_ 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': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)',
  15         'info_dict': {
  16             'id': '26168',
  17             'ext': 'mp4',
  18             'title': 'Duplicate Detection',
  19             'thumbnail': 're:^https?://.*\.jpg$',
  20             'date': '20141218',
  21             # TODO more properties, either as:
  22             # * A value
  23             # * MD5 checksum; start the string with md5:
  24             # * A regular expression; start the string with re:
  25             # * Any Python type (for example int or float)
  26         }
  27     }
  28
  29     def _real_extract(self, url):
  30         video_id = self._match_id(url)
  31         webpage = self._download_webpage(url, video_id)
  32
  33         lecture_url = self._html_search_regex(
  34                     r'href="([^"]+)" itemprop="name">', webpage, 'title')
  35         lecture_id = re.search("([0-9]+)/",lecture_url).group(1)
  36         overview_page = self._download_webpage("http://www.tele-task.de" + lecture_url,
  37             lecture_id)
  38
  39         title = self._html_search_regex(
  40             r'itemprop="name">([^"]+)</a>', webpage, 'title')
  41         url = self._html_search_regex(
  42             r'class="speaker".*?src="([^"]+)"', webpage, 'video_url', flags=re.DOTALL)
  43         description = self._html_search_regex(
  44             r'Description of the series:</p>([^"]+)</div>', overview_page,
  45             'description',flags=re.DOTALL)
  46
  47         date = self._html_search_regex(
  48             r'<td class="label">Date:</td><td>([^"]+)</td>', webpage, 'date')
  49         date = datetime.datetime.strptime(date, '%d.%m.%Y').strftime('%Y%m%d')
  50
  51
  52
  53         return {
  54             'id': video_id,
  55             'title': title,
  56             'description': description,
  57             'url': url,
  58             'upload_date': date,
  59         }