yt_dlp/extractor/rtve.py

   1 import base64
   2 import io
   3 import sys
   4
   5 from .common import InfoExtractor
   6 from ..compat import (
   7     compat_b64decode,
   8     compat_struct_unpack,
   9 )
  10 from ..utils import (
  11     determine_ext,
  12     ExtractorError,
  13     float_or_none,
  14     qualities,
  15     remove_end,
  16     remove_start,
  17     try_get,
  18 )
  19
  20 _bytes_to_chr = (lambda x: x) if sys.version_info[0] == 2 else (lambda x: map(chr, x))
  21
  22
  23 class RTVEALaCartaIE(InfoExtractor):
  24     IE_NAME = 'rtve.es:alacarta'
  25     IE_DESC = 'RTVE a la carta'
  26     _VALID_URL = r'https?://(?:www\.)?rtve\.es/(m/)?(alacarta/videos|filmoteca)/[^/]+/[^/]+/(?P<id>\d+)'
  27
  28     _TESTS = [{
  29         'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
  30         'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43',
  31         'info_dict': {
  32             'id': '2491869',
  33             'ext': 'mp4',
  34             'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia',
  35             'duration': 5024.566,
  36             'series': 'Balonmano',
  37         },
  38         'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
  39     }, {
  40         'note': 'Live stream',
  41         'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/',
  42         'info_dict': {
  43             'id': '1694255',
  44             'ext': 'mp4',
  45             'title': 're:^24H LIVE [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  46             'is_live': True,
  47         },
  48         'params': {
  49             'skip_download': 'live stream',
  50         },
  51     }, {
  52         'url': 'http://www.rtve.es/alacarta/videos/servir-y-proteger/servir-proteger-capitulo-104/4236788/',
  53         'md5': 'd850f3c8731ea53952ebab489cf81cbf',
  54         'info_dict': {
  55             'id': '4236788',
  56             'ext': 'mp4',
  57             'title': 'Servir y proteger - Capítulo 104',
  58             'duration': 3222.0,
  59         },
  60         'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
  61     }, {
  62         'url': 'http://www.rtve.es/m/alacarta/videos/cuentame-como-paso/cuentame-como-paso-t16-ultimo-minuto-nuestra-vida-capitulo-276/2969138/?media=tve',
  63         'only_matching': True,
  64     }, {
  65         'url': 'http://www.rtve.es/filmoteca/no-do/not-1-introduccion-primer-noticiario-espanol/1465256/',
  66         'only_matching': True,
  67     }]
  68
  69     def _real_initialize(self):
  70         user_agent_b64 = base64.b64encode(self.get_param('http_headers')['User-Agent'].encode('utf-8')).decode('utf-8')
  71         self._manager = self._download_json(
  72             'http://www.rtve.es/odin/loki/' + user_agent_b64,
  73             None, 'Fetching manager info')['manager']
  74
  75     @staticmethod
  76     def _decrypt_url(png):
  77         encrypted_data = io.BytesIO(compat_b64decode(png)[8:])
  78         while True:
  79             length = compat_struct_unpack('!I', encrypted_data.read(4))[0]
  80             chunk_type = encrypted_data.read(4)
  81             if chunk_type == b'IEND':
  82                 break
  83             data = encrypted_data.read(length)
  84             if chunk_type == b'tEXt':
  85                 alphabet_data, text = data.split(b'\0')
  86                 quality, url_data = text.split(b'%%')
  87                 alphabet = []
  88                 e = 0
  89                 d = 0
  90                 for l in _bytes_to_chr(alphabet_data):
  91                     if d == 0:
  92                         alphabet.append(l)
  93                         d = e = (e + 1) % 4
  94                     else:
  95                         d -= 1
  96                 url = ''
  97                 f = 0
  98                 e = 3
  99                 b = 1
 100                 for letter in _bytes_to_chr(url_data):
 101                     if f == 0:
 102                         l = int(letter) * 10
 103                         f = 1
 104                     else:
 105                         if e == 0:
 106                             l += int(letter)
 107                             url += alphabet[l]
 108                             e = (b + 3) % 4
 109                             f = 0
 110                             b += 1
 111                         else:
 112                             e -= 1
 113
 114                 yield quality.decode(), url
 115             encrypted_data.read(4)  # CRC
 116
 117     def _extract_png_formats(self, video_id):
 118         png = self._download_webpage(
 119             'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id),
 120             video_id, 'Downloading url information', query={'q': 'v2'})
