github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[sexu] Modernize (#4171)

Browse source
This commit is contained in:
Philipp Hagemeister 2014-11-13 15:20:49 +01:00
parent c47ec62b83
commit 3fa5bb3802
1 changed files with 8 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
youtube_dl/extractor/sexu.py
View file

@ -22,13 +22,11 @@ class SexuIE(InfoExtractor):
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
quality_arr = self._search_regex(r'sources:\s*\[([^\]]+)\]', webpage, 'quality formats') quality_arr = self._search_regex(
r'sources:\s*\[([^\]]+)\]', webpage, 'forrmat string')
formats = [{ formats = [{
'url': fmt[0].replace('\\', ''), 'url': fmt[0].replace('\\', ''),
'format_id': fmt[1], 'format_id': fmt[1],
@ -37,15 +35,17 @@ def _real_extract(self, url):
self._sort_formats(formats) self._sort_formats(formats)
title = self._html_search_regex( title = self._html_search_regex(
r'<title>([^<]+)\s*-\s*Sexu.Com</title>', webpage, 'title') r'<title>([^<]+)\s*-\s*Sexu\.Com</title>', webpage, 'title')
description = self._html_search_meta('description', webpage, 'description') description = self._html_search_meta(
'description', webpage, 'description')
thumbnail = self._html_search_regex( thumbnail = self._html_search_regex(
r'image:\s*"([^"]+)"', r'image:\s*"([^"]+)"',
webpage, 'thumbnail', fatal=False) webpage, 'thumbnail', fatal=False)
categories_str = self._html_search_meta('keywords', webpage, 'categories', fatal=False) categories_str = self._html_search_meta(
'keywords', webpage, 'categories')
categories = ( categories = (
None if categories_str is None None if categories_str is None
else categories_str.split(',')) else categories_str.split(','))