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

[toypics] Fix extraction

Browse source
This commit is contained in:
vobe 2017-05-19 20:18:03 +02:00 committed by Sergey M
parent 8fffac6927
commit 77d682da9d
1 changed files with 8 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
youtube_dl/extractor/toypics.py
View file

@ -24,15 +24,16 @@ def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('id')
page = self._download_webpage(url, video_id) page = self._download_webpage(url, video_id)
video_url = self._html_search_regex( formats = self._parse_html5_media_entries(url, page, video_id)[0]['formats']
r'src:\s+"(http://static[0-9]+\.toypics\.net/flvideo/[^"]+)"', page, 'video URL') title = self._html_search_regex([
title = self._html_search_regex( r'<h1[^>]+class=["\']view-video-title[^>]+>([^<]+)</h',
r'<title>Toypics - ([^<]+)</title>', page, 'title') r'<title>([^<]+) - Toypics</title>',
], page, 'title')
username = self._html_search_regex( username = self._html_search_regex(
r'toypics.net/([^/"]+)" class="user-name">', page, 'username') r'More videos from <strong>([^<]+)</strong>', page, 'username')
return { return {
'id': video_id, 'id': video_id,
'url': video_url, 'formats': formats,
'title': title, 'title': title,
'uploader': username, 'uploader': username,
'age_limit': 18, 'age_limit': 18,
@ -71,7 +72,7 @@ def _real_extract(self, url):
note='Downloading page %d/%d' % (n, page_count)) note='Downloading page %d/%d' % (n, page_count))
urls.extend( urls.extend(
re.findall( re.findall(
r'<p class="video-entry-title">\s+<a href="(https?://videos.toypics.net/view/[^"]+)">', r'<div[^>]+class=["\']preview[^>]+>\s*<a[^>]+href="(https?://videos.toypics.net/view/[^"]+)"',
lpage)) lpage))
return { return {