 121         q = qualities(['Media', 'Alta', 'HQ', 'HD_READY', 'HD_FULL'])
 122         formats = []
 123         for quality, video_url in self._decrypt_url(png):
 124             ext = determine_ext(video_url)
 125             if ext == 'm3u8':
 126                 formats.extend(self._extract_m3u8_formats(
 127                     video_url, video_id, 'mp4', 'm3u8_native',
 128                     m3u8_id='hls', fatal=False))
 129             elif ext == 'mpd':
 130                 formats.extend(self._extract_mpd_formats(
 131                     video_url, video_id, 'dash', fatal=False))
 132             else:
 133                 formats.append({
 134                     'format_id': quality,
 135                     'quality': q(quality),
 136                     'url': video_url,
 137                 })
 138         self._sort_formats(formats)
 139         return formats
 140
 141     def _real_extract(self, url):
 142         video_id = self._match_id(url)
 143         info = self._download_json(
 144             'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
 145             video_id)['page']['items'][0]
 146         if info['state'] == 'DESPU':
 147             raise ExtractorError('The video is no longer available', expected=True)
 148         title = info['title'].strip()
 149         formats = self._extract_png_formats(video_id)
 150
 151         subtitles = None
 152         sbt_file = info.get('sbtFile')
 153         if sbt_file:
 154             subtitles = self.extract_subtitles(video_id, sbt_file)
 155
 156         is_live = info.get('live') is True
 157
 158         return {
 159             'id': video_id,
 160             'title': title,
 161             'formats': formats,
 162             'thumbnail': info.get('image'),
 163             'subtitles': subtitles,
 164             'duration': float_or_none(info.get('duration'), 1000),
 165             'is_live': is_live,
 166             'series': info.get('programTitle'),
 167         }
 168
 169     def _get_subtitles(self, video_id, sub_file):
 170         subs = self._download_json(
 171             sub_file + '.json', video_id,
 172             'Downloading subtitles info')['page']['items']
 173         return dict(
 174             (s['lang'], [{'ext': 'vtt', 'url': s['src']}])
 175             for s in subs)
 176
 177
 178 class RTVEAudioIE(RTVEALaCartaIE):
 179     IE_NAME = 'rtve.es:audio'
 180     IE_DESC = 'RTVE audio'
 181     _VALID_URL = r'https?://(?:www\.)?rtve\.es/(alacarta|play)/audios/[^/]+/[^/]+/(?P<id>[0-9]+)'
 182
 183     _TESTS = [{
 184         'url': 'https://www.rtve.es/alacarta/audios/a-hombros-de-gigantes/palabra-ingeniero-codigos-informaticos-27-04-21/5889192/',
 185         'md5': 'ae06d27bff945c4e87a50f89f6ce48ce',
 186         'info_dict': {
 187             'id': '5889192',
 188             'ext': 'mp3',
 189             'title': 'Códigos informáticos',
 190             'thumbnail': r're:https?://.+/1598856591583.jpg',
 191             'duration': 349.440,
 192             'series': 'A hombros de gigantes',
 193         },
 194     }, {
 195         'url': 'https://www.rtve.es/play/audios/en-radio-3/ignatius-farray/5791165/',
 196         'md5': '072855ab89a9450e0ba314c717fa5ebc',
 197         'info_dict': {
 198             'id': '5791165',
 199             'ext': 'mp3',
 200             'title': 'Ignatius Farray',
 201             'thumbnail': r're:https?://.+/1613243011863.jpg',
 202             'duration': 3559.559,
 203             'series': 'En Radio 3'
 204         },
 205     }, {
 206         'url': 'https://www.rtve.es/play/audios/frankenstein-o-el-moderno-prometeo/capitulo-26-ultimo-muerte-victor-juan-jose-plans-mary-shelley/6082623/',
 207         'md5': '0eadab248cc8dd193fa5765712e84d5c',
 208         'info_dict': {
 209             'id': '6082623',
 210             'ext': 'mp3',
 211             'title': 'Capítulo 26 y último: La muerte de Victor',
 212             'thumbnail': r're:https?://.+/1632147445707.jpg',
 213             'duration': 3174.086,
 214             'series': 'Frankenstein o el moderno Prometeo'
 215         },
 216     }]
 217
 218     def _extract_png_formats(self, audio_id):
 219         """
 220         This function retrieves media related png thumbnail which obfuscate
 221         valuable information about the media. This information is decrypted
 222         via base class _decrypt_url function providing media quality and
 223         media url
 224         """
 225         png = self._download_webpage(
 226             'http://www.rtve.es/ztnr/movil/thumbnail/%s/audios/%s.png' %
 227             (self._manager, audio_id),
 228             audio_id, 'Downloading url information', query={'q': 'v2'})
 229         q = qualities(['Media', 'Alta', 'HQ', 'HD_READY', 'HD_FULL'])
