w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[condenast] Fix extraction (closes #14196, closes #14207)

Browse source
This commit is contained in:
Sergey M․ 2017-09-15 01:59:47 +07:00
parent fad9fc537d
commit c46680fb2a
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 32 additions and 22 deletions
Download patch file Download diff file Expand all files Collapse all files

38
youtube_dl/extractor/condenast.py
View file

@ -116,16 +116,16 @@ class CondeNastIE(InfoExtractor):
entries = [self.url_result(build_url(path), 'CondeNast') for path in paths] entries = [self.url_result(build_url(path), 'CondeNast') for path in paths]
return self.playlist_result(entries, playlist_title=title) return self.playlist_result(entries, playlist_title=title)
def _extract_video_params(self, webpage): def _extract_video_params(self, webpage, display_id):
query = {} query = self._parse_json(
params = self._search_regex( self._search_regex(
r'(?s)var params = {(.+?)}[;,]', webpage, 'player params', default=None) r'(?s)var\s+params\s*=\s*({.+?})[;,]', webpage, 'player params',
if params: default='{}'),
query.update({ display_id, transform_source=js_to_json, fatal=False)
'videoId': self._search_regex(r'videoId: [\'"](.+?)[\'"]', params, 'video id'), if query:
'playerId': self._search_regex(r'playerId: [\'"](.+?)[\'"]', params, 'player id'), query['videoId'] = self._search_regex(
'target': self._search_regex(r'target: [\'"](.+?)[\'"]', params, 'target'), r'(?:data-video-id=|currentVideoId\s*=\s*)["\']([\da-f]+)',
}) webpage, 'video id', default=None)
else: else:
params = extract_attributes(self._search_regex( params = extract_attributes(self._search_regex(
r'(<[^>]+data-js="video-player"[^>]+>)', r'(<[^>]+data-js="video-player"[^>]+>)',
@ -141,17 +141,27 @@ class CondeNastIE(InfoExtractor):
video_id = params['videoId'] video_id = params['videoId']
video_info = None video_info = None
# New API path
query = params.copy()
query['embedType'] = 'inline'
info_page = self._download_json(
'http://player.cnevids.com/embed-api.json', video_id,
'Downloading embed info', fatal=False, query=query)
# Old fallbacks
if not info_page:
if params.get('playerId'): if params.get('playerId'):
info_page = self._download_json( info_page = self._download_json(
'http://player.cnevids.com/player/video.js', 'http://player.cnevids.com/player/video.js', video_id,
video_id, 'Downloading video info', fatal=False, query=params) 'Downloading video info', fatal=False, query=params)
if info_page: if info_page:
video_info = info_page.get('video') video_info = info_page.get('video')
if not video_info: if not video_info:
info_page = self._download_webpage( info_page = self._download_webpage(
'http://player.cnevids.com/player/loader.js', 'http://player.cnevids.com/player/loader.js',
video_id, 'Downloading loader info', query=params) video_id, 'Downloading loader info', query=params)
else: if not video_info:
info_page = self._download_webpage( info_page = self._download_webpage(
'https://player.cnevids.com/inline/video/%s.js' % video_id, 'https://player.cnevids.com/inline/video/%s.js' % video_id,
video_id, 'Downloading inline info', query={ video_id, 'Downloading inline info', query={
@ -215,7 +225,7 @@ class CondeNastIE(InfoExtractor):
if url_type == 'series': if url_type == 'series':
return self._extract_series(url, webpage) return self._extract_series(url, webpage)
else: else:
params = self._extract_video_params(webpage) params = self._extract_video_params(webpage, display_id)
info = self._search_json_ld( info = self._search_json_ld(
webpage, display_id, fatal=False) webpage, display_id, fatal=False)
info.update(self._extract_video(params)) info.update(self._extract_video(params))