1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-05 10:42:37 +01:00
yt-dlp/youtube_dl/extractor/funnyordie.py
2013-06-23 22:07:17 +02:00

32 lines
1.1 KiB
Python

import re
from .common import InfoExtractor
class FunnyOrDieIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?funnyordie\.com/videos/(?P<id>[0-9a-f]+)/.*$'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
video_url = self._html_search_regex(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"',
webpage, u'video URL', flags=re.DOTALL)
title = self._html_search_regex((r"<h1 class='player_page_h1'.*?>(?P<title>.*?)</h1>",
r'<title>(?P<title>[^<]+?)</title>'), webpage, 'title', flags=re.DOTALL)
video_description = self._html_search_regex(r'<meta property="og:description" content="(?P<desc>.*?)"',
webpage, u'description', fatal=False, flags=re.DOTALL)
info = {
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': title,
'description': video_description,
}
return [info]