Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/funk.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from .nexx import NexxIE
   8 from ..utils import (
   9     int_or_none,
  10     try_get,
  11 )
  12
  13
  14 class FunkBaseIE(InfoExtractor):
  15     def _make_url_result(self, video):
  16         return {
  17             '_type': 'url_transparent',
  18             'url': 'nexx:741:%s' % video['sourceId'],
  19             'ie_key': NexxIE.ie_key(),
  20             'id': video['sourceId'],
  21             'title': video.get('title'),
  22             'description': video.get('description'),
  23             'duration': int_or_none(video.get('duration')),
  24             'season_number': int_or_none(video.get('seasonNr')),
  25             'episode_number': int_or_none(video.get('episodeNr')),
  26         }
  27
  28
  29 class FunkMixIE(FunkBaseIE):
  30     _VALID_URL = r'https?://(?:www\.)?funk\.net/mix/(?P<id>[^/]+)/(?P<alias>[^/?#&]+)'
  31     _TESTS = [{
  32         'url': 'https://www.funk.net/mix/59d65d935f8b160001828b5b/die-realste-kifferdoku-aller-zeiten',
  33         'md5': '8edf617c2f2b7c9847dfda313f199009',
  34         'info_dict': {
  35             'id': '123748',
  36             'ext': 'mp4',
  37             'title': '"Die realste Kifferdoku aller Zeiten"',
  38             'description': 'md5:c97160f5bafa8d47ec8e2e461012aa9d',
  39             'timestamp': 1490274721,
  40             'upload_date': '20170323',
  41         },
  42     }]
  43
  44     def _real_extract(self, url):
  45         mobj = re.match(self._VALID_URL, url)
  46         mix_id = mobj.group('id')
  47         alias = mobj.group('alias')
  48
  49         lists = self._download_json(
  50             'https://www.funk.net/api/v3.1/curation/curatedLists/',
  51             mix_id, headers={
  52                 'authorization': 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJjbGllbnROYW1lIjoiY3VyYXRpb24tdG9vbC12Mi4wIiwic2NvcGUiOiJzdGF0aWMtY29udGVudC1hcGksY3VyYXRpb24tc2VydmljZSxzZWFyY2gtYXBpIn0.SGCC1IXHLtZYoo8PvRKlU2gXH1su8YSu47sB3S4iXBI',
  53                 'Referer': url,
  54             }, query={
  55                 'size': 100,
  56             })['result']['lists']
  57
  58         metas = next(
  59             l for l in lists
  60             if mix_id in (l.get('entityId'), l.get('alias')))['videoMetas']
  61         video = next(
  62             meta['videoDataDelegate']
  63             for meta in metas if meta.get('alias') == alias)
  64
  65         return self._make_url_result(video)
  66
  67
  68 class FunkChannelIE(FunkBaseIE):
  69     _VALID_URL = r'https?://(?:www\.)?funk\.net/channel/(?P<id>[^/]+)/(?P<alias>[^/?#&]+)'
  70     _TESTS = [{
  71         'url': 'https://www.funk.net/channel/ba/die-lustigsten-instrumente-aus-dem-internet-teil-2',
  72         'info_dict': {
  73             'id': '1155821',
  74             'ext': 'mp4',
  75             'title': 'Die LUSTIGSTEN INSTRUMENTE aus dem Internet - Teil 2',
  76             'description': 'md5:a691d0413ef4835588c5b03ded670c1f',
  77             'timestamp': 1514507395,
  78             'upload_date': '20171229',
  79         },
  80         'params': {
  81             'skip_download': True,
  82         },
  83     }, {
  84         # only available via byIdList API
  85         'url': 'https://www.funk.net/channel/informr/martin-sonneborn-erklaert-die-eu',
  86         'info_dict': {
  87             'id': '205067',
  88             'ext': 'mp4',
  89             'title': 'Martin Sonneborn erklärt die EU',
  90             'description': 'md5:050f74626e4ed87edf4626d2024210c0',
  91             'timestamp': 1494424042,
  92             'upload_date': '20170510',
  93         },
  94         'params': {
  95             'skip_download': True,
  96         },
  97     }, {
  98         'url': 'https://www.funk.net/channel/59d5149841dca100012511e3/mein-erster-job-lovemilla-folge-1/lovemilla/',
  99         'only_matching': True,
 100     }]
 101
 102     def _real_extract(self, url):
 103         mobj = re.match(self._VALID_URL, url)
 104         channel_id = mobj.group('id')
 105         alias = mobj.group('alias')
 106
 107         headers = {
 108             'authorization': 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJjbGllbnROYW1lIjoiY3VyYXRpb24tdG9vbCIsInNjb3BlIjoic3RhdGljLWNvbnRlbnQtYXBpLGN1cmF0aW9uLWFwaSxzZWFyY2gtYXBpIn0.q4Y2xZG8PFHai24-4Pjx2gym9RmJejtmK6lMXP5wAgc',
 109             'Referer': url,
 110         }
 111
 112         video = None
 113
 114         by_id_list = self._download_json(
 115             'https://www.funk.net/api/v3.0/content/videos/byIdList', channel_id,
 116             headers=headers, query={
 117                 'ids': alias,
 118             }, fatal=False)
 119         if by_id_list:
 120             video = try_get(by_id_list, lambda x: x['result'][0], dict)
 121
 122         if not video:
 123             results = self._download_json(
 124                 'https://www.funk.net/api/v3.0/content/videos/filter', channel_id,
 125                 headers=headers, query={
 126                     'channelId': channel_id,
 127                     'size': 100,
 128                 })['result']
 129             video = next(r for r in results if r.get('alias') == alias)
 130
 131         return self._make_url_result(video)