Raphaël G. Git Repositories - youtubedl/blob - 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 compat_urlparse
  10 from ..utils import (
  11     NO_DEFAULT,
  12     smuggle_url,
  13 )
  14
  15
  16 class Tele5IE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:www\.)?tele5\.de/(?:[^/]+/)*(?P<id>[^/?#&]+)'
  18     _GEO_COUNTRIES = ['DE']
  19     _TESTS = [{
  20         'url': 'https://www.tele5.de/mediathek/filme-online/videos?vid=1549416',
  21         'info_dict': {
  22             'id': '1549416',
  23             'ext': 'mp4',
  24             'upload_date': '20180814',
  25             'timestamp': 1534290623,
  26             'title': 'Pandorum',
  27         },
  28         'params': {
  29             'skip_download': True,
  30         },
  31     }, {
  32         # jwplatform, nexx unavailable
  33         'url': 'https://www.tele5.de/filme/ghoul-das-geheimnis-des-friedhofmonsters/',
  34         'info_dict': {
  35             'id': 'WJuiOlUp',
  36             'ext': 'mp4',
  37             'upload_date': '20200603',
  38             'timestamp': 1591214400,
  39             'title': 'Ghoul - Das Geheimnis des Friedhofmonsters',
  40             'description': 'md5:42002af1d887ff3d5b2b3ca1f8137d97',
  41         },
  42         'params': {
  43             'skip_download': True,
  44         },
  45         'add_ie': [JWPlatformIE.ie_key()],
  46     }, {
  47         'url': 'https://www.tele5.de/kalkofes-mattscheibe/video-clips/politik-und-gesellschaft?ve_id=1551191',
  48         'only_matching': True,
  49     }, {
  50         'url': 'https://www.tele5.de/video-clip/?ve_id=1609440',
  51         'only_matching': True,
  52     }, {
  53         'url': 'https://www.tele5.de/filme/schlefaz-dragon-crusaders/',
  54         'only_matching': True,
  55     }, {
  56         'url': 'https://www.tele5.de/filme/making-of/avengers-endgame/',
  57         'only_matching': True,
  58     }, {
  59         'url': 'https://www.tele5.de/star-trek/raumschiff-voyager/ganze-folge/das-vinculum/',
  60         'only_matching': True,
  61     }, {
  62         'url': 'https://www.tele5.de/anders-ist-sevda/',
  63         'only_matching': True,
  64     }]
  65
  66     def _real_extract(self, url):
  67         qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
  68         video_id = (qs.get('vid') or qs.get('ve_id') or [None])[0]
  69
  70         NEXX_ID_RE = r'\d{6,}'
  71         JWPLATFORM_ID_RE = r'[a-zA-Z0-9]{8}'
  72
  73         def nexx_result(nexx_id):
  74             return self.url_result(
  75                 'https://api.nexx.cloud/v3/759/videos/byid/%s' % nexx_id,
  76                 ie=NexxIE.ie_key(), video_id=nexx_id)
  77
  78         nexx_id = jwplatform_id = None
  79
  80         if video_id:
  81             if re.match(NEXX_ID_RE, video_id):
  82                 return nexx_result(video_id)
  83             elif re.match(JWPLATFORM_ID_RE, video_id):
  84                 jwplatform_id = video_id
  85
  86         if not nexx_id:
  87             display_id = self._match_id(url)
  88             webpage = self._download_webpage(url, display_id)
  89
  90             def extract_id(pattern, name, default=NO_DEFAULT):
  91                 return self._html_search_regex(
  92                     (r'id\s*=\s*["\']video-player["\'][^>]+data-id\s*=\s*["\'](%s)' % pattern,
  93                      r'\s+id\s*=\s*["\']player_(%s)' % pattern,
  94                      r'\bdata-id\s*=\s*["\'](%s)' % pattern), webpage, name,
  95                     default=default)
  96
  97             nexx_id = extract_id(NEXX_ID_RE, 'nexx id', default=None)
  98             if nexx_id:
  99                 return nexx_result(nexx_id)
 100
 101             if not jwplatform_id:
 102                 jwplatform_id = extract_id(JWPLATFORM_ID_RE, 'jwplatform id')
 103
 104         return self.url_result(
 105             smuggle_url(
 106                 'jwplatform:%s' % jwplatform_id,
 107                 {'geo_countries': self._GEO_COUNTRIES}),
 108             ie=JWPlatformIE.ie_key(), video_id=jwplatform_id)