youtube_dl/extractor/teletask.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import unified_strdate
   7
   8
   9 class TeleTaskIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?tele-task\.de/archive/video/html5/(?P<id>[0-9]+)'
  11     _TEST = {
  12         'url': 'http://www.tele-task.de/archive/video/html5/26168/',
  13         'info_dict': {
  14             'id': '26168',
  15             'title': 'Duplicate Detection',
  16         },
  17         'playlist': [{
  18             'md5': '290ef69fb2792e481169c3958dbfbd57',
  19             'info_dict': {
  20                 'id': '26168-speaker',
  21                 'ext': 'mp4',
  22                 'title': 'Duplicate Detection',
  23                 'upload_date': '20141218',
  24             }
  25         }, {
  26             'md5': 'e1e7218c5f0e4790015a437fcf6c71b4',
  27             'info_dict': {
  28                 'id': '26168-slides',
  29                 'ext': 'mp4',
  30                 'title': 'Duplicate Detection',
  31                 'upload_date': '20141218',
  32             }
  33         }]
  34     }
  35
  36     def _real_extract(self, url):
  37         lecture_id = self._match_id(url)
  38         webpage = self._download_webpage(url, lecture_id)
  39
  40         title = self._html_search_regex(
  41             r'itemprop="name">([^<]+)</a>', webpage, 'title')
  42         upload_date = unified_strdate(self._html_search_regex(
  43             r'Date:</td><td>([^<]+)</td>', webpage, 'date', fatal=False))
  44
  45         entries = [{
  46             'id': '%s-%s' % (lecture_id, format_id),
  47             'url': video_url,
  48             'title': title,
  49             'upload_date': upload_date,
  50         } for format_id, video_url in re.findall(
  51             r'<video class="([^"]+)"[^>]*>\s*<source src="([^"]+)"', webpage)]
  52
  53         return self.playlist_result(entries, lecture_id, title)