Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/rtve.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import base64
   5 import re
   6 import time
   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     remove_end,
  18     remove_start,
  19     sanitized_Request,
  20     std_headers,
  21 )
  22
  23
  24 def _decrypt_url(png):
  25     encrypted_data = compat_b64decode(png)
  26     text_index = encrypted_data.find(b'tEXt')
  27     text_chunk = encrypted_data[text_index - 4:]
  28     length = compat_struct_unpack('!I', text_chunk[:4])[0]
  29     # Use bytearray to get integers when iterating in both python 2.x and 3.x
  30     data = bytearray(text_chunk[8:8 + length])
  31     data = [chr(b) for b in data if b != 0]
  32     hash_index = data.index('#')
  33     alphabet_data = data[:hash_index]
  34     url_data = data[hash_index + 1:]
  35     if url_data[0] == 'H' and url_data[3] == '%':
  36         # remove useless HQ%% at the start
  37         url_data = url_data[4:]
  38
  39     alphabet = []
  40     e = 0
  41     d = 0
  42     for l in alphabet_data:
  43         if d == 0:
  44             alphabet.append(l)
  45             d = e = (e + 1) % 4
  46         else:
  47             d -= 1
  48     url = ''
  49     f = 0
  50     e = 3
  51     b = 1
  52     for letter in url_data:
  53         if f == 0:
  54             l = int(letter) * 10
  55             f = 1
  56         else:
  57             if e == 0:
  58                 l += int(letter)
  59                 url += alphabet[l]
  60                 e = (b + 3) % 4
  61                 f = 0
  62                 b += 1
  63             else:
  64                 e -= 1
  65
  66     return url
  67
  68
  69 class RTVEALaCartaIE(InfoExtractor):
  70     IE_NAME = 'rtve.es:alacarta'
  71     IE_DESC = 'RTVE a la carta'
  72     _VALID_URL = r'https?://(?:www\.)?rtve\.es/(m/)?(alacarta/videos|filmoteca)/[^/]+/[^/]+/(?P<id>\d+)'
  73
  74     _TESTS = [{
  75         'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
  76         'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43',
  77         'info_dict': {
  78             'id': '2491869',
  79             'ext': 'mp4',
  80             'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia',
  81             'duration': 5024.566,
  82         },
  83     }, {
  84         'note': 'Live stream',
  85         'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/',
  86         'info_dict': {
  87             'id': '1694255',
  88             'ext': 'flv',
  89             'title': 'TODO',
  90         },
  91         'skip': 'The f4m manifest can\'t be used yet',
  92     }, {
  93         'url': 'http://www.rtve.es/alacarta/videos/servir-y-proteger/servir-proteger-capitulo-104/4236788/',
  94         'md5': 'e55e162379ad587e9640eda4f7353c0f',
  95         'info_dict': {
  96             'id': '4236788',
  97             'ext': 'mp4',
  98             'title': 'Servir y proteger - Capítulo 104 ',
  99             'duration': 3222.0,
 100         },
 101         'params': {
 102             'skip_download': True,  # requires ffmpeg
 103         },
 104     }, {
 105         'url': 'http://www.rtve.es/m/alacarta/videos/cuentame-como-paso/cuentame-como-paso-t16-ultimo-minuto-nuestra-vida-capitulo-276/2969138/?media=tve',
 106         'only_matching': True,
 107     }, {
 108         'url': 'http://www.rtve.es/filmoteca/no-do/not-1-introduccion-primer-noticiario-espanol/1465256/',
 109         'only_matching': True,
 110     }]
 111
 112     def _real_initialize(self):
 113         user_agent_b64 = base64.b64encode(std_headers['User-Agent'].encode('utf-8')).decode('utf-8')
 114         manager_info = self._download_json(
 115             'http://www.rtve.es/odin/loki/' + user_agent_b64,
 116             None, 'Fetching manager info')
 117         self._manager = manager_info['manager']
 118
 119     def _real_extract(self, url):
 120         mobj = re.match(self._VALID_URL, url)
 121         video_id = mobj.group('id')
 122         info = self._download_json(
 123             'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
 124             video_id)['page']['items'][0]
 125         if info['state'] == 'DESPU':
 126             raise ExtractorError('The video is no longer available', expected=True)
 127         title = info['title']
 128         png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id)
 129         png_request = sanitized_Request(png_url)
 130         png_request.add_header('Referer', url)
 131         png = self._download_webpage(png_request, video_id, 'Downloading url information')
 132         video_url = _decrypt_url(png)
 133         ext = determine_ext(video_url)
 134
 135         formats = []
 136         if not video_url.endswith('.f4m') and ext != 'm3u8':
 137             if '?' not in video_url:
 138                 video_url = video_url.replace('resources/', 'auth/resources/')
 139             video_url = video_url.replace('.net.rtve', '.multimedia.cdn.rtve')
 140
 141         if ext == 'm3u8':
 142             formats.extend(self._extract_m3u8_formats(
 143                 video_url, video_id, ext='mp4', entry_protocol='m3u8_native',
 144                 m3u8_id='hls', fatal=False))
 145         elif ext == 'f4m':
 146             formats.extend(self._extract_f4m_formats(
 147                 video_url, video_id, f4m_id='hds', fatal=False))
 148         else:
 149             formats.append({
 150                 'url': video_url,
 151             })
 152         self._sort_formats(formats)
