From 5e1c39ac853bfe4da7feda2a48544cb5811873d9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Petr=20Van=C4=9Bk?= <arkamar@atlas.cz> Date: Wed, 17 Jul 2019 17:47:53 +0200 Subject: [PATCH 1/7] [extractor/common] Fix typo in thumbnails resolution description (#21817) --- youtube_dl/extractor/common.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 9c3e9eec6..859786617 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -220,7 +220,7 @@ class InfoExtractor(object): * "preference" (optional, int) - quality of the image * "width" (optional, int) * "height" (optional, int) - * "resolution" (optional, string "{width}x{height"}, + * "resolution" (optional, string "{width}x{height}", deprecated) * "filesize" (optional, int) thumbnail: Full URL to a video thumbnail image. From 9c1da4a9f9fc17cffc2fa2261030c66d2a032a58 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 20 Jul 2019 23:08:26 +0700 Subject: [PATCH 2/7] [extractor/generic] Restrict --default-search schemeless URLs detection pattern (closes #21842) --- 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 77e217460..d34fc4b15 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -2226,7 +2226,7 @@ class GenericIE(InfoExtractor): default_search = 'fixup_error' if default_search in ('auto', 'auto_warning', 'fixup_error'): - if '/' in url: + if re.match(r'^[^\s/]+\.[^\s/]+/', url): self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http') return self.url_result('http://' + url) elif default_search != 'fixup_error': From 2e18adec98a44ca839cbaaed7ce27d8d07f54cfc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 20 Jul 2019 23:46:34 +0700 Subject: [PATCH 3/7] [youtube:playlist] Relax _VIDEO_RE (closes #21844) --- youtube_dl/extractor/youtube.py | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index a87a46b3b..aa316ba88 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -2432,7 +2432,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): (%(playlist_id)s) )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE} _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s' - _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?' + _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:&(?:[^"]*?index=(?P<index>\d+))?(?:[^>]+>(?P<title>[^<]+))?)?' IE_NAME = 'youtube:playlist' _TESTS = [{ 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', @@ -2556,6 +2556,16 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): 'noplaylist': True, 'skip_download': True, }, + }, { + # https://github.com/ytdl-org/youtube-dl/issues/21844 + 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', + 'info_dict': { + 'title': 'Data Analysis with Dr Mike Pound', + 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', + 'uploader_id': 'Computerphile', + 'uploader': 'Computerphile', + }, + 'playlist_mincount': 11, }, { 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21', 'only_matching': True, From 13a75688a55f32cde316b0f7d5992ff4a1f6d279 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 21 Jul 2019 00:01:46 +0700 Subject: [PATCH 4/7] [youtube] Fix some tests --- youtube_dl/extractor/youtube.py | 30 ++++++++++++++++++++++++++---- 1 file changed, 26 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index aa316ba88..b2c714505 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -2455,6 +2455,8 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): 'info_dict': { 'title': '29C3: Not my department', 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', + 'uploader': 'Christiaan008', + 'uploader_id': 'ChRiStIaAn008', }, 'playlist_count': 95, }, { @@ -2463,6 +2465,8 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): 'info_dict': { 