From c94427dd60f9836e3752077977cae3b4d0da47d1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 5 Dec 2017 22:34:56 +0700 Subject: [PATCH 01/31] [pluralsight] Detect agreement request (#14913) --- youtube_dl/extractor/pluralsight.py | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/youtube_dl/extractor/pluralsight.py b/youtube_dl/extractor/pluralsight.py index 4bf0aa786..597b11218 100644 --- a/youtube_dl/extractor/pluralsight.py +++ b/youtube_dl/extractor/pluralsight.py @@ -131,6 +131,13 @@ class PluralsightIE(PluralsightBaseIE): if BLOCKED in response: raise ExtractorError( 'Unable to login: %s' % BLOCKED, expected=True) + MUST_AGREE = 'To continue using Pluralsight, you must agree to' + if any(p in response for p in (MUST_AGREE, '>Disagree<', '>Agree<')): + raise ExtractorError( + 'Unable to login: %s some documents. Go to pluralsight.com, ' + 'log in and agree with what Pluralsight requires.' + % MUST_AGREE, expected=True) + raise ExtractorError('Unable to log in') def _get_subtitles(self, author, clip_id, lang, name, duration, video_id): From 61d18c8a4bc91602738bfd2e506c3cbbc3a3788b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 5 Dec 2017 22:42:02 +0700 Subject: [PATCH 02/31] [porncom] Fix metadata extraction (closes #14911) --- youtube_dl/extractor/porncom.py | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/porncom.py b/youtube_dl/extractor/porncom.py index 8218c7d3b..60ade06da 100644 --- a/youtube_dl/extractor/porncom.py +++ b/youtube_dl/extractor/porncom.py @@ -77,12 +77,14 @@ class PornComIE(InfoExtractor): self._sort_formats(formats) view_count = str_to_int(self._search_regex( - r'class=["\']views["\'][^>]*>

([\d,.]+)', webpage, + (r'Views:\s*\s*\s*([\d,.]+)', + r'class=["\']views["\'][^>]*>

([\d,.]+)'), webpage, 'view count', fatal=False)) def extract_list(kind): s = self._search_regex( - r'(?s)]*>%s:(.+?)

' % kind.capitalize(), + (r'(?s)%s:\s*\s*(.+?)' % kind.capitalize(), + r'(?s)]*>%s:(.+?)

' % kind.capitalize()), webpage, kind, fatal=False) return re.findall(r']+>([^<]+)', s or '') From 91328f26b05084a1ddd890866670a1133564ecd0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 5 Dec 2017 23:01:57 +0700 Subject: [PATCH 03/31] [ard] Skip invalid stream URLs (closes #14906) --- youtube_dl/extractor/ard.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 915f8862e..ef73d5a93 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -5,6 +5,7 @@ import re from .common import InfoExtractor from .generic import GenericIE +from ..compat import compat_str from ..utils import ( determine_ext, ExtractorError, @@ -126,6 +127,8 @@ class ARDMediathekIE(InfoExtractor): quality = stream.get('_quality') server = stream.get('_server') for stream_url in stream_urls: + if not isinstance(stream_url, compat_str) or '//' not in stream_url: + continue ext = determine_ext(stream_url) if quality != 'auto' and ext in ('f4m', 'm3u8'): continue @@ -146,13 +149,11 @@ class ARDMediathekIE(InfoExtractor): 'play_path': stream_url, 'format_id': 'a%s-rtmp-%s' % (num, quality), } - elif stream_url.startswith('http'): + else: f = { 'url': stream_url, 'format_id': 'a%s-%s-%s' % (num, ext, quality) } - else: - continue m = re.search(r'_(?P\d+)x(?P\d+)\.mp4$', stream_url) if m: f.update({ From d3f8b76b69b9bc986354a83a8d4ee4a8617ce52d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 5 Dec 2017 23:11:15 +0700 Subject: [PATCH 04/31] [extractor/generic] Fix typo (closes #14902) Don't pass video_id as mpd_id --- youtube_dl/extractor/generic.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 56df2ab47..c8b7c2e63 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -2195,7 +2195,7 @@ class GenericIE(InfoExtractor): return self.playlist_result(self._parse_xspf(doc, video_id), video_id) elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag): info_dict['formats'] = self._parse_mpd_formats( - doc, video_id, + doc, mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0], mpd_url=url) self._sort_formats(info_dict['formats']) From b271e3352603c523bf2c6762973937fd36925aae Mon Sep 17 00:00:00 2001 From: Windom Date: Tue, 5 Dec 2017 19:08:31 +0200 Subject: [PATCH 05/31] [xhamster] Add support for mobile URLs and fix thumbnail extraction --- youtube_dl/extractor/xhamster.py | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index 52f8ded2f..68652a22f 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -75,6 +75,10 @@ class XHamsterIE(InfoExtractor): 'params': { 'skip_download': True, }, + }, { + # mobile site + 'url': 'https://m.xhamster.com/videos/cute-teen-jacqueline-solo-masturbation-8559111', + 'only_matching': True, }, { 'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html', 'only_matching': True, @@ -93,7 +97,8 @@ class XHamsterIE(InfoExtractor): video_id = mobj.group('id') or mobj.group('id_2') display_id = mobj.group('display_id') or mobj.group('display_id_2') - webpage = self._download_webpage(url, video_id) + desktop_url = re.sub(r'^(https?://(?:.+?\.)?)m\.', r'\1', url) + webpage = self._download_webpage(desktop_url, video_id) error = self._html_search_regex( r']+id=["\']videoClosed["\'][^>]*>(.+?)', @@ -229,8 +234,8 @@ class XHamsterIE(InfoExtractor): webpage, 'uploader', default='anonymous') thumbnail = self._search_regex( - [r'''thumb\s*:\s*(?P["'])(?P.+?)(?P=q)''', - r''']+poster=(?P["'])(?P.+?)(?P=q)[^>]*>'''], + [r'''["']thumbUrl["']\s*:\s*(?P["'])(?P.+?)(?P=q)''', + r''']+"poster"=(?P["'])(?P.+?)(?P=q)[^>]*>'''], webpage, 'thumbnail', fatal=False, group='thumbnail') duration = parse_duration(self._search_regex( @@ -274,15 +279,16 @@ class XHamsterIE(InfoExtractor): class XHamsterEmbedIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?xhamster\.com/xembed\.php\?video=(?P\d+)' + _VALID_URL = r'https?://(?:.+?\.)?xhamster\.com/xembed\.php\?video=(?P\d+)' _TEST = { 'url': 'http://xhamster.com/xembed.php?video=3328539', 'info_dict': { 'id': '3328539', 'ext': 'mp4', 'title': 'Pen Masturbation', + 'timestamp': 1406581861, 'upload_date': '20140728', - 'uploader_id': 'anonymous', + 'uploader': 'ManyakisArt', 'duration': 5, 'age_limit': 18, } From 3c4fbfeca2431b120537b9eaedf5977dd0ab13b1 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 6 Dec 2017 10:54:20 +0100 Subject: [PATCH 06/31] [dailymotion] remove dailymotion cloud extractor(closes #6794) https://web.archive.org/web/20160312110217/https://www.dmcloud.net/ --- youtube_dl/extractor/dailymotion.py | 49 ----------------------------- youtube_dl/extractor/extractors.py | 1 - youtube_dl/extractor/francetv.py | 9 +----- youtube_dl/extractor/generic.py | 27 +--------------- 4 files changed, 2 insertions(+), 84 deletions(-) diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 21a2d0239..0e7d587dd 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -413,52 +413,3 @@ class DailymotionUserIE(DailymotionPlaylistIE): 'title': full_user, 'entries': self._extract_entries(user), } - - -class DailymotionCloudIE(DailymotionBaseInfoExtractor): - _VALID_URL_PREFIX = r'https?://api\.dmcloud\.net/(?:player/)?embed/' - _VALID_URL = r'%s[^/]+/(?P[^/?]+)' % _VALID_URL_PREFIX - _VALID_EMBED_URL = r'%s[^/]+/[^\'"]+' % _VALID_URL_PREFIX - - _TESTS = [{ - # From http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html - # Tested at FranceTvInfo_2 - 'url': 'http://api.dmcloud.net/embed/4e7343f894a6f677b10006b4/556e03339473995ee145930c?auth=1464865870-0-jyhsm84b-ead4c701fb750cf9367bf4447167a3db&autoplay=1', - 'only_matching': True, - }, { - # http://www.francetvinfo.fr/societe/larguez-les-amarres-le-cobaturage-se-developpe_980101.html - 'url': 'http://api.dmcloud.net/player/embed/4e7343f894a6f677b10006b4/559545469473996d31429f06?auth=1467430263-0-90tglw2l-a3a4b64ed41efe48d7fccad85b8b8fda&autoplay=1', - 'only_matching': True, - }] - - @classmethod - def _extract_dmcloud_url(cls, webpage): - mobj = re.search(r']+src=[\'"](%s)[\'"]' % cls._VALID_EMBED_URL, webpage) - if mobj: - return mobj.group(1) - - mobj = re.search( - r']+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=[\'"](%s)[\'"]' % cls._VALID_EMBED_URL, - webpage) - if mobj: - return mobj.group(1) - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage_no_ff(url, video_id) - - title = self._html_search_regex(r'([^>]+)', webpage, 'title') - - video_info = self._parse_json(self._search_regex( - r'var\s+info\s*=\s*([^;]+);', webpage, 'video info'), video_id) - - # TODO: parse ios_url, which is in fact a manifest - video_url = video_info['mp4_url'] - - return { - 'id': video_id, - 'url': video_url, - 'title': title, - 'thumbnail': video_info.get('thumbnail_url'), - } diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 2cc3bc463..9c9739ad2 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -246,7 +246,6 @@ from .dailymotion import ( DailymotionIE, DailymotionPlaylistIE, DailymotionUserIE, - DailymotionCloudIE, ) from .daisuki import ( DaisukiMottoIE, diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index 5a3abeaff..80c597015 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -13,10 +13,7 @@ from ..utils import ( parse_duration, determine_ext, ) -from .dailymotion import ( - DailymotionIE, - DailymotionCloudIE, -) +from .dailymotion import DailymotionIE class FranceTVBaseInfoExtractor(InfoExtractor): @@ -290,10 +287,6 @@ class FranceTVInfoIE(FranceTVBaseInfoExtractor): page_title = mobj.group('title') webpage = self._download_webpage(url, page_title) - dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage) - if dmcloud_url: - return self.url_result(dmcloud_url, DailymotionCloudIE.ie_key()) - dailymotion_urls = DailymotionIE._extract_urls(webpage) if dailymotion_urls: return self.playlist_result([ diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index c8b7c2e63..c7b609215 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -59,10 +59,7 @@ from .tnaflix import TNAFlixNetworkEmbedIE from .drtuber import DrTuberIE from .redtube import RedTubeIE from .vimeo import VimeoIE -from .dailymotion import ( - DailymotionIE, - DailymotionCloudIE, -) +from .dailymotion import DailymotionIE from .dailymail import DailyMailIE from .onionstudios import OnionStudiosIE from .viewlift import ViewLiftEmbedIE @@ -1472,23 +1469,6 @@ class GenericIE(InfoExtractor): 'timestamp': 1432570283, }, }, - # Dailymotion Cloud video - { - 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910', - 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38', - 'info_dict': { - 'id': 'x2uy8t3', - 'ext': 'mp4', - 'title': 'Sauvons les abeilles ! - Le débat', - 'description': 'md5:d9082128b1c5277987825d684939ca26', - 'thumbnail': r're:^https?://.