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