etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-23 02:25:11 +00:00
Code Issues Projects Releases Wiki Activity

[vporn] Fix metadata extraction (#5560)

Browse source
This commit is contained in:
Sergey M․ 2015-04-30 21:25:17 +06:00
parent e01c56f9e1
commit cd298882cd
1 changed files with 10 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

22
youtube_dl/extractor/vporn.py
View file

@ -64,29 +64,29 @@ def _real_extract(self, url):
title = self._html_search_regex( title = self._html_search_regex(
r'videoname\s*=\s*\'([^\']+)\'', webpage, 'title').strip() r'videoname\s*=\s*\'([^\']+)\'', webpage, 'title').strip()
description = self._html_search_regex( description = self._html_search_regex(
r'<div class="description_txt">(.*?)</div>', webpage, 'description', fatal=False) r'class="(?:descr|description_txt)">(.*?)</div>',
webpage, 'description', fatal=False)
thumbnail = self._html_search_regex( thumbnail = self._html_search_regex(
r'flashvars\.imageUrl\s*=\s*"([^"]+)"', webpage, 'description', fatal=False, default=None) r'flashvars\.imageUrl\s*=\s*"([^"]+)"', webpage, 'description', fatal=False, default=None)
if thumbnail: if thumbnail:
thumbnail = 'http://www.vporn.com' + thumbnail thumbnail = 'http://www.vporn.com' + thumbnail
uploader = self._html_search_regex( uploader = self._html_search_regex(
r'(?s)UPLOADED BY.*?<a href="/user/[^"]+">([^<]+)</a>', r'(?s)Uploaded by:.*?<a href="/user/[^"]+">([^<]+)</a>',
webpage, 'uploader', fatal=False) webpage, 'uploader', fatal=False)
categories = re.findall(r'<a href="/cat/[^"]+">([^<]+)</a>', webpage) categories = re.findall(r'<a href="/cat/[^"]+">([^<]+)</a>', webpage)
duration = parse_duration(self._search_regex( duration = parse_duration(self._search_regex(
r'duration (\d+ min \d+ sec)', webpage, 'duration', fatal=False)) r'Runtime:\s*</span>\s*(\d+ min \d+ sec)',
webpage, 'duration', fatal=False))
view_count = str_to_int(self._html_search_regex( view_count = str_to_int(self._search_regex(
r'<span>([\d,\.]+) VIEWS</span>', webpage, 'view count', fatal=False)) r'class="views">([\d,\.]+) [Vv]iews<',
like_count = str_to_int(self._html_search_regex( webpage, 'view count', fatal=False))
r'<span id="like" class="n">([\d,\.]+)</span>', webpage, 'like count', fatal=False))
dislike_count = str_to_int(self._html_search_regex(
r'<span id="dislike" class="n">([\d,\.]+)</span>', webpage, 'dislike count', fatal=False))
comment_count = str_to_int(self._html_search_regex( comment_count = str_to_int(self._html_search_regex(
r'<h4>Comments \(<b>([\d,\.]+)</b>\)</h4>', webpage, 'comment count', fatal=False)) r"'Comments \(([\d,\.]+)\)'",
webpage, 'comment count', default=None))
formats = [] formats = []
@ -117,8 +117,6 @@ def _real_extract(self, url):
'categories': categories, 'categories': categories,
'duration': duration, 'duration': duration,
'view_count': view_count, 'view_count': view_count,
'like_count': like_count,
'dislike_count': dislike_count,
'comment_count': comment_count, 'comment_count': comment_count,
'age_limit': 18, 'age_limit': 18,
'formats': formats, 'formats': formats,