Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/rtl2.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import base64
   5 import re
   6
   7 from .common import InfoExtractor
   8 from ..aes import aes_cbc_decrypt
   9 from ..compat import (
  10     compat_ord,
  11     compat_str,
  12 )
  13 from ..utils import (
  14     bytes_to_intlist,
  15     ExtractorError,
  16     intlist_to_bytes,
  17     int_or_none,
  18     strip_or_none,
  19 )
  20
  21
  22 class RTL2IE(InfoExtractor):
  23     IE_NAME = 'rtl2'
  24     _VALID_URL = r'http?://(?:www\.)?rtl2\.de/[^?#]*?/(?P<id>[^?#/]*?)(?:$|/(?:$|[?#]))'
  25     _TESTS = [{
  26         'url': 'http://www.rtl2.de/sendung/grip-das-motormagazin/folge/folge-203-0',
  27         'info_dict': {
  28             'id': 'folge-203-0',
  29             'ext': 'f4v',
  30             'title': 'GRIP sucht den Sommerkönig',
  31             'description': 'md5:e3adbb940fd3c6e76fa341b8748b562f'
  32         },
  33         'params': {
  34             # rtmp download
  35             'skip_download': True,
  36         },
  37     }, {
  38         'url': 'http://www.rtl2.de/sendung/koeln-50667/video/5512-anna/21040-anna-erwischt-alex/',
  39         'info_dict': {
  40             'id': '21040-anna-erwischt-alex',
  41             'ext': 'mp4',
  42             'title': 'Anna erwischt Alex!',
  43             'description': 'Anna nimmt ihrem Vater nicht ab, dass er nicht spielt. Und tatsächlich erwischt sie ihn auf frischer Tat.'
  44         },
  45         'params': {
  46             # rtmp download
  47             'skip_download': True,
  48         },
  49     }]
  50
  51     def _real_extract(self, url):
  52         # Some rtl2 urls have no slash at the end, so append it.
  53         if not url.endswith('/'):
  54             url += '/'
  55
  56         video_id = self._match_id(url)
  57         webpage = self._download_webpage(url, video_id)
  58
  59         mobj = re.search(
  60             r'<div[^>]+data-collection="(?P<vico_id>\d+)"[^>]+data-video="(?P<vivi_id>\d+)"',
  61             webpage)
  62         if mobj:
  63             vico_id = mobj.group('vico_id')
  64             vivi_id = mobj.group('vivi_id')
  65         else:
  66             vico_id = self._html_search_regex(
  67                 r'vico_id\s*:\s*([0-9]+)', webpage, 'vico_id')
  68             vivi_id = self._html_search_regex(
  69                 r'vivi_id\s*:\s*([0-9]+)', webpage, 'vivi_id')
  70
  71         info = self._download_json(
  72             'http://www.rtl2.de/sites/default/modules/rtl2/mediathek/php/get_video_jw.php',
  73             video_id, query={
  74                 'vico_id': vico_id,
  75                 'vivi_id': vivi_id,
  76             })
  77         video_info = info['video']
  78         title = video_info['titel']
  79
  80         formats = []
  81
  82         rtmp_url = video_info.get('streamurl')
  83         if rtmp_url:
  84             rtmp_url = rtmp_url.replace('\\', '')
  85             stream_url = 'mp4:' + self._html_search_regex(r'/ondemand/(.+)', rtmp_url, 'stream URL')
  86             rtmp_conn = ['S:connect', 'O:1', 'NS:pageUrl:' + url, 'NB:fpad:0', 'NN:videoFunction:1', 'O:0']
  87
  88             formats.append({
  89                 'format_id': 'rtmp',
  90                 'url': rtmp_url,
  91                 'play_path': stream_url,
  92                 'player_url': 'http://www.rtl2.de/flashplayer/vipo_player.swf',
  93                 'page_url': url,
  94                 'flash_version': 'LNX 11,2,202,429',
  95                 'rtmp_conn': rtmp_conn,
  96                 'no_resume': True,
  97                 'preference': 1,
  98             })
  99
 100         m3u8_url = video_info.get('streamurl_hls')
 101         if m3u8_url:
 102             formats.extend(self._extract_akamai_formats(m3u8_url, video_id))
 103
 104         self._sort_formats(formats)
 105
 106         return {
 107             'id': video_id,
 108             'title': title,
 109             'thumbnail': video_info.get('image'),
