yt_dlp/extractor/rtve.py

   1 import base64
   2 import io
   3 import struct
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     ExtractorError,
   8     determine_ext,
   9     float_or_none,
  10     qualities,
  11     remove_end,
  12     remove_start,
  13     try_get,
  14 )
  15
  16
  17 class RTVEALaCartaIE(InfoExtractor):
  18     IE_NAME = 'rtve.es:alacarta'
  19     IE_DESC = 'RTVE a la carta'
  20     _VALID_URL = r'https?://(?:www\.)?rtve\.es/(m/)?(alacarta/videos|filmoteca)/[^/]+/[^/]+/(?P<id>\d+)'
  21
  22     _TESTS = [{
  23         'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
  24         'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43',
  25         'info_dict': {
  26             'id': '2491869',
  27             'ext': 'mp4',
  28             'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia',
  29             'duration': 5024.566,
  30             'series': 'Balonmano',
  31         },
  32         'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
  33     }, {
  34         'note': 'Live stream',
  35         'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/',
  36         'info_dict': {
  37             'id': '1694255',
  38             'ext': 'mp4',
  39             'title': 're:^24H LIVE [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  40             'is_live': True,
  41         },
  42         'params': {
  43             'skip_download': 'live stream',
  44         },
  45     }, {
  46         'url': 'http://www.rtve.es/alacarta/videos/servir-y-proteger/servir-proteger-capitulo-104/4236788/',
  47         'md5': 'd850f3c8731ea53952ebab489cf81cbf',
  48         'info_dict': {
  49             'id': '4236788',
  50             'ext': 'mp4',
  51             'title': 'Servir y proteger - Capítulo 104',
  52             'duration': 3222.0,
  53         },
  54         'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
  55     }, {
  56         'url': 'http://www.rtve.es/m/alacarta/videos/cuentame-como-paso/cuentame-como-paso-t16-ultimo-minuto-nuestra-vida-capitulo-276/2969138/?media=tve',
  57         'only_matching': True,
  58     }, {
  59         'url': 'http://www.rtve.es/filmoteca/no-do/not-1-introduccion-primer-noticiario-espanol/1465256/',
  60         'only_matching': True,
  61     }]
  62
  63     def _real_initialize(self):
  64         user_agent_b64 = base64.b64encode(self.get_param('http_headers')['User-Agent'].encode()).decode('utf-8')
  65         self._manager = self._download_json(
  66             'http://www.rtve.es/odin/loki/' + user_agent_b64,
  67             None, 'Fetching manager info')['manager']
  68
  69     @staticmethod
  70     def _decrypt_url(png):
  71         encrypted_data = io.BytesIO(base64.b64decode(png)[8:])
  72         while True:
  73             length = struct.unpack('!I', encrypted_data.read(4))[0]
  74             chunk_type = encrypted_data.read(4)
  75             if chunk_type == b'IEND':
  76                 break
  77             data = encrypted_data.read(length)
  78             if chunk_type == b'tEXt':
  79                 alphabet_data, text = data.split(b'\0')
  80                 quality, url_data = text.split(b'%%')
  81                 alphabet = []
  82                 e = 0
  83                 d = 0
  84                 for l in alphabet_data.decode('iso-8859-1'):
  85                     if d == 0:
  86                         alphabet.append(l)
  87                         d = e = (e + 1) % 4
  88                     else:
  89                         d -= 1
  90                 url = ''
  91                 f = 0
  92                 e = 3
  93                 b = 1
  94                 for letter in url_data.decode('iso-8859-1'):
  95                     if f == 0:
  96                         l = int(letter) * 10
  97                         f = 1
  98                     else:
  99                         if e == 0:
 100                             l += int(letter)
 101                             url += alphabet[l]
 102                             e = (b + 3) % 4
 103                             f = 0
 104                             b += 1
 105                         else:
 106                             e -= 1
 107
 108                 yield quality.decode(), url
 109             encrypted_data.read(4)  # CRC
 110
 111     def _extract_png_formats(self, video_id):
 112         png = self._download_webpage(
 113             f'http://www.rtve.es/ztnr/movil/thumbnail/{self._manager}/videos/{video_id}.png',
 114             video_id, 'Downloading url information', query={'q': 'v2'})
 115         q = qualities(['Media', 'Alta', 'HQ', 'HD_READY', 'HD_FULL'])
 116         formats = []
 117         for quality, video_url in self._decrypt_url(png):