 153
 154         subtitles = None
 155         if info.get('sbtFile') is not None:
 156             subtitles = self.extract_subtitles(video_id, info['sbtFile'])
 157
 158         return {
 159             'id': video_id,
 160             'title': title,
 161             'formats': formats,
 162             'thumbnail': info.get('image'),
 163             'page_url': url,
 164             'subtitles': subtitles,
 165             'duration': float_or_none(info.get('duration'), scale=1000),
 166         }
 167
 168     def _get_subtitles(self, video_id, sub_file):
 169         subs = self._download_json(
 170             sub_file + '.json', video_id,
 171             'Downloading subtitles info')['page']['items']
 172         return dict(
 173             (s['lang'], [{'ext': 'vtt', 'url': s['src']}])
 174             for s in subs)
 175
 176
 177 class RTVEInfantilIE(InfoExtractor):
 178     IE_NAME = 'rtve.es:infantil'
 179     IE_DESC = 'RTVE infantil'
 180     _VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/(?P<show>[^/]*)/video/(?P<short_title>[^/]*)/(?P<id>[0-9]+)/'
 181
 182     _TESTS = [{
 183         'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/',
 184         'md5': '915319587b33720b8e0357caaa6617e6',
 185         'info_dict': {
 186             'id': '3040283',
 187             'ext': 'mp4',
 188             'title': 'Maneras de vivir',
 189             'thumbnail': 'http://www.rtve.es/resources/jpg/6/5/1426182947956.JPG',
 190             'duration': 357.958,
 191         },
 192     }]
 193
 194     def _real_extract(self, url):
 195         video_id = self._match_id(url)
 196         info = self._download_json(
 197             'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
 198             video_id)['page']['items'][0]
 199
 200         webpage = self._download_webpage(url, video_id)
 201         vidplayer_id = self._search_regex(
 202             r' id="vidplayer([0-9]+)"', webpage, 'internal video ID')
 203
 204         png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % vidplayer_id
 205         png = self._download_webpage(png_url, video_id, 'Downloading url information')
 206         video_url = _decrypt_url(png)
 207
 208         return {
 209             'id': video_id,
 210             'ext': 'mp4',
 211             'title': info['title'],
 212             'url': video_url,
 213             'thumbnail': info.get('image'),
 214             'duration': float_or_none(info.get('duration'), scale=1000),
 215         }
 216
 217
 218 class RTVELiveIE(InfoExtractor):
 219     IE_NAME = 'rtve.es:live'
 220     IE_DESC = 'RTVE.es live streams'
 221     _VALID_URL = r'https?://(?:www\.)?rtve\.es/directo/(?P<id>[a-zA-Z0-9-]+)'
 222
 223     _TESTS = [{
 224         'url': 'http://www.rtve.es/directo/la-1/',
 225         'info_dict': {
 226             'id': 'la-1',
 227             'ext': 'mp4',
 228             'title': 're:^La 1 [0-9]{4}-[0-9]{2}-[0-9]{2}Z[0-9]{6}$',
 229         },
 230         'params': {
 231             'skip_download': 'live stream',
 232         }
 233     }]
 234
 235     def _real_extract(self, url):
 236         mobj = re.match(self._VALID_URL, url)
 237         start_time = time.gmtime()
 238         video_id = mobj.group('id')
 239
 240         webpage = self._download_webpage(url, video_id)
 241         title = remove_end(self._og_search_title(webpage), ' en directo en RTVE.es')
 242         title = remove_start(title, 'Estoy viendo ')
 243         title += ' ' + time.strftime('%Y-%m-%dZ%H%M%S', start_time)
 244
 245         vidplayer_id = self._search_regex(
 246             (r'playerId=player([0-9]+)',
 247              r'class=["\'].*?\blive_mod\b.*?["\'][^>]+data-assetid=["\'](\d+)',
 248              r'data-id=["\'](\d+)'),
 249             webpage, 'internal video ID')
 250         png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/amonet/videos/%s.png' % vidplayer_id
 251         png = self._download_webpage(png_url, video_id, 'Downloading url information')
 252         m3u8_url = _decrypt_url(png)
 253         formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
 254         self._sort_formats(formats)
 255
 256         return {
 257             'id': video_id,
 258             'title': title,
 259             'formats': formats,
 260             'is_live': True,
 261         }
 262
 263
 264 class RTVETelevisionIE(InfoExtractor):
 265     IE_NAME = 'rtve.es:television'
 266     _VALID_URL = r'https?://(?:www\.)?rtve\.es/television/[^/]+/[^/]+/(?P<id>\d+).shtml'
 267
 268     _TEST = {
 269         'url': 'http://www.rtve.es/television/20160628/revolucion-del-movil/1364141.shtml',
 270         'info_dict': {
 271             'id': '3069778',
 272             'ext': 'mp4',
 273             'title': 'Documentos TV - La revolución del móvil',
 274             'duration': 3496.948,
 275         },
 276         'params': {
 277             'skip_download': True,
 278         },
 279     }
 280
 281     def _real_extract(self, url):
 282         page_id = self._match_id(url)
 283         webpage = self._download_webpage(url, page_id)
 284
 285         alacarta_url = self._search_regex(
 286             r'data-location="alacarta_videos"[^<]+url&quot;:&quot;(http://www\.rtve\.es/alacarta.+?)&',
 287             webpage, 'alacarta url', default=None)
 288         if alacarta_url is None:
 289             raise ExtractorError(
 290                 'The webpage doesn\'t contain any video', expected=True)
 291
 292         return self.url_result(alacarta_url, ie=RTVEALaCartaIE.ie_key())