*\.jpe?g$', - 'timestamp': 1434970506, - 'upload_date': '20150622', - 'uploader': 'Public Sénat', - 'uploader_id': 'xa9gza', - }, - 'skip': 'File not found.', - }, # OnionStudios embed { 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537', @@ -2704,11 +2684,6 @@ class GenericIE(InfoExtractor): if senate_isvp_url: return self.url_result(senate_isvp_url, 'SenateISVP') - # Look for Dailymotion Cloud videos - dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage) - if dmcloud_url: - return self.url_result(dmcloud_url, 'DailymotionCloud') - # Look for OnionStudios embeds onionstudios_url = OnionStudiosIE._extract_url(webpage) if onionstudios_url: From 684ae102360dbef6d1e5fcd75a0f86266030e02d Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Wed, 6 Dec 2017 22:56:14 +0100 Subject: [PATCH 07/31] [fox] add support for adobe pass auth and extract subtitles(close #14489)(closes #14205) --- youtube_dl/extractor/fox.py | 25 ++++++++++++++++++++++--- 1 file changed, 22 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/fox.py b/youtube_dl/extractor/fox.py index 5f98d017b..11d6c9c32 100644 --- a/youtube_dl/extractor/fox.py +++ b/youtube_dl/extractor/fox.py @@ -11,6 +11,7 @@ from ..utils import ( parse_duration, try_get, unified_timestamp, + update_url_query, ) @@ -62,7 +63,8 @@ class FOXIE(AdobePassIE): duration = int_or_none(video.get('durationInSeconds')) or int_or_none( video.get('duration')) or parse_duration(video.get('duration')) timestamp = unified_timestamp(video.get('datePublished')) - age_limit = parse_age_limit(video.get('contentRating')) + rating = video.get('contentRating') + age_limit = parse_age_limit(rating) data = try_get( video, lambda x: x['trackingData']['properties'], dict) or {} @@ -77,8 +79,24 @@ class FOXIE(AdobePassIE): release_year = int_or_none(video.get('releaseYear')) if data.get('authRequired'): - # TODO: AP - pass + resource = self._get_mvpd_resource( + 'fbc-fox', title, video.get('guid'), rating) + release_url = update_url_query( + release_url, { + 'auth': self._extract_mvpd_auth( + url, video_id, 'fbc-fox', resource) + }) + + subtitles = {} + for doc_rel in video.get('documentReleases', []): + rel_url = doc_rel.get('url') + if not url or doc_rel.get('format') != 'SCC': + continue + subtitles['en'] = [{ + 'url': rel_url, + 'ext': 'scc', + }] + break info = { 'id': video_id, @@ -93,6 +111,7 @@ class FOXIE(AdobePassIE): 'episode': episode, 'episode_number': episode_number, 'release_year': release_year, + 'subtitles': subtitles, } urlh = self._request_webpage(HEADRequest(release_url), video_id) From 1bd4fc96e6f8978f83e90ca913df18a979445028 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Thu, 7 Dec 2017 08:46:30 +0100 Subject: [PATCH 08/31] [sonyliv] extract higher quality formats and bypass geo restriction(closes #14922) --- youtube_dl/extractor/sonyliv.py | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/sonyliv.py b/youtube_dl/extractor/sonyliv.py index accd112aa..c3078e285 100644 --- a/youtube_dl/extractor/sonyliv.py +++ b/youtube_dl/extractor/sonyliv.py @@ -2,6 +2,7 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..utils import smuggle_url class SonyLIVIE(InfoExtractor): @@ -10,12 +11,12 @@ class SonyLIVIE(InfoExtractor): 'url': "http://www.sonyliv.com/details/episodes/5024612095001/Ep.-1---Achaari-Cheese-Toast---Bachelor's-Delight", 'info_dict': { 'title': "Ep. 1 - Achaari Cheese Toast - Bachelor's Delight", - 'id': '5024612095001', + 'id': 'ref:5024612095001', 'ext': 'mp4', - 'upload_date': '20160707', + 'upload_date': '20170923', 'description': 'md5:7f28509a148d5be9d0782b4d5106410d', - 'uploader_id': '4338955589001', - 'timestamp': 1467870968, + 'uploader_id': '5182475815001', + 'timestamp': 1506200547, }, 'params': { 'skip_download': True, @@ -26,9 +27,11 @@ class SonyLIVIE(InfoExtractor): 'only_matching': True, }] - BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/4338955589001/default_default/index.html?videoId=%s' + # BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/4338955589001/default_default/index.html?videoId=%s' + BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5182475815001/default_default/index.html?videoId=ref:%s' def _real_extract(self, url): brightcove_id = self._match_id(url) return self.url_result( - self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id) + smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, {'geo_countries': ['IN']}), + 'BrightcoveNew', brightcove_id) From a670b1ba266533c520a436469585904321808a1b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 7 Dec 2017 22:16:41 +0700 Subject: [PATCH 09/31] [README.md] Add is_live, start_time and end_time to output template section (closes #14926) --- README.md | 3 +++ 1 file changed, 3 insertions(+) diff --git a/README.md b/README.md index ea321d536..cd30d147a 100644 --- a/README.md +++ b/README.md @@ -511,6 +511,9 @@ The basic usage is not to set any template arguments when downloading a single f - `average_rating` (numeric): Average rating give by users, the scale used depends on the webpage - `comment_count` (numeric): Number of comments on the video - `age_limit` (numeric): Age restriction for the video (years) + - `is_live` (boolean): Whether this video is a live stream or a fixed-length video + - `start_time` (numeric): Time in seconds where the reproduction should start, as specified in the URL + - `end_time` (numeric): Time in seconds where the reproduction should end, as specified in the URL - `format` (string): A human-readable description of the format - `format_id` (string): Format code specified by `--format` - `format_note` (string): Additional info about the format From d21d0ba6c14e8a6696130090641da4e2028e1bb3 Mon Sep 17 00:00:00 2001 From: Timendum Date: Mon, 23 Oct 2017 15:32:45 +0200 Subject: [PATCH 10/31] [raiplay:playlist] Add extractor --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/rai.py | 26 ++++++++++++++++++++++++++ 2 files changed, 27 insertions(+) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 9c9739ad2..d8f9f94cc 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -857,6 +857,7 @@ from .rai import ( RaiPlayIE, RaiPlayLiveIE, RaiIE, + RaiPlaylistIE, ) from .rbmaradio import RBMARadioIE from .rds import RDSIE diff --git a/youtube_dl/extractor/rai.py b/youtube_dl/extractor/rai.py index 5bf64a56b..625458380 100644 --- a/youtube_dl/extractor/rai.py +++ b/youtube_dl/extractor/rai.py @@ -455,3 +455,29 @@ class RaiIE(RaiBaseIE): info.update(relinker_info) return info + + +class RaiPlaylistIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?raiplay\.it/programmi/(?P[^/]+)' + _TESTS = [{ + 'url': 'http://www.raiplay.it/programmi/nondirloalmiocapo/', + 'info_dict': { + 'id': 'nondirloalmiocapo', + 'title': 'Non dirlo al mio capo', + }, + 'playlist_mincount': 12, + }] + + def _real_extract(self, url): + playlist_id = self._match_id(url) + webpage = self._download_webpage(url, playlist_id) + title = self._html_search_meta('programma', webpage, default=None) + video_urls = re.findall(' href="(/raiplay/video.+)"', webpage) + video_urls = [urljoin(url, video_url) for video_url in video_urls] + entries = [ + self.url_result( + video_url, + RaiPlayIE.ie_key()) + for video_url in video_urls if RaiPlayIE.suitable(video_url) + ] + return self.playlist_result(entries, playlist_id, title) From 1115271ac61b89cc4ac1ca922eff8a4bed0fbf57 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 9 Dec 2017 00:46:28 +0700 Subject: [PATCH 11/31] [raiplay:playlist] Fix issues and improve (closes #14563) --- youtube_dl/extractor/extractors.py | 2 +- youtube_dl/extractor/rai.py | 62 +++++++++++++++++------------- 2 files changed, 37 insertions(+), 27 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index d8f9f94cc..b9c97fac4 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -856,8 +856,8 @@ from .radiofrance import RadioFranceIE from .rai import ( RaiPlayIE, RaiPlayLiveIE, + RaiPlayPlaylistIE, RaiIE, - RaiPlaylistIE, ) from .rbmaradio import RBMARadioIE from .rds import RDSIE diff --git a/youtube_dl/extractor/rai.py b/youtube_dl/extractor/rai.py index 625458380..d22311031 100644 --- a/youtube_dl/extractor/rai.py +++ b/youtube_dl/extractor/rai.py @@ -17,6 +17,7 @@ from ..utils import ( parse_duration, strip_or_none, try_get, + unescapeHTML, unified_strdate, unified_timestamp, update_url_query, @@ -249,6 +250,41 @@ class RaiPlayLiveIE(RaiBaseIE): } +class RaiPlayPlaylistIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?raiplay\.it/programmi/(?P[^/?#&]+)' + _TESTS = [{ + 'url': 'http://www.raiplay.it/programmi/nondirloalmiocapo/', + 'info_dict': { + 'id': 'nondirloalmiocapo', + 'title': 'Non dirlo al mio capo', + 'description': 'md5:9f3d603b2947c1c7abb098f3b14fac86', + }, + 'playlist_mincount': 12, + }] + + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage(url, playlist_id) + + title = self._html_search_meta( + ('programma', 'nomeProgramma'), webpage, 'title') + description = unescapeHTML(self._html_search_meta( + ('description', 'og:description'), webpage, 'description')) + print(description) + + entries = [] + for mobj in re.finditer( + r']+\bhref=(["\'])(?P/raiplay/video/.+?)\1', + webpage): + video_url = urljoin(url, mobj.group('path')) + entries.append(self.url_result( + video_url, ie=RaiPlayIE.ie_key(), + video_id=RaiPlayIE._match_id(video_url))) + + return self.playlist_result(entries, playlist_id, title, description) + + class RaiIE(RaiBaseIE): _VALID_URL = r'https?://[^/]+\.(?:rai\.(?:it|tv)|rainews\.it)/dl/.+?-(?P%s)(?:-.+?)?\.html' % RaiBaseIE._UUID_RE _TESTS = [{ @@ -455,29 +491,3 @@ class RaiIE(RaiBaseIE): info.update(relinker_info) return info - - -class RaiPlaylistIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?raiplay\.it/programmi/(?P[^/]+)' - _TESTS = [{ - 'url': 'http://www.raiplay.it/programmi/nondirloalmiocapo/', - 'info_dict': { - 'id': 'nondirloalmiocapo', - 'title': 'Non dirlo al mio capo', - }, - 'playlist_mincount': 12, - }] - - def _real_extract(self, url): - playlist_id = self._match_id(url) - webpage = self._download_webpage(url, playlist_id) - title = self._html_search_meta('programma', webpage, default=None) - video_urls = re.findall(' href="(/raiplay/video.+)"', webpage) - video_urls = [urljoin(url, video_url) for video_url in video_urls] - entries = [ - self.url_result( - video_url, - RaiPlayIE.ie_key()) - for video_url in video_urls if RaiPlayIE.suitable(video_url) - ] - return self.playlist_result(entries, playlist_id, title) From e2707a832cd53e2cfa68b99db997890a6a5bd685 Mon Sep 17 00:00:00 2001 From: Alex Seiler Date: Mon, 23 Oct 2017 21:15:48 +0200 Subject: [PATCH 12/31] [ellentube] Fix extraction (closes #14407) --- youtube_dl/extractor/ellentube.py | 140 +++++++++++++++++++++++++++++ youtube_dl/extractor/ellentv.py | 101 --------------------- youtube_dl/extractor/extractors.py | 8 +- 3 files changed, 145 insertions(+), 104 deletions(-) create mode 100644 youtube_dl/extractor/ellentube.py delete mode 100644 youtube_dl/extractor/ellentv.py diff --git a/youtube_dl/extractor/ellentube.py b/youtube_dl/extractor/ellentube.py new file mode 100644 index 000000000..68fe17273 --- /dev/null +++ b/youtube_dl/extractor/ellentube.py @@ -0,0 +1,140 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + clean_html, + int_or_none, +) + + +class EllenTubeIE(InfoExtractor): + _VALID_URL = r'''(?x) + (?: + https://api-prod\.ellentube\.com/ellenapi/api/item/ + |ellentube: + ) + (?P + [\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12} + )''' + + _TESTS = [{ + 'url': 'https://api-prod.ellentube.com/ellenapi/api/item/75c64c16-aefd-4558-b4f5-3de09b22e6fc', + 'match_only': True, + }, { + 'url': 'ellentube:734a3353-f697-4e79-9ca9-bfc3002dc1e0', + 'match_only': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + data = self._download_json( + 'https://api-prod.ellentube.com/ellenapi/api/item/%s' % video_id, video_id) + title = data['title'] + description = data.get('description') + publish_time = int_or_none(data.get('publishTime')) + thumbnail = data.get('thumbnail') + + formats = [] + duration = None + for entry in data.get('media'): + if entry.get('id') == 'm3u8': + formats = self._extract_m3u8_formats( + entry.get('url'), video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls') + duration = int_or_none(entry.get('duration')) + break + self._sort_formats(formats) + return { + 'id': video_id, + 'title': title, + 'description': description, + 'duration': duration, + 'thumbnail': thumbnail, + 'timestamp': publish_time, + 'formats': formats, + } + + +class EllenTubeVideoIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?ellentube\.com/video/(?P.+)\.html' + + _TEST = { + 'url': 'https://www.ellentube.com/video/ellen-meets-las-vegas-survivors-jesus-campos-and-stephen-schuck.html', + 'md5': '2fabc277131bddafdd120e0fc0f974c9', + 'info_dict': { + 'id': '0822171c-3829-43bf-b99f-d77358ae75e3', + 'ext': 'mp4', + 'title': 'Ellen Meets Las Vegas Survivors Jesus Campos and Stephen Schuck', + 'description': 'md5:76e3355e2242a78ad9e3858e5616923f', + 'duration': 514, + 'timestamp': 1508505120000, + 'thumbnail': 'https://warnerbros-h.assetsadobe.com/is/image/content/dam/ellen/videos/episodes/season15/32/video--2728751654987218111', + } + } + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + video_id = self._html_search_regex( + r'(?s).*data-config.