yt_dlp/extractor/rtl2.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..aes import aes_cbc_decrypt_bytes, unpad_pkcs7
   8 from ..compat import (
   9     compat_b64decode,
  10     compat_str,
  11 )
  12 from ..utils import (
  13     ExtractorError,
  14     int_or_none,
  15     strip_or_none,
  16 )
  17
  18
  19 class RTL2IE(InfoExtractor):
  20     IE_NAME = 'rtl2'
  21     _VALID_URL = r'https?://(?:www\.)?rtl2\.de/sendung/[^/]+/(?:video/(?P<vico_id>\d+)[^/]+/(?P<vivi_id>\d+)-|folge/)(?P<id>[^/?#]+)'
  22     _TESTS = [{
  23         'url': 'http://www.rtl2.de/sendung/grip-das-motormagazin/folge/folge-203-0',
  24         'info_dict': {
  25             'id': 'folge-203-0',
  26             'ext': 'f4v',
  27             'title': 'GRIP sucht den Sommerkönig',
  28             'description': 'md5:e3adbb940fd3c6e76fa341b8748b562f'
  29         },
  30         'params': {
  31             # rtmp download
  32             'skip_download': True,
  33         },
  34         'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
  35     }, {
  36         'url': 'http://www.rtl2.de/sendung/koeln-50667/video/5512-anna/21040-anna-erwischt-alex/',
  37         'info_dict': {
  38             'id': 'anna-erwischt-alex',
  39             'ext': 'mp4',
  40             'title': 'Anna erwischt Alex!',
  41             'description': 'Anna nimmt ihrem Vater nicht ab, dass er nicht spielt. Und tatsächlich erwischt sie ihn auf frischer Tat.'
  42         },
  43         'params': {
  44             # rtmp download
  45             'skip_download': True,
  46         },
  47         'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
  48     }]
  49
  50     def _real_extract(self, url):
  51         vico_id, vivi_id, display_id = self._match_valid_url(url).groups()
  52         if not vico_id:
  53             webpage = self._download_webpage(url, display_id)
  54
  55             mobj = re.search(
  56                 r'data-collection="(?P<vico_id>\d+)"[^>]+data-video="(?P<vivi_id>\d+)"',
  57                 webpage)
  58             if mobj:
  59                 vico_id = mobj.group('vico_id')
  60                 vivi_id = mobj.group('vivi_id')
  61             else:
  62                 vico_id = self._html_search_regex(
  63                     r'vico_id\s*:\s*([0-9]+)', webpage, 'vico_id')
  64                 vivi_id = self._html_search_regex(
  65                     r'vivi_id\s*:\s*([0-9]+)', webpage, 'vivi_id')
  66
  67         info = self._download_json(
  68             'https://service.rtl2.de/api-player-vipo/video.php',
  69             display_id, query={
  70                 'vico_id': vico_id,
  71                 'vivi_id': vivi_id,
  72             })
  73         video_info = info['video']
  74         title = video_info['titel']
  75
  76         formats = []
  77
  78         rtmp_url = video_info.get('streamurl')
  79         if rtmp_url:
  80             rtmp_url = rtmp_url.replace('\\', '')
  81             stream_url = 'mp4:' + self._html_search_regex(r'/ondemand/(.+)', rtmp_url, 'stream URL')
  82             rtmp_conn = ['S:connect', 'O:1', 'NS:pageUrl:' + url, 'NB:fpad:0', 'NN:videoFunction:1', 'O:0']
  83
  84             formats.append({
  85                 'format_id': 'rtmp',
  86                 'url': rtmp_url,
  87                 'play_path': stream_url,
  88                 'player_url': 'https://www.rtl2.de/sites/default/modules/rtl2/jwplayer/jwplayer-7.6.0/jwplayer.flash.swf',
  89                 'page_url': url,
  90                 'flash_version': 'LNX 11,2,202,429',
  91                 'rtmp_conn': rtmp_conn,
  92                 'no_resume': True,
  93                 'quality': 1,
  94             })
  95
  96         m3u8_url = video_info.get('streamurl_hls')
  97         if m3u8_url:
  98             formats.extend(self._extract_akamai_formats(m3u8_url, display_id))
  99
 100         self._sort_formats(formats)
 101
 102         return {
 103             'id': display_id,
