1
mirror of https://github.com/yt-dlp/yt-dlp synced 2024-12-14 20:59:16 +01:00
yt-dlp/youtube_dl/extractor/keek.py

41 lines
1.3 KiB
Python
Raw Normal View History

2013-06-23 22:16:41 +02:00
import re
from .common import InfoExtractor
class KeekIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<videoID>\w+)'
IE_NAME = u'keek'
2013-06-27 20:46:46 +02:00
_TEST = {
u'url': u'http://www.keek.com/ytdl/keeks/NODfbab',
u'file': u'NODfbab.mp4',
u'md5': u'9b0636f8c0f7614afa4ea5e4c6e57e83',
u'info_dict': {
u"uploader": u"ytdl",
u"title": u"test chars: \"'/\\\u00e4<>This is a test video for youtube-dl.For more information, contact phihag@phihag.de ."
}
}
2013-06-23 22:16:41 +02:00
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
video_id = m.group('videoID')
video_url = u'http://cdn.keek.com/keek/video/%s' % video_id
thumbnail = u'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id
webpage = self._download_webpage(url, video_id)
video_title = self._og_search_title(webpage)
2013-06-23 22:16:41 +02:00
uploader = self._html_search_regex(r'<div class="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>',
webpage, u'uploader', fatal=False)
info = {
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': video_title,
'thumbnail': thumbnail,
'uploader': uploader
}
return [info]