+([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})', + webpage, 'video id') + return self.url_result('ellentube:%s' % video_id, 'EllenTube') + + +class EllenTubePlaylistIE(InfoExtractor): + def _extract_videos_from_json(self, data, display_id): + return [self.url_result('ellentube:%s' % elem['id'], 'EllenTube') + for elem in data if elem.get('type') == 'VIDEO'] + + def _extract_playlist(self, url, display_id, extract_description=True): + webpage = self._download_webpage(url, display_id) + playlist_data = self._html_search_regex( + r'', webpage, 'playlist data') + playlist_title = self._search_regex( + r'"title"\s*:\s*"(.+?)"', playlist_data, 'playlist title') + playlist_description = clean_html(self._search_regex( + r'"description"\s*:\s*"(.+?)"', playlist_data, 'playlist description', + fatal=False)) if extract_description else None + api_search = self._search_regex( + r'"filter"\s*:\s*"(.+?)"', playlist_data, 'playlist api request') + api_data = self._download_json( + 'https://api-prod.ellentube.com/ellenapi/api/feed/?%s' % api_search, + display_id) + return self.playlist_result( + self._extract_videos_from_json(api_data, display_id), + display_id, playlist_title, playlist_description) + + +class EllenTubeEpisodeIE(EllenTubePlaylistIE): + _VALID_URL = r'https?://(?:www\.)?ellentube\.com/episode/(?P.+)\.html' + + _TEST = { + 'url': 'https://www.ellentube.com/episode/dax-shepard-jordan-fisher-haim.html', + 'info_dict': { + 'id': 'dax-shepard-jordan-fisher-haim', + 'title': 'Dax Shepard, \'DWTS\' Team Jordan Fisher & Lindsay Arnold, HAIM', + 'description': 'md5:aed85d42892f6126e71ec5ed2aea2a0d' + }, + 'playlist_count': 6, + } + + def _real_extract(self, url): + display_id = self._match_id(url) + return self._extract_playlist(url, display_id) + + +class EllenTubeStudioIE(EllenTubePlaylistIE): + _VALID_URL = r'https?://(?:www\.)?ellentube\.com/studios/(?P.+)\.html' + + _TEST = { + 'url': 'https://www.ellentube.com/studios/macey-goes-rving0.html', + 'info_dict': { + 'id': 'macey-goes-rving0', + 'title': 'Macey Goes RVing', + }, + 'playlist_mincount': 3, + } + + def _real_extract(self, url): + display_id = self._match_id(url) + return self._extract_playlist(url, display_id, False) diff --git a/youtube_dl/extractor/ellentv.py b/youtube_dl/extractor/ellentv.py deleted file mode 100644 index e0a13dd76..000000000 --- a/youtube_dl/extractor/ellentv.py +++ /dev/null @@ -1,101 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor -from .kaltura import KalturaIE -from ..utils import NO_DEFAULT - - -class EllenTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P[a-z0-9_-]+)' - _TESTS = [{ - 'url': 'http://www.ellentv.com/videos/0-ipq1gsai/', - 'md5': '4294cf98bc165f218aaa0b89e0fd8042', - 'info_dict': { - 'id': '0_ipq1gsai', - 'ext': 'mov', - 'title': 'Fast Fingers of Fate', - 'description': 'md5:3539013ddcbfa64b2a6d1b38d910868a', - 'timestamp': 1428035648, - 'upload_date': '20150403', - 'uploader_id': 'batchUser', - }, - }, { - # not available via http://widgets.ellentube.com/ - 'url': 'http://www.ellentv.com/videos/1-szkgu2m2/', - 'info_dict': { - 'id': '1_szkgu2m2', - 'ext': 'flv', - 'title': "Ellen's Amazingly Talented Audience", - 'description': 'md5:86ff1e376ff0d717d7171590e273f0a5', - 'timestamp': 1255140900, - 'upload_date': '20091010', - 'uploader_id': 'ellenkaltura@gmail.com', - }, - 'params': { - 'skip_download': True, - }, - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - - URLS = ('http://widgets.ellentube.com/videos/%s' % video_id, url) - - for num, url_ in enumerate(URLS, 1): - webpage = self._download_webpage( - url_, video_id, fatal=num == len(URLS)) - - default = NO_DEFAULT if num == len(URLS) else None - - partner_id = self._search_regex( - r"var\s+partnerId\s*=\s*'([^']+)", webpage, 'partner id', - default=default) - - kaltura_id = self._search_regex( - [r'id="kaltura_player_([^"]+)"', - r"_wb_entry_id\s*:\s*'([^']+)", - r'data-kaltura-entry-id="([^"]+)'], - webpage, 'kaltura id', default=default) - - if partner_id and kaltura_id: - break - - return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), KalturaIE.ie_key()) - - -class EllenTVClipsIE(InfoExtractor): - IE_NAME = 'EllenTV:clips' - _VALID_URL = r'https?://(?:www\.)?ellentv\.com/episodes/(?P[a-z0-9_-]+)' - _TEST = { - 'url': 'http://www.ellentv.com/episodes/meryl-streep-vanessa-hudgens/', - 'info_dict': { - 'id': 'meryl-streep-vanessa-hudgens', - 'title': 'Meryl Streep, Vanessa Hudgens', - }, - 'playlist_mincount': 5, - } - - def _real_extract(self, url): - playlist_id = self._match_id(url) - - webpage = self._download_webpage(url, playlist_id) - playlist = self._extract_playlist(webpage, playlist_id) - - return { - '_type': 'playlist', - 'id': playlist_id, - 'title': self._og_search_title(webpage), - 'entries': self._extract_entries(playlist) - } - - def _extract_playlist(self, webpage, playlist_id): - json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json') - return self._parse_json('[{' + json_string + '}]', playlist_id) - - def _extract_entries(self, playlist): - return [ - self.url_result( - 'kaltura:%s:%s' % (item['kaltura_partner_id'], item['kaltura_entry_id']), - KalturaIE.ie_key(), video_id=item['kaltura_entry_id']) - for item in playlist] diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index b9c97fac4..55d2dd1fe 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -311,9 +311,11 @@ from .ehow import EHowIE from .eighttracks import EightTracksIE from .einthusan import EinthusanIE from .eitb import EitbIE -from .ellentv import ( - EllenTVIE, - EllenTVClipsIE, +from .ellentube import ( + EllenTubeIE, + EllenTubeEpisodeIE, + EllenTubeStudioIE, + EllenTubeVideoIE, ) from .elpais import ElPaisIE from .embedly import EmbedlyIE From 2a57b62b8007973b5b4974a1d9f5ab06ae78c86e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 9 Dec 2017 02:16:23 +0700 Subject: [PATCH 13/31] [ellentube] Fix issues, improve and simplify (closes #14570) --- youtube_dl/extractor/ellentube.py | 167 ++++++++++++++--------------- youtube_dl/extractor/extractors.py | 3 +- 2 files changed, 81 insertions(+), 89 deletions(-) diff --git a/youtube_dl/extractor/ellentube.py b/youtube_dl/extractor/ellentube.py index 68fe17273..544473274 100644 --- a/youtube_dl/extractor/ellentube.py +++ b/youtube_dl/extractor/ellentube.py @@ -4,137 +4,130 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( clean_html, + extract_attributes, + float_or_none, int_or_none, + try_get, ) -class EllenTubeIE(InfoExtractor): - _VALID_URL = r'''(?x) - (?: - https://api-prod\.ellentube\.com/ellenapi/api/item/ - |ellentube: - ) - (?P - [\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12} - )''' +class EllenTubeBaseIE(InfoExtractor): + def _extract_data_config(self, webpage, video_id): + details = self._search_regex( + r'(<[^>]+\bdata-component=(["\'])[Dd]etails.+?>)', webpage, + 'details') + return self._parse_json( + extract_attributes(details)['data-config'], video_id) - _TESTS = [{ - 'url': 'https://api-prod.ellentube.com/ellenapi/api/item/75c64c16-aefd-4558-b4f5-3de09b22e6fc', - 'match_only': True, - }, { - 'url': 'ellentube:734a3353-f697-4e79-9ca9-bfc3002dc1e0', - 'match_only': True, - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - data = self._download_json( - 'https://api-prod.ellentube.com/ellenapi/api/item/%s' % video_id, video_id) + def _extract_video(self, data, video_id): title = data['title'] - description = data.get('description') - publish_time = int_or_none(data.get('publishTime')) - thumbnail = data.get('thumbnail') formats = [] duration = None for entry in data.get('media'): if entry.get('id') == 'm3u8': formats = self._extract_m3u8_formats( - entry.get('url'), video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls') + entry['url'], video_id, 'mp4', + entry_protocol='m3u8_native', m3u8_id='hls') duration = int_or_none(entry.get('duration')) break self._sort_formats(formats) + + def get_insight(kind): + return int_or_none(try_get( + data, lambda x: x['insight']['%ss' % kind])) + return { + 'extractor_key': EllenTubeIE.ie_key(), 'id': video_id, 'title': title, - 'description': description, + 'description': data.get('description'), 'duration': duration, - 'thumbnail': thumbnail, - 'timestamp': publish_time, + 'thumbnail': data.get('thumbnail'), + 'timestamp': float_or_none(data.get('publishTime'), scale=1000), + 'view_count': get_insight('view'), + 'like_count': get_insight('like'), 'formats': formats, } -class EllenTubeVideoIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?ellentube\.com/video/(?P.+)\.html' - - _TEST = { - 'url': 'https://www.ellentube.com/video/ellen-meets-las-vegas-survivors-jesus-campos-and-stephen-schuck.html', +class EllenTubeIE(EllenTubeBaseIE): + _VALID_URL = r'''(?x) + (?: + ellentube:| + https://api-prod\.ellentube\.com/ellenapi/api/item/ + ) + (?P[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}) + ''' + _TESTS = [{ + 'url': 'https://api-prod.ellentube.com/ellenapi/api/item/0822171c-3829-43bf-b99f-d77358ae75e3', 'md5': '2fabc277131bddafdd120e0fc0f974c9', 'info_dict': { 'id': '0822171c-3829-43bf-b99f-d77358ae75e3', 'ext': 'mp4', 'title': 'Ellen Meets Las Vegas Survivors Jesus Campos and Stephen Schuck', 'description': 'md5:76e3355e2242a78ad9e3858e5616923f', + 'thumbnail': r're:^https?://.+?', 'duration': 514, - 'timestamp': 1508505120000, - 'thumbnail': 'https://warnerbros-h.assetsadobe.com/is/image/content/dam/ellen/videos/episodes/season15/32/video--2728751654987218111', + 'timestamp': 1508505120, + 'upload_date': '20171020', + 'view_count': int, + 'like_count': int, } + }, { + 'url': 'ellentube:734a3353-f697-4e79-9ca9-bfc3002dc1e0', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + data = self._download_json( + 'https://api-prod.ellentube.com/ellenapi/api/item/%s' % video_id, + video_id) + return self._extract_video(data, video_id) + + +class EllenTubeVideoIE(EllenTubeBaseIE): + _VALID_URL = r'https?://(?:www\.)?ellentube\.com/video/(?P.+?)\.html' + _TEST = { + 'url': 'https://www.ellentube.com/video/ellen-meets-las-vegas-survivors-jesus-campos-and-stephen-schuck.html', + 'only_matching': True, } def _real_extract(self, url): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) - video_id = self._html_search_regex( - r'(?s).*data-config.+([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})', - webpage, 'video id') - return self.url_result('ellentube:%s' % video_id, 'EllenTube') + video_id = self._extract_data_config(webpage, display_id)['id'] + return self.url_result( + 'ellentube:%s' % video_id, ie=EllenTubeIE.ie_key(), + video_id=video_id) -class EllenTubePlaylistIE(InfoExtractor): - def _extract_videos_from_json(self, data, display_id): - return [self.url_result('ellentube:%s' % elem['id'], 'EllenTube') - for elem in data if elem.get('type') == 'VIDEO'] - - def _extract_playlist(self, url, display_id, extract_description=True): - webpage = self._download_webpage(url, display_id) - playlist_data = self._html_search_regex( - r'', webpage, 'playlist data') - playlist_title = self._search_regex( - r'"title"\s*:\s*"(.+?)"', playlist_data, 'playlist title') - playlist_description = clean_html(self._search_regex( - r'"description"\s*:\s*"(.+?)"', playlist_data, 'playlist description', - fatal=False)) if extract_description else None - api_search = self._search_regex( - r'"filter"\s*:\s*"(.+?)"', playlist_data, 'playlist api request') - api_data = self._download_json( - 'https://api-prod.ellentube.com/ellenapi/api/feed/?%s' % api_search, - display_id) - return self.playlist_result( - self._extract_videos_from_json(api_data, display_id), - display_id, playlist_title, playlist_description) - - -class EllenTubeEpisodeIE(EllenTubePlaylistIE): - _VALID_URL = r'https?://(?:www\.)?ellentube\.com/episode/(?P.+)\.html' - - _TEST = { +class EllenTubePlaylistIE(EllenTubeBaseIE): + _VALID_URL = r'https?://(?:www\.)?ellentube\.com/(?:episode|studios)/(?P.+?)