yt_dlp/extractor/rtve.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import base64
   5 import io
   6 import sys
   7
   8 from .common import InfoExtractor
   9 from ..compat import (
  10     compat_b64decode,
  11     compat_struct_unpack,
  12 )
  13 from ..utils import (
  14     determine_ext,
  15     ExtractorError,
  16     float_or_none,
  17     qualities,
  18     remove_end,
  19     remove_start,
  20     try_get,
  21 )
  22
  23 _bytes_to_chr = (lambda x: x) if sys.version_info[0] == 2 else (lambda x: map(chr, x))
  24
  25
  26 class RTVEALaCartaIE(InfoExtractor):
  27     IE_NAME = 'rtve.es:alacarta'
  28     IE_DESC = 'RTVE a la carta'
  29     _VALID_URL = r'https?://(?:www\.)?rtve\.es/(m/)?(alacarta/videos|filmoteca)/[^/]+/[^/]+/(?P<id>\d+)'
  30
  31     _TESTS = [{
  32         'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
  33         'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43',
  34         'info_dict': {
  35             'id': '2491869',
  36             'ext': 'mp4',
  37             'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia',
  38             'duration': 5024.566,
  39             'series': 'Balonmano',
  40         },
  41         'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
  42     }, {
  43         'note': 'Live stream',
  44         'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/',
  45         'info_dict': {
  46             'id': '1694255',
  47             'ext': 'mp4',
  48             'title': 're:^24H LIVE [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  49             'is_live': True,
  50         },
  51         'params': {
  52             'skip_download': 'live stream',
  53         },
  54     }, {
  55         'url': 'http://www.rtve.es/alacarta/videos/servir-y-proteger/servir-proteger-capitulo-104/4236788/',
  56         'md5': 'd850f3c8731ea53952ebab489cf81cbf',
  57         'info_dict': {
  58             'id': '4236788',
  59             'ext': 'mp4',
  60             'title': 'Servir y proteger - Capítulo 104',
  61             'duration': 3222.0,
  62         },
  63         'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
  64     }, {
  65         'url': 'http://www.rtve.es/m/alacarta/videos/cuentame-como-paso/cuentame-como-paso-t16-ultimo-minuto-nuestra-vida-capitulo-276/2969138/?media=tve',
  66         'only_matching': True,
  67     }, {
  68         'url': 'http://www.rtve.es/filmoteca/no-do/not-1-introduccion-primer-noticiario-espanol/1465256/',
  69         'only_matching': True,
  70     }]
  71
  72     def _real_initialize(self):
  73         user_agent_b64 = base64.b64encode(self.get_param('http_headers')['User-Agent'].encode('utf-8')).decode('utf-8')
  74         self._manager = self._download_json(
  75             'http://www.rtve.es/odin/loki/' + user_agent_b64,
  76             None, 'Fetching manager info')['manager']
  77
  78     @staticmethod
  79     def _decrypt_url(png):
  80         encrypted_data = io.BytesIO(compat_b64decode(png)[8:])
  81         while True:
  82             length = compat_struct_unpack('!I', encrypted_data.read(4))[0]
  83             chunk_type = encrypted_data.read(4)
  84             if chunk_type == b'IEND':
  85                 break
  86             data = encrypted_data.read(length)
  87             if chunk_type == b'tEXt':
  88                 alphabet_data, text = data.split(b'\0')
  89                 quality, url_data = text.split(b'%%')
  90                 alphabet = []
  91                 e = 0
  92                 d = 0
  93                 for l in _bytes_to_chr(alphabet_data):
  94                     if d == 0:
  95                         alphabet.append(l)
  96                         d = e = (e + 1) % 4
  97                     else:
  98                         d -= 1
  99                 url = ''
 100                 f = 0
 101                 e = 3
 102                 b = 1
 103                 for letter in _bytes_to_chr(url_data):
 104                     if f == 0:
 105                         l = int(letter) * 10
 106                         f = 1
 107                     else:
 108                         if e == 0:
 109                             l += int(letter)
 110                             url += alphabet[l]
 111                             e = (b + 3) % 4
 112                             f = 0
 113                             b += 1
 114                         else:
 115                             e -= 1
 116
 117                 yield quality.decode(), url
 118             encrypted_data.read(4)  # CRC
 119
 120     def _extract_png_formats(self, video_id):
 121         png = self._download_webpage(
 122             'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id),
 123             video_id, 'Downloading url information', query={'q': 'v2'})
