youtube_dl/extractor/servus.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class ServusIE(InfoExtractor):
  10     _VALID_URL = r'''(?x)
  11                     https?://
  12                         (?:www\.)?
  13                         (?:
  14                             servus\.com/(?:(?:at|de)/p/[^/]+|tv/videos)|
  15                             servustv\.com/videos
  16                         )
  17                         /(?P<id>[aA]{2}-\w+|\d+-\d+)
  18                     '''
  19     _TESTS = [{
  20         # new URL schema
  21         'url': 'https://www.servustv.com/videos/aa-1t6vbu5pw1w12/',
  22         'md5': '3e1dd16775aa8d5cbef23628cfffc1f4',
  23         'info_dict': {
  24             'id': 'AA-1T6VBU5PW1W12',
  25             'ext': 'mp4',
  26             'title': 'Die Grünen aus Sicht des Volkes',
  27             'description': 'md5:1247204d85783afe3682644398ff2ec4',
  28             'thumbnail': r're:^https?://.*\.jpg',
  29         }
  30     }, {
  31         # old URL schema
  32         'url': 'https://www.servus.com/de/p/Die-Gr%C3%BCnen-aus-Sicht-des-Volkes/AA-1T6VBU5PW1W12/',
  33         'only_matching': True,
  34     }, {
  35         'url': 'https://www.servus.com/at/p/Wie-das-Leben-beginnt/1309984137314-381415152/',
  36         'only_matching': True,
  37     }, {
  38         'url': 'https://www.servus.com/tv/videos/aa-1t6vbu5pw1w12/',
  39         'only_matching': True,
  40     }, {
  41         'url': 'https://www.servus.com/tv/videos/1380889096408-1235196658/',
  42         'only_matching': True,
  43     }]
  44
  45     def _real_extract(self, url):
  46         video_id = self._match_id(url).upper()
  47         webpage = self._download_webpage(url, video_id)
  48
  49         title = self._search_regex(
  50             (r'videoLabel\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1',
  51              r'<h\d+[^>]+\bclass=["\']heading--(?:one|two)["\'][^>]*>(?P<title>[^<]+)'),
  52             webpage, 'title', default=None,
  53             group='title') or self._og_search_title(webpage)
  54         title = re.sub(r'\s*-\s*Servus TV\s*$', '', title)
  55         description = self._og_search_description(webpage)
  56         thumbnail = self._og_search_thumbnail(webpage)
  57
  58         formats = self._extract_m3u8_formats(
  59             'https://stv.rbmbtnx.net/api/v1/manifests/%s.m3u8' % video_id,
  60             video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
  61         self._sort_formats(formats)
  62
  63         return {
  64             'id': video_id,
  65             'title': title,
  66             'description': description,
  67             'thumbnail': thumbnail,
  68             'formats': formats,
  69         }