From a820dc722e93b40450b8280a23110c4960800123 Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sat, 16 Jan 2021 18:12:05 +0100 Subject: [PATCH] Update to ytdl-2021.01.24.1 --- README.md | 2 +- test/test_YoutubeDL.py | 15 +- youtube_dlc/YoutubeDL.py | 15 +- youtube_dlc/__init__.py | 1 + youtube_dlc/extractor/aenetworks.py | 2 +- youtube_dlc/extractor/aljazeera.py | 41 +++- youtube_dlc/extractor/americastestkitchen.py | 97 ++++++++- youtube_dlc/extractor/aol.py | 12 +- youtube_dlc/extractor/ard.py | 36 ++-- youtube_dlc/extractor/comedycentral.py | 141 +++---------- youtube_dlc/extractor/extractors.py | 22 ++- youtube_dlc/extractor/franceculture.py | 20 +- youtube_dlc/extractor/lbry.py | 9 +- youtube_dlc/extractor/minds.py | 196 +++++++++++++++++++ youtube_dlc/extractor/mtv.py | 23 ++- youtube_dlc/extractor/ninegag.py | 189 ++++++++++-------- youtube_dlc/extractor/njpwworld.py | 54 ++--- youtube_dlc/extractor/spike.py | 25 +-- youtube_dlc/extractor/spotify.py | 156 +++++++++++++++ youtube_dlc/extractor/trovo.py | 193 ++++++++++++++++++ youtube_dlc/extractor/wat.py | 64 ++---- youtube_dlc/extractor/yahoo.py | 80 ++++---- youtube_dlc/options.py | 6 +- 23 files changed, 987 insertions(+), 412 deletions(-) create mode 100644 youtube_dlc/extractor/minds.py create mode 100644 youtube_dlc/extractor/spotify.py create mode 100644 youtube_dlc/extractor/trovo.py diff --git a/README.md b/README.md index 59999245bf..59886a2666 100644 --- a/README.md +++ b/README.md @@ -814,7 +814,7 @@ Available for the media that is a track or a part of a music album: - `disc_number` (numeric): Number of the disc or other physical medium the track belongs to - `release_year` (numeric): Year (YYYY) when the album was released -Each aforementioned sequence when referenced in an output template will be replaced by the actual value corresponding to the sequence name. Note that some of the sequences are not guaranteed to be present since they depend on the metadata obtained by a particular extractor. Such sequences will be replaced with `NA`. +Each aforementioned sequence when referenced in an output template will be replaced by the actual value corresponding to the sequence name. Note that some of the sequences are not guaranteed to be present since they depend on the metadata obtained by a particular extractor. Such sequences will be replaced with placeholder value provided with `--output-na-placeholder` (`NA` by default). For example for `-o %(title)s-%(id)s.%(ext)s` and an mp4 video with title `youtube-dlc test video` and id `BaW_jenozKcj`, this will result in a `youtube-dlc test video-BaW_jenozKcj.mp4` file created in the current directory. diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py index bacab60a4f..43a5dcd749 100644 --- a/test/test_YoutubeDL.py +++ b/test/test_YoutubeDL.py @@ -637,13 +637,20 @@ class TestYoutubeDL(unittest.TestCase): 'title2': '%PATH%', } - def fname(templ): - ydl = YoutubeDL({'outtmpl': templ}) + def fname(templ, na_placeholder='NA'): + params = {'outtmpl': templ} + if na_placeholder != 'NA': + params['outtmpl_na_placeholder'] = na_placeholder + ydl = YoutubeDL(params) return ydl.prepare_filename(info) self.assertEqual(fname('%(id)s.%(ext)s'), '1234.mp4') self.assertEqual(fname('%(id)s-%(width)s.%(ext)s'), '1234-NA.mp4') - # Replace missing fields with 'NA' - self.assertEqual(fname('%(uploader_date)s-%(id)s.%(ext)s'), 'NA-1234.mp4') + NA_TEST_OUTTMPL = '%(uploader_date)s-%(width)d-%(id)s.%(ext)s' + # Replace missing fields with 'NA' by default + self.assertEqual(fname(NA_TEST_OUTTMPL), 'NA-NA-1234.mp4') + # Or by provided placeholder + self.assertEqual(fname(NA_TEST_OUTTMPL, na_placeholder='none'), 'none-none-1234.mp4') + self.assertEqual(fname(NA_TEST_OUTTMPL, na_placeholder=''), '--1234.mp4') self.assertEqual(fname('%(height)d.%(ext)s'), '1080.mp4') self.assertEqual(fname('%(height)6d.%(ext)s'), ' 1080.mp4') self.assertEqual(fname('%(height)-6d.%(ext)s'), '1080 .mp4') diff --git a/youtube_dlc/YoutubeDL.py b/youtube_dlc/YoutubeDL.py index 02cc976259..ce990507ca 100644 --- a/youtube_dlc/YoutubeDL.py +++ b/youtube_dlc/YoutubeDL.py @@ -181,9 +181,12 @@ class YoutubeDL(object): allow_multiple_video_streams: Allow multiple video streams to be merged into a single file allow_multiple_audio_streams: Allow multiple audio streams to be merged into a single file outtmpl: Template for output names. - restrictfilenames: Do not allow "&" and spaces in file names. - trim_file_name: Limit length of filename (extension excluded). - ignoreerrors: Do not stop on download errors. (Default True when running youtube-dlc, but False when directly accessing YoutubeDL class) + outtmpl_na_placeholder: Placeholder for unavailable meta fields. + restrictfilenames: Do not allow "&" and spaces in file names + trim_file_name: Limit length of filename (extension excluded) + ignoreerrors: Do not stop on download errors + (Default True when running youtube-dlc, + but False when directly accessing YoutubeDL class) force_generic_extractor: Force downloader to use the generic extractor overwrites: Overwrite all video and metadata files if True, overwrite only non-video files if None @@ -741,7 +744,7 @@ class YoutubeDL(object): template_dict = dict((k, v if isinstance(v, compat_numeric_types) else sanitize(k, v)) for k, v in template_dict.items() if v is not None and not isinstance(v, (list, tuple, dict))) - template_dict = collections.defaultdict(lambda: 'NA', template_dict) + template_dict = collections.defaultdict(lambda: self.params.get('outtmpl_na_placeholder', 'NA'), template_dict) outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL) @@ -761,8 +764,8 @@ class YoutubeDL(object): # Missing numeric fields used together with integer presentation types # in format specification will break the argument substitution since - # string 'NA' is returned for missing fields. We will patch output - # template for missing fields to meet string presentation type. + # string NA placeholder is returned for missing fields. We will patch + # output template for missing fields to meet string presentation type. for numeric_field in self._NUMERIC_FIELDS: if numeric_field not in template_dict: # As of [1] format syntax is: diff --git a/youtube_dlc/__init__.py b/youtube_dlc/__init__.py index ee61203959..e2db662665 100644 --- a/youtube_dlc/__init__.py +++ b/youtube_dlc/__init__.py @@ -373,6 +373,7 @@ def _real_main(argv=None): 'listformats': opts.listformats, 'listformats_table': opts.listformats_table, 'outtmpl': outtmpl, + 'outtmpl_na_placeholder': opts.outtmpl_na_placeholder, 'paths': opts.paths, 'autonumber_size': opts.autonumber_size, 'autonumber_start': opts.autonumber_start, diff --git a/youtube_dlc/extractor/aenetworks.py b/youtube_dlc/extractor/aenetworks.py index 8e49631317..a5d88ebbea 100644 --- a/youtube_dlc/extractor/aenetworks.py +++ b/youtube_dlc/extractor/aenetworks.py @@ -256,7 +256,7 @@ class AENetworksShowIE(AENetworksListBaseIE): 'title': 'Ancient Aliens', 'description': 'md5:3f6d74daf2672ff3ae29ed732e37ea7f', }, - 'playlist_mincount': 168, + 'playlist_mincount': 150, }] _RESOURCE = 'series' _ITEMS_KEY = 'episodes' diff --git a/youtube_dlc/extractor/aljazeera.py b/youtube_dlc/extractor/aljazeera.py index c68be31340..c4f915a3c1 100644 --- a/youtube_dlc/extractor/aljazeera.py +++ b/youtube_dlc/extractor/aljazeera.py @@ -1,13 +1,16 @@ from __future__ import unicode_literals +import json +import re + from .common import InfoExtractor class AlJazeeraIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?aljazeera\.com/(?:programmes|video)/.*?/(?P[^/]+)\.html' + _VALID_URL = r'https?://(?:www\.)?aljazeera\.com/(?Pprogram/[^/]+|(?:feature|video)s)/\d{4}/\d{1,2}/\d{1,2}/(?P[^/?