yt_dlp/extractor/rtve.py

   1 import base64
   2 import io
   3 import struct
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_b64decode
   7 from ..utils import (
   8     ExtractorError,
   9     determine_ext,
  10     float_or_none,
  11     qualities,
  12     remove_end,
  13     remove_start,
  14     try_get,
  15 )
  16
  17
  18 class RTVEALaCartaIE(InfoExtractor):
  19     IE_NAME = 'rtve.es:alacarta'
  20     IE_DESC = 'RTVE a la carta'
  21     _VALID_URL = r'https?://(?:www\.)?rtve\.es/(m/)?(alacarta/videos|filmoteca)/[^/]+/[^/]+/(?P<id>\d+)'
  22
  23     _TESTS = [{
  24         'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
  25         'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43',
  26         'info_dict': {
  27             'id': '2491869',
  28             'ext': 'mp4',
  29             'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia',
  30             'duration': 5024.566,
  31             'series': 'Balonmano',
  32         },
  33         'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
  34     }, {
  35         'note': 'Live stream',
  36         'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/',
  37         'info_dict': {
  38             'id': '1694255',
  39             'ext': 'mp4',
  40             'title': 're:^24H LIVE [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  41             'is_live': True,
  42         },
  43         'params': {
  44             'skip_download': 'live stream',
  45         },
  46     }, {
  47         'url': 'http://www.rtve.es/alacarta/videos/servir-y-proteger/servir-proteger-capitulo-104/4236788/',
  48         'md5': 'd850f3c8731ea53952ebab489cf81cbf',
  49         'info_dict': {
  50             'id': '4236788',
  51             'ext': 'mp4',
  52             'title': 'Servir y proteger - Capítulo 104',
  53             'duration': 3222.0,
  54         },
  55         'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
  56     }, {
  57         'url': 'http://www.rtve.es/m/alacarta/videos/cuentame-como-paso/cuentame-como-paso-t16-ultimo-minuto-nuestra-vida-capitulo-276/2969138/?media=tve',
  58         'only_matching': True,
  59     }, {
  60         'url': 'http://www.rtve.es/filmoteca/no-do/not-1-introduccion-primer-noticiario-espanol/1465256/',
  61         'only_matching': True,
  62     }]
  63
  64     def _real_initialize(self):
  65         user_agent_b64 = base64.b64encode(self.get_param('http_headers')['User-Agent'].encode('utf-8')).decode('utf-8')
  66         self._manager = self._download_json(
  67             'http://www.rtve.es/odin/loki/' + user_agent_b64,
  68             None, 'Fetching manager info')['manager']
  69
  70     @staticmethod
  71     def _decrypt_url(png):
  72         encrypted_data = io.BytesIO(compat_b64decode(png)[8:])
  73         while True:
  74             length = struct.unpack('!I', encrypted_data.read(4))[0]
  75             chunk_type = encrypted_data.read(4)
  76             if chunk_type == b'IEND':
  77                 break
  78             data = encrypted_data.read(length)
  79             if chunk_type == b'tEXt':
  80                 alphabet_data, text = data.split(b'\0')
  81                 quality, url_data = text.split(b'%%')
  82                 alphabet = []
  83                 e = 0
  84                 d = 0
  85                 for l in alphabet_data.decode('iso-8859-1'):
  86                     if d == 0:
  87                         alphabet.append(l)
  88                         d = e = (e + 1) % 4
  89                     else:
  90                         d -= 1
  91                 url = ''
  92                 f = 0
  93                 e = 3
  94                 b = 1
  95                 for letter in url_data.decode('iso-8859-1'):
  96                     if f == 0:
  97                         l = int(letter) * 10
  98                         f = 1
  99                     else:
 100                         if e == 0:
 101                             l += int(letter)
 102                             url += alphabet[l]
 103                             e = (b + 3) % 4
 104                             f = 0
 105                             b += 1
 106                         else:
 107                             e -= 1
 108
 109                 yield quality.decode(), url
 110             encrypted_data.read(4)  # CRC
 111
 112     def _extract_png_formats(self, video_id):
 113         png = self._download_webpage(
 114             'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id),
 115             video_id, 'Downloading url information', query={'q': 'v2'})
 116         q = qualities(['Media', 'Alta', 'HQ', 'HD_READY', 'HD_FULL'])
 117         formats = []
