ytdl-nightly/youtube_dl/extractor/keek.py

41 lines
1.3 KiB
Python
Raw Normal View History

from __future__ import unicode_literals
2013-06-23 22:16:41 +02:00
import re
from .common import InfoExtractor
class KeekIE(InfoExtractor):
2013-07-25 09:40:19 +02:00
_VALID_URL = r'https?://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<videoID>\w+)'
IE_NAME = 'keek'
2013-06-27 20:46:46 +02:00
_TEST = {
'url': 'https://www.keek.com/ytdl/keeks/NODfbab',
'file': 'NODfbab.mp4',
'md5': '9b0636f8c0f7614afa4ea5e4c6e57e83',
'info_dict': {
'uploader': 'ytdl',
'title': 'test chars: "\'/\\\u00e4<>This is a test video for youtube-dl.For more information, contact phihag@phihag.de .',
},
2013-06-27 20:46:46 +02:00
}
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 = 'http://cdn.keek.com/keek/video/%s' % video_id
thumbnail = 'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id
2013-06-23 22:16:41 +02:00
webpage = self._download_webpage(url, video_id)
uploader = self._html_search_regex(
r'<div class="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>',
webpage, 'uploader', fatal=False)
return {
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': self._og_search_title(webpage),
'thumbnail': thumbnail,
'uploader': uploader
2013-06-23 22:16:41 +02:00
}