&#]+)' _TESTS = [{ - 'url': 'http://www.aljazeera.com/programmes/the-slum/2014/08/deliverance-201482883754237240.html', + 'url': 'https://www.aljazeera.com/program/episode/2014/9/19/deliverance', 'info_dict': { 'id': '3792260579001', 'ext': 'mp4', @@ -20,14 +23,34 @@ class AlJazeeraIE(InfoExtractor): 'add_ie': ['BrightcoveNew'], 'skip': 'Not accessible from Travis CI server', }, { - 'url': 'http://www.aljazeera.com/video/news/2017/05/sierra-leone-709-carat-diamond-auctioned-170511100111930.html', + 'url': 'https://www.aljazeera.com/videos/2017/5/11/sierra-leone-709-carat-diamond-to-be-auctioned-off', + 'only_matching': True, + }, { + 'url': 'https://www.aljazeera.com/features/2017/8/21/transforming-pakistans-buses-into-art', 'only_matching': True, }] - BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/665003303001/default_default/index.html?videoId=%s' + BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_default/index.html?videoId=%s' def _real_extract(self, url): - program_name = self._match_id(url) - webpage = self._download_webpage(url, program_name) - brightcove_id = self._search_regex( - r'RenderPagesVideo\(\'(.+?)\'', webpage, 'brightcove id') - return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id) + post_type, name = re.match(self._VALID_URL, url).groups() + post_type = { + 'features': 'post', + 'program': 'episode', + 'videos': 'video', + }[post_type.split('/')[0]] + video = self._download_json( + 'https://www.aljazeera.com/graphql', name, query={ + 'operationName': 'SingleArticleQuery', + 'variables': json.dumps({ + 'name': name, + 'postType': post_type, + }), + }, headers={ + 'wp-site': 'aje', + })['data']['article']['video'] + video_id = video['id'] + account_id = video.get('accountId') or '665003303001' + player_id = video.get('playerId') or 'BkeSH5BDb' + return self.url_result( + self.BRIGHTCOVE_URL_TEMPLATE % (account_id, player_id, video_id), + 'BrightcoveNew', video_id) diff --git a/youtube_dlc/extractor/americastestkitchen.py b/youtube_dlc/extractor/americastestkitchen.py index e20f00fc3e..be960c0f93 100644 --- a/youtube_dlc/extractor/americastestkitchen.py +++ b/youtube_dlc/extractor/americastestkitchen.py @@ -1,13 +1,16 @@ # coding: utf-8 from __future__ import unicode_literals +import json import re from .common import InfoExtractor from ..utils import ( clean_html, + int_or_none, try_get, unified_strdate, + unified_timestamp, ) @@ -22,8 +25,8 @@ class AmericasTestKitchenIE(InfoExtractor): 'ext': 'mp4', 'description': 'md5:64e606bfee910627efc4b5f050de92b3', 'thumbnail': r're:^https?://', - 'timestamp': 1523664000, - 'upload_date': '20180414', + 'timestamp': 1523318400, + 'upload_date': '20180410', 'release_date': '20180410', 'series': "America's Test Kitchen", 'season_number': 18, @@ -33,6 +36,27 @@ class AmericasTestKitchenIE(InfoExtractor): 'params': { 'skip_download': True, }, + }, { + # Metadata parsing behaves differently for newer episodes (705) as opposed to older episodes (582 above) + 'url': 'https://www.americastestkitchen.com/episode/705-simple-chicken-dinner', + 'md5': '06451608c57651e985a498e69cec17e5', + 'info_dict': { + 'id': '5fbe8c61bda2010001c6763b', + 'title': 'Simple Chicken Dinner', + 'ext': 'mp4', + 'description': 'md5:eb68737cc2fd4c26ca7db30139d109e7', + 'thumbnail': r're:^https?://', + 'timestamp': 1610755200, + 'upload_date': '20210116', + 'release_date': '20210116', + 'series': "America's Test Kitchen", + 'season_number': 21, + 'episode': 'Simple Chicken Dinner', + 'episode_number': 3, + }, + 'params': { + 'skip_download': True, + }, }, { 'url': 'https://www.americastestkitchen.com/videos/3420-pan-seared-salmon', 'only_matching': True, @@ -60,7 +84,76 @@ class AmericasTestKitchenIE(InfoExtractor): 'url': 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % video['zypeId'], 'ie_key': 'Zype', 'description': clean_html(video.get('description')), + 'timestamp': unified_timestamp(video.get('publishDate')), 'release_date': unified_strdate(video.get('publishDate')), + 'episode_number': int_or_none(episode.get('number')), + 'season_number': int_or_none(episode.get('season')), 'series': try_get(episode, lambda x: x['show']['title']), 'episode': episode.get('title'), } + + +class AmericasTestKitchenSeasonIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?(?Pamericastestkitchen|cookscountry)\.com/episodes/browse/season_(?P\d+)' + _TESTS = [{ + # ATK Season + 'url': 'https://www.americastestkitchen.com/episodes/browse/season_1', + 'info_dict': { + 'id': 'season_1', + 'title': 'Season 1', + }, + 'playlist_count': 13, + }, { + # Cooks Country Season + 'url': 'https://www.cookscountry.com/episodes/browse/season_12', + 'info_dict': { + 'id': 'season_12', + 'title': 'Season 12', + }, + 'playlist_count': 13, + }] + + def _real_extract(self, url): + show_name, season_number = re.match(self._VALID_URL, url).groups() + season_number = int(season_number) + + slug = 'atk' if show_name == 'americastestkitchen' else 'cco' + + season = 'Season %d' % season_number + + season_search = self._download_json( + 'https://y1fnzxui30-dsn.algolia.net/1/indexes/everest_search_%s_season_desc_production' % slug, + season, headers={ + 'Origin': 'https://www.%s.com' % show_name, + 'X-Algolia-API-Key': '8d504d0099ed27c1b73708d22871d805', + 'X-Algolia-Application-Id': 'Y1FNZXUI30', + }, query={ + 'facetFilters': json.dumps([ + 'search_season_list:' + season, + 'search_document_klass:episode', + 'search_show_slug:' + slug, + ]), + 'attributesToRetrieve': 'description,search_%s_episode_number,search_document_date,search_url,title' % slug, + 'attributesToHighlight': '', + 'hitsPerPage': 1000, + }) + + def entries(): + for episode in (season_search.get('hits') or []): + search_url = episode.get('search_url') + if not search_url: + continue + yield { + '_type': 'url', + 'url': 'https://www.%s.com%s' % (show_name, search_url), + 'id': try_get(episode, lambda e: e['objectID'].split('_')[-1]), + 'title': episode.get('title'), + 'description': episode.get('description'), + 'timestamp': unified_timestamp(episode.get('search_document_date')), + 'season_number': season_number, + 'episode_number': int_or_none(episode.get('search_%s_episode_number' % slug)), + 'ie_key': AmericasTestKitchenIE.ie_key(), + } + + return self.playlist_result( + entries(), 'season_%d' % season_number, season) diff --git a/youtube_dlc/extractor/aol.py b/youtube_dlc/extractor/aol.py index e87994a6aa..f6ecb8438f 100644 --- a/youtube_dlc/extractor/aol.py +++ b/youtube_dlc/extractor/aol.py @@ -3,7 +3,7 @@ from __future__ import unicode_literals import re -from .common import InfoExtractor +from .yahoo import YahooIE from ..compat import ( compat_parse_qs, compat_urllib_parse_urlparse, @@ -15,9 +15,9 @@ from ..utils import ( ) -class AolIE(InfoExtractor): +class AolIE(YahooIE): IE_NAME = 'aol.com' - _VALID_URL = r'(?:aol-video:|https?://(?:www\.)?aol\.(?:com|ca|co\.uk|de|jp)/video/(?:[^/]+/)*)(?P[0-9a-f]+)' + _VALID_URL = r'(?:aol-video:|https?://(?:www\.)?aol\.(?:com|ca|co\.uk|de|jp)/video/(?:[^/]+/)*)(?P\d{9}|[0-9a-f]{24}|[0-9a-f]{8}-(?:[0-9a-f]{4}-){3}[0-9a-f]{12})' _TESTS = [{ # video with 5min ID @@ -76,10 +76,16 @@ class AolIE(InfoExtractor): }, { 'url': 'https://www.aol.jp/video/playlist/5a28e936a1334d000137da0c/5a28f3151e642219fde19831/', 'only_matching': True, + }, { + # Yahoo video + 'url': 'https://www.aol.com/video/play/991e6700-ac02-11ea-99ff-357400036f61/24bbc846-3e30-3c46-915e-fe8ccd7fcc46/', + 'only_matching': True, }] def _real_extract(self, url): video_id = self._match_id(url) + if '-' in video_id: + return self._extract_yahoo_video(video_id, 'us') response = self._download_json( 'https://feedapi.b2c.on.aol.com/v1.0/app/videos/aolon/%s/details' % video_id, diff --git a/youtube_dlc/extractor/ard.py b/youtube_dlc/extractor/ard.py index 6f1e477a90..7337931452 100644 --- a/youtube_dlc/extractor/ard.py +++ b/youtube_dlc/extractor/ard.py @@ -226,13 +226,13 @@ class ARDMediathekIE(ARDMediathekBaseIE): if doc.tag == 'rss': return GenericIE()._extract_rss(url, video_id, doc) - title = self._html_search_regex( + title = self._og_search_title(webpage, default=None) or self._html_search_regex( [r'(.*?)', r'', r'

(.*?)

