R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[XTube] Fix extraction.

Browse Source
This commit is contained in:
Paul LaMendola 2016-07-02 13:09:03 -04:00
parent 397b305cfe
commit bac2ed765f
1 changed files with 16 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
youtube_dl/extractor/xtube.py
View File

@ -26,7 +26,6 @@ class XTubeIE(InfoExtractor):
'title': 'strange erotica', 'title': 'strange erotica',
'description': 'contains:an ET kind of thing', 'description': 'contains:an ET kind of thing',
'uploader': 'greenshowers', 'uploader': 'greenshowers',
'duration': 450,
'age_limit': 18, 'age_limit': 18,
} }
}, { }, {
@ -51,38 +50,39 @@ class XTubeIE(InfoExtractor):
req.add_header('Cookie', 'age_verified=1; cookiesAccepted=1') req.add_header('Cookie', 'age_verified=1; cookiesAccepted=1')
webpage = self._download_webpage(req, display_id) webpage = self._download_webpage(req, display_id)
flashvars = self._parse_json( sources = self._search_regex(r'sources:\s*({.+?}),', webpage, 'sources')
self._search_regex(
r'xt\.playerOps\s*=\s*({.+?});', webpage, 'player ops'),
video_id)['flashvars']
title = flashvars.get('title') or self._search_regex( sourcesdict = self._parse_json(sources, video_id)
r'<h1>([^<]+)</h1>', webpage, 'title')
video_url = compat_urllib_parse_unquote(flashvars['video_url']) formats = []
duration = int_or_none(flashvars.get('video_duration')) for formatkey in sourcesdict.keys():
curformat = {}
curformat['height'] = int(formatkey)
curformat['url'] = sourcesdict[formatkey]
formats.append(curformat)
formats = self._sort_formats(formats)
title = self._search_regex(
r'videoTitle:\s*\'(.+?)\',', webpage, 'title')
uploader = self._search_regex( uploader = self._search_regex(
r'<input[^>]+name="contentOwnerId"[^>]+value="([^"]+)"', r'<span class=\"nickname\">([^<]+)',
webpage, 'uploader', fatal=False) webpage, 'uploader', fatal=False)
description = self._search_regex( description = self._search_regex(
r'</h1>\s*<p>([^<]+)', webpage, 'description', fatal=False) r'</h1>\s*<p>([^<]+)', webpage, 'description', fatal=False)
view_count = str_to_int(self._search_regex( view_count = str_to_int(self._search_regex(
r'<dt>Views:</dt>\s*<dd>([\d,\.]+)</dd>', r'<dt>Views:</dt>\s*<dd>([\d,\.]+)</dd>',
webpage, 'view count', fatal=False)) webpage, 'view count', fatal=False))
comment_count = str_to_int(self._html_search_regex(
r'>Comments? \(([\d,\.]+)\)<',
webpage, 'comment count', fatal=False))
return { return {
'id': video_id, 'id': video_id,
'display_id': display_id, 'display_id': display_id,
'url': video_url, 'formats': formats,
'title': title, 'title': title,
'description': description, 'description': description,
'uploader': uploader, 'uploader': uploader,
'duration': duration,
'view_count': view_count, 'view_count': view_count,
'comment_count': comment_count,
'age_limit': 18, 'age_limit': 18,
} }