [PATCH 64/65] [go90] remove extractor --- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/go90.py | 149 ----------------------------- 2 files changed, 150 deletions(-) delete mode 100644 youtube_dl/extractor/go90.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 5d20ba863..e9b59ce52 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -422,7 +422,6 @@ from .globo import ( GloboArticleIE, ) from .go import GoIE -from .go90 import Go90IE from .godtube import GodTubeIE from .golem import GolemIE from .googledrive import GoogleDriveIE diff --git a/youtube_dl/extractor/go90.py b/youtube_dl/extractor/go90.py deleted file mode 100644 index c3ea717bc..000000000 --- a/youtube_dl/extractor/go90.py +++ /dev/null @@ -1,149 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..compat import compat_HTTPError -from ..utils import ( - determine_ext, - ExtractorError, - int_or_none, - parse_age_limit, - parse_iso8601, -) - - -class Go90IE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?go90\.com/(?:videos|embed)/(?P[0-9a-zA-Z]+)' - _TESTS = [{ - 'url': 'https://www.go90.com/videos/84BUqjLpf9D', - 'md5': 'efa7670dbbbf21a7b07b360652b24a32', - 'info_dict': { - 'id': '84BUqjLpf9D', - 'ext': 'mp4', - 'title': 'Daily VICE - Inside The Utah Coalition Against Pornography Convention', - 'description': 'VICE\'s Karley Sciortino meets with activists who discuss the state\'s strong anti-porn stance. Then, VICE Sports explains NFL contracts.', - 'timestamp': 1491868800, - 'upload_date': '20170411', - 'age_limit': 14, - } - }, { - 'url': 'https://www.go90.com/embed/261MflWkD3N', - 'only_matching': True, - }] - _GEO_BYPASS = False - - def _real_extract(self, url): - video_id = self._match_id(url) - - try: - headers = self.geo_verification_headers() - headers.update({ - 'Content-Type': 'application/json; charset=utf-8', - }) - video_data = self._download_json( - 'https://www.go90.com/api/view/items/' + video_id, video_id, - headers=headers, data=b'{"client":"web","device_type":"pc"}') - except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400: - message = self._parse_json(e.cause.read().decode(), None)['error']['message'] - if 'region unavailable' in message: - self.raise_geo_restricted(countries=['US']) - raise ExtractorError(message, expected=True) - raise - - if video_data.get('requires_drm'): - raise ExtractorError('This video is DRM protected.', expected=True) - main_video_asset = video_data['main_video_asset'] - - episode_number = int_or_none(video_data.get('episode_number')) - series = None - season = None - season_id = None - season_number = None - for metadata in video_data.get('__children', {}).get('Item', {}).values(): - if metadata.get('type') == 'show': - series = metadata.get('title') - elif metadata.get('type') == 'season': - season = metadata.get('title') - season_id = metadata.get('id') - season_number = int_or_none(metadata.get('season_number')) - - title = episode = video_data.get('title') or series - if series and series != title: - title = '%s - %s' % (series, title) - - thumbnails = [] - formats = [] - subtitles = {} - for asset in video_data.get('assets'): - if asset.get('id') == main_video_asset: - for source in asset.get('sources', []): - source_location = source.get('location') - if not source_location: - continue - source_type = source.get('type') - if source_type == 'hls': - m3u8_formats = self._extract_m3u8_formats( - source_location, video_id, 'mp4', - 'm3u8_native', m3u8_id='hls', fatal=False) - for f in m3u8_formats: - mobj = re.search(r'/hls-(\d+)-(\d+)K', f['url']) - if mobj: - height, tbr = mobj.groups() - height = int_or_none(height) - f.update({ - 'height': f.get('height') or height, - 'width': f.get('width') or int_or_none(height / 9.0 * 16.0 if height else None), - 'tbr': f.get('tbr') or int_or_none(tbr), - }) - formats.extend(m3u8_formats) - elif source_type == 'dash': - formats.extend(self._extract_mpd_formats( - source_location, video_id, mpd_id='dash', fatal=False)) - else: - formats.append({ - 'format_id': source.get('name'), - 'url': source_location, - 'width': int_or_none(source.get('width')), - 'height': int_or_none(source.get('height')), - 'tbr': int_or_none(source.get('bitrate')), - }) - - for caption in asset.get('caption_metadata', []): - caption_url = caption.get('source_url') - if not caption_url: - continue - subtitles.setdefault(caption.get('language', 'en'), []).append({ - 'url': caption_url, - 'ext': determine_ext(caption_url, 'vtt'), - }) - elif asset.get('type') == 'image': - asset_location = asset.get('location') - if not asset_location: - continue - thumbnails.append({ - 'url': asset_location, - 'width': int_or_none(asset.get('width')), - 'height': int_or_none(asset.get('height')), - }) - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': title, - 'formats': formats, - 'thumbnails': thumbnails, - 'description': video_data.get('short_description'), - 'like_count': int_or_none(video_data.get('like_count')), - 'timestamp': parse_iso8601(video_data.get('released_at')), - 'series': series, - 'episode': episode, - 'season': season, - 'season_id': season_id, - 'season_number': season_number, - 'episode_number': episode_number, - 'subtitles': subtitles, - 'age_limit': parse_age_limit(video_data.get('rating')), - } From 152f22920d73bb0dc24fa357d5904a8dd97a5bf6 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Fri, 1 Nov 2019 17:44:34 +0100 Subject: [PATCH 65/65] [wistia] reduce embed extraction false positives and support inline embeds(closes #22931) --- youtube_dl/extractor/wistia.py | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/wistia.py b/youtube_dl/extractor/wistia.py index fa142b974..0fbc888ec 100644 --- a/youtube_dl/extractor/wistia.py +++ b/youtube_dl/extractor/wistia.py @@ -12,7 +12,7 @@ from ..utils import ( class WistiaIE(InfoExtractor): - _VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/)(?P[a-z0-9]+)' + _VALID_URL = r'(?:wistia:|https?://(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/)(?P[a-z0-9]{10})' _API_URL = 'http://fast.wistia.com/embed/medias/%s.json' _IFRAME_URL = 'http://fast.wistia.net/embed/iframe/%s' @@ -43,25 +43,26 @@ class WistiaIE(InfoExtractor): 'only_matching': True, }] + # https://wistia.com/support/embed-and-share/video-on-your-website @staticmethod def _extract_url(webpage): match = re.search( - r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/iframe/.+?)\1', webpage) + r'<(?:meta[^>]+?content|(?:iframe|script)[^>]+?src)=["\'](?P(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/[a-z0-9]{10})', webpage) if match: return unescapeHTML(match.group('url')) - match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P[^"\']+)', webpage) - if match: - return 'wistia:%s' % match.group('id') - match = re.search( r'''(?sx) ]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*? - ]+class=(["']).*?\bwistia_async_(?P[a-z0-9]+)\b.*?\2 + ]+class=(["']).*?\bwistia_async_(?P[a-z0-9]{10})\b.*?\2 ''', webpage) if match: return 'wistia:%s' % match.group('id') + match = re.search(r'(?:data-wistia-?id=["\']|Wistia\.embed\(["\']|id=["\']wistia_)(?P[a-z0-9]{10})', webpage) + if match: + return 'wistia:%s' % match.group('id') + def _real_extract(self, url): video_id = self._match_id(url)