', r']*>(.*?)'], webpage, 'title') - description = self._html_search_meta( + description = self._og_search_description(webpage, default=None) or self._html_search_meta( 'dcterms.abstract', webpage, 'description', default=None) if description is None: description = self._html_search_meta( @@ -289,18 +289,18 @@ class ARDMediathekIE(ARDMediathekBaseIE): class ARDIE(InfoExtractor): - _VALID_URL = r'(?Phttps?://(www\.)?daserste\.de/[^?#]+/videos(?:extern)?/(?P[^/?#]+)-(?P[0-9]+))\.html' + _VALID_URL = r'(?Phttps?://(?:www\.)?daserste\.de/[^?#]+/videos(?:extern)?/(?P[^/?#]+)-(?:video-?)?(?P[0-9]+))\.html' _TESTS = [{ - # available till 14.02.2019 - 'url': 'http://www.daserste.de/information/talk/maischberger/videos/das-groko-drama-zerlegen-sich-die-volksparteien-video-102.html', - 'md5': '8e4ec85f31be7c7fc08a26cdbc5a1f49', + # available till 7.01.2022 + 'url': 'https://www.daserste.de/information/talk/maischberger/videos/maischberger-die-woche-video100.html', + 'md5': '867d8aa39eeaf6d76407c5ad1bb0d4c1', 'info_dict': { - 'display_id': 'das-groko-drama-zerlegen-sich-die-volksparteien-video', - 'id': '102', + 'display_id': 'maischberger-die-woche', + 'id': '100', 'ext': 'mp4', - 'duration': 4435.0, - 'title': 'Das GroKo-Drama: Zerlegen sich die Volksparteien?', - 'upload_date': '20180214', + 'duration': 3687.0, + 'title': 'maischberger. die woche vom 7. Januar 2021', + 'upload_date': '20210107', 'thumbnail': r're:^https?://.*\.jpg$', }, }, { @@ -355,17 +355,17 @@ class ARDIE(InfoExtractor): class ARDBetaMediathekIE(ARDMediathekBaseIE): _VALID_URL = r'https://(?:(?:beta|www)\.)?ardmediathek\.de/(?P[^/]+)/(?Pplayer|live|video|sendung|sammlung)/(?P(?:[^/]+/)*)(?P[a-zA-Z0-9]+)' _TESTS = [{ - 'url': 'https://ardmediathek.de/ard/video/die-robuste-roswita/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE', - 'md5': 'dfdc87d2e7e09d073d5a80770a9ce88f', + 'url': 'https://www.ardmediathek.de/mdr/video/die-robuste-roswita/Y3JpZDovL21kci5kZS9iZWl0cmFnL2Ntcy84MWMxN2MzZC0wMjkxLTRmMzUtODk4ZS0wYzhlOWQxODE2NGI/', + 'md5': 'a1dc75a39c61601b980648f7c9f9f71d', 'info_dict': { 'display_id': 'die-robuste-roswita', - 'id': '70153354', + 'id': '78566716', 'title': 'Die robuste Roswita', - 'description': r're:^Der Mord.*trüber ist als die Ilm.', + 'description': r're:^Der Mord.*totgeglaubte Ehefrau Roswita', 'duration': 5316, - 'thumbnail': 'https://img.ardmediathek.de/standard/00/70/15/33/90/-1852531467/16x9/960?mandant=ard', - 'timestamp': 1577047500, - 'upload_date': '20191222', + 'thumbnail': 'https://img.ardmediathek.de/standard/00/78/56/67/84/575672121/16x9/960?mandant=ard', + 'timestamp': 1596658200, + 'upload_date': '20200805', 'ext': 'mp4', }, }, { diff --git a/youtube_dlc/extractor/comedycentral.py b/youtube_dlc/extractor/comedycentral.py index f54c4adeb9..1bfa912be4 100644 --- a/youtube_dlc/extractor/comedycentral.py +++ b/youtube_dlc/extractor/comedycentral.py @@ -1,142 +1,51 @@ from __future__ import unicode_literals from .mtv import MTVServicesInfoExtractor -from .common import InfoExtractor class ComedyCentralIE(MTVServicesInfoExtractor): - _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/ - (video-clips|episodes|cc-studios|video-collections|shows(?=/[^/]+/(?!full-episodes))) - /(?P.*)''' + _VALID_URL = r'https?://(?:www\.)?cc\.com/(?:episodes|video(?:-clips)?)/(?P<id>[0-9a-z]{6})' _FEED_URL = 'http://comedycentral.com/feeds/mrss/' _TESTS = [{ - 'url': 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother', - 'md5': 'c4f48e9eda1b16dd10add0744344b6d8', + 'url': 'http://www.cc.com/video-clips/5ke9v2/the-daily-show-with-trevor-noah-doc-rivers-and-steve-ballmer---the-nba-player-strike', + 'md5': 'b8acb347177c680ff18a292aa2166f80', 'info_dict': { - 'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354', + 'id': '89ccc86e-1b02-4f83-b0c9-1d9592ecd025', 'ext': 'mp4', - 'title': 'CC:Stand-Up|August 18, 2013|1|0101|Uncensored - Too Good of a Mother', - 'description': 'After a certain point, breastfeeding becomes c**kblocking.', - 'timestamp': 1376798400, - 'upload_date': '20130818', + 'title': 'The Daily Show with Trevor Noah|August 28, 2020|25|25149|Doc Rivers and Steve Ballmer - The NBA Player Strike', + 'description': 'md5:5334307c433892b85f4f5e5ac9ef7498', + 'timestamp': 1598670000, + 'upload_date': '20200829', }, }, { - 'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/interviews/6yx39d/exclusive-rand-paul-extended-interview', + 'url': 'http://www.cc.com/episodes/pnzzci/drawn-together--american-idol--parody-clip-show-season-3-ep-314', 'only_matching': True, - }] - - -class ComedyCentralFullEpisodesIE(MTVServicesInfoExtractor): - _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/ - (?:full-episodes|shows(?=/[^/]+/full-episodes)) - /(?P<id>[^?]+)''' - _FEED_URL = 'http://comedycentral.com/feeds/mrss/' - - _TESTS = [{ - 'url': 'http://www.cc.com/full-episodes/pv391a/the-daily-show-with-trevor-noah-november-28--2016---ryan-speedo-green-season-22-ep-22028', - 'info_dict': { - 'description': 'Donald Trump is accused of exploiting his president-elect status for personal gain, Cuban leader Fidel Castro dies, and Ryan Speedo Green discusses "Sing for Your Life."', - 'title': 'November 28, 2016 - Ryan Speedo Green', - }, - 'playlist_count': 4, }, { - 'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes', - 'only_matching': True, - }] - - def _real_extract(self, url): - playlist_id = self._match_id(url) - webpage = self._download_webpage(url, playlist_id) - mgid = self._extract_mgid(webpage, url, data_zone='t2_lc_promo1') - videos_info = self._get_videos_info(mgid) - return videos_info - - -class ToshIE(MTVServicesInfoExtractor): - IE_DESC = 'Tosh.0' - _VALID_URL = r'^https?://tosh\.cc\.com/video-(?:clips|collections)/[^/]+/(?P<videotitle>[^/?#]+)' - _FEED_URL = 'http://tosh.cc.com/feeds/mrss' - - _TESTS = [{ - 'url': 'http://tosh.cc.com/video-clips/68g93d/twitter-users-share-summer-plans', - 'info_dict': { - 'description': 'Tosh asked fans to share their summer plans.', - 'title': 'Twitter Users Share Summer Plans', - }, - 'playlist': [{ - 'md5': 'f269e88114c1805bb6d7653fecea9e06', - 'info_dict': { - 'id': '90498ec2-ed00-11e0-aca6-0026b9414f30', - 'ext': 'mp4', - 'title': 'Tosh.0|June 9, 2077|2|211|Twitter Users Share Summer Plans', - 'description': 'Tosh asked fans to share their summer plans.', - 'thumbnail': r're:^https?://.*\.jpg', - # It's really reported to be published on year 2077 - 'upload_date': '20770610', - 'timestamp': 3390510600, - 'subtitles': { - 'en': 'mincount:3', - }, - }, - }] - }, { - 'url': 'http://tosh.cc.com/video-collections/x2iz7k/just-plain-foul/m5q4fp', + 'url': 'https://www.cc.com/video/k3sdvm/the-daily-show-with-jon-stewart-exclusive-the-fourth-estate', 'only_matching': True, }] class ComedyCentralTVIE(MTVServicesInfoExtractor): - _VALID_URL = r'https?://(?:www\.)?comedycentral\.tv/(?:staffeln|shows)/(?P<id>[^/?#&]+)' + _VALID_URL = r'https?://(?:www\.)?comedycentral\.tv/folgen/(?P<id>[0-9a-z]{6})' _TESTS = [{ - 'url': 'http://www.comedycentral.tv/staffeln/7436-the-mindy-project-staffel-4', + 'url': 'https://www.comedycentral.tv/folgen/pxdpec/josh-investigates-klimawandel-staffel-1-ep-1', 'info_dict': { - 'id': 'local_playlist-f99b626bdfe13568579a', - 'ext': 'flv', - 'title': 'Episode_the-mindy-project_shows_season-4_episode-3_full-episode_part1', + 'id': '15907dc3-ec3c-11e8-a442-0e40cf2fc285', + 'ext': 'mp4', + 'title': 'Josh Investigates', + 'description': 'Steht uns das Ende der Welt bevor?', }, - 'params': { - # rtmp download - 'skip_download': True, - }, - }, { - 'url': 'http://www.comedycentral.tv/shows/1074-workaholics', - 'only_matching': True, - }, { - 'url': 'http://www.comedycentral.tv/shows/1727-the-mindy-project/bonus', - 'only_matching': True, }] + _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed' + _GEO_COUNTRIES = ['DE'] - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - mrss_url = self._search_regex( - r'data-mrss=(["\'])(?P<url>(?:(?!\1).)