yt_dlp/extractor/teletask.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import unified_strdate
   5
   6
   7 class TeleTaskIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?tele-task\.de/archive/video/html5/(?P<id>[0-9]+)'
   9     _TEST = {
  10         'url': 'http://www.tele-task.de/archive/video/html5/26168/',
  11         'info_dict': {
  12             'id': '26168',
  13             'title': 'Duplicate Detection',
  14         },
  15         'playlist': [{
  16             'md5': '290ef69fb2792e481169c3958dbfbd57',
  17             'info_dict': {
  18                 'id': '26168-speaker',
  19                 'ext': 'mp4',
  20                 'title': 'Duplicate Detection',
  21                 'upload_date': '20141218',
  22             }
  23         }, {
  24             'md5': 'e1e7218c5f0e4790015a437fcf6c71b4',
  25             'info_dict': {
  26                 'id': '26168-slides',
  27                 'ext': 'mp4',
  28                 'title': 'Duplicate Detection',
  29                 'upload_date': '20141218',
  30             }
  31         }]
  32     }
  33
  34     def _real_extract(self, url):
  35         lecture_id = self._match_id(url)
  36         webpage = self._download_webpage(url, lecture_id)
  37
  38         title = self._html_search_regex(
  39             r'itemprop="name">([^<]+)</a>', webpage, 'title')
  40         upload_date = unified_strdate(self._html_search_regex(
  41             r'Date:</td><td>([^<]+)</td>', webpage, 'date', fatal=False))
  42
  43         entries = [{
  44             'id': '%s-%s' % (lecture_id, format_id),
  45             'url': video_url,
  46             'title': title,
  47             'upload_date': upload_date,
  48         } for format_id, video_url in re.findall(
  49             r'<video class="([^"]+)"[^>]*>\s*<source src="([^"]+)"', webpage)]
  50
  51         return self.playlist_result(entries, lecture_id, title)