 124         q = qualities(['Media', 'Alta', 'HQ', 'HD_READY', 'HD_FULL'])
 125         formats = []
 126         for quality, video_url in self._decrypt_url(png):
 127             ext = determine_ext(video_url)
 128             if ext == 'm3u8':
 129                 formats.extend(self._extract_m3u8_formats(
 130                     video_url, video_id, 'mp4', 'm3u8_native',
 131                     m3u8_id='hls', fatal=False))
 132             elif ext == 'mpd':
 133                 formats.extend(self._extract_mpd_formats(
 134                     video_url, video_id, 'dash', fatal=False))
 135             else:
 136                 formats.append({
 137                     'format_id': quality,
 138                     'quality': q(quality),
 139                     'url': video_url,
 140                 })
 141         self._sort_formats(formats)
 142         return formats
 143
 144     def _real_extract(self, url):
 145         video_id = self._match_id(url)
 146         info = self._download_json(
 147             'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
 148             video_id)['page']['items'][0]
 149         if info['state'] == 'DESPU':
 150             raise ExtractorError('The video is no longer available', expected=True)
 151         title = info['title'].strip()
 152         formats = self._extract_png_formats(video_id)
 153
 154         subtitles = None
 155         sbt_file = info.get('sbtFile')
 156         if sbt_file:
 157             subtitles = self.extract_subtitles(video_id, sbt_file)
 158
 159         is_live = info.get('live') is True
 160
 161         return {
 162             'id': video_id,
 163             'title': title,
 164             'formats': formats,
 165             'thumbnail': info.get('image'),
 166             'subtitles': subtitles,
 167             'duration': float_or_none(info.get('duration'), 1000),
 168             'is_live': is_live,
 169             'series': info.get('programTitle'),
 170         }
 171
 172     def _get_subtitles(self, video_id, sub_file):
 173         subs = self._download_json(
 174             sub_file + '.json', video_id,
 175             'Downloading subtitles info')['page']['items']
 176         return dict(
 177             (s['lang'], [{'ext': 'vtt', 'url': s['src']}])
 178             for s in subs)
 179
 180
 181 class RTVEAudioIE(RTVEALaCartaIE):
 182     IE_NAME = 'rtve.es:audio'
 183     IE_DESC = 'RTVE audio'
 184     _VALID_URL = r'https?://(?:www\.)?rtve\.es/(alacarta|play)/audios/[^/]+/[^/]+/(?P<id>[0-9]+)'
 185
 186     _TESTS = [{
 187         'url': 'https://www.rtve.es/alacarta/audios/a-hombros-de-gigantes/palabra-ingeniero-codigos-informaticos-27-04-21/5889192/',
 188         'md5': 'ae06d27bff945c4e87a50f89f6ce48ce',
 189         'info_dict': {
 190             'id': '5889192',
 191             'ext': 'mp3',
 192             'title': 'Códigos informáticos',
 193             'thumbnail': r're:https?://.+/1598856591583.jpg',
 194             'duration': 349.440,
 195             'series': 'A hombros de gigantes',
 196         },
 197     }, {
 198         'url': 'https://www.rtve.es/play/audios/en-radio-3/ignatius-farray/5791165/',
 199         'md5': '072855ab89a9450e0ba314c717fa5ebc',
 200         'info_dict': {
 201             'id': '5791165',
 202             'ext': 'mp3',
 203             'title': 'Ignatius Farray',
 204             'thumbnail': r're:https?://.+/1613243011863.jpg',
 205             'duration': 3559.559,
 206             'series': 'En Radio 3'
 207         },
 208     }, {
 209         'url': 'https://www.rtve.es/play/audios/frankenstein-o-el-moderno-prometeo/capitulo-26-ultimo-muerte-victor-juan-jose-plans-mary-shelley/6082623/',
 210         'md5': '0eadab248cc8dd193fa5765712e84d5c',
 211         'info_dict': {
 212             'id': '6082623',
 213             'ext': 'mp3',
 214             'title': 'Capítulo 26 y último: La muerte de Victor',
 215             'thumbnail': r're:https?://.+/1632147445707.jpg',
 216             'duration': 3174.086,
 217             'series': 'Frankenstein o el moderno Prometeo'
 218         },
 219     }]
 220
 221     def _extract_png_formats(self, audio_id):
 222         """
 223         This function retrieves media related png thumbnail which obfuscate
 224         valuable information about the media. This information is decrypted
 225         via base class _decrypt_url function providing media quality and
 226         media url
 227         """
 228         png = self._download_webpage(
 229             'http://www.rtve.es/ztnr/movil/thumbnail/%s/audios/%s.png' %
 230             (self._manager, audio_id),
 231             audio_id, 'Downloading url information', query={'q': 'v2'})
 232         q = qualities(['Media', 'Alta', 'HQ', 'HD_READY', 'HD_FULL'])
