2 from __future__ import unicode_literals
7 from .common import InfoExtractor
10 class TeleTaskIE(InfoExtractor):
11 _VALID_URL = r'http?://(?:www\.)?tele-task\.de/archive/video/html5/(?P<id>[0-9]+)/'
13 'url': 'http://www.tele-task.de/archive/video/html5/26168/',
14 'md5': '290ef69fb2792e481169c3958dbfbd57',
18 'title': 'Duplicate Detection',
19 'upload_date': '20141218',
23 def _real_extract(self, url):
24 video_id = self._match_id(url)
25 webpage = self._download_webpage(url, video_id)
27 title = self._html_search_regex(
28 r'itemprop="name">([^"]+)</a>', webpage, 'title')
29 url = self._html_search_regex(
30 r'class="speaker".*?src="([^"]+)"', webpage, 'video_url', flags=re.DOTALL)
32 date = self._html_search_regex(
33 r'<td class="label">Date:</td><td>([^"]+)</td>', webpage, 'date')
34 date = datetime.datetime.strptime(date, '%d.%m.%Y').strftime('%Y%m%d')