\.html' + _TESTS = [{ 'url': 'https://www.ellentube.com/episode/dax-shepard-jordan-fisher-haim.html', 'info_dict': { 'id': 'dax-shepard-jordan-fisher-haim', - 'title': 'Dax Shepard, \'DWTS\' Team Jordan Fisher & Lindsay Arnold, HAIM', - 'description': 'md5:aed85d42892f6126e71ec5ed2aea2a0d' + 'title': "Dax Shepard, 'DWTS' Team Jordan Fisher & Lindsay Arnold, HAIM", + 'description': 'md5:bfc982194dabb3f4e325e43aa6b2e21c', }, 'playlist_count': 6, - } - - def _real_extract(self, url): - display_id = self._match_id(url) - return self._extract_playlist(url, display_id) - - -class EllenTubeStudioIE(EllenTubePlaylistIE): - _VALID_URL = r'https?://(?:www\.)?ellentube\.com/studios/(?P.+)\.html' - - _TEST = { + }, { 'url': 'https://www.ellentube.com/studios/macey-goes-rving0.html', - 'info_dict': { - 'id': 'macey-goes-rving0', - 'title': 'Macey Goes RVing', - }, - 'playlist_mincount': 3, - } + 'only_matching': True, + }] def _real_extract(self, url): display_id = self._match_id(url) - return self._extract_playlist(url, display_id, False) + webpage = self._download_webpage(url, display_id) + data = self._extract_data_config(webpage, display_id)['data'] + feed = self._download_json( + 'https://api-prod.ellentube.com/ellenapi/api/feed/?%s' + % data['filter'], display_id) + entries = [ + self._extract_video(elem, elem['id']) + for elem in feed if elem.get('type') == 'VIDEO' and elem.get('id')] + return self.playlist_result( + entries, display_id, data.get('title'), + clean_html(data.get('description'))) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 55d2dd1fe..0177a2cff 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -313,9 +313,8 @@ from .einthusan import EinthusanIE from .eitb import EitbIE from .ellentube import ( EllenTubeIE, - EllenTubeEpisodeIE, - EllenTubeStudioIE, EllenTubeVideoIE, + EllenTubePlaylistIE, ) from .elpais import ElPaisIE from .embedly import EmbedlyIE From f4cc03d60b5dd713fb8964cd9ecf8ca2b1a8a556 Mon Sep 17 00:00:00 2001 From: Andrew Bottom Date: Tue, 24 Oct 2017 11:50:02 -0500 Subject: [PATCH 14/31] [stretchinternet] Add extractor --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/stretchinternet.py | 28 +++++++++++++++++++++++++ 2 files changed, 29 insertions(+) create mode 100644 youtube_dl/extractor/stretchinternet.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 0177a2cff..612fd35d4 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1001,6 +1001,7 @@ from .streamango import StreamangoIE from .streamcloud import StreamcloudIE from .streamcz import StreamCZIE from .streetvoice import StreetVoiceIE +from .stretchinternet import StretchInternetIE from .sunporno import SunPornoIE from .svt import ( SVTIE, diff --git a/youtube_dl/extractor/stretchinternet.py b/youtube_dl/extractor/stretchinternet.py new file mode 100644 index 000000000..9a0ec0e65 --- /dev/null +++ b/youtube_dl/extractor/stretchinternet.py @@ -0,0 +1,28 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class StretchInternetIE(InfoExtractor): + IE_DESC = 'StretchInternet' + _VALID_URL = r'https?://.*?stretchinternet\.com/[^/_?].*(?<=eventId=)(?P.*)(?=&).*' + _TEST = { + 'url': 'https://portal.stretchinternet.com/umary/portal.htm?eventId=313900&streamType=video', + 'info_dict': { + 'id': '313900', + 'ext': 'mp4', + 'title': 'StretchInternet' + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + stream = self._download_json('https://neo-client.stretchinternet.com/streamservice/v1/media/stream/v%s' % video_id, video_id) + stream_url = stream.get('source') + return { + 'ie_key': 'Generic', + 'id': video_id, + 'url': 'http://%s' % stream_url, + 'title': 'StretchInternet' + } From a3de5e6c0e0efef4e8ff0cd37961c594b13c7fb9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 9 Dec 2017 17:58:08 +0700 Subject: [PATCH 15/31] [stretchinternet] Fix issues and improve (closes #14576) --- youtube_dl/extractor/stretchinternet.py | 38 +++++++++++++++++++------ 1 file changed, 29 insertions(+), 9 deletions(-) diff --git a/youtube_dl/extractor/stretchinternet.py b/youtube_dl/extractor/stretchinternet.py index 9a0ec0e65..ae2ac1b42 100644 --- a/youtube_dl/extractor/stretchinternet.py +++ b/youtube_dl/extractor/stretchinternet.py @@ -1,28 +1,48 @@ -# coding: utf-8 from __future__ import unicode_literals from .common import InfoExtractor +from ..utils import int_or_none class StretchInternetIE(InfoExtractor): - IE_DESC = 'StretchInternet' - _VALID_URL = r'https?://.*?stretchinternet\.com/[^/_?].*(?<=eventId=)(?P.*)(?=&).*' + _VALID_URL = r'https?://portal\.stretchinternet\.com/[^/]+/portal\.htm\?.*?\beventId=(?P\d+)' _TEST = { 'url': 'https://portal.stretchinternet.com/umary/portal.htm?eventId=313900&streamType=video', 'info_dict': { 'id': '313900', 'ext': 'mp4', - 'title': 'StretchInternet' + 'title': 'Augustana (S.D.) Baseball vs University of Mary', + 'description': 'md5:7578478614aae3bdd4a90f578f787438', + 'timestamp': 1490468400, + 'upload_date': '20170325', } } def _real_extract(self, url): video_id = self._match_id(url) - stream = self._download_json('https://neo-client.stretchinternet.com/streamservice/v1/media/stream/v%s' % video_id, video_id) - stream_url = stream.get('source') + + stream = self._download_json( + 'https://neo-client.stretchinternet.com/streamservice/v1/media/stream/v%s' + % video_id, video_id) + + video_url = 'https://%s' % stream['source'] + + event = self._download_json( + 'https://neo-client.stretchinternet.com/portal-ws/getEvent.json', + video_id, query={ + 'clientID': 99997, + 'eventID': video_id, + 'token': 'asdf', + })['event'] + + title = event.get('title') or event['mobileTitle'] + description = event.get('customText') + timestamp = int_or_none(event.get('longtime')) + return { - 'ie_key': 'Generic', 'id': video_id, - 'url': 'http://%s' % stream_url, - 'title': 'StretchInternet' + 'title': title, + 'description': description, + 'timestamp': timestamp, + 'url': video_url, } From 6f1ec339a0332041d6469887a91cf4e3ff557477 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 9 Dec 2017 19:52:31 +0700 Subject: [PATCH 16/31] [udemy] Improve course id extraction (closes #14938) --- youtube_dl/extractor/udemy.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/udemy.py b/youtube_dl/extractor/udemy.py index c248ea727..b66033923 100644 --- a/youtube_dl/extractor/udemy.py +++ b/youtube_dl/extractor/udemy.py @@ -62,11 +62,11 @@ class UdemyIE(InfoExtractor): def _extract_course_info(self, webpage, video_id): course = self._parse_json( unescapeHTML(self._search_regex( - r'ng-init=["\'].*\bcourse=({.+?});', webpage, 'course', default='{}')), + r'ng-init=["\'].*\bcourse=({.+?})[;"\']', + webpage, 'course', default='{}')), video_id, fatal=False) or {} course_id = course.get('id') or self._search_regex( - (r'"id"\s*:\s*(\d+)', r'data-course-id=["\'](\d+)'), - webpage, 'course id') + r'data-course-id=["\'](\d+)', webpage, 'course id') return course_id, course.get('title') def _enroll_course(self, base_url, webpage, course_id): From 913b61eeee9436a3ddf5675ec935d00c3a05b7a4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 9 Dec 2017 20:02:19 +0700 Subject: [PATCH 17/31] [udemy] Extract more HLS formats --- youtube_dl/extractor/udemy.py | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/youtube_dl/extractor/udemy.py b/youtube_dl/extractor/udemy.py index b66033923..195f5ce78 100644 --- a/youtube_dl/extractor/udemy.py +++ b/youtube_dl/extractor/udemy.py @@ -257,6 +257,11 @@ class UdemyIE(InfoExtractor): video_url = source.get('file') or source.get('src') if not video_url or not isinstance(video_url, compat_str): continue + if source.get('type') == 'application/x-mpegURL' or determine_ext(video_url) == 'm3u8': + formats.extend(self._extract_m3u8_formats( + video_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False)) + continue format_id = source.get('label') f = { 'url': video_url, From 51f2863357af55dfe026bfe47808bf104e7eebf9 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sun, 10 Dec 2017 14:10:52 +0100 Subject: [PATCH 18/31] [twitter] improve extraction(closes #14197) --- youtube_dl/extractor/twitter.py | 141 +++++++++++++++----------------- 1 file changed, 64 insertions(+), 77 deletions(-) diff --git a/youtube_dl/extractor/twitter.py b/youtube_dl/extractor/twitter.py index 1b0b96371..d7e425041 100644 --- a/youtube_dl/extractor/twitter.py +++ b/youtube_dl/extractor/twitter.py @@ -43,7 +43,7 @@ class TwitterBaseIE(InfoExtractor): class TwitterCardIE(TwitterBaseIE): IE_NAME = 'twitter:card' - _VALID_URL = r'https?://(?:www\.)?twitter\.com/i/(?:cards/tfw/v1|videos(?:/tweet)?)/(?P\d+)' + _VALID_URL = r'https?://(?:www\.)?twitter\.com/i/(?Pcards/tfw/v1|videos(?:/tweet)?)/(?P\d+)' _TESTS = [ { 'url': 'https://twitter.com/i/cards/tfw/v1/560070183650213889', @@ -51,11 +51,10 @@ class TwitterCardIE(TwitterBaseIE): 'info_dict': { 'id': '560070183650213889', 'ext': 'mp4', - 'title': 'Twitter Card', + 'title': 'Twitter web player', 'thumbnail': r're:^https?://.*\.jpg$', 'duration': 30.033, }, - 'skip': 'Video gone', }, { 'url': 'https://twitter.com/i/cards/tfw/v1/623160978427936768', @@ -63,11 +62,9 @@ class TwitterCardIE(TwitterBaseIE): 'info_dict': { 'id': '623160978427936768', 'ext': 'mp4', - 'title': 'Twitter Card', - 'thumbnail': r're:^https?://.*\.jpg', - 'duration': 80.155, + 'title': 'Twitter web player', + 'thumbnail': r're:^https?://.*(?:\bformat=|\.)jpg', }, - 'skip': 'Video gone', }, { 'url': 'https://twitter.com/i/cards/tfw/v1/654001591733886977', @@ -120,15 +117,15 @@ class TwitterCardIE(TwitterBaseIE): elif media_url.endswith('.mpd'): formats.extend(self._extract_mpd_formats(media_url, video_id, mpd_id='dash')) else: - vbr = int_or_none(dict_get(media_variant, ('bitRate', 'bitrate')), scale=1000) + tbr = int_or_none(dict_get(media_variant, ('bitRate', 'bitrate')), scale=1000) a_format = { 'url': media_url, - 'format_id': 'http-%d' % vbr if vbr else 'http', - 'vbr': vbr, + 'format_id': 'http-%d' % tbr if tbr else 'http', + 'tbr': tbr, } # Reported bitRate may be zero - if not a_format['vbr']: - del a_format['vbr'] + if not a_format['tbr']: + del a_format['tbr'] self._search_dimensions_in_video_url(a_format, media_url) @@ -150,79 +147,83 @@ class TwitterCardIE(TwitterBaseIE): bearer_token = self._search_regex( r'BEARER_TOKEN\s*:\s*"([^"]+)"', main_script, 'bearer token') - guest_token = self._search_regex( - r'document\.cookie\s*=\s*decodeURIComponent\("gt=(\d+)', - webpage, 'guest token') + # https://developer.twitter.com/en/docs/tweets/post-and-engage/api-reference/get-statuses-show-id api_data = self._download_json( - 'https://api.twitter.com/2/timeline/conversation/%s.json' % video_id, - video_id, 'Downloading mobile API data', + 'https://api.twitter.com/1.1/statuses/show/%s.json' % video_id, + video_id, 'Downloading API data', headers={ 'Authorization': 'Bearer ' + bearer_token, - 'x-guest-token': guest_token, }) - media_info = try_get(api_data, lambda o: o['globalObjects']['tweets'][video_id] - ['extended_entities']['media'][0]['video_info']) or {} + media_info = try_get(api_data, lambda o: o['extended_entities']['media'][0]['video_info']) or {} return self._parse_media_info(media_info, video_id) def _real_extract(self, url): - video_id = self._match_id(url) + path, video_id = re.search(self._VALID_URL, url).groups() config = None formats = [] duration = None - webpage = self._download_webpage(url, video_id) + urls = [url] + if path.startswith('cards/'): + urls.append('https://twitter.com/i/videos/' + video_id) - iframe_url = self._html_search_regex( - r']+src="((?:https?:)?//(?:www\.youtube\.com/embed/[^"]+|(?:www\.)?vine\.co/v/\w+/card))"', - webpage, 'video iframe', default=None) - if iframe_url: - return self.url_result(iframe_url) + for u in urls: + webpage = self._download_webpage(u, video_id) - config = self._parse_json(self._html_search_regex( - r'data-(?:player-)?config="([^"]+)"', webpage, - 'data player config', default='{}'), - video_id) + iframe_url = self._html_search_regex( + r']+src="((?:https?:)?//(?:www\.youtube\.com/embed/[^"]+|(?:www\.)