 104             'title': title,
 105             'thumbnail': video_info.get('image'),
 106             'description': video_info.get('beschreibung'),
 107             'duration': int_or_none(video_info.get('duration')),
 108             'formats': formats,
 109         }
 110
 111
 112 class RTL2YouBaseIE(InfoExtractor):
 113     _BACKWERK_BASE_URL = 'https://p-you-backwerk.rtl2apps.de/'
 114
 115
 116 class RTL2YouIE(RTL2YouBaseIE):
 117     IE_NAME = 'rtl2:you'
 118     _VALID_URL = r'http?://you\.rtl2\.de/(?:video/\d+/|youplayer/index\.html\?.*?\bvid=)(?P<id>\d+)'
 119     _TESTS = [{
 120         'url': 'http://you.rtl2.de/video/3002/15740/MJUNIK%20%E2%80%93%20Home%20of%20YOU/307-hirn-wo-bist-du',
 121         'info_dict': {
 122             'id': '15740',
 123             'ext': 'mp4',
 124             'title': 'MJUNIK – Home of YOU - #307 Hirn, wo bist du?!',
 125             'description': 'md5:ddaa95c61b372b12b66e115b2772fe01',
 126             'age_limit': 12,
 127         },
 128     }, {
 129         'url': 'http://you.rtl2.de/youplayer/index.html?vid=15712',
 130         'only_matching': True,
 131     }]
 132     _AES_KEY = b'\xe9W\xe4.<*\xb8\x1a\xd2\xb6\x92\xf3C\xd3\xefL\x1b\x03*\xbbbH\xc0\x03\xffo\xc2\xf2(\xaa\xaa!'
 133     _GEO_COUNTRIES = ['DE']
 134
 135     def _real_extract(self, url):
 136         video_id = self._match_id(url)
 137
 138         stream_data = self._download_json(
 139             self._BACKWERK_BASE_URL + 'stream/video/' + video_id, video_id)
 140
 141         data, iv = compat_b64decode(stream_data['streamUrl']).decode().split(':')
 142         stream_url = unpad_pkcs7(aes_cbc_decrypt_bytes(
 143             compat_b64decode(data), self._AES_KEY, compat_b64decode(iv)))
 144         if b'rtl2_you_video_not_found' in stream_url:
 145             raise ExtractorError('video not found', expected=True)
 146
 147         formats = self._extract_m3u8_formats(stream_url.decode(), video_id, 'mp4', 'm3u8_native')
 148         self._sort_formats(formats)
 149
 150         video_data = self._download_json(
 151             self._BACKWERK_BASE_URL + 'video/' + video_id, video_id)
 152
 153         series = video_data.get('formatTitle')
 154         title = episode = video_data.get('title') or series
 155         if series and series != title:
 156             title = '%s - %s' % (series, title)
 157
 158         return {
 159             'id': video_id,
 160             'title': title,
 161             'formats': formats,
 162             'description': strip_or_none(video_data.get('description')),
 163             'thumbnail': video_data.get('image'),
 164             'duration': int_or_none(stream_data.get('duration') or video_data.get('duration'), 1000),
 165             'series': series,
 166             'episode': episode,
 167             'age_limit': int_or_none(video_data.get('minimumAge')),
 168         }
 169
 170
 171 class RTL2YouSeriesIE(RTL2YouBaseIE):
 172     IE_NAME = 'rtl2:you:series'
 173     _VALID_URL = r'http?://you\.rtl2\.de/videos/(?P<id>\d+)'
 174     _TEST = {
 175         'url': 'http://you.rtl2.de/videos/115/dragon-ball',
 176         'info_dict': {
 177             'id': '115',
 178         },
 179         'playlist_mincount': 5,
 180     }
 181
 182     def _real_extract(self, url):
 183         series_id = self._match_id(url)
 184         stream_data = self._download_json(
 185             self._BACKWERK_BASE_URL + 'videos',
 186             series_id, query={
 187                 'formatId': series_id,
 188                 'limit': 1000000000,
 189             })
 190
 191         entries = []
 192         for video in stream_data.get('videos', []):
 193             video_id = compat_str(video['videoId'])
 194             if not video_id:
 195                 continue
 196             entries.append(self.url_result(
 197                 'http://you.rtl2.de/video/%s/%s' % (series_id, video_id),
 198                 'RTL2You', video_id))
 199         return self.playlist_result(entries, series_id)