+)\1', - webpage, 'mrss url', group='url') - - return self._get_videos_info_from_url(mrss_url, video_id) - - -class ComedyCentralShortnameIE(InfoExtractor): - _VALID_URL = r'^:(?P<id>tds|thedailyshow|theopposition)$' - _TESTS = [{ - 'url': ':tds', - 'only_matching': True, - }, { - 'url': ':thedailyshow', - 'only_matching': True, - }, { - 'url': ':theopposition', - 'only_matching': True, - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - shortcut_map = { - 'tds': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes', - 'thedailyshow': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes', - 'theopposition': 'http://www.cc.com/shows/the-opposition-with-jordan-klepper/full-episodes', + def _get_feed_query(self, uri): + return { + 'accountOverride': 'intl.mtvi.com', + 'arcEp': 'web.cc.tv', + 'ep': 'b9032c3a', + 'imageEp': 'web.cc.tv', + 'mgid': uri, } - return self.url_result(shortcut_map[video_id]) diff --git a/youtube_dlc/extractor/extractors.py b/youtube_dlc/extractor/extractors.py index 6ea86c0973..10fd4a0b57 100644 --- a/youtube_dlc/extractor/extractors.py +++ b/youtube_dlc/extractor/extractors.py @@ -50,7 +50,10 @@ from .animelab import ( AnimeLabIE, AnimeLabShowsIE, ) -from .americastestkitchen import AmericasTestKitchenIE +from .americastestkitchen import ( + AmericasTestKitchenIE, + AmericasTestKitchenSeasonIE, +) from .animeondemand import AnimeOnDemandIE from .anvato import AnvatoIE from .aol import AolIE @@ -244,11 +247,8 @@ from .cnn import ( ) from .coub import CoubIE from .comedycentral import ( - ComedyCentralFullEpisodesIE, ComedyCentralIE, - ComedyCentralShortnameIE, ComedyCentralTVIE, - ToshIE, ) from .commonmistakes import CommonMistakesIE, UnicodeBOMIE from .commonprotocols import ( @@ -682,6 +682,11 @@ from .mildom import ( MildomVodIE, MildomUserVodIE, ) +from .minds import ( + MindsIE, + MindsChannelIE, + MindsGroupIE, +) from .ministrygrid import MinistryGridIE from .minoto import MinotoIE from .miomio import MioMioIE @@ -1162,6 +1167,10 @@ from .stitcher import StitcherIE from .sport5 import Sport5IE from .sportbox import SportBoxIE from .sportdeutschland import SportDeutschlandIE +from .spotify import ( + SpotifyIE, + SpotifyShowIE, +) from .spreaker import ( SpreakerIE, SpreakerPageIE, @@ -1270,7 +1279,10 @@ from .toutv import TouTvIE from .toypics import ToypicsUserIE, ToypicsIE from .traileraddict import TrailerAddictIE from .trilulilu import TriluliluIE -from .trovolive import TrovoLiveIE +from .trovo import ( + TrovoIE, + TrovoVodIE, +) from .trunews import TruNewsIE from .trutv import TruTVIE from .tube8 import Tube8IE diff --git a/youtube_dlc/extractor/franceculture.py b/youtube_dlc/extractor/franceculture.py index 306b45fc99..14f4cb4890 100644 --- a/youtube_dlc/extractor/franceculture.py +++ b/youtube_dlc/extractor/franceculture.py @@ -11,7 +11,7 @@ from ..utils import ( class FranceCultureIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?franceculture\.fr/emissions/(?:[^/]+/)*(?P<id>[^/?#&]+)' - _TEST = { + _TESTS = [{ 'url': 'http://www.franceculture.fr/emissions/carnet-nomade/rendez-vous-au-pays-des-geeks', 'info_dict': { 'id': 'rendez-vous-au-pays-des-geeks', @@ -20,10 +20,14 @@ class FranceCultureIE(InfoExtractor): 'title': 'Rendez-vous au pays des geeks', 'thumbnail': r're:^https?://.*\.jpg$', 'upload_date': '20140301', - 'timestamp': 1393642916, + 'timestamp': 1393700400, 'vcodec': 'none', } - } + }, { + # no thumbnail + 'url': 'https://www.franceculture.fr/emissions/la-recherche-montre-en-main/la-recherche-montre-en-main-du-mercredi-10-octobre-2018', + 'only_matching': True, + }] def _real_extract(self, url): display_id = self._match_id(url) @@ -36,19 +40,19 @@ class FranceCultureIE(InfoExtractor): </h1>| <div[^>]+class="[^"]*?(?:title-zone-diffusion|heading-zone-(?:wrapper|player-button))[^"]*?"[^>]*> ).*? - (<button[^>]+data-asset-source="[^"]+"[^>]+>) + (<button[^>]+data-(?:url|asset-source)="[^"]+"[^>]+>) ''', webpage, 'video data')) - video_url = video_data['data-asset-source'] - title = video_data.get('data-asset-title') or self._og_search_title(webpage) + video_url = video_data.get('data-url') or video_data['data-asset-source'] + title = video_data.get('data-asset-title') or video_data.get('data-diffusion-title') or self._og_search_title(webpage) description = self._html_search_regex( r'(?s)<div[^>]+class="intro"[^>]*>.*?<h2>(.+?)</h2>', webpage, 'description', default=None) thumbnail = self._search_regex( r'(?s)<figure[^>]+itemtype="https://schema.org/ImageObject"[^>]*>.*?<img[^>]+(?:data-dejavu-)?src="([^"]+)"', - webpage, 'thumbnail', fatal=False) + webpage, 'thumbnail', default=None) uploader = self._html_search_regex( r'(?s)<span class="author">(.*?)</span>', webpage, 'uploader', default=None) @@ -64,6 +68,6 @@ class FranceCultureIE(InfoExtractor): 'ext': ext, 'vcodec': 'none' if ext == 'mp3' else None, 'uploader': uploader, - 'timestamp': int_or_none(video_data.get('data-asset-created-date')), + 'timestamp': int_or_none(video_data.get('data-start-time')) or int_or_none(video_data.get('data-asset-created-date')), 'duration': int_or_none(video_data.get('data-duration')), } diff --git a/youtube_dlc/extractor/lbry.py b/youtube_dlc/extractor/lbry.py index 41cc245ebd..413215a992 100644 --- a/youtube_dlc/extractor/lbry.py +++ b/youtube_dlc/extractor/lbry.py @@ -5,7 +5,10 @@ import functools import json from .common import InfoExtractor -from ..compat import compat_str +from ..compat import ( + compat_str, + compat_urllib_parse_unquote, +) from ..utils import ( determine_ext, ExtractorError, @@ -131,6 +134,9 @@ class LBRYIE(LBRYBaseIE): }, { 'url': 'https://lbry.tv/$/download/Episode-1/e7d93d772bd87e2b62d5ab993c1c3ced86ebb396', 'only_matching': True, + }, { + 'url': 'https://lbry.tv/@lacajadepandora:a/TRUMP-EST%C3%81-BIEN-PUESTO-con-Pilar-Baselga,-Carlos-Senra,-Luis-Palacios-(720p_30fps_H264-192kbit_AAC):1', + 'only_matching': True, }] def _real_extract(self, url): @@ -139,6 +145,7 @@ class LBRYIE(LBRYBaseIE): display_id = display_id.split('/', 2)[-1].replace('/', ':') else: display_id = display_id.replace(':', '#') + display_id = compat_urllib_parse_unquote(display_id) uri = 'lbry://' + display_id result = self._resolve_url(uri, display_id, 'stream') result_value = result['value'] diff --git a/youtube_dlc/extractor/minds.py b/youtube_dlc/extractor/minds.py new file mode 100644 index 0000000000..8e9f0f8254 --- /dev/null +++ b/youtube_dlc/extractor/minds.py @@ -0,0 +1,196 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + clean_html, + int_or_none, + str_or_none, + strip_or_none, +) + + +class MindsBaseIE(InfoExtractor): + _VALID_URL_BASE = r'https?://(?:www\.)?minds\.com/' + + def _call_api(self, path, video_id, resource, query=None): + api_url = 'https://www.minds.com/api/' + path + token = self._get_cookies(api_url).get('XSRF-TOKEN') + return self._download_json( + api_url, video_id, 'Downloading %s JSON metadata' % resource, headers={ + 'Referer': 'https://www.minds.com/', + 'X-XSRF-TOKEN': token.value if token else '', + }, query=query) + + +class MindsIE(MindsBaseIE): + IE_NAME = 'minds' + _VALID_URL = MindsBaseIE._VALID_URL_BASE + r'(?:media|newsfeed|archive/view)/(?P<id>[0-9]+)' + _TESTS = [{ + 'url': 'https://www.minds.com/media/100000000000086822', + 'md5': '215a658184a419764852239d4970b045', + 'info_dict': { + 'id': '100000000000086822', + 'ext': 'mp4', + 'title': 'Minds intro sequence', + 'thumbnail': r're:https?://.+\.png', + 'uploader_id': 'ottman', + 'upload_date': '20130524', + 'timestamp': 1369404826, + 'uploader': 'Bill Ottman', + 'view_count': int, + 'like_count': int, + 'dislike_count': int, + 'tags': ['animation'], + 'comment_count': int, + 'license': 'attribution-cc', + }, + }, { + # entity.type == 'activity' and empty title + 'url': 'https://www.minds.com/newsfeed/798025111988506624', + 'md5': 'b2733a74af78d7fd3f541c4cbbaa5950', + 'info_dict': { + 'id': '798022190320226304', + 'ext': 'mp4', + 'title': '798022190320226304', + 'uploader': 'ColinFlaherty', + 'upload_date': '20180111', + 'timestamp': 1515639316, + 'uploader_id': 'ColinFlaherty', + }, + }, { + 'url': 'https://www.minds.com/archive/view/715172106794442752', + 'only_matching': True, + }, { + # youtube perma_url + 'url': 'https://www.minds.com/newsfeed/1197131838022602752', + 'only_matching': True, + }] + + def _real_extract(self, url): + entity_id = self._match_id(url) + entity = self._call_api( + 'v1/entities/entity/' + entity_id, entity_id, 'entity')['entity'] + if entity.get('type') == 'activity': + if entity.get('custom_type') == 'video': + video_id = entity['entity_guid'] + else: + return self.url_result(entity['perma_url']) + else: + assert(entity['subtype'] == 'video') + video_id = entity_id + # 1080p and webm formats available only on the sources array + video = self._call_api( + 'v2/media/video/' + video_id, video_id, 'video') + + formats = [] + for source in (video.get('sources') or []): + src = source.get('src') + if not src: + continue + formats.append({ + 'format_id': source.get('label'), + 'height': int_or_none(source.get('size')), + 'url': src, + }) + self._sort_formats(formats) + + entity = video.get('entity') or entity + owner = entity.get('ownerObj') or {} + uploader_id = owner.get('username') + + tags = entity.get('tags') + if tags and isinstance(tags, compat_str): + tags = [tags] + + thumbnail = None + poster = video.get('poster') or entity.get('thumbnail_src') + if poster: + urlh = self._request_webpage(poster, video_id, fatal=False) + if urlh: + thumbnail = urlh.geturl() + + return { + 'id': video_id, + 'title': entity.get('title') or video_id, + 'formats': formats, + 'description': clean_html(entity.get('description')) or None, + 'license': str_or_none(entity.get('license')), + 'timestamp': int_or_none(entity.get('time_created')), + 'uploader': strip_or_none(owner.get('name')), + 'uploader_id': uploader_id, + 'uploader_url': 'https://www.minds.com/' + uploader_id if uploader_id else None, + 'view_count': int_or_none(entity.get('play:count')), + 'like_count': int_or_none(entity.get('thumbs:up:count')), + 'dislike_count': int_or_none(entity.get('thumbs:down:count')), + 'tags': tags, + 'comment_count': int_or_none(entity.get('comments:count')), + 'thumbnail': thumbnail, + } + + +class MindsFeedBaseIE(MindsBaseIE): + _PAGE_SIZE = 150 + + def _entries(self, feed_id): + query = {'limit': self._PAGE_SIZE, 'sync': 1} + i = 1 + while True: + data = self._call_api( + 'v2/feeds/container/%s/videos' % feed_id, + feed_id, 'page %s' % i, query) + entities = data.get('entities') or [] + for entity in entities: + guid = entity.get('guid') + if not guid: + continue + yield self.url_result( + 'https://www.minds.com/newsfeed/' + guid, + MindsIE.ie_key(), guid) + query['from_timestamp'] = data['load-next'] + if not (query['from_timestamp'] and len(entities) == self._PAGE_SIZE): + break + i += 1 + + def _real_extract(self, url): + feed_id = self._match_id(url) + feed = self._call_api( + 'v1/%s/%s' % (self._FEED_PATH, feed_id), + feed_id, self._FEED_TYPE)[self._FEED_TYPE] + + return self.playlist_result( + self._entries(feed['guid']), feed_id, + strip_or_none(feed.get('name')), + feed.get('briefdescription')) + + +class MindsChannelIE(MindsFeedBaseIE): + _FEED_TYPE = 'channel' + IE_NAME = 'minds:' + _FEED_TYPE + _VALID_URL = MindsBaseIE._VALID_URL_BASE + r'(?!(?:newsfeed|media|api|archive|groups)/)(?P<id>[^/?&#]+)' + _FEED_PATH = 'channel' + _TEST = { + 'url': 'https://www.minds.com/ottman', + 'info_dict': { + 'id': 'ottman', + 'title': 'Bill Ottman', + 'description': 'Co-creator & CEO @minds', + }, + 'playlist_mincount': 54, + } + + +class MindsGroupIE(MindsFeedBaseIE): + _FEED_TYPE = 'group' + IE_NAME = 'minds:' + _FEED_TYPE + _VALID_URL = MindsBaseIE._VALID_URL_BASE + r'groups/profile/(?P<id>[0-9]+)' + _FEED_PATH = 'groups/group' + _TEST = { + 'url': 'https://www.minds.com/groups/profile/785582576369672204/feed/videos', + 'info_dict': { + 'id': '785582576369672204', + 'title': 'Cooking Videos', + }, + 'playlist_mincount': 1, + } diff --git a/youtube_dlc/extractor/mtv.py b/youtube_dlc/extractor/mtv.py index d31f53137a..68e81ad47a 100644 --- a/youtube_dlc/extractor/mtv.py +++ b/youtube_dlc/extractor/mtv.py @@ -255,6 +255,10 @@ class MTVServicesInfoExtractor(InfoExtractor): return try_get(feed, lambda x: x['result']['data']['id'], compat_str) + @staticmethod + def _extract_child_with_type(parent, t): + return next(c for c in parent['children'] if c.get('type') == t) + def _extract_new_triforce_mgid(self, webpage, url='', video_id=None): if url == '': return @@ -332,6 +336,13 @@ class MTVServicesInfoExtractor(InfoExtractor): if not mgid: mgid = self._extract_triforce_mgid(webpage, data_zone) + if not mgid: + data = self._parse_json(self._search_regex( + r'__DATA__\s*=\s*({.+?});', webpage, 'data'), None) + main_container = self._extract_child_with_type(data, 'MainContainer') + video_player = self._extract_child_with_type(main_container, 'VideoPlayer') + mgid = video_player['props']['media']['video']['config']['uri'] + return mgid def _real_extract(self, url): @@ -403,18 +414,6 @@ class MTVIE(MTVServicesInfoExtractor): 'only_matching': True, }] - @staticmethod - def extract_child_with_type(parent, t): - children = parent['children'] - return next(c for c in children if c.get('type') == t) - - def _extract_mgid(self, webpage): - data = self._parse_json(self._search_regex( - r'__DATA__\s*=\s*({.+?});', webpage, 'data'), None) - main_container = self.extract_child_with_type(data, 'MainContainer') - video_player = self.extract_child_with_type(main_container, 'VideoPlayer') - return video_player['props']['media']['video']['config']['uri'] - class MTVJapanIE(MTVServicesInfoExtractor): IE_NAME = 'mtvjapan' diff --git a/youtube_dlc/extractor/ninegag.py b/youtube_dlc/extractor/ninegag.py index dc6a27d364..440f865bce 100644 --- a/youtube_dlc/extractor/ninegag.py +++ b/youtube_dlc/extractor/ninegag.py @@ -1,104 +1,125 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import str_to_int +from ..utils import ( + determine_ext, + ExtractorError, + int_or_none, + try_get, + url_or_none, +) class NineGagIE(InfoExtractor): IE_NAME = '9gag' - _VALID_URL = r'https?://(?:www\.)?9gag(?:\.com/tv|\.tv)/(?:p|embed)/(?P<id>[a-zA-Z0-9]+)(?:/(?P<display_id>[^?#/]+))?' + _VALID_URL = r'https?://(?:www\.)?9gag\.com/gag/(?P<id>[^/?&#]+)' - _TESTS = [{ - 'url': 'http://9gag.com/tv/p/Kk2X5/people-are-awesome-2013-is-absolutely-awesome', + _TEST = { + 'url': 'https://9gag.com/gag/ae5Ag7B', 'info_dict': { - 'id': 'kXzwOKyGlSA', + 'id': 'ae5Ag7B', 'ext': 'mp4', - 'description': 'This 3-minute video will make you smile and then make you feel untalented and insignificant. Anyway, you should share this awesomeness. (Thanks, Dino!)', - 'title': '\"People Are Awesome 2013\" Is Absolutely Awesome', - 'uploader_id': 'UCdEH6EjDKwtTe-sO2f0_1XA', - 'uploader': 'CompilationChannel', - 'upload_date': '20131110', - 'view_count': int, - }, - 'add_ie': ['Youtube'], - }, { - 'url': 'http://9gag.com/tv/p/aKolP3', - 'info_dict': { - 'id': 'aKolP3', - 'ext': 'mp4', - 'title': 'This Guy Travelled 11 countries In 44 days Just To Make This Amazing Video', - 'description': "I just saw more in 1 minute than I've seen in 1 year. This guy's video is epic!!", - 'uploader_id': 'rickmereki', - 'uploader': 'Rick Mereki', - 'upload_date': '20110803', - 'view_count': int, - }, - 'add_ie': ['Vimeo'], - }, { - 'url': 'http://9gag.com/tv/p/KklwM', - 'only_matching': True, - }, { - 'url': 'http://9gag.tv/p/Kk2X5', - 'only_matching': True, - }, { - 'url': 'http://9gag.com/tv/embed/a5Dmvl', - 'only_matching': True, - }] - - _EXTERNAL_VIDEO_PROVIDER = { - '1': { - 'url': '%s', - 'ie_key': 'Youtube', - }, - '2': { - 'url': 'http://player.vimeo.com/video/%s', - 'ie_key': 'Vimeo', - }, - '3': { - 'url': 'http://instagram.com/p/%s', - 'ie_key': 'Instagram', - }, - '4': { - 'url': 'http://vine.co/v/%s', - 'ie_key': 'Vine', - }, + 'title': 'Capybara Agility Training', + 'upload_date': '20191108', + 'timestamp': 1573237208, + 'categories': ['Awesome'], + 'tags': ['Weimaraner', 'American Pit Bull Terrier'], + 'duration': 44, + 'like_count': int, + 'dislike_count': int, + 'comment_count': int, + } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - display_id = mobj.group('display_id') or video_id + post_id = self._match_id(url) + post = self._download_json( + 'https://9gag.com/v1/post', post_id, query={ + 'id': post_id + })['data']['post'] - webpage = self._download_webpage(url, display_id) + if post.get('type') != 'Animated': + raise ExtractorError( + 'The given url does not contain a video', + expected=True) - post_view = self._parse_json( - self._search_regex( - r'var\s+postView\s*=\s*new\s+app\.PostView\({\s*post:\s*({.+?