mirrors/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-07-10 19:03:29 +00:00
Code Issues Projects Releases Wiki Activity

[Go] Update extractor and tests for current sites and API version

Browse source 
Fixes yt-dl version of https://github.com/yt-dlp/yt-dlp/issues/2764
This commit is contained in:
dirkf 2022-02-15 02:48:44 +00:00
parent 74f8cc48af
commit 54e9d638f2
1 changed files with 95 additions and 28 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

123
youtube_dl/extractor/go.py
View file

@ -20,10 +20,12 @@ class GoIE(AdobePassIE):
'abc': { 'abc': {
'brand': '001', 'brand': '001',
'requestor_id': 'ABC', 'requestor_id': 'ABC',
'go': True,
}, },
'freeform': { 'freeform': {
'brand': '002', 'brand': '002',
'requestor_id': 'ABCFamily', 'requestor_id': 'ABCFamily',
'go': True,
}, },
'watchdisneychannel': { 'watchdisneychannel': {
'brand': '004', 'brand': '004',
@ -40,6 +42,7 @@ class GoIE(AdobePassIE):
'disneynow': { 'disneynow': {
'brand': '011', 'brand': '011',
'resource_id': 'Disney', 'resource_id': 'Disney',
'go': True,
}, },
'fxnow.fxnetworks': { 'fxnow.fxnetworks': {
'brand': '025', 'brand': '025',
@ -48,15 +51,19 @@ class GoIE(AdobePassIE):
} }
_VALID_URL = r'''(?x) _VALID_URL = r'''(?x)
https?:// https?://
(?: (?P<sub_domain>
(?:(?P<sub_domain>%s)\.)?go| (?:(?:%(sites)s)\.)?go|fxnow\.fxnetworks|
(?P<sub_domain_2>abc|freeform|disneynow|fxnow\.fxnetworks) (?:www\.)?(?:%(sites)s)
)\.com/ )\.com/
(?: (?:
(?:[^/]+/)*(?P<id>[Vv][Dd][Kk][Aa]\w+)| (?:[^/]+/)*(?P<id>[Vv][Dd][Kk][Aa]\w+)|
(?:[^/]+/)*(?P<display_id>[^/?\#]+) (?:[^/]+/)*(?P<display_id>[^/?\#]+)
) )
''' % '|'.join(list(_SITE_INFO.keys())) ''' % {
'sites':
# keep _SITE_INFO in scope
(lambda s: '|'.join(re.escape(k) for k in s.keys() if s[k].get('go')))(_SITE_INFO),
}
_TESTS = [{ _TESTS = [{
'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643', 'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643',
'info_dict': { 'info_dict': {
@ -70,14 +77,9 @@ class GoIE(AdobePassIE):
'skip_download': True, 'skip_download': True,
}, },
'skip': 'This content is no longer available.', 'skip': 'This content is no longer available.',
}, { },
'url': 'http://watchdisneyxd.go.com/doraemon', # Disney XD app withdrawn 2018: 'http://watchdisneyxd.go.com/doraemon',
'info_dict': { {
'title': 'Doraemon',
'id': 'SH55574025',
},
'playlist_mincount': 51,
}, {
'url': 'http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood', 'url': 'http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood',
'info_dict': { 'info_dict': {
'id': 'VDKA3609139', 'id': 'VDKA3609139',
@ -85,23 +87,37 @@ class GoIE(AdobePassIE):
'title': 'This Guilty Blood', 'title': 'This Guilty Blood',
'description': 'md5:f18e79ad1c613798d95fdabfe96cd292', 'description': 'md5:f18e79ad1c613798d95fdabfe96cd292',
'age_limit': 14, 'age_limit': 14,
'duration': 2544,
'episode': 'Episode 1',
'thumbnail': r're:https?://.*?\.jpg',
'season_number': 2,
'episode_number': 1,
'season': 'Season 2',
'series': 'Shadowhunters',
}, },
'params': { 'params': {
'geo_bypass_ip_block': '3.244.239.0/24', 'geo_bypass_ip_block': '6.48.97.0/24',
# m3u8 download # m3u8 download
'skip_download': True, 'skip_download': True,
}, },
}, { }, {
'url': 'https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet', 'url': 'https://abc.com/shows/the-rookie/episode-guide/season-04/13-fight-or-flight',
'info_dict': { 'info_dict': {
