youtube_dl/extractor/tele5.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from .jwplatform import JWPlatformIE
   8 from .nexx import NexxIE
   9 from ..compat import (
  10     compat_str,
  11     compat_urlparse,
  12 )
  13 from ..utils import (
  14     NO_DEFAULT,
  15     try_get,
  16 )
  17
  18
  19 class Tele5IE(InfoExtractor):
  20     _VALID_URL = r'https?://(?:www\.)?tele5\.de/(?:[^/]+/)*(?P<id>[^/?#&]+)'
  21     _TESTS = [{
  22         'url': 'https://www.tele5.de/mediathek/filme-online/videos?vid=1549416',
  23         'info_dict': {
  24             'id': '1549416',
  25             'ext': 'mp4',
  26             'upload_date': '20180814',
  27             'timestamp': 1534290623,
  28             'title': 'Pandorum',
  29         },
  30         'params': {
  31             'skip_download': True,
  32         },
  33     }, {
  34         'url': 'https://www.tele5.de/kalkofes-mattscheibe/video-clips/politik-und-gesellschaft?ve_id=1551191',
  35         'only_matching': True,
  36     }, {
  37         'url': 'https://www.tele5.de/video-clip/?ve_id=1609440',
  38         'only_matching': True,
  39     }, {
  40         'url': 'https://www.tele5.de/filme/schlefaz-dragon-crusaders/',
  41         'only_matching': True,
  42     }, {
  43         'url': 'https://www.tele5.de/filme/making-of/avengers-endgame/',
  44         'only_matching': True,
  45     }, {
  46         'url': 'https://www.tele5.de/star-trek/raumschiff-voyager/ganze-folge/das-vinculum/',
  47         'only_matching': True,
  48     }, {
  49         'url': 'https://www.tele5.de/anders-ist-sevda/',
  50         'only_matching': True,
  51     }]
  52
  53     def _real_extract(self, url):
  54         qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
  55         video_id = (qs.get('vid') or qs.get('ve_id') or [None])[0]
  56
  57         NEXX_ID_RE = r'\d{6,}'
  58         JWPLATFORM_ID_RE = r'[a-zA-Z0-9]{8}'
  59
  60         def nexx_result(nexx_id):
  61             return self.url_result(
  62                 'https://api.nexx.cloud/v3/759/videos/byid/%s' % nexx_id,
  63                 ie=NexxIE.ie_key(), video_id=nexx_id)
  64
  65         nexx_id = jwplatform_id = None
  66
  67         if video_id:
  68             if re.match(NEXX_ID_RE, video_id):
  69                 return nexx_result(video_id)
  70             elif re.match(JWPLATFORM_ID_RE, video_id):
  71                 jwplatform_id = video_id
  72
  73         if not nexx_id:
  74             display_id = self._match_id(url)
  75             webpage = self._download_webpage(url, display_id)
  76
  77             def extract_id(pattern, name, default=NO_DEFAULT):
  78                 return self._html_search_regex(
  79                     (r'id\s*=\s*["\']video-player["\'][^>]+data-id\s*=\s*["\'](%s)' % pattern,
  80                      r'\s+id\s*=\s*["\']player_(%s)' % pattern,
  81                      r'\bdata-id\s*=\s*["\'](%s)' % pattern), webpage, name,
  82                     default=default)
  83
  84             nexx_id = extract_id(NEXX_ID_RE, 'nexx id', default=None)
  85             if nexx_id:
  86                 return nexx_result(nexx_id)
  87
  88             if not jwplatform_id:
  89                 jwplatform_id = extract_id(JWPLATFORM_ID_RE, 'jwplatform id')
  90
  91             media = self._download_json(
  92                 'https://cdn.jwplayer.com/v2/media/' + jwplatform_id,
  93                 display_id)
  94             nexx_id = try_get(
  95                 media, lambda x: x['playlist'][0]['nexx_id'], compat_str)
  96
  97             if nexx_id:
  98                 return nexx_result(nexx_id)
  99
 100         return self.url_result(
 101             'jwplatform:%s' % jwplatform_id, ie=JWPlatformIE.ie_key(),
 102             video_id=jwplatform_id)