})\s*,\s*posts:\s*prefetchedCurrentPost', - webpage, 'post view'), - display_id) + title = post['title'] - ie_key = None - source_url = post_view.get('sourceUrl') - if not source_url: - external_video_id = post_view['videoExternalId'] - external_video_provider = post_view['videoExternalProvider'] - source_url = self._EXTERNAL_VIDEO_PROVIDER[external_video_provider]['url'] % external_video_id - ie_key = self._EXTERNAL_VIDEO_PROVIDER[external_video_provider]['ie_key'] - title = post_view['title'] - description = post_view.get('description') - view_count = str_to_int(post_view.get('externalView')) - thumbnail = post_view.get('thumbnail_700w') or post_view.get('ogImageUrl') or post_view.get('thumbnail_300w') + duration = None + formats = [] + thumbnails = [] + for key, image in (post.get('images') or {}).items(): + image_url = url_or_none(image.get('url')) + if not image_url: + continue + ext = determine_ext(image_url) + image_id = key.strip('image') + common = { + 'url': image_url, + 'width': int_or_none(image.get('width')), + 'height': int_or_none(image.get('height')), + } + if ext in ('jpg', 'png'): + webp_url = image.get('webpUrl') + if webp_url: + t = common.copy() + t.update({ + 'id': image_id + '-webp', + 'url': webp_url, + }) + thumbnails.append(t) + common.update({ + 'id': image_id, + 'ext': ext, + }) + thumbnails.append(common) + elif ext in ('webm', 'mp4'): + if not duration: + duration = int_or_none(image.get('duration')) + common['acodec'] = 'none' if image.get('hasAudio') == 0 else None + for vcodec in ('vp8', 'vp9', 'h265'): + c_url = image.get(vcodec + 'Url') + if not c_url: + continue + c_f = common.copy() + c_f.update({ + 'format_id': image_id + '-' + vcodec, + 'url': c_url, + 'vcodec': vcodec, + }) + formats.append(c_f) + common.update({ + 'ext': ext, + 'format_id': image_id, + }) + formats.append(common) + self._sort_formats(formats) + + section = try_get(post, lambda x: x['postSection']['name']) + + tags = None + post_tags = post.get('tags') + if post_tags: + tags = [] + for tag in post_tags: + tag_key = tag.get('key') + if not tag_key: + continue + tags.append(tag_key) + + get_count = lambda x: int_or_none(post.get(x + 'Count')) return { - '_type': 'url_transparent', - 'url': source_url, - 'ie_key': ie_key, - 'id': video_id, - 'display_id': display_id, + 'id': post_id, 'title': title, - 'description': description, - 'view_count': view_count, - 'thumbnail': thumbnail, + 'timestamp': int_or_none(post.get('creationTs')), + 'duration': duration, + 'formats': formats, + 'thumbnails': thumbnails, + 'like_count': get_count('upVote'), + 'dislike_count': get_count('downVote'), + 'comment_count': get_count('comments'), + 'age_limit': 18 if post.get('nsfw') == 1 else None, + 'categories': [section] if section else None, + 'tags': tags, } diff --git a/youtube_dlc/extractor/njpwworld.py b/youtube_dlc/extractor/njpwworld.py index 025c5d249c..3639d142ff 100644 --- a/youtube_dlc/extractor/njpwworld.py +++ b/youtube_dlc/extractor/njpwworld.py @@ -6,30 +6,40 @@ import re from .common import InfoExtractor from ..compat import compat_urlparse from ..utils import ( - extract_attributes, get_element_by_class, urlencode_postdata, ) class NJPWWorldIE(InfoExtractor): - _VALID_URL = r'https?://njpwworld\.com/p/(?P<id>[a-z0-9_]+)' + _VALID_URL = r'https?://(front\.)?njpwworld\.com/p/(?P<id>[a-z0-9_]+)' IE_DESC = '新日本プロレスワールド' _NETRC_MACHINE = 'njpwworld' - _TEST = { + _TESTS = [{ 'url': 'http://njpwworld.com/p/s_series_00155_1_9/', 'info_dict': { 'id': 's_series_00155_1_9', 'ext': 'mp4', - 'title': '第9試合　ランディ・サベージ　vs　リック・スタイナー', + 'title': '闘強導夢2000 2000年1月4日 東京ドーム 第9試合 ランディ・サベージ VS リック・スタイナー', 'tags': list, }, 'params': { 'skip_download': True, # AES-encrypted m3u8 }, 'skip': 'Requires login', - } + }, { + 'url': 'https://front.njpwworld.com/p/s_series_00563_16_bs', + 'info_dict': { + 'id': 's_series_00563_16_bs', + 'ext': 'mp4', + 'title': 'WORLD TAG LEAGUE 2020 & BEST OF THE SUPER Jr.27 2020年12月6日 福岡・福岡国際センター バックステージコメント（字幕あり）', + 'tags': ["福岡・福岡国際センター", "バックステージコメント", "2020", "20年代"], + }, + 'params': { + 'skip_download': True, + }, + }] _LOGIN_URL = 'https://front.njpwworld.com/auth/login' @@ -64,35 +74,27 @@ class NJPWWorldIE(InfoExtractor): webpage = self._download_webpage(url, video_id) formats = [] - for mobj in re.finditer(r'<a[^>]+\bhref=(["\'])/player.+?[^>]*>', webpage): - player = extract_attributes(mobj.group(0)) - player_path = player.get('href') - if not player_path: - continue - kind = self._search_regex( - r'(low|high)$', player.get('class') or '', 'kind', - default='low') + for kind, vid in re.findall(r'if\s+\(\s*imageQualityType\s*==\s*\'([^\']+)\'\s*\)\s*{\s*video_id\s*=\s*"(\d+)"', webpage): + player_path = '/intent?id=%s&type=url' % vid player_url = compat_urlparse.urljoin(url, player_path) - player_page = self._download_webpage( - player_url, video_id, note='Downloading player page') - entries = self._parse_html5_media_entries( - player_url, player_page, video_id, m3u8_id='hls-%s' % kind, - m3u8_entry_protocol='m3u8_native') - kind_formats = entries[0]['formats'] - for f in kind_formats: - f['quality'] = 2 if kind == 'high' else 1 - formats.extend(kind_formats) + formats.append({ + 'url': player_url, + 'format_id': kind, + 'ext': 'mp4', + 'protocol': 'm3u8', + 'quality': 2 if kind == 'high' else 1, + }) self._sort_formats(formats) - post_content = get_element_by_class('post-content', webpage) + tag_block = get_element_by_class('tag-block', webpage) tags = re.findall( - r'<li[^>]+class="tag-[^"]+"><a[^>]*>([^<]+)</a></li>', post_content - ) if post_content else None + r'<a[^>]+class="tag-[^"]+"[^>]*>([^<]+)</a>', tag_block + ) if tag_block else None return { 'id': video_id, - 'title': self._og_search_title(webpage), + 'title': get_element_by_class('article-title', webpage) or self._og_search_title(webpage), 'formats': formats, 'tags': tags, } diff --git a/youtube_dlc/extractor/spike.py b/youtube_dlc/extractor/spike.py index 4180e71efa..5805f3d445 100644 --- a/youtube_dlc/extractor/spike.py +++ b/youtube_dlc/extractor/spike.py @@ -20,19 +20,6 @@ class BellatorIE(MTVServicesInfoExtractor): _FEED_URL = 'http://www.bellator.com/feeds/mrss/' _GEO_COUNTRIES = ['US'] - def _extract_mgid(self, webpage, url): - mgid = None - - if not mgid: - mgid = self._extract_triforce_mgid(webpage) - - if not mgid: - mgid = self._extract_new_triforce_mgid(webpage, url) - - return mgid - -# TODO Remove - Reason: Outdated Site - class ParamountNetworkIE(MTVServicesInfoExtractor): _VALID_URL = r'https?://(?:www\.)?paramountnetwork\.com/[^/]+/[\da-z]{6}(?:[/?#&]|$)' @@ -56,16 +43,6 @@ class ParamountNetworkIE(MTVServicesInfoExtractor): def _get_feed_query(self, uri): return { 'arcEp': 'paramountnetwork.com', + 'imageEp': 'paramountnetwork.com', 'mgid': uri, } - - def _extract_mgid(self, webpage, url): - root_data = self._parse_json(self._search_regex( - r'window\.__DATA__\s*=\s*({.+})', - webpage, 'data'), None) - - def find_sub_data(data, data_type): - return next(c for c in data['children'] if c.get('type') == data_type) - - c = find_sub_data(find_sub_data(root_data, 'MainContainer'), 'VideoPlayer') - return c['props']['media']['video']['config']['uri'] diff --git a/youtube_dlc/extractor/spotify.py b/youtube_dlc/extractor/spotify.py new file mode 100644 index 0000000000..826f98cffc --- /dev/null +++ b/youtube_dlc/extractor/spotify.py @@ -0,0 +1,156 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import ( + clean_podcast_url, + float_or_none, + int_or_none, + strip_or_none, + try_get, + unified_strdate, +) + + +class SpotifyBaseIE(InfoExtractor): + _ACCESS_TOKEN = None + _OPERATION_HASHES = { + 'Episode': '8276d4423d709ae9b68ec1b74cc047ba0f7479059a37820be730f125189ac2bf', + 'MinimalShow': '13ee079672fad3f858ea45a55eb109553b4fb0969ed793185b2e34cbb6ee7cc0', + 'ShowEpisodes': 'e0e5ce27bd7748d2c59b4d44ba245a8992a05be75d6fabc3b20753fc8857444d', + } + _VALID_URL_TEMPL = r'https?://open\.spotify\.com/%s/(?P<id>[^/?