'title': '[OLD]Team Fortress 2 (Class-based LP)', 'id': 'PLBB231211A4F62143', + 'uploader': 'Wickydoo', + 'uploader_id': 'Wickydoo', }, 'playlist_mincount': 26, }, { @@ -2471,6 +2475,8 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): 'info_dict': { 'title': 'Uploads from Cauchemar', 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q', + 'uploader': 'Cauchemar', + 'uploader_id': 'Cauchemar89', }, 'playlist_mincount': 799, }, { @@ -2488,13 +2494,17 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): 'info_dict': { 'title': 'JODA15', 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', + 'uploader': 'milan', + 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw', } }, { 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', 'playlist_mincount': 485, 'info_dict': { - 'title': '2017 華語最新單曲 (2/24更新)', + 'title': '2018 Chinese New Singles (11/6 updated)', 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', + 'uploader': 'LBK', + 'uploader_id': 'sdragonfang', } }, { 'note': 'Embedded SWF player', @@ -2503,13 +2513,16 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): 'info_dict': { 'title': 'JODA7', 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ', - } + }, + 'skip': 'This playlist does not exist', }, { 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos', 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA', 'info_dict': { 'title': 'Uploads from Interstellar Movie', 'id': 'UUXw-G3eDE9trcvY2sBMM_aA', + 'uploader': 'Interstellar Movie', + 'uploader_id': 'InterstellarMovie1', }, 'playlist_mincount': 21, }, { @@ -2534,6 +2547,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): 'params': { 'skip_download': True, }, + 'skip': 'This video is not available.', 'add_ie': [YoutubeIE.ie_key()], }, { 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5', @@ -2545,7 +2559,6 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): 'uploader_id': 'backuspagemuseum', 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum', 'upload_date': '20161008', - 'license': 'Standard YouTube License', 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a', 'categories': ['Nonprofits & Activism'], 'tags': list, @@ -2732,6 +2745,8 @@ class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor): 'info_dict': { 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w', 'title': 'Uploads from lex will', + 'uploader': 'lex will', + 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', } }, { 'note': 'Age restricted channel', @@ -2741,6 +2756,8 @@ class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor): 'info_dict': { 'id': 'UUs0ifCMCm1icqRbqhUINa0w', 'title': 'Uploads from Deus Ex', + 'uploader': 'Deus Ex', + 'uploader_id': 'DeusExOfficial', }, }, { 'url': 'https://invidio.us/channel/UC23qupoDRn9YOAVzeoxjOQA', @@ -2825,6 +2842,8 @@ class YoutubeUserIE(YoutubeChannelIE): 'info_dict': { 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ', 'title': 'Uploads from The Linux Foundation', + 'uploader': 'The Linux Foundation', + 'uploader_id': 'TheLinuxFoundation', } }, { # Only available via https://www.youtube.com/c/12minuteathlete/videos @@ -2834,6 +2853,8 @@ class YoutubeUserIE(YoutubeChannelIE): 'info_dict': { 'id': 'UUVjM-zV6_opMDx7WYxnjZiQ', 'title': 'Uploads from 12 Minute Athlete', + 'uploader': '12 Minute Athlete', + 'uploader_id': 'the12minuteathlete', } }, { 'url': 'ytuser:phihag', @@ -2927,7 +2948,7 @@ class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor): 'playlist_mincount': 4, 'info_dict': { 'id': 'ThirstForScience', - 'title': 'Thirst for Science', + 'title': 'ThirstForScience', }, }, { # with "Load more" button @@ -2944,6 +2965,7 @@ class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor): 'id': 'UCiU1dHvZObB2iP6xkJ__Icw', 'title': 'Chem Player', }, + 'skip': 'Blocked', }] From 3b446ab3519948980630e3328b971385826ffba8 Mon Sep 17 00:00:00 2001 From: Remita Amine <remitamine@gmail.com> Date: Sat, 20 Jul 2019 20:20:30 +0100 Subject: [PATCH 5/7] [discovery] add support go.discovery.com URLs --- youtube_dl/extractor/discovery.