 230         formats = []
 231         for quality, audio_url in self._decrypt_url(png):
 232             ext = determine_ext(audio_url)
 233             if ext == 'm3u8':
 234                 formats.extend(self._extract_m3u8_formats(
 235                     audio_url, audio_id, 'mp4', 'm3u8_native',
 236                     m3u8_id='hls', fatal=False))
 237             elif ext == 'mpd':
 238                 formats.extend(self._extract_mpd_formats(
 239                     audio_url, audio_id, 'dash', fatal=False))
 240             else:
 241                 formats.append({
 242                     'format_id': quality,
 243                     'quality': q(quality),
 244                     'url': audio_url,
 245                 })
 246         self._sort_formats(formats)
 247         return formats
 248
 249     def _real_extract(self, url):
 250         audio_id = self._match_id(url)
 251         info = self._download_json(
 252             'https://www.rtve.es/api/audios/%s.json' % audio_id,
 253             audio_id)['page']['items'][0]
 254
 255         return {
 256             'id': audio_id,
 257             'title': info['title'].strip(),
 258             'thumbnail': info.get('thumbnail'),
 259             'duration': float_or_none(info.get('duration'), 1000),
 260             'series': try_get(info, lambda x: x['programInfo']['title']),
 261             'formats': self._extract_png_formats(audio_id),
 262         }
 263
 264
 265 class RTVEInfantilIE(RTVEALaCartaIE):
 266     IE_NAME = 'rtve.es:infantil'
 267     IE_DESC = 'RTVE infantil'
 268     _VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/[^/]+/video/[^/]+/(?P<id>[0-9]+)/'
 269
 270     _TESTS = [{
 271         'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/',
 272         'md5': '5747454717aedf9f9fdf212d1bcfc48d',
 273         'info_dict': {
 274             'id': '3040283',
 275             'ext': 'mp4',
 276             'title': 'Maneras de vivir',
 277             'thumbnail': r're:https?://.+/1426182947956\.JPG',
 278             'duration': 357.958,
 279         },
 280         'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
 281     }]
 282
 283
 284 class RTVELiveIE(RTVEALaCartaIE):
 285     IE_NAME = 'rtve.es:live'
 286     IE_DESC = 'RTVE.es live streams'
 287     _VALID_URL = r'https?://(?:www\.)?rtve\.es/directo/(?P<id>[a-zA-Z0-9-]+)'
 288
 289     _TESTS = [{
 290         'url': 'http://www.rtve.es/directo/la-1/',
 291         'info_dict': {
 292             'id': 'la-1',
 293             'ext': 'mp4',
 294             'title': 're:^La 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
 295         },
 296         'params': {
 297             'skip_download': 'live stream',
 298         }
 299     }]
 300
 301     def _real_extract(self, url):
 302         mobj = self._match_valid_url(url)
 303         video_id = mobj.group('id')
 304
 305         webpage = self._download_webpage(url, video_id)
 306         title = remove_end(self._og_search_title(webpage), ' en directo en RTVE.es')
 307         title = remove_start(title, 'Estoy viendo ')
 308
 309         vidplayer_id = self._search_regex(
 310             (r'playerId=player([0-9]+)',
 311              r'class=["\'].*?\blive_mod\b.*?["\'][^>]+data-assetid=["\'](\d+)',
 312              r'data-id=["\'](\d+)'),
 313             webpage, 'internal video ID')
 314
 315         return {
 316             'id': video_id,
 317             'title': title,
 318             'formats': self._extract_png_formats(vidplayer_id),
 319             'is_live': True,
 320         }
 321
 322
 323 class RTVETelevisionIE(InfoExtractor):
 324     IE_NAME = 'rtve.es:television'
 325     _VALID_URL = r'https?://(?:www\.)?rtve\.es/television/[^/]+/[^/]+/(?P<id>\d+).shtml'
 326
 327     _TEST = {
 328         'url': 'http://www.rtve.es/television/20160628/revolucion-del-movil/1364141.shtml',
 329         'info_dict': {
 330             'id': '3069778',
 331             'ext': 'mp4',
 332             'title': 'Documentos TV - La revolución del móvil',
 333             'duration': 3496.948,
 334         },
 335         'params': {
 336             'skip_download': True,
 337         },
 338     }
 339
 340     def _real_extract(self, url):
 341         page_id = self._match_id(url)
 342         webpage = self._download_webpage(url, page_id)
 343
 344         alacarta_url = self._search_regex(
 345             r'data-location="alacarta_videos"[^<]+url&quot;:&quot;(http://www\.rtve\.es/alacarta.+?)&',
 346             webpage, 'alacarta url', default=None)
 347         if alacarta_url is None:
 348             raise ExtractorError(
 349                 'The webpage doesn\'t contain any video', expected=True)
 350
 351         return self.url_result(alacarta_url, ie=RTVEALaCartaIE.ie_key())