&#]+)' + + def _real_initialize(self): + self._ACCESS_TOKEN = self._download_json( + 'https://open.spotify.com/get_access_token', None)['accessToken'] + + def _call_api(self, operation, video_id, variables): + return self._download_json( + 'https://api-partner.spotify.com/pathfinder/v1/query', video_id, query={ + 'operationName': 'query' + operation, + 'variables': json.dumps(variables), + 'extensions': json.dumps({ + 'persistedQuery': { + 'sha256Hash': self._OPERATION_HASHES[operation], + }, + }) + }, headers={'authorization': 'Bearer ' + self._ACCESS_TOKEN})['data'] + + def _extract_episode(self, episode, series): + episode_id = episode['id'] + title = episode['name'].strip() + + formats = [] + audio_preview = episode.get('audioPreview') or {} + audio_preview_url = audio_preview.get('url') + if audio_preview_url: + f = { + 'url': audio_preview_url.replace('://p.scdn.co/mp3-preview/', '://anon-podcast.scdn.co/'), + 'vcodec': 'none', + } + audio_preview_format = audio_preview.get('format') + if audio_preview_format: + f['format_id'] = audio_preview_format + mobj = re.match(r'([0-9A-Z]{3})_(?:[A-Z]+_)?(\d+)', audio_preview_format) + if mobj: + f.update({ + 'abr': int(mobj.group(2)), + 'ext': mobj.group(1).lower(), + }) + formats.append(f) + + for item in (try_get(episode, lambda x: x['audio']['items']) or []): + item_url = item.get('url') + if not (item_url and item.get('externallyHosted')): + continue + formats.append({ + 'url': clean_podcast_url(item_url), + 'vcodec': 'none', + }) + + thumbnails = [] + for source in (try_get(episode, lambda x: x['coverArt']['sources']) or []): + source_url = source.get('url') + if not source_url: + continue + thumbnails.append({ + 'url': source_url, + 'width': int_or_none(source.get('width')), + 'height': int_or_none(source.get('height')), + }) + + return { + 'id': episode_id, + 'title': title, + 'formats': formats, + 'thumbnails': thumbnails, + 'description': strip_or_none(episode.get('description')), + 'duration': float_or_none(try_get( + episode, lambda x: x['duration']['totalMilliseconds']), 1000), + 'release_date': unified_strdate(try_get( + episode, lambda x: x['releaseDate']['isoString'])), + 'series': series, + } + + +class SpotifyIE(SpotifyBaseIE): + IE_NAME = 'spotify' + _VALID_URL = SpotifyBaseIE._VALID_URL_TEMPL % 'episode' + _TEST = { + 'url': 'https://open.spotify.com/episode/4Z7GAJ50bgctf6uclHlWKo', + 'md5': '74010a1e3fa4d9e1ab3aa7ad14e42d3b', + 'info_dict': { + 'id': '4Z7GAJ50bgctf6uclHlWKo', + 'ext': 'mp3', + 'title': 'From the archive: Why time management is ruining our lives', + 'description': 'md5:b120d9c4ff4135b42aa9b6d9cde86935', + 'duration': 2083.605, + 'release_date': '20201217', + 'series': "The Guardian's Audio Long Reads", + } + } + + def _real_extract(self, url): + episode_id = self._match_id(url) + episode = self._call_api('Episode', episode_id, { + 'uri': 'spotify:episode:' + episode_id + })['episode'] + return self._extract_episode( + episode, try_get(episode, lambda x: x['podcast']['name'])) + + +class SpotifyShowIE(SpotifyBaseIE): + IE_NAME = 'spotify:show' + _VALID_URL = SpotifyBaseIE._VALID_URL_TEMPL % 'show' + _TEST = { + 'url': 'https://open.spotify.com/show/4PM9Ke6l66IRNpottHKV9M', + 'info_dict': { + 'id': '4PM9Ke6l66IRNpottHKV9M', + 'title': 'The Story from the Guardian', + 'description': 'The Story podcast is dedicated to our finest audio documentaries, investigations and long form stories', + }, + 'playlist_mincount': 36, + } + + def _real_extract(self, url): + show_id = self._match_id(url) + podcast = self._call_api('ShowEpisodes', show_id, { + 'limit': 1000000000, + 'offset': 0, + 'uri': 'spotify:show:' + show_id, + })['podcast'] + podcast_name = podcast.get('name') + + entries = [] + for item in (try_get(podcast, lambda x: x['episodes']['items']) or []): + episode = item.get('episode') + if not episode: + continue + entries.append(self._extract_episode(episode, podcast_name)) + + return self.playlist_result( + entries, show_id, podcast_name, podcast.get('description')) diff --git a/youtube_dlc/extractor/trovo.py b/youtube_dlc/extractor/trovo.py new file mode 100644 index 0000000000..43745213da --- /dev/null +++ b/youtube_dlc/extractor/trovo.py @@ -0,0 +1,193 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import json + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + int_or_none, + str_or_none, + try_get, +) + + +class TrovoBaseIE(InfoExtractor): + _VALID_URL_BASE = r'https?://(?:www\.)?trovo\.live/' + + def _extract_streamer_info(self, data): + streamer_info = data.get('streamerInfo') or {} + username = streamer_info.get('userName') + return { + 'uploader': streamer_info.get('nickName'), + 'uploader_id': str_or_none(streamer_info.get('uid')), + 'uploader_url': 'https://trovo.live/' + username if username else None, + } + + +class TrovoIE(TrovoBaseIE): + _VALID_URL = TrovoBaseIE._VALID_URL_BASE + r'(?!(?:clip|video)/)(?P<id>[^/?&#]+)' + + def _real_extract(self, url): + username = self._match_id(url) + live_info = self._download_json( + 'https://gql.trovo.live/', username, query={ + 'query': '''{ + getLiveInfo(params: {userName: "%s"}) { + isLive + programInfo { + coverUrl + id + streamInfo { + desc + playUrl + } + title + } + streamerInfo { + nickName + uid + userName + } + } +}''' % username, + })['data']['getLiveInfo'] + if live_info.get('isLive') == 0: + raise ExtractorError('%s is offline' % username, expected=True) + program_info = live_info['programInfo'] + program_id = program_info['id'] + title = self._live_title(program_info['title']) + + formats = [] + for stream_info in (program_info.get('streamInfo') or []): + play_url = stream_info.get('playUrl') + if not play_url: + continue + format_id = stream_info.get('desc') + formats.append({ + 'format_id': format_id, + 'height': int_or_none(format_id[:-1]) if format_id else None, + 'url': play_url, + }) + self._sort_formats(formats) + + info = { + 'id': program_id, + 'title': title, + 'formats': formats, + 'thumbnail': program_info.get('coverUrl'), + 'is_live': True, + } + info.update(self._extract_streamer_info(live_info)) + return info + + +class TrovoVodIE(TrovoBaseIE): + _VALID_URL = TrovoBaseIE._VALID_URL_BASE + r'(?:clip|video)/(?P<id>[^/?&#]+)' + _TESTS = [{ + 'url': 'https://trovo.live/video/ltv-100095501_100095501_1609596043', + 'info_dict': { + 'id': 'ltv-100095501_100095501_1609596043', + 'ext': 'mp4', + 'title': 'Spontaner 12 Stunden Stream! - Ok Boomer!', + 'uploader': 'Exsl', + 'timestamp': 1609640305, + 'upload_date': '20210103', + 'uploader_id': '100095501', + 'duration': 43977, + 'view_count': int, + 'like_count': int, + 'comment_count': int, + 'comments': 'mincount:8', + 'categories': ['Grand Theft Auto V'], + }, + }, { + 'url': 'https://trovo.live/clip/lc-5285890810184026005', + 'only_matching': True, + }] + + def _real_extract(self, url): + vid = self._match_id(url) + resp = self._download_json( + 'https://gql.trovo.live/', vid, data=json.dumps([{ + 'query': '''{ + batchGetVodDetailInfo(params: {vids: ["%s"]}) { + VodDetailInfos + } +}''' % vid, + }, { + 'query': '''{ + getCommentList(params: {appInfo: {postID: "%s"}, pageSize: 1000000000, preview: {}}) { + commentList { + author { + nickName + uid + } + commentID + content + createdAt + parentID + } + } +}''' % vid, + }]).encode(), headers={ + 'Content-Type': 'application/json', + }) + vod_detail_info = resp[0]['data']['batchGetVodDetailInfo']['VodDetailInfos'][vid] + vod_info = vod_detail_info['vodInfo'] + title = vod_info['title'] + + language = vod_info.get('languageName') + formats = [] + for play_info in (vod_info.get('playInfos') or []): + play_url = play_info.get('playUrl') + if not play_url: + continue + format_id = play_info.get('desc') + formats.append({ + 'ext': 'mp4', + 'filesize': int_or_none(play_info.get('fileSize')), + 'format_id': format_id, + 'height': int_or_none(format_id[:-1]) if format_id else None, + 'language': language, + 'protocol': 'm3u8_native', + 'tbr': int_or_none(play_info.get('bitrate')), + 'url': play_url, + }) + self._sort_formats(formats) + + category = vod_info.get('categoryName') + get_count = lambda x: int_or_none(vod_info.get(x + 'Num')) + + comment_list = try_get(resp, lambda x: x[1]['data']['getCommentList']['commentList'], list) or [] + comments = [] + for comment in comment_list: + content = comment.get('content') + if not content: + continue + author = comment.get('author') or {} + parent = comment.get('parentID') + comments.append({ + 'author': author.get('nickName'), + 'author_id': str_or_none(author.get('uid')), + 'id': str_or_none(comment.get('commentID')), + 'text': content, + 'timestamp': int_or_none(comment.get('createdAt')), + 'parent': 'root' if parent == 0 else str_or_none(parent), + }) + + info = { + 'id': vid, + 'title': title, + 'formats': formats, + 'thumbnail': vod_info.get('coverUrl'), + 'timestamp': int_or_none(vod_info.get('publishTs')), + 'duration': int_or_none(vod_info.get('duration')), + 'view_count': get_count('watch'), + 'like_count': get_count('like'), + 'comment_count': get_count('comment'), + 'comments': comments, + 'categories': [category] if category else None, + } + info.update(self._extract_streamer_info(vod_detail_info)) + return info diff --git a/youtube_dlc/extractor/wat.py b/youtube_dlc/extractor/wat.py index 8ef3e09064..f6940b371b 100644 --- a/youtube_dlc/extractor/wat.py +++ b/youtube_dlc/extractor/wat.py @@ -1,12 +1,9 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..compat import compat_str from ..utils import ( - ExtractorError, unified_strdate, HEADRequest, int_or_none, @@ -46,15 +43,6 @@ class WatIE(InfoExtractor): }, ] - _FORMATS = ( - (200, 416, 234), - (400, 480, 270), - (600, 640, 360), - (1200, 640, 360), - (1800, 960, 540), - (2500, 1280, 720), - ) - def _real_extract(self, url): video_id = self._match_id(url) video_id = video_id if video_id.isdigit() and len(video_id) > 6 else compat_str(int(video_id, 36)) @@ -97,46 +85,20 @@ class WatIE(InfoExtractor): return red_url return None - def remove_bitrate_limit(manifest_url): - return re.sub(r'(?:max|min)_bitrate=\d+&?', '', manifest_url) - formats = [] - try: - alt_urls = lambda manifest_url: [re.sub(r'(?:wdv|ssm)?\.ism/', repl + '.ism/', manifest_url) for repl in ('', 'ssm')] - manifest_urls = self._download_json( - 'http://www.wat.tv/get/webhtml/' + video_id, video_id) - m3u8_url = manifest_urls.get('hls') - if m3u8_url: - m3u8_url = remove_bitrate_limit(m3u8_url) - for m3u8_alt_url in alt_urls(m3u8_url): - formats.extend(self._extract_m3u8_formats( - m3u8_alt_url, video_id, 'mp4', - 'm3u8_native', m3u8_id='hls', fatal=False)) - formats.extend(self._extract_f4m_formats( - m3u8_alt_url.replace('ios', 'web').replace('.m3u8', '.f4m'), - video_id, f4m_id='hds', fatal=False)) - mpd_url = manifest_urls.get('mpd') - if mpd_url: - mpd_url = remove_bitrate_limit(mpd_url) - for mpd_alt_url in alt_urls(mpd_url): - formats.extend(self._extract_mpd_formats( - mpd_alt_url, video_id, mpd_id='dash', fatal=False)) - self._sort_formats(formats) - except ExtractorError: - abr = 64 - for vbr, width, height in self._FORMATS: - tbr = vbr + abr - format_id = 'http-%s' % tbr - fmt_url = 'http://dnl.adv.tf1.fr/2/USP-0x0/%s/%s/%s/ssm/%s-%s-64k.mp4' % (video_id[-4:-2], video_id[-2:], video_id, video_id, vbr) - if self._is_valid_url(fmt_url, video_id, format_id): - formats.append({ - 'format_id': format_id, - 'url': fmt_url, - 'vbr': vbr, - 'abr': abr, - 'width': width, - 'height': height, - }) + manifest_urls = self._download_json( + 'http://www.wat.tv/get/webhtml/' + video_id, video_id) + m3u8_url = manifest_urls.get('hls') + if m3u8_url: + formats.extend(self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', + 'm3u8_native', m3u8_id='hls', fatal=False)) + mpd_url = manifest_urls.get('mpd') + if mpd_url: + formats.extend(self._extract_mpd_formats( + mpd_url.replace('://das-q1.tf1.fr/', '://das-q1-ssl.tf1.fr/'), + video_id, mpd_id='dash', fatal=False)) + self._sort_formats(formats) date_diffusion = first_chapter.get('date_diffusion') or video_data.get('configv4', {}).get('estatS4') upload_date = unified_strdate(date_diffusion) if date_diffusion else None diff --git a/youtube_dlc/extractor/yahoo.py b/youtube_dlc/extractor/yahoo.py index e4615376c4..a17b10d6eb 100644 --- a/youtube_dlc/extractor/yahoo.py +++ b/youtube_dlc/extractor/yahoo.py @@ -177,46 +177,9 @@ class YahooIE(InfoExtractor): 'only_matching': True, }] - def _real_extract(self, url): - url, country, display_id = re.match(self._VALID_URL, url).groups() - if not country: - country = 'us' - else: - country = country.split('-')[0] - api_base = 'https://%s.yahoo.com/_td/api/resource/' % country - - for i, uuid in enumerate(['url=' + url, 'ymedia-alias=' + display_id]): - content = self._download_json( - api_base + 'content;getDetailView=true;uuids=["%s"]' % uuid, - display_id, 'Downloading content JSON metadata', fatal=i == 1) - if content: - item = content['items'][0] - break - - if item.get('type') != 'video': - entries = [] - - cover = item.get('cover') or {} - if cover.get('type') == 'yvideo': - cover_url = cover.get('url') - if cover_url: - entries.append(self.url_result( - cover_url, 'Yahoo', cover.get('uuid'))) - - for e in item.get('body', []): - if e.get('type') == 'videoIframe': - iframe_url = e.get('url') - if not iframe_url: - continue - entries.append(self.url_result(iframe_url)) - - return self.playlist_result( - entries, item.get('uuid'), - item.get('title'), item.get('summary')) - - video_id = item['uuid'] + def _extract_yahoo_video(self, video_id, country): video = self._download_json( - api_base + 'VideoService.videos;view=full;video_ids=["%s"]' % video_id, + 'https://%s.yahoo.com/_td/api/resource/VideoService.videos;view=full;video_ids=["%s"]' % (country, video_id), video_id, 'Downloading video JSON metadata')[0] title = video['title'] @@ -298,7 +261,6 @@ class YahooIE(InfoExtractor): 'id': video_id, 'title': self._live_title(title) if is_live else title, 'formats': formats, - 'display_id': display_id, 'thumbnails': thumbnails, 'description': clean_html(video.get('description')), 'timestamp': parse_iso8601(video.get('publish_time')), @@ -311,6 +273,44 @@ class YahooIE(InfoExtractor): 'episode_number': int_or_none(series_info.get('episode_number')), } + def _real_extract(self, url): + url, country, display_id = re.match(self._VALID_URL, url).groups() + if not country: + country = 'us' + else: + country = country.split('-')[0] + + item = self._download_json( + 'https://%s.yahoo.com/caas/content/article' % country, display_id, + 'Downloading content JSON metadata', query={ + 'url': url + })['items'][0]['data']['partnerData'] + + if item.get('type') != 'video': + entries = [] + + cover = item.get('cover') or {} + if cover.get('type') == 'yvideo': + cover_url = cover.get('url') + if cover_url: + entries.append(self.url_result( + cover_url, 'Yahoo', cover.get('uuid'))) + + for e in (item.get('body') or []): + if e.get('type') == 'videoIframe': + iframe_url = e.get('url') + if not iframe_url: + continue + entries.append(self.url_result(iframe_url)) + + return self.playlist_result( + entries, item.get('uuid'), + item.get('title'), item.get('summary')) + + info = self._extract_yahoo_video(item['uuid'], country) + info['display_id'] = display_id + return info + class YahooSearchIE(SearchInfoExtractor): IE_DESC = 'Yahoo screen search' diff --git a/youtube_dlc/options.py b/youtube_dlc/options.py index 97e8964d61..8b8c81c35c 100644 --- a/youtube_dlc/options.py +++ b/youtube_dlc/options.py @@ -842,6 +842,10 @@ def parseOpts(overrideArguments=None): '-o', '--output', dest='outtmpl', metavar='TEMPLATE', help='Output filename template, see "OUTPUT TEMPLATE" for details') + filesystem.add_option( + '--output-na-placeholder', + dest='outtmpl_na_placeholder', metavar='PLACEHOLDER', default='NA', + help=('Placeholder value for unavailable meta fields in output filename template (default is "%default")')) filesystem.add_option( '--autonumber-size', dest='autonumber_size', metavar='NUMBER', type=int, @@ -997,7 +1001,7 @@ def parseOpts(overrideArguments=None): postproc.add_option( '-x', '--extract-audio', action='store_true', dest='extractaudio', default=False, - help='Convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)') + help='Convert video files to audio-only files (requires ffmpeg/avconv and ffprobe/avprobe)') postproc.add_option( '--audio-format', metavar='FORMAT', dest='audioformat', default='best', help='Specify audio format: "best", "aac", "flac", "mp3", "m4a", "opus", "vorbis", or "wav"; "%default" by default; No effect without -x')