 110             'description': video_info.get('beschreibung'),
 111             'duration': int_or_none(video_info.get('duration')),
 112             'formats': formats,
 113         }
 114
 115
 116 class RTL2YouBaseIE(InfoExtractor):
 117     _BACKWERK_BASE_URL = 'https://p-you-backwerk.rtl2apps.de/'
 118
 119
 120 class RTL2YouIE(RTL2YouBaseIE):
 121     IE_NAME = 'rtl2:you'
 122     _VALID_URL = r'http?://you\.rtl2\.de/(?:video/\d+/|youplayer/index\.html\?.*?\bvid=)(?P<id>\d+)'
 123     _TESTS = [{
 124         'url': 'http://you.rtl2.de/video/3002/15740/MJUNIK%20%E2%80%93%20Home%20of%20YOU/307-hirn-wo-bist-du',
 125         'info_dict': {
 126             'id': '15740',
 127             'ext': 'mp4',
 128             'title': 'MJUNIK – Home of YOU - #307 Hirn, wo bist du?!',
 129             'description': 'md5:ddaa95c61b372b12b66e115b2772fe01',
 130             'age_limit': 12,
 131         },
 132     }, {
 133         'url': 'http://you.rtl2.de/youplayer/index.html?vid=15712',
 134         'only_matching': True,
 135     }]
 136     _AES_KEY = b'\xe9W\xe4.<*\xb8\x1a\xd2\xb6\x92\xf3C\xd3\xefL\x1b\x03*\xbbbH\xc0\x03\xffo\xc2\xf2(\xaa\xaa!'
 137     _GEO_COUNTRIES = ['DE']
 138
 139     def _real_extract(self, url):
 140         video_id = self._match_id(url)
 141
 142         stream_data = self._download_json(
 143             self._BACKWERK_BASE_URL + 'stream/video/' + video_id, video_id)
 144
 145         data, iv = base64.b64decode(stream_data['streamUrl']).decode().split(':')
 146         stream_url = intlist_to_bytes(aes_cbc_decrypt(
 147             bytes_to_intlist(base64.b64decode(data)),
 148             bytes_to_intlist(self._AES_KEY),
 149             bytes_to_intlist(base64.b64decode(iv))
 150         ))
 151         if b'rtl2_you_video_not_found' in stream_url:
 152             raise ExtractorError('video not found', expected=True)
 153
 154         formats = self._extract_m3u8_formats(
 155             stream_url[:-compat_ord(stream_url[-1])].decode(),
 156             video_id, 'mp4', 'm3u8_native')
 157         self._sort_formats(formats)
 158
 159         video_data = self._download_json(
 160             self._BACKWERK_BASE_URL + 'video/' + video_id, video_id)
 161
 162         series = video_data.get('formatTitle')
 163         title = episode = video_data.get('title') or series
 164         if series and series != title:
 165             title = '%s - %s' % (series, title)
 166
 167         return {
 168             'id': video_id,
 169             'title': title,
 170             'formats': formats,
 171             'description': strip_or_none(video_data.get('description')),
 172             'thumbnail': video_data.get('image'),
 173             'duration': int_or_none(stream_data.get('duration') or video_data.get('duration'), 1000),
 174             'series': series,
 175             'episode': episode,
 176             'age_limit': int_or_none(video_data.get('minimumAge')),
 177         }
 178
 179
 180 class RTL2YouSeriesIE(RTL2YouBaseIE):
 181     IE_NAME = 'rtl2:you:series'
 182     _VALID_URL = r'http?://you\.rtl2\.de/videos/(?P<id>\d+)'
 183     _TEST = {
 184         'url': 'http://you.rtl2.de/videos/115/dragon-ball',
 185         'info_dict': {
 186             'id': '115',
 187         },
 188         'playlist_mincount': 5,
 189     }
 190
 191     def _real_extract(self, url):
 192         series_id = self._match_id(url)
 193         stream_data = self._download_json(
 194             self._BACKWERK_BASE_URL + 'videos',
 195             series_id, query={
 196                 'formatId': series_id,
 197                 'limit': 1000000000,
 198             })
 199
 200         entries = []
 201         for video in stream_data.get('videos', []):
 202             video_id = compat_str(video['videoId'])
 203             if not video_id:
 204                 continue
 205             entries.append(self.url_result(
 206                 'http://you.rtl2.de/video/%s/%s' % (series_id, video_id),
 207                 'RTL2You', video_id))
 208         return self.playlist_result(entries, series_id)