_ Git - youtube-dl/blob - youtube_dl/extractor/lecture2go.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import determine_ext
   8
   9
  10 class Lecture2GoIE(InfoExtractor):
  11     _VALID_URL = r'https?://lecture2go\.uni-hamburg\.de/veranstaltungen/-/v/(?P<id>\d+)'
  12     _TEST = {
  13         'url': 'https://lecture2go.uni-hamburg.de/veranstaltungen/-/v/17473',
  14         'md5': 'a9e76f83b3ef58019c4b7dbc35f406c1',
  15         'info_dict': {
  16             'id': '17473',
  17             'ext': 'mp4',
  18             'url': 'https://fms1.rrz.uni-hamburg.de/abo/64.050_FrankHeitmann_2015-04-13_14-35.mp4',
  19             'title': '2 - Endliche Automaten und reguläre Sprachen'
  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(r'<em[^>]+class="title">(.+)</em>', webpage, 'title')
  28
  29         formats = []
  30         for url in set(re.findall(r'"src","([^"]+)"', webpage)):
  31             ext = determine_ext(url)
  32             if ext == 'f4m':
  33                 formats.extend(self._extract_f4m_formats(url, video_id))
  34             elif ext == 'm3u8':
  35                 formats.extend(self._extract_m3u8_formats(url, video_id))
  36             else:
  37                 formats.append({
  38                     'url': url,
  39                 })
  40
  41         self._sort_formats(formats)
  42
  43         creator = self._html_search_regex(r'<div[^>]+id="description">([^<]+)</div>', webpage, 'creator')
  44
  45         return {
  46             'id': video_id,
  47             'title': title,
  48             'formats': formats,
  49             'creator': creator
  50         }