Merge pull request #7599 from lalinsky/fix-youtube
[youtube] More explicit player config JSON extraction (fixes #7468)
This commit is contained in:
commit
5ae17037a3
1 changed files with 30 additions and 8 deletions
|
@ -691,7 +691,23 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||||
{
|
{
|
||||||
'url': 'http://vid.plus/FlRa-iH7PGw',
|
'url': 'http://vid.plus/FlRa-iH7PGw',
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
}
|
},
|
||||||
|
{
|
||||||
|
# Title with JS-like syntax "};"
|
||||||
|
'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
|
||||||
|
'info_dict': {
|
||||||
|
'id': 'lsguqyKfVQg',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
|
||||||
|
'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
|
||||||
|
'upload_date': '20151119',
|
||||||
|
'uploader_id': 'IronSoulElf',
|
||||||
|
'uploader': 'IronSoulElf',
|
||||||
|
},
|
||||||
|
'params': {
|
||||||
|
'skip_download': True,
|
||||||
|
},
|
||||||
|
},
|
||||||
]
|
]
|
||||||
|
|
||||||
def __init__(self, *args, **kwargs):
|
def __init__(self, *args, **kwargs):
|
||||||
|
@ -875,16 +891,24 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||||
return {}
|
return {}
|
||||||
return sub_lang_list
|
return sub_lang_list
|
||||||
|
|
||||||
|
def _get_ytplayer_config(self, webpage):
|
||||||
|
patterns = [
|
||||||
|
r';ytplayer\.config\s*=\s*({.*?});ytplayer',
|
||||||
|
r';ytplayer\.config\s*=\s*({.*?});',
|
||||||
|
]
|
||||||
|
config = self._search_regex(patterns, webpage, 'ytconfig.player', default=None)
|
||||||
|
if config is not None:
|
||||||
|
return json.loads(uppercase_escape(config))
|
||||||
|
|
||||||
def _get_automatic_captions(self, video_id, webpage):
|
def _get_automatic_captions(self, video_id, webpage):
|
||||||
"""We need the webpage for getting the captions url, pass it as an
|
"""We need the webpage for getting the captions url, pass it as an
|
||||||
argument to speed up the process."""
|
argument to speed up the process."""
|
||||||
self.to_screen('%s: Looking for automatic captions' % video_id)
|
self.to_screen('%s: Looking for automatic captions' % video_id)
|
||||||
mobj = re.search(r';ytplayer.config = ({.*?});', webpage)
|
player_config = self._get_ytplayer_config(webpage)
|
||||||
err_msg = 'Couldn\'t find automatic captions for %s' % video_id
|
err_msg = 'Couldn\'t find automatic captions for %s' % video_id
|
||||||
if mobj is None:
|
if player_config is None:
|
||||||
self._downloader.report_warning(err_msg)
|
self._downloader.report_warning(err_msg)
|
||||||
return {}
|
return {}
|
||||||
player_config = json.loads(mobj.group(1))
|
|
||||||
try:
|
try:
|
||||||
args = player_config['args']
|
args = player_config['args']
|
||||||
caption_url = args['ttsurl']
|
caption_url = args['ttsurl']
|
||||||
|
@ -1091,10 +1115,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||||
age_gate = False
|
age_gate = False
|
||||||
video_info = None
|
video_info = None
|
||||||
# Try looking directly into the video webpage
|
# Try looking directly into the video webpage
|
||||||
mobj = re.search(r';ytplayer\.config\s*=\s*({.*?});', video_webpage)
|
ytplayer_config = self._get_ytplayer_config(video_webpage)
|
||||||
if mobj:
|
if ytplayer_config is not None:
|
||||||
json_code = uppercase_escape(mobj.group(1))
|
|
||||||
ytplayer_config = json.loads(json_code)
|
|
||||||
args = ytplayer_config['args']
|
args = ytplayer_config['args']
|
||||||
if args.get('url_encoded_fmt_stream_map'):
|
if args.get('url_encoded_fmt_stream_map'):
|
||||||
# Convert to the same format returned by compat_parse_qs
|
# Convert to the same format returned by compat_parse_qs
|
||||||
|
|
Loading…
Reference in a new issue