 118         for quality, video_url in self._decrypt_url(png):
 119             ext = determine_ext(video_url)
 120             if ext == 'm3u8':
 121                 formats.extend(self._extract_m3u8_formats(
 122                     video_url, video_id, 'mp4', 'm3u8_native',
 123                     m3u8_id='hls', fatal=False))
 124             elif ext == 'mpd':
 125                 formats.extend(self._extract_mpd_formats(
 126                     video_url, video_id, 'dash', fatal=False))
 127             else:
 128                 formats.append({
 129                     'format_id': quality,
 130                     'quality': q(quality),
 131                     'url': video_url,
 132                 })
 133         return formats
 134
 135     def _real_extract(self, url):
 136         video_id = self._match_id(url)
 137         info = self._download_json(
 138             'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
 139             video_id)['page']['items'][0]
 140         if info['state'] == 'DESPU':
 141             raise ExtractorError('The video is no longer available', expected=True)
 142         title = info['title'].strip()
 143         formats = self._extract_png_formats(video_id)
 144
 145         subtitles = None
 146         sbt_file = info.get('sbtFile')
 147         if sbt_file:
 148             subtitles = self.extract_subtitles(video_id, sbt_file)
 149
 150         is_live = info.get('live') is True
 151
 152         return {
 153             'id': video_id,
 154             'title': title,
 155             'formats': formats,
 156             'thumbnail': info.get('image'),
 157             'subtitles': subtitles,
 158             'duration': float_or_none(info.get('duration'), 1000),
 159             'is_live': is_live,
 160             'series': info.get('programTitle'),
 161         }
 162
 163     def _get_subtitles(self, video_id, sub_file):
 164         subs = self._download_json(
 165             sub_file + '.json', video_id,
 166             'Downloading subtitles info')['page']['items']
 167         return dict(
 168             (s['lang'], [{'ext': 'vtt', 'url': s['src']}])
 169             for s in subs)
 170
 171
 172 class RTVEAudioIE(RTVEALaCartaIE):  # XXX: Do not subclass from concrete IE
 173     IE_NAME = 'rtve.es:audio'
 174     IE_DESC = 'RTVE audio'
 175     _VALID_URL = r'https?://(?:www\.)?rtve\.es/(alacarta|play)/audios/[^/]+/[^/]+/(?P<id>[0-9]+)'
 176
 177     _TESTS = [{
 178         'url': 'https://www.rtve.es/alacarta/audios/a-hombros-de-gigantes/palabra-ingeniero-codigos-informaticos-27-04-21/5889192/',
 179         'md5': 'ae06d27bff945c4e87a50f89f6ce48ce',
 180         'info_dict': {
 181             'id': '5889192',
 182             'ext': 'mp3',
 183             'title': 'Códigos informáticos',
 184             'thumbnail': r're:https?://.+/1598856591583.jpg',
 185             'duration': 349.440,
 186             'series': 'A hombros de gigantes',
 187         },
 188     }, {
 189         'url': 'https://www.rtve.es/play/audios/en-radio-3/ignatius-farray/5791165/',
 190         'md5': '072855ab89a9450e0ba314c717fa5ebc',
 191         'info_dict': {
 192             'id': '5791165',
 193             'ext': 'mp3',
 194             'title': 'Ignatius Farray',
 195             'thumbnail': r're:https?://.+/1613243011863.jpg',
 196             'duration': 3559.559,
 197             'series': 'En Radio 3'
 198         },
 199     }, {
 200         'url': 'https://www.rtve.es/play/audios/frankenstein-o-el-moderno-prometeo/capitulo-26-ultimo-muerte-victor-juan-jose-plans-mary-shelley/6082623/',
 201         'md5': '0eadab248cc8dd193fa5765712e84d5c',
 202         'info_dict': {
 203             'id': '6082623',
 204             'ext': 'mp3',
 205             'title': 'Capítulo 26 y último: La muerte de Victor',
 206             'thumbnail': r're:https?://.+/1632147445707.jpg',
 207             'duration': 3174.086,
 208             'series': 'Frankenstein o el moderno Prometeo'
 209         },
 210     }]
 211
 212     def _extract_png_formats(self, audio_id):
 213         """
 214         This function retrieves media related png thumbnail which obfuscate
 215         valuable information about the media. This information is decrypted
 216         via base class _decrypt_url function providing media quality and
 217         media url
 218         """
 219         png = self._download_webpage(
 220             'http://www.rtve.es/ztnr/movil/thumbnail/%s/audios/%s.png' %
 221             (self._manager, audio_id),
 222             audio_id, 'Downloading url information', query={'q': 'v2'})
 223         q = qualities(['Media', 'Alta', 'HQ', 'HD_READY', 'HD_FULL'])
 224         formats = []
 225         for quality, audio_url in self._decrypt_url(png):