?vine\.co/v/\w+/card))"', + webpage, 'video iframe', default=None) + if iframe_url: + return self.url_result(iframe_url) - if config.get('source_type') == 'vine': - return self.url_result(config['player_url'], 'Vine') + config = self._parse_json(self._html_search_regex( + r'data-(?:player-)?config="([^"]+)"', webpage, + 'data player config', default='{}'), + video_id) - periscope_url = PeriscopeIE._extract_url(webpage) - if periscope_url: - return self.url_result(periscope_url, PeriscopeIE.ie_key()) + if config.get('source_type') == 'vine': + return self.url_result(config['player_url'], 'Vine') - video_url = config.get('video_url') or config.get('playlist', [{}])[0].get('source') + periscope_url = PeriscopeIE._extract_url(webpage) + if periscope_url: + return self.url_result(periscope_url, PeriscopeIE.ie_key()) - if video_url: - if determine_ext(video_url) == 'm3u8': - formats.extend(self._extract_m3u8_formats(video_url, video_id, ext='mp4', m3u8_id='hls')) - else: - f = { - 'url': video_url, - } + video_url = config.get('video_url') or config.get('playlist', [{}])[0].get('source') - self._search_dimensions_in_video_url(f, video_url) + if video_url: + if determine_ext(video_url) == 'm3u8': + formats.extend(self._extract_m3u8_formats(video_url, video_id, ext='mp4', m3u8_id='hls')) + else: + f = { + 'url': video_url, + } - formats.append(f) + self._search_dimensions_in_video_url(f, video_url) - vmap_url = config.get('vmapUrl') or config.get('vmap_url') - if vmap_url: - formats.extend( - self._extract_formats_from_vmap_url(vmap_url, video_id)) + formats.append(f) - media_info = None + vmap_url = config.get('vmapUrl') or config.get('vmap_url') + if vmap_url: + formats.extend( + self._extract_formats_from_vmap_url(vmap_url, video_id)) - for entity in config.get('status', {}).get('entities', []): - if 'mediaInfo' in entity: - media_info = entity['mediaInfo'] + media_info = None - if media_info: - formats.extend(self._parse_media_info(media_info, video_id)) - duration = float_or_none(media_info.get('duration', {}).get('nanos'), scale=1e9) + for entity in config.get('status', {}).get('entities', []): + if 'mediaInfo' in entity: + media_info = entity['mediaInfo'] - username = config.get('user', {}).get('screen_name') - if username: - formats.extend(self._extract_mobile_formats(username, video_id)) + if media_info: + formats.extend(self._parse_media_info(media_info, video_id)) + duration = float_or_none(media_info.get('duration', {}).get('nanos'), scale=1e9) + + username = config.get('user', {}).get('screen_name') + if username: + formats.extend(self._extract_mobile_formats(username, video_id)) + + if formats: + break self._remove_duplicate_formats(formats) self._sort_formats(formats) @@ -258,9 +259,6 @@ class TwitterIE(InfoExtractor): 'uploader_id': 'freethenipple', 'duration': 12.922, }, - 'params': { - 'skip_download': True, # requires ffmpeg - }, }, { 'url': 'https://twitter.com/giphz/status/657991469417025536/photo/1', 'md5': 'f36dcd5fb92bf7057f155e7d927eeb42', @@ -277,7 +275,6 @@ class TwitterIE(InfoExtractor): 'skip': 'Account suspended', }, { 'url': 'https://twitter.com/starwars/status/665052190608723968', - 'md5': '39b7199856dee6cd4432e72c74bc69d4', 'info_dict': { 'id': '665052190608723968', 'ext': 'mp4', @@ -303,20 +300,16 @@ class TwitterIE(InfoExtractor): }, }, { 'url': 'https://twitter.com/jaydingeer/status/700207533655363584', - 'md5': '', 'info_dict': { 'id': '700207533655363584', 'ext': 'mp4', - 'title': 'あかさ - BEAT PROD: @suhmeduh #Damndaniel', - 'description': 'あかさ on Twitter: "BEAT PROD: @suhmeduh https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ"', + 'title': 'JG - BEAT PROD: @suhmeduh #Damndaniel', + 'description': 'JG on Twitter: "BEAT PROD: @suhmeduh https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ"', 'thumbnail': r're:^https?://.*\.jpg', - 'uploader': 'あかさ', + 'uploader': 'JG', 'uploader_id': 'jaydingeer', 'duration': 30.0, }, - 'params': { - 'skip_download': True, # requires ffmpeg - }, }, { 'url': 'https://twitter.com/Filmdrunk/status/713801302971588609', 'md5': '89a15ed345d13b86e9a5a5e051fa308a', @@ -342,9 +335,6 @@ class TwitterIE(InfoExtractor): 'uploader': 'Captain America', 'duration': 3.17, }, - 'params': { - 'skip_download': True, # requires ffmpeg - }, }, { 'url': 'https://twitter.com/OPP_HSD/status/779210622571536384', 'info_dict': { @@ -370,9 +360,6 @@ class TwitterIE(InfoExtractor): 'uploader_id': 'news_al3alm', 'duration': 277.4, }, - 'params': { - 'format': 'best[format_id^=http-]', - }, }, { 'url': 'https://twitter.com/i/web/status/910031516746514432', 'info_dict': { From c38970ca10fc8c8e3ba05019d5f73ff235de9fc8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 10 Dec 2017 22:46:21 +0700 Subject: [PATCH 19/31] [culturebox] Improve video id extraction (closes #14947) --- youtube_dl/extractor/francetv.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index 80c597015..095bb3954 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -356,6 +356,7 @@ class CultureboxIE(FranceTVBaseInfoExtractor): raise ExtractorError('Video %s is not available' % name, expected=True) video_id, catalogue = self._search_regex( - r'"https?://videos\.francetv\.fr/video/([^@]+@[^"]+)"', webpage, 'video id').split('@') + r'["\'>]https?://videos\.francetv\.fr/video/([^@]+@.+?)["\'<]', + webpage, 'video id').split('@') return self._extract_video(video_id, catalogue) From fa1dd6d2cdaa41b67ee2fc47dc5184a040004d41 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 10 Dec 2017 23:15:24 +0700 Subject: [PATCH 20/31] [ChangeLog] Actualize --- ChangeLog | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/ChangeLog b/ChangeLog index 63837d62b..fd3f3ebf8 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,30 @@ +version + +Core ++ [utils] Add sami mimetype to mimetype2ext + +Extractors +* [culturebox] Improve video id extraction (#14947) +* [twitter] Improve extraction (#14197) ++ [udemy] Extract more HLS formats +* [udemy] Improve course id extraction (#14938) ++ [stretchinternet] Add support for portal.stretchinternet.com (#14576) +* [ellentube] Fix extraction (#14407, #14570) ++ [raiplay:playlist] Add support for playlists (#14563) +* [sonyliv] Bypass geo restriction +* [sonyliv] Extract higher quality formats (#14922) +* [fox] Extract subtitles ++ [fox] Add support for Adobe Pass authentication (#14205, #14489) +- [dailymotion:cloud] Remove extractor (#6794) +* [xhamster] Fix thumbnail extraction (#14780) ++ [xhamster] Add support for mobile URLs (#14780) +* [generic] Don't pass video id as mpd id while extracting DASH (#14902) +* [ard] Skip invalid stream URLs (#14906) +* [porncom] Fix metadata extraction (#14911) +* [pluralsight] Detect agreement request (#14913) +* [toutv] Fix login (#14614) + + version 2017.12.02 Core From 1fa0dce2c044826eec87b712f90964b90198aaa4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 10 Dec 2017 23:18:53 +0700 Subject: [PATCH 21/31] release 2017.12.10 --- .github/ISSUE_TEMPLATE.md | 6 +++--- ChangeLog | 2 +- docs/supportedsites.md | 8 +++++--- youtube_dl/version.py | 2 +- 4 files changed, 10 insertions(+), 8 deletions(-) diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 513823b9b..736869bf0 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.12.02*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.12.02** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.12.10*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.12.10** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -35,7 +35,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2017.12.02 +[debug] youtube-dl version 2017.12.10 [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/ChangeLog b/ChangeLog index fd3f3ebf8..a1fdcab99 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,4 @@ -version +version 2017.12.10 Core + [utils] Add sami mimetype to mimetype2ext diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 0287a4011..d5e3a8a67 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -198,7 +198,6 @@ - **dailymotion** - **dailymotion:playlist** - **dailymotion:user** - - **DailymotionCloud** - **DaisukiMotto** - **DaisukiMottoPlaylist** - **daum.net** @@ -243,8 +242,9 @@ - **eHow** - **Einthusan** - **eitb.tv** - - **EllenTV** - - **EllenTV:clips** + - **EllenTube** + - **EllenTubePlaylist** + - **EllenTubeVideo** - **ElPais**: El País - **Embedly** - **EMPFlix** @@ -662,6 +662,7 @@ - **Rai** - **RaiPlay** - **RaiPlayLive** + - **RaiPlayPlaylist** - **RBMARadio** - **RDS**: RDS.ca - **RedBullTV** @@ -781,6 +782,7 @@ - **streamcloud.eu** - **StreamCZ** - **StreetVoice** + - **StretchInternet** - **SunPorno** - **SVT** - **SVTPlay**: SVT Play and Öppet arkiv diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 88bf1d652..d0c438317 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2017.12.02' +__version__ = '2017.12.10' From b6f78d76c14a1787606aad23c2df0d5158d1fde1 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 11 Dec 2017 13:38:55 +0100 Subject: [PATCH 22/31] [tbs] fix extraction(fixes #13658) --- youtube_dl/extractor/tbs.py | 134 +++++++++++++++++++++++---------- youtube_dl/extractor/turner.py | 48 ++++++------ 2 files changed, 120 insertions(+), 62 deletions(-) diff --git a/youtube_dl/extractor/tbs.py b/youtube_dl/extractor/tbs.py index e9474533f..460bc5d74 100644 --- a/youtube_dl/extractor/tbs.py +++ b/youtube_dl/extractor/tbs.py @@ -4,58 +4,110 @@ from __future__ import unicode_literals import re from .turner import TurnerBaseIE -from ..utils import extract_attributes +from ..utils import ( + float_or_none, + int_or_none, + strip_or_none, +) class TBSIE(TurnerBaseIE): - # https://github.com/rg3/youtube-dl/issues/13658 - _WORKING = False - - _VALID_URL = r'https?://(?:www\.)?(?Ptbs|tntdrama)\.com/videos/(?:[^/]+/)+(?P[^/?#]+)\.html' + _VALID_URL = r'https?://(?:www\.)?(?Ptbs|tntdrama)\.com/(?:movies|shows/[^/]+/(?:clips|season-\d+/episode-\d+))/(?P[^/?#]+)' _TESTS = [{ - 'url': 'http://www.tbs.com/videos/people-of-earth/season-1/extras/2007318/theatrical-trailer.html', - 'md5': '9e61d680e2285066ade7199e6408b2ee', + 'url': 'http://www.tntdrama.com/shows/the-alienist/clips/monster', 'info_dict': { - 'id': '2007318', + 'id': '8d384cde33b89f3a43ce5329de42903ed5099887', 'ext': 'mp4', - 'title': 'Theatrical Trailer', - 'description': 'Catch the latest comedy from TBS, People of Earth, premiering Halloween night--Monday, October 31, at 9/8c.', + 'title': 'Monster', + 'description': 'Get a first look at the theatrical trailer for TNT’s highly anticipated new psychological thriller The Alienist, which premieres January 22 on TNT.', + 'timestamp': 1508175329, + 'upload_date': '20171016', }, - 'skip': 'TBS videos are deleted after a while', + 'params': { + # m3u8 download + 'skip_download': True, + } }, { - 'url': 'http://www.tntdrama.com/videos/good-behavior/season-1/extras/1538823/you-better-run.html', - 'md5': 'ce53c6ead5e9f3280b4ad2031a6fab56', - 'info_dict': { - 'id': '1538823', - 'ext': 'mp4', - 'title': 'You Better Run', - 'description': 'Letty Raines must figure out what she\'s running toward while running away from her past. Good Behavior premieres November 15 at 9/8c.', - }, - 'skip': 'TBS videos are deleted after a while', + 'url': 'http://www.tbs.com/shows/search-party/season-1/episode-1/explicit-the-mysterious-disappearance-of-the-girl-no-one-knew', + 'only_matching': True, + }, { + 'url': 'http://www.tntdrama.com/movies/star-wars-a-new-hope', + 'only_matching': True, }] def _real_extract(self, url): domain, display_id = re.match(self._VALID_URL, url).groups() site = domain[:3] webpage = self._download_webpage(url, display_id) - video_params = extract_attributes(self._search_regex(r'(<[^>]+id="page-video"[^>]*>)', webpage, 'video params')) - query = None - clip_id = video_params.get('clipid') - if clip_id: - query = 'id=' + clip_id - else: - query = 'titleId=' + video_params['titleid'] - return self._extract_cvp_info( - 'http://www.%s.com/service/cvpXml?%s' % (domain, query), display_id, { - 'default': { - 'media_src': 'http://ht.cdn.turner.com/%s/big' % site, - }, - 'secure': { - 'media_src': 'http://androidhls-secure.cdn.turner.com/%s/big' % site, - 'tokenizer_src': 'http://www.