_ Git - youtube-dl/blob - youtube_dl/extractor/teletask.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import datetime
   6
   7 from .common import InfoExtractor
   8
   9
  10 class TeleTaskIE(InfoExtractor):
  11     _VALID_URL = r'http?://(?:www\.)?tele-task\.de/archive/video/html5/(?P<id>[0-9]+)/'
  12     _TEST = {
  13         'url': 'http://www.tele-task.de/archive/video/html5/26168/',
  14         'md5': '290ef69fb2792e481169c3958dbfbd57',
  15         'info_dict': {
  16             'id': '26168',
  17             'ext': 'mp4',
  18             'title': 'Duplicate Detection',
  19             'upload_date': '20141218',
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         video_id = self._match_id(url)
  25         webpage = self._download_webpage(url, video_id)
  26
  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)
  31
  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')
  35
  36
  37
  38         return {
  39             'id': video_id,
  40             'title': title,
  41             'url': url,
  42             'upload_date': date,
  43         }