 226             ext = determine_ext(audio_url)
 227             if ext == 'm3u8':
 228                 formats.extend(self._extract_m3u8_formats(
 229                     audio_url, audio_id, 'mp4', 'm3u8_native',
 230                     m3u8_id='hls', fatal=False))
 231             elif ext == 'mpd':
 232                 formats.extend(self._extract_mpd_formats(
 233                     audio_url, audio_id, 'dash', fatal=False))
 234             else:
 235                 formats.append({
 236                     'format_id': quality,
 237                     'quality': q(quality),
 238                     'url': audio_url,
 239                 })
 240         return formats
 241
 242     def _real_extract(self, url):
 243         audio_id = self._match_id(url)
 244         info = self._download_json(
 245             'https://www.rtve.es/api/audios/%s.json' % audio_id,
 246             audio_id)['page']['items'][0]
 247
 248         return {
 249             'id': audio_id,
 250             'title': info['title'].strip(),
 251             'thumbnail': info.get('thumbnail'),
 252             'duration': float_or_none(info.get('duration'), 1000),
 253             'series': try_get(info, lambda x: x['programInfo']['title']),
 254             'formats': self._extract_png_formats(audio_id),
 255         }
 256
 257
 258 class RTVEInfantilIE(RTVEALaCartaIE):  # XXX: Do not subclass from concrete IE
 259     IE_NAME = 'rtve.es:infantil'
 260     IE_DESC = 'RTVE infantil'
 261     _VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/[^/]+/video/[^/]+/(?P<id>[0-9]+)/'
 262
 263     _TESTS = [{
 264         'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/',
 265         'md5': '5747454717aedf9f9fdf212d1bcfc48d',
 266         'info_dict': {
 267             'id': '3040283',
 268             'ext': 'mp4',
 269             'title': 'Maneras de vivir',
 270             'thumbnail': r're:https?://.+/1426182947956\.JPG',
 271             'duration': 357.958,
 272         },
 273         'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
 274     }]
 275
 276
 277 class RTVELiveIE(RTVEALaCartaIE):  # XXX: Do not subclass from concrete IE
 278     IE_NAME = 'rtve.es:live'
 279     IE_DESC = 'RTVE.es live streams'
 280     _VALID_URL = r'https?://(?:www\.)?rtve\.es/directo/(?P<id>[a-zA-Z0-9-]+)'
 281
 282     _TESTS = [{
 283         'url': 'http://www.rtve.es/directo/la-1/',
 284         'info_dict': {
 285             'id': 'la-1',
 286             'ext': 'mp4',
 287             'title': 're:^La 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
 288         },
 289         'params': {
 290             'skip_download': 'live stream',
 291         }
 292     }]
 293
 294     def _real_extract(self, url):
 295         mobj = self._match_valid_url(url)
 296         video_id = mobj.group('id')
 297
 298         webpage = self._download_webpage(url, video_id)
 299         title = remove_end(self._og_search_title(webpage), ' en directo en RTVE.es')
 300         title = remove_start(title, 'Estoy viendo ')
 301
 302         vidplayer_id = self._search_regex(
 303             (r'playerId=player([0-9]+)',
 304              r'class=["\'].*?\blive_mod\b.*?["\'][^>]+data-assetid=["\'](\d+)',
 305              r'data-id=["\'](\d+)'),
 306             webpage, 'internal video ID')
 307
 308         return {
 309             'id': video_id,
 310             'title': title,
 311             'formats': self._extract_png_formats(vidplayer_id),
 312             'is_live': True,
 313         }
 314
 315
 316 class RTVETelevisionIE(InfoExtractor):
 317     IE_NAME = 'rtve.es:television'
 318     _VALID_URL = r'https?://(?:www\.)?rtve\.es/television/[^/]+/[^/]+/(?P<id>\d+).shtml'
 319
 320     _TEST = {
 321         'url': 'http://www.rtve.es/television/20160628/revolucion-del-movil/1364141.shtml',
 322         'info_dict': {
 323             'id': '3069778',
 324             'ext': 'mp4',
 325             'title': 'Documentos TV - La revolución del móvil',
 326             'duration': 3496.948,
 327         },
 328         'params': {
 329             'skip_download': True,
 330         },
 331     }
 332
 333     def _real_extract(self, url):
 334         page_id = self._match_id(url)
 335         webpage = self._download_webpage(url, page_id)
 336
 337         alacarta_url = self._search_regex(
 338             r'data-location="alacarta_videos"[^<]+url&quot;:&quot;(http://www\.rtve\.es/alacarta.+?)&',
 339             webpage, 'alacarta url', default=None)
 340         if alacarta_url is None:
 341             raise ExtractorError(
 342                 'The webpage doesn\'t contain any video', expected=True)
 343
 344         return self.url_result(alacarta_url, ie=RTVEALaCartaIE.ie_key())