%s.com/video/processors/services/token_ipadAdobe.do' % domain, - }, - }, { - 'url': url, - 'site_name': site.upper(), - 'auth_required': video_params.get('isAuthRequired') != 'false', - }) + video_data = self._parse_json(self._search_regex( + r']+?data-drupal-selector="drupal-settings-json"[^>]*?>({.+?})', + webpage, 'drupal setting'), display_id)['turner_playlist'][0] + + media_id = video_data['mediaID'] + title = video_data['title'] + + streams_data = self._download_json( + 'http://medium.ngtv.io/media/%s/tv' % media_id, + media_id)['media']['tv'] + duration = None + chapters = [] + formats = [] + for supported_type in ('unprotected', 'bulkaes'): + stream_data = streams_data.get(supported_type, {}) + m3u8_url = stream_data.get('secureUrl') or stream_data.get('url') + if not m3u8_url: + continue + if stream_data.get('playlistProtection') == 'spe': + m3u8_url = self._add_akamai_spe_token( + 'http://www.%s.com/service/token_spe' % site, + m3u8_url, media_id, { + 'url': url, + 'site_name': site.upper(), + 'auth_required': video_data.get('authRequired') == '1', + }) + formats.extend(self._extract_m3u8_formats( + m3u8_url, media_id, 'mp4', m3u8_id='hls', fatal=False)) + + duration = float_or_none(stream_data.get('totalRuntime') or video_data.get('duration')) + + if not chapters: + for chapter in stream_data.get('contentSegments', []): + start_time = float_or_none(chapter.get('start')) + duration = float_or_none(chapter.get('duration')) + if start_time is None or duration is None: + continue + chapters.append({ + 'start_time': start_time, + 'end_time': start_time + duration, + }) + self._sort_formats(formats) + + thumbnails = [] + for image_id, image in video_data.get('images', {}).items(): + image_url = image.get('url') + if not image_url or image.get('type') != 'video': + continue + i = { + 'id': image_id, + 'url': image_url, + } + mobj = re.search(r'(\d+)x(\d+)', image_url) + if mobj: + i.update({ + 'width': int(mobj.group(1)), + 'height': int(mobj.group(2)), + }) + thumbnails.append(i) + + return { + 'id': media_id, + 'title': title, + 'description': strip_or_none(video_data.get('descriptionNoTags') or video_data.get('shortDescriptionNoTags')), + 'duration': duration, + 'timestamp': int_or_none(video_data.get('created')), + 'season_number': int_or_none(video_data.get('season')), + 'episode_number': int_or_none(video_data.get('episode')), + 'cahpters': chapters, + 'thumbnails': thumbnails, + 'formats': formats, + } diff --git a/youtube_dl/extractor/turner.py b/youtube_dl/extractor/turner.py index efeb677ee..e73b64aeb 100644 --- a/youtube_dl/extractor/turner.py +++ b/youtube_dl/extractor/turner.py @@ -18,9 +18,32 @@ from ..utils import ( class TurnerBaseIE(AdobePassIE): + _AKAMAI_SPE_TOKEN_CACHE = {} + def _extract_timestamp(self, video_data): return int_or_none(xpath_attr(video_data, 'dateCreated', 'uts')) + def _add_akamai_spe_token(self, tokenizer_src, video_url, content_id, ap_data): + secure_path = self._search_regex(r'https?://[^/]+(.+/)', video_url, 'secure path') + '*' + token = self._AKAMAI_SPE_TOKEN_CACHE.get(secure_path) + if not token: + query = { + 'path': secure_path, + 'videoId': content_id, + } + if ap_data.get('auth_required'): + query['accessToken'] = self._extract_mvpd_auth(ap_data['url'], content_id, ap_data['site_name'], ap_data['site_name']) + auth = self._download_xml( + tokenizer_src, content_id, query=query) + error_msg = xpath_text(auth, 'error/msg') + if error_msg: + raise ExtractorError(error_msg, expected=True) + token = xpath_text(auth, 'token') + if not token: + return video_url + self._AKAMAI_SPE_TOKEN_CACHE[secure_path] = token + return video_url + '?hdnea=' + token + def _extract_cvp_info(self, data_src, video_id, path_data={}, ap_data={}): video_data = self._download_xml(data_src, video_id) video_id = video_data.attrib['id'] @@ -33,7 +56,6 @@ class TurnerBaseIE(AdobePassIE): # rtmp_src = splited_rtmp_src[1] # aifp = xpath_text(video_data, 'akamai/aifp', default='') - tokens = {} urls = [] formats = [] rex = re.compile( @@ -67,26 +89,10 @@ class TurnerBaseIE(AdobePassIE): secure_path_data = path_data.get('secure') if not secure_path_data: continue - video_url = secure_path_data['media_src'] + video_url - secure_path = self._search_regex(r'https?://[^/]+(.+/)', video_url, 'secure path') + '*' - token = tokens.get(secure_path) - if not token: - query = { - 'path': secure_path, - 'videoId': content_id, - } - if ap_data.get('auth_required'): - query['accessToken'] = self._extract_mvpd_auth(ap_data['url'], video_id, ap_data['site_name'], ap_data['site_name']) - auth = self._download_xml( - secure_path_data['tokenizer_src'], video_id, query=query) - error_msg = xpath_text(auth, 'error/msg') - if error_msg: - raise ExtractorError(error_msg, expected=True) - token = xpath_text(auth, 'token') - if not token: - continue - tokens[secure_path] = token - video_url = video_url + '?hdnea=' + token + video_url = self._add_akamai_spe_token( + secure_path_data['tokenizer_src'], + secure_path_data['media_src'] + video_url, + content_id, ap_data) elif not re.match('https?://', video_url): base_path_data = path_data.get(ext, path_data.get('default', {})) media_src = base_path_data.get('media_src') From 5868079e9921bfb03c64439d2188b765fc30dcfc Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 11 Dec 2017 14:37:03 +0100 Subject: [PATCH 23/31] [nick.com] improve extraction(fixes #14876) --- youtube_dl/extractor/nick.py | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/nick.py b/youtube_dl/extractor/nick.py index 310eea2cf..cae8faf3e 100644 --- a/youtube_dl/extractor/nick.py +++ b/youtube_dl/extractor/nick.py @@ -10,7 +10,7 @@ from ..utils import update_url_query class NickIE(MTVServicesInfoExtractor): # None of videos on the website are still alive? IE_NAME = 'nick.com' - _VALID_URL = r'https?://(?:(?:www|beta)\.)?nick(?:jr)?\.com/(?:[^/]+/)?(?:videos/clip|[^/]+/videos)/(?P[^/?#.]+)' + _VALID_URL = r'https?://(?P(?:(?:www|beta)\.)?nick(?:jr)?\.com)/(?:[^/]+/)?(?:videos/clip|[^/]+/videos)/(?P[^/?#.]+)' _FEED_URL = 'http://udat.mtvnservices.com/service1/dispatch.htm' _GEO_COUNTRIES = ['US'] _TESTS = [{ @@ -69,8 +69,14 @@ class NickIE(MTVServicesInfoExtractor): 'mgid': uri, } - def _extract_mgid(self, webpage): - return self._search_regex(r'data-contenturi="([^"]+)', webpage, 'mgid') + def _real_extract(self, url): + domain, display_id = re.match(self._VALID_URL, url).groups() + video_data = self._download_json( + 'http://%s/data/video.endLevel.json' % domain, + display_id, query={ + 'urlKey': display_id, + }) + return self._get_videos_info(video_data['player'] + video_data['id']) class NickDeIE(MTVServicesInfoExtractor): From 08d77a95c98a1d1dcaa5df99b709f119e7a64f37 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 11 Dec 2017 17:18:05 +0100 Subject: [PATCH 24/31] [nickelodeon:br] add support for Nickelodeon(Brazil) websites(closes #14893) --- youtube_dl/extractor/nick.py | 45 ++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) diff --git a/youtube_dl/extractor/nick.py b/youtube_dl/extractor/nick.py index cae8faf3e..f38c2c725 100644 --- a/youtube_dl/extractor/nick.py +++ b/youtube_dl/extractor/nick.py @@ -79,6 +79,51 @@ class NickIE(MTVServicesInfoExtractor): return self._get_videos_info(video_data['player'] + video_data['id']) +class NickBeIE(MTVServicesInfoExtractor): + IE_NAME = 'nickelodeon:br' + _VALID_URL = r'https?://(?P(?:www\.)?nickjr|mundonick\.uol)\.com\.br/(?:programas/)?[^/]+/videos/(?:episodios/)?(?P[^/?#.]+)' + _TESTS = [{ + 'url': 'http://www.nickjr.com.br/patrulha-canina/videos/210-labirinto-de-pipoca/', + 'only_matching': True, + }, { + 'url': 'http://mundonick.uol.com.br/programas/the-loud-house/videos/muitas-irmas/7ljo9j', + 'only_matching': True, + }] + + def _real_extract(self, url): + domain, display_id = re.match(self._VALID_URL, url).groups() + webpage = self._download_webpage(url, display_id) + uri = self._search_regex( + r'data-(?:contenturi|mgid)="([^"]+)', webpage, 'mgid') + video_id = self._id_from_uri(uri) + config = self._download_json( + 'http://media.mtvnservices.com/pmt/e1/access/index.html', + video_id, query={ + 'uri': uri, + 'configtype': 'edge', + }, headers={ + 'Referer': url, + }) + info_url = self._remove_template_parameter(config['feedWithQueryParams']) + if info_url == 'None': + if domain.startswith('www.'): + domain = domain[4:] + content_domain = { + 'mundonick.uol': 'mundonick.com.br', + 'nickjr': 'br.nickelodeonjunior.tv', + }[domain] + query = { + 'mgid': uri, + 'imageEp': content_domain, + 'arcEp': content_domain, + } + if domain == 'nickjr.com.br': + query['ep'] = 'c4b16088' + info_url = update_url_query( + 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed', query) + return self._get_videos_info_from_url(info_url, video_id) + + class NickDeIE(MTVServicesInfoExtractor): IE_NAME = 'nick.de' _VALID_URL = r'https?://(?:www\.)?(?Pnick\.(?:de|com\.pl|ch)|nickelodeon\.(?:nl|be|at|dk|no|se))/[^/]+/(?:[^/]+/)*(?P[^/?#&]+)' From e4f201bc1b4ffbf6423278e8d744727aa7d6f415 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 11 Dec 2017 17:19:16 +0100 Subject: [PATCH 25/31] [extractors] add import for NickBrIE --- youtube_dl/extractor/extractors.py | 1 + 1 file changed, 1 insertion(+) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 612fd35d4..25c4ce0de 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -689,6 +689,7 @@ from .nhl import ( ) from .nick import ( NickIE, + NickBeIE, NickDeIE, NickNightIE, NickRuIE, From 127e98d31dd96b135f0f511c4ca171a300e089cc Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 11 Dec 2017 17:21:31 +0100 Subject: [PATCH 26/31] [nickelodeon:br] correct extractor name --- youtube_dl/extractor/extractors.py | 2 +- youtube_dl/extractor/nick.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 25c4ce0de..99887ee89 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -689,7 +689,7 @@ from .nhl import ( ) from .nick import ( NickIE, - NickBeIE, + NickBrIE, NickDeIE, NickNightIE, NickRuIE, diff --git a/youtube_dl/extractor/nick.py b/youtube_dl/extractor/nick.py index f38c2c725..7edd68472 100644 --- a/youtube_dl/extractor/nick.py +++ b/youtube_dl/extractor/nick.py @@ -79,7 +79,7 @@ class NickIE(MTVServicesInfoExtractor): return self._get_videos_info(video_data['player'] + video_data['id']) -class NickBeIE(MTVServicesInfoExtractor): +class NickBrIE(MTVServicesInfoExtractor): IE_NAME = 'nickelodeon:br' _VALID_URL = r'https?://(?P(?:www\.)?nickjr|mundonick\.uol)\.com\.br/(?:programas/)?[^/]+/videos/(?:episodios/)?(?P[^/?#.]+)' _TESTS = [{ From 23b6e23002d8bd3af3b2ccb2e1b833c1dd1b3cbf Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Mon, 11 Dec 2017 21:36:12 +0100 Subject: [PATCH 27/31] [tvnow] fix extraction(closes #7831) --- youtube_dl/extractor/extractors.py | 8 +- youtube_dl/extractor/nowtv.py | 261 ----------------------------- youtube_dl/extractor/tvnow.py | 175 +++++++++++++++++++ 3 files changed, 179 insertions(+), 265 deletions(-) delete mode 100644 youtube_dl/extractor/nowtv.py create mode 100644 youtube_dl/extractor/tvnow.