[yahoo] Fix extraction (#435)

Fixes: https://github.com/ytdl-org/youtube-dl/issues/28290

Co-authored-by: llacb47, pukkandan
This commit is contained in:
LE 2021-06-24 11:57:48 -04:00 committed by GitHub
parent d534c4520b
commit 412cce82b0
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -22,6 +22,7 @@
) )
from .brightcove import BrightcoveNewIE from .brightcove import BrightcoveNewIE
from .youtube import YoutubeIE
class YahooIE(InfoExtractor): class YahooIE(InfoExtractor):
@ -38,6 +39,7 @@ class YahooIE(InfoExtractor):
'timestamp': 1369812016, 'timestamp': 1369812016,
'upload_date': '20130529', 'upload_date': '20130529',
}, },
'skip': 'No longer exists',
}, { }, {
'url': 'https://screen.yahoo.com/community/community-sizzle-reel-203225340.html?format=embed', 'url': 'https://screen.yahoo.com/community/community-sizzle-reel-203225340.html?format=embed',
'md5': '7993e572fac98e044588d0b5260f4352', 'md5': '7993e572fac98e044588d0b5260f4352',
@ -50,6 +52,7 @@ class YahooIE(InfoExtractor):
'timestamp': 1406838636, 'timestamp': 1406838636,
'upload_date': '20140731', 'upload_date': '20140731',
}, },
'skip': 'Unfortunately, this video is not available in your region',
}, { }, {
'url': 'https://uk.screen.yahoo.com/editor-picks/cute-raccoon-freed-drain-using-091756545.html', 'url': 'https://uk.screen.yahoo.com/editor-picks/cute-raccoon-freed-drain-using-091756545.html',
'md5': '71298482f7c64cbb7fa064e4553ff1c1', 'md5': '71298482f7c64cbb7fa064e4553ff1c1',
@ -61,7 +64,8 @@ class YahooIE(InfoExtractor):
'duration': 97, 'duration': 97,
'timestamp': 1414489862, 'timestamp': 1414489862,
'upload_date': '20141028', 'upload_date': '20141028',
} },
'skip': 'No longer exists',
}, { }, {
'url': 'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html', 'url': 'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html',
'md5': '88e209b417f173d86186bef6e4d1f160', 'md5': '88e209b417f173d86186bef6e4d1f160',
@ -120,6 +124,7 @@ class YahooIE(InfoExtractor):
'season_number': 6, 'season_number': 6,
'episode_number': 1, 'episode_number': 1,
}, },
'skip': 'No longer exists',
}, { }, {
# ytwnews://cavideo/ # ytwnews://cavideo/
'url': 'https://tw.video.yahoo.com/movie-tw/單車天使-中文版預-092316541.html', 'url': 'https://tw.video.yahoo.com/movie-tw/單車天使-中文版預-092316541.html',
@ -156,7 +161,7 @@ class YahooIE(InfoExtractor):
'id': '352CFDOQrKg', 'id': '352CFDOQrKg',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Kyndal Inskeep "Performs the Hell Out of" Sia\'s "Elastic Heart" - The Voice Knockouts 2019', 'title': 'Kyndal Inskeep "Performs the Hell Out of" Sia\'s "Elastic Heart" - The Voice Knockouts 2019',
'description': 'md5:35b61e94c2ae214bc965ff4245f80d11', 'description': 'md5:7fe8e3d5806f96002e55f190d1d94479',
'uploader': 'The Voice', 'uploader': 'The Voice',
'uploader_id': 'NBCTheVoice', 'uploader_id': 'NBCTheVoice',
'upload_date': '20191029', 'upload_date': '20191029',
@ -165,7 +170,7 @@ class YahooIE(InfoExtractor):
'params': { 'params': {
'playlistend': 2, 'playlistend': 2,
}, },
'expected_warnings': ['HTTP Error 404'], 'expected_warnings': ['HTTP Error 404', 'Ignoring subtitle tracks'],
}, { }, {
'url': 'https://malaysia.news.yahoo.com/video/bystanders-help-ontario-policeman-bust-190932818.html', 'url': 'https://malaysia.news.yahoo.com/video/bystanders-help-ontario-policeman-bust-190932818.html',
'only_matching': True, 'only_matching': True,
@ -280,12 +285,13 @@ def _real_extract(self, url):
else: else:
country = country.split('-')[0] country = country.split('-')[0]
item = self._download_json( items = self._download_json(
'https://%s.yahoo.com/caas/content/article' % country, display_id, 'https://%s.yahoo.com/caas/content/article' % country, display_id,
'Downloading content JSON metadata', query={ 'Downloading content JSON metadata', query={
'url': url 'url': url
})['items'][0]['data']['partnerData'] })['items'][0]
item = items['data']['partnerData']
if item.get('type') != 'video': if item.get('type') != 'video':
entries = [] entries = []
@ -299,9 +305,19 @@ def _real_extract(self, url):
for e in (item.get('body') or []): for e in (item.get('body') or []):
if e.get('type') == 'videoIframe': if e.get('type') == 'videoIframe':
iframe_url = e.get('url') iframe_url = e.get('url')
if not iframe_url: if iframe_url:
continue entries.append(self.url_result(iframe_url))
if item.get('type') == 'storywithleadvideo':
iframe_url = try_get(item, lambda x: x['meta']['player']['url'])
if iframe_url:
entries.append(self.url_result(iframe_url)) entries.append(self.url_result(iframe_url))
else:
self.report_warning("Yahoo didn't provide an iframe url for this storywithleadvideo")
if items.get('markup'):
entries.extend(
self.url_result(yt_url) for yt_url in YoutubeIE._extract_urls(items['markup']))
return self.playlist_result( return self.playlist_result(
entries, item.get('uuid'), entries, item.get('uuid'),