 233         formats = []
 234         for quality, audio_url in self._decrypt_url(png):
 235             ext = determine_ext(audio_url)
 236             if ext == 'm3u8':
 237                 formats.extend(self._extract_m3u8_formats(
 238                     audio_url, audio_id, 'mp4', 'm3u8_native',
 239                     m3u8_id='hls', fatal=False))
 240             elif ext == 'mpd':
 241                 formats.extend(self._extract_mpd_formats(
 242                     audio_url, audio_id, 'dash', fatal=False))
 243             else:
 244                 formats.append({
 245                     'format_id': quality,
 246                     'quality': q(quality),
 247                     'url': audio_url,
 248                 })
 249         self._sort_formats(formats)
 250         return formats
 251
 252     def _real_extract(self, url):
 253         audio_id = self._match_id(url)
 254         info = self._download_json(
 255             'https://www.rtve.es/api/audios/%s.json' % audio_id,
 256             audio_id)['page']['items'][0]
 257
 258         return {
 259             'id': audio_id,
 260             'title': info['title'].strip(),
 261             'thumbnail': info.get('thumbnail'),
 262             'duration': float_or_none(info.get('duration'), 1000),
 263             'series': try_get(info, lambda x: x['programInfo']['title']),
 264             'formats': self._extract_png_formats(audio_id),
 265         }
 266
 267
 268 class RTVEInfantilIE(RTVEALaCartaIE):
 269     IE_NAME = 'rtve.es:infantil'
 270     IE_DESC = 'RTVE infantil'
 271     _VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/[^/]+/video/[^/]+/(?P<id>[0-9]+)/'
 272
 273     _TESTS = [{
 274         'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/',
 275         'md5': '5747454717aedf9f9fdf212d1bcfc48d',
 276         'info_dict': {
 277             'id': '3040283',
 278             'ext': 'mp4',
 279             'title': 'Maneras de vivir',
 280             'thumbnail': r're:https?://.+/1426182947956\.JPG',
 281             'duration': 357.958,
 282         },
 283         'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
 284     }]
 285
 286
 287 class RTVELiveIE(RTVEALaCartaIE):
 288     IE_NAME = 'rtve.es:live'
 289     IE_DESC = 'RTVE.es live streams'
 290     _VALID_URL = r'https?://(?:www\.)?rtve\.es/directo/(?P<id>[a-zA-Z0-9-]+)'
 291
 292     _TESTS = [{
 293         'url': 'http://www.rtve.es/directo/la-1/',
 294         'info_dict': {
 295             'id': 'la-1',
 296             'ext': 'mp4',
 297             'title': 're:^La 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
 298         },
 299         'params': {
 300             'skip_download': 'live stream',
 301         }
 302     }]
 303
 304     def _real_extract(self, url):
 305         mobj = self._match_valid_url(url)
 306         video_id = mobj.group('id')
 307
 308         webpage = self._download_webpage(url, video_id)
 309         title = remove_end(self._og_search_title(webpage), ' en directo en RTVE.es')
 310         title = remove_start(title, 'Estoy viendo ')
 311
 312         vidplayer_id = self._search_regex(
 313             (r'playerId=player([0-9]+)',
 314              r'class=["\'].*?\blive_mod\b.*?["\'][^>]+data-assetid=["\'](\d+)',
 315              r'data-id=["\'](\d+)'),
 316             webpage, 'internal video ID')
 317
 318         return {
 319             'id': video_id,
 320             'title': title,
 321             'formats': self._extract_png_formats(vidplayer_id),
 322             'is_live': True,
 323         }
 324
 325
 326 class RTVETelevisionIE(InfoExtractor):
 327     IE_NAME = 'rtve.es:television'
 328     _VALID_URL = r'https?://(?:www\.)?rtve\.es/television/[^/]+/[^/]+/(?P<id>\d+).shtml'
 329
 330     _TEST = {
 331         'url': 'http://www.rtve.es/television/20160628/revolucion-del-movil/1364141.shtml',
 332         'info_dict': {
 333             'id': '3069778',
 334             'ext': 'mp4',
 335             'title': 'Documentos TV - La revolución del móvil',
 336             'duration': 3496.948,
 337         },
 338         'params': {
 339             'skip_download': True,
 340         },
 341     }
 342
 343     def _real_extract(self, url):
 344         page_id = self._match_id(url)
 345         webpage = self._download_webpage(url, page_id)
 346
 347         alacarta_url = self._search_regex(
 348             r'data-location="alacarta_videos"[^<]+url&quot;:&quot;(http://www\.rtve\.es/alacarta.+?)&',
 349             webpage, 'alacarta url', default=None)
 350         if alacarta_url is None:
 351             raise ExtractorError(
 352                 'The webpage doesn\'t contain any video', expected=True)
 353
 354         return self.url_result(alacarta_url, ie=RTVEALaCartaIE.ie_key())