etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-30 02:01:05 +00:00
Code Issues Projects Releases Wiki Activity

[sockshare] Simplify (#3268)

Browse source
This commit is contained in:
Philipp Hagemeister 2014-07-21 13:25:59 +02:00
parent 7dabd2ac45
commit 06c155420f
1 changed files with 9 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

17
youtube_dl/extractor/sockshare.py
View file

@ -5,7 +5,6 @@
ExtractorError, ExtractorError,
compat_urllib_parse, compat_urllib_parse,
compat_urllib_request, compat_urllib_request,
determine_ext,
) )
import re import re
@ -34,7 +33,7 @@ def _real_extract(self, url):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
if re.search(self._FILE_DELETED_REGEX, webpage) is not None: if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
raise ExtractorError(u'Video %s does not exist' % video_id, raise ExtractorError('Video %s does not exist' % video_id,
expected=True) expected=True)
confirm_hash = self._html_search_regex(r'''(?x)<input\s+ confirm_hash = self._html_search_regex(r'''(?x)<input\s+
@ -54,19 +53,21 @@ def _real_extract(self, url):
req.add_header('Host', 'www.sockshare.com') req.add_header('Host', 'www.sockshare.com')
req.add_header('Content-type', 'application/x-www-form-urlencoded') req.add_header('Content-type', 'application/x-www-form-urlencoded')
webpage = self._download_webpage(req, video_id, 'Downloading video page') webpage = self._download_webpage(
req, video_id, 'Downloading video page')
video_url = self._html_search_regex(r'<a href="([^"]*)".+class="download_file_link"', webpage, 'file url') video_url = self._html_search_regex(
r'<a href="([^"]*)".+class="download_file_link"',
webpage, 'file url')
video_url = "http://www.sockshare.com" + video_url video_url = "http://www.sockshare.com" + video_url
title = self._html_search_regex(r'<h1>(.+)<strong>', webpage, 'title') title = self._html_search_regex(r'<h1>(.+)<strong>', webpage, 'title')
thumbnail = self._html_search_regex(r'<img\ssrc="([^"]*)".+name="bg"', thumbnail = self._html_search_regex(
webpage, 'thumbnail') r'<img\s+src="([^"]*)".+?name="bg"',
ext = determine_ext(title) webpage, 'thumbnail')
formats = [{ formats = [{
'format_id': 'sd', 'format_id': 'sd',
'url': video_url, 'url': video_url,
'ext': ext,
}] }]
return { return {