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 99887ee89..fb9f365f2 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -722,10 +722,6 @@ from .nowness import ( NownessPlaylistIE, NownessSeriesIE, ) -from .nowtv import ( - NowTVIE, - NowTVListIE, -) from .noz import NozIE from .npo import ( AndereTijdenIE, @@ -1105,6 +1101,10 @@ from .tvigle import TvigleIE from .tvland import TVLandIE from .tvn24 import TVN24IE from .tvnoe import TVNoeIE +from .tvnow import ( + TVNowIE, + TVNowListIE, +) from .tvp import ( TVPEmbedIE, TVPIE, diff --git a/youtube_dl/extractor/nowtv.py b/youtube_dl/extractor/nowtv.py deleted file mode 100644 index e43b37136..000000000 --- a/youtube_dl/extractor/nowtv.py +++ /dev/null @@ -1,261 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..compat import compat_str -from ..utils import ( - ExtractorError, - determine_ext, - int_or_none, - parse_iso8601, - parse_duration, - remove_start, -) - - -class NowTVBaseIE(InfoExtractor): - _VIDEO_FIELDS = ( - 'id', 'title', 'free', 'geoblocked', 'articleLong', 'articleShort', - 'broadcastStartDate', 'seoUrl', 'duration', 'files', - 'format.defaultImage169Format', 'format.defaultImage169Logo') - - def _extract_video(self, info, display_id=None): - video_id = compat_str(info['id']) - - files = info['files'] - if not files: - if info.get('geoblocked', False): - raise ExtractorError( - 'Video %s is not available from your location due to geo restriction' % video_id, - expected=True) - if not info.get('free', True): - raise ExtractorError( - 'Video %s is not available for free' % video_id, expected=True) - - formats = [] - for item in files['items']: - if determine_ext(item['path']) != 'f4v': - continue - app, play_path = remove_start(item['path'], '/').split('/', 1) - formats.append({ - 'url': 'rtmpe://fms.rtl.de', - 'app': app, - 'play_path': 'mp4:%s' % play_path, - 'ext': 'flv', - 'page_url': 'http://rtlnow.rtl.de', - 'player_url': 'http://cdn.static-fra.de/now/vodplayer.swf', - 'tbr': int_or_none(item.get('bitrate')), - }) - self._sort_formats(formats) - - title = info['title'] - description = info.get('articleLong') or info.get('articleShort') - timestamp = parse_iso8601(info.get('broadcastStartDate'), ' ') - duration = parse_duration(info.get('duration')) - - f = info.get('format', {}) - thumbnail = f.get('defaultImage169Format') or f.get('defaultImage169Logo') - - return { - 'id': video_id, - 'display_id': display_id or info.get('seoUrl'), - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'timestamp': timestamp, - 'duration': duration, - 'formats': formats, - } - - -class NowTVIE(NowTVBaseIE): - _WORKING = False - _VALID_URL = r'https?://(?:www\.)?nowtv\.(?:de|at|ch)/(?:rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P[^/]+)/(?:(?:list/[^/]+|jahr/\d{4}/\d{1,2})/)?(?P[^/]+)/(?:player|preview)' - - _TESTS = [{ - # rtl - 'url': 'http://www.nowtv.de/rtl/bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit/player', - 'info_dict': { - 'id': '203519', - 'display_id': 'bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit', - 'ext': 'flv', - 'title': 'Inka Bause stellt die neuen Bauern vor', - 'description': 'md5:e234e1ed6d63cf06be5c070442612e7e', - 'thumbnail': r're:^https?://.*\.jpg$', - 'timestamp': 1432580700, - 'upload_date': '20150525', - 'duration': 2786, - }, - 'params': { - # rtmp download - 'skip_download': True, - }, - }, { - # rtl2 - 'url': 'http://www.nowtv.de/rtl2/berlin-tag-nacht/berlin-tag-nacht-folge-934/player', - 'info_dict': { - 'id': '203481', - 'display_id': 'berlin-tag-nacht/berlin-tag-nacht-folge-934', - 'ext': 'flv', - 'title': 'Berlin - Tag & Nacht (Folge 934)', - 'description': 'md5:c85e88c2e36c552dfe63433bc9506dd0', - 'thumbnail': r're:^https?://.*\.jpg$', - 'timestamp': 1432666800, - 'upload_date': '20150526', - 'duration': 2641, - }, - 'params': { - # rtmp download - 'skip_download': True, - }, - }, { - # rtlnitro - 'url': 'http://www.nowtv.de/rtlnitro/alarm-fuer-cobra-11-die-autobahnpolizei/hals-und-beinbruch-2014-08-23-21-10-00/player', - 'info_dict': { - 'id': '165780', - 'display_id': 'alarm-fuer-cobra-11-die-autobahnpolizei/hals-und-beinbruch-2014-08-23-21-10-00', - 'ext': 'flv', - 'title': 'Hals- und Beinbruch', - 'description': 'md5:b50d248efffe244e6f56737f0911ca57', - 'thumbnail': r're:^https?://.*\.jpg$', - 'timestamp': 1432415400, - 'upload_date': '20150523', - 'duration': 2742, - }, - 'params': { - # rtmp download - 'skip_download': True, - }, - }, { - # superrtl - 'url': 'http://www.nowtv.de/superrtl/medicopter-117/angst/player', - 'info_dict': { - 'id': '99205', - 'display_id': 'medicopter-117/angst', - 'ext': 'flv', - 'title': 'Angst!', - 'description': 'md5:30cbc4c0b73ec98bcd73c9f2a8c17c4e', - 'thumbnail': r're:^https?://.*\.jpg$', - 'timestamp': 1222632900, - 'upload_date': '20080928', - 'duration': 3025, - }, - 'params': { - # rtmp download - 'skip_download': True, - }, - }, { - # ntv - 'url': 'http://www.nowtv.de/ntv/ratgeber-geld/thema-ua-der-erste-blick-die-apple-watch/player', - 'info_dict': { - 'id': '203521', - 'display_id': 'ratgeber-geld/thema-ua-der-erste-blick-die-apple-watch', - 'ext': 'flv', - 'title': 'Thema u.a.: Der erste Blick: Die Apple Watch', - 'description': 'md5:4312b6c9d839ffe7d8caf03865a531af', - 'thumbnail': r're:^https?://.*\.jpg$', - 'timestamp': 1432751700, - 'upload_date': '20150527', - 'duration': 1083, - }, - 'params': { - # rtmp download - 'skip_download': True, - }, - }, { - # vox - 'url': 'http://www.nowtv.de/vox/der-hundeprofi/buero-fall-chihuahua-joel/player', - 'info_dict': { - 'id': '128953', - 'display_id': 'der-hundeprofi/buero-fall-chihuahua-joel', - 'ext': 'flv', - 'title': "Büro-Fall / Chihuahua 'Joel'", - 'description': 'md5:e62cb6bf7c3cc669179d4f1eb279ad8d', - 'thumbnail': r're:^https?://.*\.jpg$', - 'timestamp': 1432408200, - 'upload_date': '20150523', - 'duration': 3092, - }, - 'params': { - # rtmp download - 'skip_download': True, - }, - }, { - 'url': 'http://www.nowtv.de/rtl/bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit/preview', - 'only_matching': True, - }, { - 'url': 'http://www.nowtv.at/rtl/bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit/preview?return=/rtl/bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit', - 'only_matching': True, - }, { - 'url': 'http://www.nowtv.de/rtl2/echtzeit/list/aktuell/schnelles-geld-am-ende-der-welt/player', - 'only_matching': True, - }, { - 'url': 'http://www.nowtv.de/rtl2/zuhause-im-glueck/jahr/2015/11/eine-erschuetternde-diagnose/player', - 'only_matching': True, - }] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - display_id = '%s/%s' % (mobj.group('show_id'), mobj.group('id')) - - info = self._download_json( - 'https://api.nowtv.de/v3/movies/%s?fields=%s' - % (display_id, ','.join(self._VIDEO_FIELDS)), display_id) - - return self._extract_video(info, display_id) - - -class NowTVListIE(NowTVBaseIE): - _VALID_URL = r'https?://(?:www\.)?nowtv\.(?:de|at|ch)/(?:rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P[^/]+)/list/(?P[^?/#&]+)$' - - _SHOW_FIELDS = ('title', ) - _SEASON_FIELDS = ('id', 'headline', 'seoheadline', ) - - _TESTS = [{ - 'url': 'http://www.nowtv.at/rtl/stern-tv/list/aktuell', - 'info_dict': { - 'id': '17006', - 'title': 'stern TV - Aktuell', - }, - 'playlist_count': 1, - }, { - 'url': 'http://www.nowtv.at/rtl/das-supertalent/list/free-staffel-8', - 'info_dict': { - 'id': '20716', - 'title': 'Das Supertalent - FREE Staffel 8', - }, - 'playlist_count': 14, - }] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - show_id = mobj.group('show_id') - season_id = mobj.group('id') - - fields = [] - fields.extend(self._SHOW_FIELDS) - fields.extend('formatTabs.%s' % field for field in self._SEASON_FIELDS) - fields.extend( - 'formatTabs.formatTabPages.container.movies.%s' % field - for field in self._VIDEO_FIELDS) - - list_info = self._download_json( - 'https://api.nowtv.de/v3/formats/seo?fields=%s&name=%s.php' - % (','.join(fields), show_id), - season_id) - - season = next( - season for season in list_info['formatTabs']['items'] - if season.get('seoheadline') == season_id) - - title = '%s - %s' % (list_info['title'], season['headline']) - - entries = [] - for container in season['formatTabPages']['items']: - for info in ((container.get('container') or {}).get('movies') or {}).get('items') or []: - entries.append(self._extract_video(info)) - - return self.playlist_result( - entries, compat_str(season.get('id') or season_id), title) diff --git a/youtube_dl/extractor/tvnow.py b/youtube_dl/extractor/tvnow.py new file mode 100644 index 000000000..e2169f2bc --- /dev/null +++ b/youtube_dl/extractor/tvnow.py @@ -0,0 +1,175 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + ExtractorError, + parse_iso8601, + parse_duration, + update_url_query, +) + + +class TVNowBaseIE(InfoExtractor): + _VIDEO_FIELDS = ( + 'id', 'title', 'free', 'geoblocked', 'articleLong', 'articleShort', + 'broadcastStartDate', 'isDrm', 'duration', 'manifest.dashclear', + 'format.defaultImage169Format', 'format.defaultImage169Logo') + + def _call_api(self, path, video_id, query): + return self._download_json( + 'https://api.tvnow.de/v3/' + path, + video_id, query=query) + + def _extract_video(self, info, display_id): + video_id = compat_str(info['id']) + title = info['title'] + + mpd_url = info['manifest']['dashclear'] + if not mpd_url: + if info.get('isDrm'): + raise ExtractorError( + 'Video %s is DRM protected' % video_id, expected=True) + if info.get('geoblocked'): + raise ExtractorError( + 'Video %s is not available from your location due to geo restriction' % video_id, + expected=True) + if not info.get('free', True): + raise ExtractorError( + 'Video %s is not available for free' % video_id, expected=True) + + mpd_url = update_url_query(mpd_url, {'filter': ''}) + formats = self._extract_mpd_formats(mpd_url, video_id, mpd_id='dash', fatal=False) + formats.extend(self._extract_ism_formats( + mpd_url.replace('dash.', 'hss.').replace('/.mpd', '/Manifest'), + video_id, ism_id='mss', fatal=False)) + formats.extend(self._extract_m3u8_formats( + mpd_url.replace('dash.', 'hls.').replace('/.mpd', '/.m3u8'), + video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) + self._sort_formats(formats) + + description = info.get('articleLong') or info.get('articleShort') + timestamp = parse_iso8601(info.get('broadcastStartDate'), ' ') + duration = parse_duration(info.get('duration')) + + f = info.get('format', {}) + thumbnail = f.get('defaultImage169Format') or f.get('defaultImage169Logo') + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'duration': duration, + 'formats': formats, + } + + +class TVNowIE(TVNowBaseIE): + _VALID_URL = r'https?://(?:www\.)?tvnow\.(?:de|at|ch)/(?:rtl(?:2|plus)?|nitro|superrtl|ntv|vox)/(?P[^/]+)/(?:(?:list/[^/]+|jahr/\d{4}/\d{1,2})/)?(?P[^/]+)/(?:player|preview)' + + _TESTS = [{ + # rtl + 'url': 'https://www.tvnow.de/rtl/alarm-fuer-cobra-11/freier-fall/player?return=/rtl', + 'info_dict': { + 'id': '385314', + 'display_id': 'alarm-fuer-cobra-11/freier-fall', + 'ext': 'mp4', + 'title': 'Freier Fall', + 'description': 'md5:8c2d8f727261adf7e0dc18366124ca02', + 'thumbnail': r're:^https?://.*\.jpg$', + 'timestamp': 1512677700, + 'upload_date': '20171207', + 'duration': 2862.0, + }, + }, { + # rtl2 + 'url': 'https://www.tvnow.de/rtl2/armes-deutschland/episode-0008/player', + 'only_matching': 'True', + }, { + # rtlnitro + 'url': 'https://www.tvnow.de/nitro/alarm-fuer-cobra-11-die-autobahnpolizei/auf-eigene-faust-pilot/player', + 'only_matching': 'True', + }, { + # superrtl + 'url': 'https://www.tvnow.de/superrtl/die-lustigsten-schlamassel-der-welt/u-a-ketchup-effekt/player', + 'only_matching': 'True', + }, { + # ntv + 'url': 'https://www.tvnow.de/ntv/startup-news/goetter-in-weiss/player', + 'only_matching': 'True', + }, { + # vox + 'url': 'https://www.tvnow.de/vox/auto-mobil/neues-vom-automobilmarkt-2017-11-19-17-00-00/player', + 'only_matching': 'True', + }, { + # rtlplus + 'url': 'https://www.tvnow.de/rtlplus/op-ruft-dr-bruckner/die-vernaehte-frau/player', + 'only_matching': 'True', + }] + + def _real_extract(self, url): + display_id = '%s/%s' % re.match(self._VALID_URL, url).groups() + + info = self._call_api( + 'movies/' + display_id, display_id, query={ + 'fields': ','.join(self._VIDEO_FIELDS), + }) + + return self._extract_video(info, display_id) + + +class TVNowListIE(TVNowBaseIE): + _VALID_URL = r'(?Phttps?://(?:www\.)?tvnow\.(?:de|at|ch)/(?:rtl(?:2|plus)?|nitro|superrtl|ntv|vox)/(?P[^/]+)/)list/(?P[^?/#&]+)$' + + _SHOW_FIELDS = ('title', ) + _SEASON_FIELDS = ('id', 'headline', 'seoheadline', ) + _VIDEO_FIELDS = ('id', 'headline', 'seoUrl', ) + + _TESTS = [{ + 'url': 'https://www.tvnow.de/rtl/30-minuten-deutschland/list/aktuell', + 'info_dict': { + 'id': '28296', + 'title': '30 Minuten Deutschland - Aktuell', + }, + 'playlist_mincount': 1, + }] + + def _real_extract(self, url): + base_url, show_id, season_id = re.match(self._VALID_URL, url).groups() + + fields = [] + fields.extend(self._SHOW_FIELDS) + fields.extend('formatTabs.