yt_dlp/extractor/rtl2.py

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