'id': 'VDKA13435179', 'id': 'VDKA26139487',
'ext': 'mp4', 'ext': 'mp4',
'title': 'The Bet', 'title': 'Fight or Flight',
'description': 'md5:c66de8ba2e92c6c5c113c3ade84ab404', 'episode': 'Episode 13',
'thumbnail': r're:https?://.*?\.jpg',
'series': 'The Rookie',
'description': 'md5:8caf91de9806a1c5f79823059fe80267',
'duration': 2575,
'episode_number': 13,
'season_number': 4,
'season': 'Season 4',
'age_limit': 14, 'age_limit': 14,
}, },
'params': { 'params': {
'geo_bypass_ip_block': '3.244.239.0/24', 'geo_bypass_ip_block': '6.48.97.0/24',
# m3u8 download # m3u8 download
'skip_download': True, 'skip_download': True,
}, },
@ -112,9 +128,13 @@ class GoIE(AdobePassIE):
'ext': 'mp4', 'ext': 'mp4',
'title': 'First Look: Better Things - Season 2', 'title': 'First Look: Better Things - Season 2',
'description': 'md5:fa73584a95761c605d9d54904e35b407', 'description': 'md5:fa73584a95761c605d9d54904e35b407',
'duration': 161,
'series': 'Better Things',
'age_limit': 14,
'thumbnail': r're:https?://.*?\.jpg',
}, },
'params': { 'params': {
'geo_bypass_ip_block': '3.244.239.0/24', 'geo_bypass_ip_block': '6.48.97.0/24',
# m3u8 download # m3u8 download
'skip_download': True, 'skip_download': True,
}, },
@ -125,6 +145,14 @@ class GoIE(AdobePassIE):
'ext': 'mp4', 'ext': 'mp4',
'title': 'Pilot', 'title': 'Pilot',
'description': 'md5:74306df917cfc199d76d061d66bebdb4', 'description': 'md5:74306df917cfc199d76d061d66bebdb4',
'season': 'Season 1',
'episode': 'Episode 1',
'series': 'Modern Family',
'season_number': 1,
'duration': 1301,
'episode_number': 1,
'age_limit': 0,
'thumbnail': r're:https?://.*?\.jpg',
}, },
'params': { 'params': {
# m3u8 download # m3u8 download
@ -147,17 +175,48 @@ class GoIE(AdobePassIE):
}, { }, {
'url': 'https://disneynow.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013', 'url': 'https://disneynow.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013',
'only_matching': True, 'only_matching': True,
}, {
'url': 'https://www.freeform.com/shows/cruel-summer/episode-guide/season-01/01-happy-birthday-jeanette-turner',
'only_matching': True,
}, {
'url': 'https://disneynow.com/shows/ducktales-disney-channel/season-02/episode-09-the-outlaw-scrooge-mcduck/vdka9680773',
'info_dict': {
'id': 'VDKA9680773',
'ext': 'mp4',
'season_number': 2,
'title': 'The Outlaw Scrooge McDuck!',
'episode': 'Episode 9',
'season': 'Season 2',
'episode_number': 9,
'age_limit': 7,
'series': 'DuckTales',
'description': 'md5:3d450c1094a5e7544ac094f1e6da2827',
'duration': 1348,
'thumbnail': r're:https?://.*?\.jpg',
},
'params': {
# AES-128: ffmpeg
'skip_download': True,
},
}, {
'url': 'https://disneynow.com/shows/ducktales-disney-channel',
'info_dict': {
'title': 'DuckTales TV Show',
'id': 'SH553923438',
},
'playlist_mincount': 33,
'expected_warnings': ['Ignoring subtitle tracks', ],
}] }]
def _extract_videos(self, brand, video_id='-1', show_id='-1'): def _extract_videos(self, brand, video_id='-1', show_id='-1'):
display_id = video_id if video_id != '-1' else show_id display_id = video_id if video_id != '-1' else show_id
return self._download_json( return self._download_json(
'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/%s/001/-1/%s/-1/%s/-1/-1.json' % (brand, show_id, video_id), 'http://api.contents.watchabc.go.com/vp2/ws/contents/4000/videos/%s/001/-1/%s/-1/%s/-1/-1.json' % (brand, show_id, video_id),
display_id)['video'] display_id)['video']