%s' % field for field in self._SEASON_FIELDS) + fields.extend( + 'formatTabs.formatTabPages.container.movies.%s' % field + for field in self._VIDEO_FIELDS) + + list_info = self._call_api( + 'formats/seo', season_id, query={ + 'fields': ','.join(fields), + 'name': show_id + '.php' + }) + + season = next( + season for season in list_info['formatTabs']['items'] + if season.get('seoheadline') == season_id) + + title = '%s - %s' % (list_info['title'], season['headline']) + + entries = [] + for container in season['formatTabPages']['items']: + for info in ((container.get('container') or {}).get('movies') or {}).get('items') or []: + seo_url = info.get('seoUrl') + if not seo_url: + continue + entries.append(self.url_result( + base_url + seo_url + '/player', 'TVNow', info.get('id'))) + + return self.playlist_result( + entries, compat_str(season.get('id') or season_id), title) From cb0c2310fbf232e09ae41013be3400034171d6d2 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Tue, 12 Dec 2017 10:33:03 +0100 Subject: [PATCH 28/31] [discovery] fix free videos extraction(#14157)(#14954) --- youtube_dl/extractor/discovery.py | 122 +++++++++++++--------------- youtube_dl/extractor/discoverygo.py | 72 ++++++++-------- 2 files changed, 94 insertions(+), 100 deletions(-) diff --git a/youtube_dl/extractor/discovery.py b/youtube_dl/extractor/discovery.py index 55853f76f..f9cec1d23 100644 --- a/youtube_dl/extractor/discovery.py +++ b/youtube_dl/extractor/discovery.py @@ -1,14 +1,18 @@ from __future__ import unicode_literals -from .common import InfoExtractor +import random +import re +import string + +from .discoverygo import DiscoveryGoBaseIE from ..utils import ( - parse_duration, - parse_iso8601, + ExtractorError, + update_url_query, ) -from ..compat import compat_str +from ..compat import compat_HTTPError -class DiscoveryIE(InfoExtractor): +class DiscoveryIE(DiscoveryGoBaseIE): _VALID_URL = r'''(?x)https?://(?:www\.)?(?: discovery| investigationdiscovery| @@ -19,79 +23,65 @@ class DiscoveryIE(InfoExtractor): sciencechannel| tlc| velocity - )\.com/(?:[^/]+/)*(?P[^./?#]+)''' + )\.com(?P/tv-shows/[^/]+/(?:video|full-episode)s/(?P[^./?#]+))''' _TESTS = [{ - 'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm', + 'url': 'https://www.discovery.com/tv-shows/cash-cab/videos/dave-foley', 'info_dict': { - 'id': '20769', + 'id': '5a2d9b4d6b66d17a5026e1fd', 'ext': 'mp4', - 'title': 'Mission Impossible Outtakes', - 'description': ('Watch Jamie Hyneman and Adam Savage practice being' - ' each other -- to the point of confusing Jamie\'s dog -- and ' - 'don\'t miss Adam moon-walking as Jamie ... behind Jamie\'s' - ' back.'), - 'duration': 156, - 'timestamp': 1302032462, - 'upload_date': '20110405', - 'uploader_id': '103207', + 'title': 'Dave Foley', + 'description': 'md5:4b39bcafccf9167ca42810eb5f28b01f', + 'duration': 608, }, 'params': { 'skip_download': True, # requires ffmpeg } }, { - 'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mythbusters-the-simpsons', - 'info_dict': { - 'id': 'mythbusters-the-simpsons', - 'title': 'MythBusters: The Simpsons', - }, - 'playlist_mincount': 10, - }, { - 'url': 'http://www.animalplanet.com/longfin-eels-maneaters/', - 'info_dict': { - 'id': '78326', - 'ext': 'mp4', - 'title': 'Longfin Eels: Maneaters?', - 'description': 'Jeremy Wade tests whether or not New Zealand\'s longfin eels are man-eaters by covering himself in fish guts and getting in the water with them.', - 'upload_date': '20140725', - 'timestamp': 1406246400, - 'duration': 116, - 'uploader_id': '103207', - }, - 'params': { - 'skip_download': True, # requires ffmpeg - } + 'url': 'https://www.investigationdiscovery.com/tv-shows/final-vision/full-episodes/final-vision', + 'only_matching': True, }] + _GEO_COUNTRIES = ['US'] + _GEO_BYPASS = False def _real_extract(self, url): - display_id = self._match_id(url) - info = self._download_json(url + '?flat=1', display_id) + path, display_id = re.match(self._VALID_URL, url).groups() + webpage = self._download_webpage(url, display_id) - video_title = info.get('playlist_title') or info.get('video_title') + react_data = self._parse_json(self._search_regex( + r'window\.__reactTransmitPacket\s*=\s*({.+?});', + webpage, 'react data'), display_id) + content_blocks = react_data['layout'][path]['contentBlocks'] + video = next(cb for cb in content_blocks if cb.get('type') == 'video')['content']['items'][0] + video_id = video['id'] - entries = [] + access_token = self._download_json( + 'https://www.discovery.com/anonymous', display_id, query={ + 'authLink': update_url_query( + 'https://login.discovery.com/v1/oauth2/authorize', { + 'client_id': react_data['application']['apiClientId'], + 'redirect_uri': 'https://fusion.ddmcdn.com/app/mercury-sdk/180/redirectHandler.html', + 'response_type': 'anonymous', + 'state': 'nonce,' + ''.join([random.choice(string.ascii_letters) for _ in range(32)]), + }) + })['access_token'] - for idx, video_info in enumerate(info['playlist']): - subtitles = {} - caption_url = video_info.get('captionsUrl') - if caption_url: - subtitles = { - 'en': [{ - 'url': caption_url, - }] - } + try: + stream = self._download_json( + 'https://api.discovery.com/v1/streaming/video/' + video_id, + display_id, headers={ + 'Authorization': 'Bearer ' + access_token, + }) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + e_description = self._parse_json( + e.cause.read().decode(), display_id)['description'] + if 'resource not available for country' in e_description: + self.raise_geo_restricted(countries=self._GEO_COUNTRIES) + if 'Authorized Networks' in e_description: + raise ExtractorError( + 'This video is only available via cable service provider subscription that' + ' is not currently supported. You may want to use --cookies.', expected=True) + raise ExtractorError(e_description) + raise - entries.append({ - '_type': 'url_transparent', - 'url': 'http://players.brightcove.net/103207/default_default/index.html?videoId=ref:%s' % video_info['referenceId'], - 'id': compat_str(video_info['id']), - 'title': video_info['title'], - 'description': video_info.get('description'), - 'duration': parse_duration(video_info.get('video_length')), - 'webpage_url': video_info.get('href') or video_info.get('url'), - 'thumbnail': video_info.get('thumbnailURL'), - 'alt_title': video_info.get('secondary_title'), - 'timestamp': parse_iso8601(video_info.get('publishedDate')), - 'subtitles': subtitles, - }) - - return self.playlist_result(entries, display_id, video_title) + return self._extract_video_info(video, stream, display_id) diff --git a/youtube_dl/extractor/discoverygo.py b/youtube_dl/extractor/discoverygo.py index 7cd5d4291..99376454b 100644 --- a/youtube_dl/extractor/discoverygo.py +++ b/youtube_dl/extractor/discoverygo.py @@ -27,42 +27,9 @@ class DiscoveryGoBaseIE(InfoExtractor): velocitychannel )go\.com/%s(?P[^/?#&]+)''' - -class DiscoveryGoIE(DiscoveryGoBaseIE): - _VALID_URL = DiscoveryGoBaseIE._VALID_URL_TEMPLATE % r'(?:[^/]+/)+' - _GEO_COUNTRIES = ['US'] - _TEST = { - 'url': 'https://www.discoverygo.com/bering-sea-gold/reaper-madness/', - 'info_dict': { - 'id': '58c167d86b66d12f2addeb01', - 'ext': 'mp4', - 'title': 'Reaper Madness', - 'description': 'md5:09f2c625c99afb8946ed4fb7865f6e78', - 'duration': 2519, - 'series': 'Bering Sea Gold', - 'season_number': 8, - 'episode_number': 6, - 'age_limit': 14, - }, - } - - def _real_extract(self, url): - display_id = self._match_id(url) - - webpage = self._download_webpage(url, display_id) - - container = extract_attributes( - self._search_regex( - r'(]+class=["\']video-player-container[^>]+>)', - webpage, 'video container')) - - video = self._parse_json( - container.get('data-video') or container.get('data-json'), - display_id) - + def _extract_video_info(self, video, stream, display_id): title = video['name'] - stream = video.get('stream') if not stream: if video.get('authenticated') is True: raise ExtractorError( @@ -124,6 +91,43 @@ class DiscoveryGoIE(DiscoveryGoBaseIE): } +class DiscoveryGoIE(DiscoveryGoBaseIE): + _VALID_URL = DiscoveryGoBaseIE._VALID_URL_TEMPLATE % r'(?:[^/]+/)+' + _GEO_COUNTRIES = ['US'] + _TEST = { + 'url': 'https://www.discoverygo.com/bering-sea-gold/reaper-madness/', + 'info_dict': { + 'id': '58c167d86b66d12f2addeb01', + 'ext': 'mp4', + 'title': 'Reaper Madness', + 'description': 'md5:09f2c625c99afb8946ed4fb7865f6e78', + 'duration': 2519, + 'series': 'Bering Sea Gold', + 'season_number': 8, + 'episode_number': 6, + 'age_limit': 14, + }, + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + container = extract_attributes( + self._search_regex( + r'(]+class=["\']video-player-container[^>]+>)', + webpage, 'video container')) + + video = self._parse_json( + container.get('data-video') or container.get('data-json'), + display_id) + + stream = video.get('stream') + + return self._extract_video_info(video, stream, display_id) + + class DiscoveryGoPlaylistIE(DiscoveryGoBaseIE): _VALID_URL = DiscoveryGoBaseIE._VALID_URL_TEMPLATE % '' _TEST = { From e6b8803d599df4de3c115e4de4ef192a1e10c749 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Tue, 12 Dec 2017 11:11:44 +0100 Subject: [PATCH 29/31] [toutv] add support special video urls(closes #14179) --- youtube_dl/extractor/toutv.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/toutv.py b/youtube_dl/extractor/toutv.py index 17c0adc15..2e7876cc5 100644 --- a/youtube_dl/extractor/toutv.py +++ b/youtube_dl/extractor/toutv.py @@ -16,7 +16,7 @@ from ..utils import ( class TouTvIE(InfoExtractor): _NETRC_MACHINE = 'toutv' IE_NAME = 'tou.tv' - _VALID_URL = r'https?://ici\.tou\.tv/(?P[a-zA-Z0-9_-]+(?:/S[0-9]+E[0-9]+)?)' + _VALID_URL = r'https?://ici\.tou\.tv/(?P[a-zA-Z0-9_-]+(?:/S[0-9]+[EC][0-9]+)?)' _access_token = None _claims = None @@ -37,6 +37,9 @@ class TouTvIE(InfoExtractor): }, { 'url': 'http://ici.tou.tv/hackers', 'only_matching': True, + }, { + 'url': 'https://ici.tou.tv/l-age-adulte/S01C501', + 'only_matching': True, }] def _real_initialize(self): From 6b2d8c91823c8f4c5dcda42cf174ab5468c44661 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Tue, 12 Dec 2017 18:04:05 +0100 Subject: [PATCH 30/31] [bbc.co.uk] fix extraction for 320k m3u8 streams broken since 197224b7a4e37a6581bf1a0da18d0f67ea61a476 --- youtube_dl/extractor/bbc.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index 5525f7c9b..8b20c03d6 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -386,7 +386,7 @@ class BBCCoUkIE(InfoExtractor): m3u8_id=format_id, fatal=False)) if re.search(self._USP_RE, href): usp_formats = self._extract_m3u8_formats( - re.sub(self._USP_RE, r'/\1\.ism/\1\.m3u8', href), + re.sub(self._USP_RE, r'/\1.ism/\1.m3u8', href), programme_id, ext='mp4', entry_protocol='m3u8_native', m3u8_id=format_id, fatal=False) for f in usp_formats: From 15960255fe3caaae58132116d772d1c1bcf415fa Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Tue, 12 Dec 2017 18:16:45 +0100 Subject: [PATCH 31/31] [tbs] fix typo --- youtube_dl/extractor/tbs.py | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/tbs.py b/youtube_dl/extractor/tbs.py index 460bc5d74..eab22c38f 100644 --- a/youtube_dl/extractor/tbs.py +++ b/youtube_dl/extractor/tbs.py @@ -36,8 +36,7 @@ class TBSIE(TurnerBaseIE): }] def _real_extract(self, url): - domain, display_id = re.match(self._VALID_URL, url).groups() - site = domain[:3] + site, display_id = re.match(self._VALID_URL, url).groups() webpage = self._download_webpage(url, display_id) video_data = self._parse_json(self._search_regex( r']+?data-drupal-selector="drupal-settings-json"[^>]*?>({.+?})', @@ -62,7 +61,7 @@ class TBSIE(TurnerBaseIE): 'http://www.%s.com/service/token_spe' % site, m3u8_url, media_id, { 'url': url, - 'site_name': site.upper(), + 'site_name': site[:3].upper(), 'auth_required': video_data.get('authRequired') == '1', }) formats.extend(self._extract_m3u8_formats(