 118             ext = determine_ext(video_url)
 119             if ext == 'm3u8':
 120                 formats.extend(self._extract_m3u8_formats(
 121                     video_url, video_id, 'mp4', 'm3u8_native',
 122                     m3u8_id='hls', fatal=False))
 123             elif ext == 'mpd':
 124                 formats.extend(self._extract_mpd_formats(
 125                     video_url, video_id, 'dash', fatal=False))
 126             else:
 127                 formats.append({
 128                     'format_id': quality,
 129                     'quality': q(quality),
 130                     'url': video_url,
 131                 })
 132         return formats
 133
 134     def _real_extract(self, url):
 135         video_id = self._match_id(url)
 136         info = self._download_json(
 137             f'http://www.rtve.es/api/videos/{video_id}/config/alacarta_videos.json',
 138             video_id)['page']['items'][0]
 139         if info['state'] == 'DESPU':
 140             raise ExtractorError('The video is no longer available', expected=True)
 141         title = info['title'].strip()
 142         formats = self._extract_png_formats(video_id)
 143
 144         subtitles = None
 145         sbt_file = info.get('sbtFile')
 146         if sbt_file:
 147             subtitles = self.extract_subtitles(video_id, sbt_file)
 148
 149         is_live = info.get('live') is True
 150
 151         return {
 152             'id': video_id,
 153             'title': title,
 154             'formats': formats,
 155             'thumbnail': info.get('image'),
 156             'subtitles': subtitles,
 157             'duration': float_or_none(info.get('duration'), 1000),
 158             'is_live': is_live,
 159             'series': info.get('programTitle'),
 160         }
 161
 162     def _get_subtitles(self, video_id, sub_file):
 163         subs = self._download_json(
 164             sub_file + '.json', video_id,
 165             'Downloading subtitles info')['page']['items']
 166         return dict(
 167             (s['lang'], [{'ext': 'vtt', 'url': s['src']}])
 168             for s in subs)
 169
 170
 171 class RTVEAudioIE(RTVEALaCartaIE):  # XXX: Do not subclass from concrete IE
 172     IE_NAME = 'rtve.es:audio'
 173     IE_DESC = 'RTVE audio'
 174     _VALID_URL = r'https?://(?:www\.)?rtve\.es/(alacarta|play)/audios/[^/]+/[^/]+/(?P<id>[0-9]+)'
 175
 176     _TESTS = [{
 177         'url': 'https://www.rtve.es/alacarta/audios/a-hombros-de-gigantes/palabra-ingeniero-codigos-informaticos-27-04-21/5889192/',
 178         'md5': 'ae06d27bff945c4e87a50f89f6ce48ce',
 179         'info_dict': {
 180             'id': '5889192',
 181             'ext': 'mp3',
 182             'title': 'Códigos informáticos',
 183             'thumbnail': r're:https?://.+/1598856591583.jpg',
 184             'duration': 349.440,
 185             'series': 'A hombros de gigantes',
 186         },
 187     }, {
 188         'url': 'https://www.rtve.es/play/audios/en-radio-3/ignatius-farray/5791165/',
 189         'md5': '072855ab89a9450e0ba314c717fa5ebc',
 190         'info_dict': {
 191             'id': '5791165',
 192             'ext': 'mp3',
 193             'title': 'Ignatius Farray',
 194             'thumbnail': r're:https?://.+/1613243011863.jpg',
 195             'duration': 3559.559,
 196             'series': 'En Radio 3',
 197         },
 198     }, {
 199         'url': 'https://www.rtve.es/play/audios/frankenstein-o-el-moderno-prometeo/capitulo-26-ultimo-muerte-victor-juan-jose-plans-mary-shelley/6082623/',
 200         'md5': '0eadab248cc8dd193fa5765712e84d5c',
 201         'info_dict': {
 202             'id': '6082623',
 203             'ext': 'mp3',
 204             'title': 'Capítulo 26 y último: La muerte de Victor',
 205             'thumbnail': r're:https?://.+/1632147445707.jpg',
 206             'duration': 3174.086,
 207             'series': 'Frankenstein o el moderno Prometeo',
 208         },
 209     }]
 210
 211     def _extract_png_formats(self, audio_id):
 212         """
 213         This function retrieves media related png thumbnail which obfuscate
 214         valuable information about the media. This information is decrypted
 215         via base class _decrypt_url function providing media quality and
 216         media url
 217         """
 218         png = self._download_webpage(
 219             f'http://www.rtve.es/ztnr/movil/thumbnail/{self._manager}/audios/{audio_id}.png',
 220             audio_id, 'Downloading url information', query={'q': 'v2'})
 221         q = qualities(['Media', 'Alta', 'HQ', 'HD_READY', 'HD_FULL'])
 222         formats = []
 223         for quality, audio_url in self._decrypt_url(png):