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
sub_domain = mobj.group('sub_domain') or mobj.group('sub_domain_2') sub_domain = re.sub(r'^(?:www\.)?(.+?)(?:\.go)?$', r'\1', mobj.group('sub_domain') or '')
video_id, display_id = mobj.group('id', 'display_id') video_id, display_id = mobj.group('id', 'display_id')
site_info = self._SITE_INFO.get(sub_domain, {}) site_info = self._SITE_INFO.get(sub_domain, {})
brand = site_info.get('brand') brand = site_info.get('brand')
@ -181,26 +240,33 @@ class GoIE(AdobePassIE):
( (
# There may be inner quotes, e.g. data-video-id="'VDKA3609139'" # There may be inner quotes, e.g. data-video-id="'VDKA3609139'"
# from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood # from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood
r'data-video-id=["\']*(VDKA\w+)', r'data-video-id\s*=\s*["\']{,2}(VDKA\w+)',
# page.analytics.videoIdCode # page.analytics.videoIdCode
r'\bvideoIdCode["\']\s*:\s*["\']((?:vdka|VDKA)\w+)', r'\bvideoIdCode["\']\s*:\s*["\']((?:vdka|VDKA)\w+)',
# This obsolete pattern, if matched, overrides detection of DisneyNow show pages
# https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet # https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet
r'\b(?:video)?id["\']\s*:\s*["\'](VDKA\w+)' # r'\b(?:video)?id["\']\s*:\s*["\'](VDKA\w+)'
), webpage, 'video id', default=video_id) ), webpage, 'video id', default=video_id)
if not site_info: if not site_info:
brand = self._search_regex( brand = self._search_regex(
(r'data-brand=\s*["\']\s*(\d+)', (r'data-brand=\s*["\']\s*(\d+)',
r'data-page-brand=\s*["\']\s*(\d+)'), webpage, 'brand', r'data-page-brand=\s*["\']\s*(\d+)',
default='004') r'"brand"\s*:\s*"(\d+)"'), webpage, 'brand',
# default to a brand that has an active domain
default='011')
site_info = next( site_info = next(
si for _, si in self._SITE_INFO.items() si for si in self._SITE_INFO.values()
if si.get('brand') == brand) if si.get('brand') == brand)
if not video_id: if not video_id:
# show extraction works for Disney, DisneyJunior and DisneyXD # show extraction works for Disney, DisneyJunior and DisneyXD
# ABC and Freeform has different layout # ABC and Freeform has different layout
show_id = self._search_regex(r'data-show-id=["\']*(SH\d+)', webpage, 'show id') show_id = self._search_regex(r'data-show-id=["\']*(SH\d+)', webpage, 'show id')
videos = self._extract_videos(brand, show_id=show_id) videos = self._extract_videos(brand, show_id=show_id)
show_title = self._search_regex(r'data-show-title="([^"]+)"', webpage, 'show title', fatal=False) show_title = (
self._search_regex(r'data-show-title="([^"]+)"', webpage, 'show title', default=None)
or self._og_search_title(webpage, fatal=False))
if show_title:
show_title = re.sub(r'^(?:Watch\s+)?(.+?)(?:\s*\|\s*Disney.*)?$', r'\1', show_title)
entries = [] entries = []
for video in videos: for video in videos:
entries.append(self.url_result( entries.append(self.url_result(
@ -262,7 +328,8 @@ class GoIE(AdobePassIE):
if re.search(r'(?:/mp4/source/|_source\.mp4)', asset_url): if re.search(r'(?:/mp4/source/|_source\.mp4)', asset_url):
f.update({ f.update({
'format_id': ('%s-' % format_id if format_id else '') + 'SOURCE', 'format_id': ('%s-' % format_id if format_id else '') + 'SOURCE',
'preference': 1, 'quality': 1,
# 'preference': 1,
}) })
else: else:
mobj = re.search(r'/(\d+)x(\d+)/', asset_url) mobj = re.search(r'/(\d+)x(\d+)/', asset_url)