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/discovery.py b/youtube_dl/extractor/discovery.py index b70c307a7..9003545ce 100644 --- a/youtube_dl/extractor/discovery.py +++ b/youtube_dl/extractor/discovery.py @@ -19,9 +19,9 @@ from ..compat import compat_HTTPError class DiscoveryIE(DiscoveryGoBaseIE): _VALID_URL = r'''(?x)https?:// (?P<site> + (?:(?:www|go)\.)?discovery| (?:www\.)? (?: - discovery| investigationdiscovery| discoverylife| animalplanet| @@ -56,6 +56,9 @@ class DiscoveryIE(DiscoveryGoBaseIE): }, { 'url': 'https://www.investigationdiscovery.com/tv-shows/final-vision/full-episodes/final-vision', 'only_matching': True, + }, { + 'url': 'https://go.discovery.com/tv-shows/alaskan-bush-people/videos/follow-your-own-road', + 'only_matching': True, }] _GEO_COUNTRIES = ['US'] _GEO_BYPASS = False From ab794a553c36ddd690e2243450653c3ede43e606 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sun, 21 Jul 2019 13:20:21 +0700 Subject: [PATCH 6/7] [ctsnews] PEP 8 --- youtube_dl/extractor/ctsnews.py | 1 + 1 file changed, 1 insertion(+) diff --git a/youtube_dl/extractor/ctsnews.py b/youtube_dl/extractor/ctsnews.py index dcda7e89d..679f1d92e 100644 --- a/youtube_dl/extractor/ctsnews.py +++ b/youtube_dl/extractor/ctsnews.py @@ -5,6 +5,7 @@ from .common import InfoExtractor from ..utils import unified_timestamp from .youtube import YoutubeIE + class CtsNewsIE(InfoExtractor): IE_DESC = '華視新聞' _VALID_URL = r'https?://news\.cts\.com\.tw/[a-z]+/[a-z]+/\d+/(?P<id>\d+)\.html' From 608b8a4300fab7792e637fd9b7045adf1c0cb2aa Mon Sep 17 00:00:00 2001 From: Kyle <40903431+kylepw@users.noreply.github.com> Date: Mon, 22 Jul 2019 02:59:36 +0900 Subject: [PATCH 7/7] [yahoo:japannews] Add extractor (closes #21698) (#21265) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/yahoo.py | 131 +++++++++++++++++++++++++++++ 2 files changed, 132 insertions(+) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 15f54a214..06de556b7 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1448,6 +1448,7 @@ from .yahoo import ( YahooSearchIE, YahooGyaOPlayerIE, YahooGyaOIE, + YahooJapanNewsIE, ) from .yandexdisk import YandexDiskIE from .yandexmusic import ( diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index a3b5f00c8..e5ebdd180 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -1,12 +1,14 @@ # coding: utf-8 from __future__ import unicode_literals +import hashlib import itertools import json import re from .common import InfoExtractor, SearchInfoExtractor from ..compat import ( + compat_str, compat_urllib_parse, compat_urlparse, ) @@ -18,7 +20,9 @@ from ..utils import ( int_or_none, mimetype2ext, smuggle_url, + try_get, unescapeHTML, + url_or_none, ) from .brightcove import ( @@ -556,3 +560,130 @@ class YahooGyaOIE(InfoExtractor): 'https://gyao.yahoo.co.jp/player/%s/' % video_id.replace(':', '/'), YahooGyaOPlayerIE.ie_key(), video_id)) return self.playlist_result(entries, program_id) + + +class YahooJapanNewsIE(InfoExtractor): + IE_NAME = 'yahoo:japannews' + IE_DESC = 'Yahoo! Japan News' + _VALID_URL = r'https?://(?P<host>(?:news|headlines)\.yahoo\.co\.jp)[^\d]*(?P<id>\d[\d-]*\d)?' + _GEO_COUNTRIES = ['JP'] + _TESTS = [{ + 'url': 'https://headlines.yahoo.co.jp/videonews/ann?a=20190716-00000071-ann-int', + 'info_dict': { + 'id': '1736242', + 'ext': 'mp4', + 'title': 'ムン大統領が対日批判を強化“現金化”効果は?