 224             ext = determine_ext(audio_url)
 225             if ext == 'm3u8':
 226                 formats.extend(self._extract_m3u8_formats(
 227                     audio_url, audio_id, 'mp4', 'm3u8_native',
 228                     m3u8_id='hls', fatal=False))
 229             elif ext == 'mpd':
 230                 formats.extend(self._extract_mpd_formats(
 231                     audio_url, audio_id, 'dash', fatal=False))
 232             else:
 233                 formats.append({
 234                     'format_id': quality,
 235                     'quality': q(quality),
 236                     'url': audio_url,
 237                 })
 238         return formats
 239
 240     def _real_extract(self, url):
 241         audio_id = self._match_id(url)
 242         info = self._download_json(
 243             f'https://www.rtve.es/api/audios/{audio_id}.json',
 244             audio_id)['page']['items'][0]
 245
 246         return {
 247             'id': audio_id,
 248             'title': info['title'].strip(),
 249             'thumbnail': info.get('thumbnail'),
 250             'duration': float_or_none(info.get('duration'), 1000),
 251             'series': try_get(info, lambda x: x['programInfo']['title']),
 252             'formats': self._extract_png_formats(audio_id),
 253         }
 254
 255
 256 class RTVEInfantilIE(RTVEALaCartaIE):  # XXX: Do not subclass from concrete IE
 257     IE_NAME = 'rtve.es:infantil'
 258     IE_DESC = 'RTVE infantil'
 259     _VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/[^/]+/video/[^/]+/(?P<id>[0-9]+)/'
 260
 261     _TESTS = [{
 262         'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/',
 263         'md5': '5747454717aedf9f9fdf212d1bcfc48d',
 264         'info_dict': {
 265             'id': '3040283',
 266             'ext': 'mp4',
 267             'title': 'Maneras de vivir',
 268             'thumbnail': r're:https?://.+/1426182947956\.JPG',
 269             'duration': 357.958,
 270         },
 271         'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
 272     }]
 273
 274
 275 class RTVELiveIE(RTVEALaCartaIE):  # XXX: Do not subclass from concrete IE
 276     IE_NAME = 'rtve.es:live'
 277     IE_DESC = 'RTVE.es live streams'
 278     _VALID_URL = r'https?://(?:www\.)?rtve\.es/directo/(?P<id>[a-zA-Z0-9-]+)'
 279
 280     _TESTS = [{
 281         'url': 'http://www.rtve.es/directo/la-1/',
 282         'info_dict': {
 283             'id': 'la-1',
 284             'ext': 'mp4',
 285             'title': 're:^La 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
 286         },
 287         'params': {
 288             'skip_download': 'live stream',
 289         },
 290     }]
 291
 292     def _real_extract(self, url):
 293         mobj = self._match_valid_url(url)
 294         video_id = mobj.group('id')
 295
 296         webpage = self._download_webpage(url, video_id)
 297         title = remove_end(self._og_search_title(webpage), ' en directo en RTVE.es')
 298         title = remove_start(title, 'Estoy viendo ')
 299
 300         vidplayer_id = self._search_regex(
 301             (r'playerId=player([0-9]+)',
 302              r'class=["\'].*?\blive_mod\b.*?["\'][^>]+data-assetid=["\'](\d+)',
 303              r'data-id=["\'](\d+)'),
 304             webpage, 'internal video ID')
 305
 306         return {
 307             'id': video_id,
 308             'title': title,
 309             'formats': self._extract_png_formats(vidplayer_id),
 310             'is_live': True,
 311         }
 312
 313
 314 class RTVETelevisionIE(InfoExtractor):
 315     IE_NAME = 'rtve.es:television'
 316     _VALID_URL = r'https?://(?:www\.)?rtve\.es/television/[^/]+/[^/]+/(?P<id>\d+).shtml'
 317
 318     _TEST = {
 319         'url': 'http://www.rtve.es/television/20160628/revolucion-del-movil/1364141.shtml',
 320         'info_dict': {
 321             'id': '3069778',
 322             'ext': 'mp4',
 323             'title': 'Documentos TV - La revolución del móvil',
 324             'duration': 3496.948,
 325         },
 326         'params': {
 327             'skip_download': True,
 328         },
 329     }
 330
 331     def _real_extract(self, url):
 332         page_id = self._match_id(url)
 333         webpage = self._download_webpage(url, page_id)
 334
 335         alacarta_url = self._search_regex(
 336             r'data-location="alacarta_videos"[^<]+url&quot;:&quot;(http://www\.rtve\.es/alacarta.+?)&',
 337             webpage, 'alacarta url', default=None)
 338         if alacarta_url is None:
 339             raise ExtractorError(
 340                 'The webpage doesn\'t contain any video', expected=True)
 341
 342         return self.url_result(alacarta_url, ie=RTVEALaCartaIE.ie_key())