(テレビ朝日系(ANN)) - Yahoo!ニュース', + 'description': '韓国の元徴用工らを巡る裁判の原告が弁護士が差し押さえた三菱重工業の資産を売却して - Yahoo!ニュース(テレビ朝日系(ANN))', + 'thumbnail': r're:^https?://.*\.[a-zA-Z\d]{3,4}$', + }, + 'params': { + 'skip_download': True, + }, + }, { + # geo restricted + 'url': 'https://headlines.yahoo.co.jp/hl?a=20190721-00000001-oxv-l04', + 'only_matching': True, + }, { + 'url': 'https://headlines.yahoo.co.jp/videonews/', + 'only_matching': True, + }, { + 'url': 'https://news.yahoo.co.jp', + 'only_matching': True, + }, { + 'url': 'https://news.yahoo.co.jp/byline/hashimotojunji/20190628-00131977/', + 'only_matching': True, + }, { + 'url': 'https://news.yahoo.co.jp/feature/1356', + 'only_matching': True + }] + + def _extract_formats(self, json_data, content_id): + formats = [] + + video_data = try_get( + json_data, + lambda x: x['ResultSet']['Result'][0]['VideoUrlSet']['VideoUrl'], + list) + for vid in video_data or []: + delivery = vid.get('delivery') + url = url_or_none(vid.get('Url')) + if not delivery or not url: + continue + elif delivery == 'hls': + formats.extend( + self._extract_m3u8_formats( + url, content_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) + else: + formats.append({ + 'url': url, + 'format_id': 'http-%s' % compat_str(vid.get('bitrate', '')), + 'height': int_or_none(vid.get('height')), + 'width': int_or_none(vid.get('width')), + 'tbr': int_or_none(vid.get('bitrate')), + }) + self._remove_duplicate_formats(formats) + self._sort_formats(formats) + + return formats + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + host = mobj.group('host') + display_id = mobj.group('id') or host + + webpage = self._download_webpage(url, display_id) + + title = self._html_search_meta( + ['og:title', 'twitter:title'], webpage, 'title', default=None + ) or self._html_search_regex('<title>([^<]+)</title>', webpage, 'title') + + if display_id == host: + # Headline page (w/ multiple BC playlists) ('news.yahoo.co.jp', 'headlines.yahoo.co.jp/videonews/', ...) + stream_plists = re.findall(r'plist=(\d+)', webpage) or re.findall(r'plist["\']:\s*["\']([^"\']+)', webpage) + entries = [ + self.url_result( + smuggle_url( + 'http://players.brightcove.net/5690807595001/HyZNerRl7_default/index.html?playlistId=%s' % plist_id, + {'geo_countries': ['JP']}), + ie='BrightcoveNew', video_id=plist_id) + for plist_id in stream_plists] + return self.playlist_result(entries, playlist_title=title) + + # Article page + description = self._html_search_meta( + ['og:description', 'description', 'twitter:description'], + webpage, 'description', default=None) + thumbnail = self._og_search_thumbnail( + webpage, default=None) or self._html_search_meta( + 'twitter:image', webpage, 'thumbnail', default=None) + space_id = self._search_regex([ + r'<script[^>]+class=["\']yvpub-player["\'][^>]+spaceid=([^&"\']+)', + r'YAHOO\.JP\.srch\.\w+link\.onLoad[^;]+spaceID["\' ]*:["\' ]+([^"\']+)', + r'<!--\s+SpaceID=(\d+)' + ], webpage, 'spaceid') + + content_id = self._search_regex( + r'<script[^>]+class=["\']yvpub-player["\'][^>]+contentid=(?P<contentid>[^&"\']+)', + webpage, 'contentid', group='contentid') + + json_data = self._download_json( + 'https://feapi-yvpub.yahooapis.jp/v1/content/%s' % content_id, + content_id, + query={ + 'appid': 'dj0zaiZpPVZMTVFJR0FwZWpiMyZzPWNvbnN1bWVyc2VjcmV0Jng9YjU-', + 'output': 'json', + 'space_id': space_id, + 'domain': host, + 'ak': hashlib.md5('_'.join((space_id, host)).encode()).hexdigest(), + 'device_type': '1100', + }) + formats = self._extract_formats(json_data, content_id) + + return { + 'id': content_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'formats': formats, + }