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_struct_unpack,
  11 )
  12 from ..utils import (
  13     determine_ext,
  14     ExtractorError,
  15     float_or_none,
  16     remove_end,
  17     remove_start,
  18     sanitized_Request,
  19     std_headers,
  20 )
  21
  22
  23 def _decrypt_url(png):
  24     encrypted_data = base64.b64decode(png.encode('utf-8'))
  25     text_index = encrypted_data.find(b'tEXt')
  26     text_chunk = encrypted_data[text_index - 4:]
  27     length = compat_struct_unpack('!I', text_chunk[:4])[0]
  28     # Use bytearray to get integers when iterating in both python 2.x and 3.x
  29     data = bytearray(text_chunk[8:8 + length])
  30     data = [chr(b) for b in data if b != 0]
  31     hash_index = data.index('#')
  32     alphabet_data = data[:hash_index]
  33     url_data = data[hash_index + 1:]
  34
  35     alphabet = []
  36     e = 0
  37     d = 0
  38     for l in alphabet_data:
  39         if d == 0:
  40             alphabet.append(l)
  41             d = e = (e + 1) % 4
  42         else:
  43             d -= 1
  44     url = ''
  45     f = 0
  46     e = 3
  47     b = 1
  48     for letter in url_data:
  49         if f == 0:
  50             l = int(letter) * 10
  51             f = 1
  52         else:
  53             if e == 0:
  54                 l += int(letter)
  55                 url += alphabet[l]
  56                 e = (b + 3) % 4
  57                 f = 0
  58                 b += 1
  59             else:
  60                 e -= 1
  61
  62     return url
  63
  64
  65 class RTVEALaCartaIE(InfoExtractor):
  66     IE_NAME = 'rtve.es:alacarta'
  67     IE_DESC = 'RTVE a la carta'
  68     _VALID_URL = r'https?://(?:www\.)?rtve\.es/(m/)?(alacarta/videos|filmoteca)/[^/]+/[^/]+/(?P<id>\d+)'
  69
  70     _TESTS = [{
  71         'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
  72         'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43',
  73         'info_dict': {
  74             'id': '2491869',
  75             'ext': 'mp4',
  76             'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia',
  77             'duration': 5024.566,
  78         },
  79     }, {
  80         'note': 'Live stream',
  81         'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/',
  82         'info_dict': {
  83             'id': '1694255',
  84             'ext': 'flv',
  85             'title': 'TODO',
  86         },
  87         'skip': 'The f4m manifest can\'t be used yet',
  88     }, {
  89         'url': 'http://www.rtve.es/alacarta/videos/servir-y-proteger/servir-proteger-capitulo-104/4236788/',
  90         'md5': 'e55e162379ad587e9640eda4f7353c0f',
  91         'info_dict': {
  92             'id': '4236788',
  93             'ext': 'mp4',
  94             'title': 'Servir y proteger - Capítulo 104 ',
  95             'duration': 3222.0,
  96         },
  97         'params': {
  98             'skip_download': True,  # requires ffmpeg
  99         },
 100     }, {
 101         'url': 'http://www.rtve.es/m/alacarta/videos/cuentame-como-paso/cuentame-como-paso-t16-ultimo-minuto-nuestra-vida-capitulo-276/2969138/?media=tve',
 102         'only_matching': True,
 103     }, {
 104         'url': 'http://www.rtve.es/filmoteca/no-do/not-1-introduccion-primer-noticiario-espanol/1465256/',
 105         'only_matching': True,
 106     }]
 107
 108     def _real_initialize(self):
 109         user_agent_b64 = base64.b64encode(std_headers['User-Agent'].encode('utf-8')).decode('utf-8')
 110         manager_info = self._download_json(
 111             'http://www.rtve.es/odin/loki/' + user_agent_b64,
 112             None, 'Fetching manager info')
 113         self._manager = manager_info['manager']
 114
 115     def _real_extract(self, url):
 116         mobj = re.match(self._VALID_URL, url)
 117         video_id = mobj.group('id')
 118         info = self._download_json(
 119             'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
 120             video_id)['page']['items'][0]
 121         if info['state'] == 'DESPU':
 122             raise ExtractorError('The video is no longer available', expected=True)
 123         title = info['title']
 124         png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id)
 125         png_request = sanitized_Request(png_url)
 126         png_request.add_header('Referer', url)
 127         png = self._download_webpage(png_request, video_id, 'Downloading url information')
 128         video_url = _decrypt_url(png)
 129         ext = determine_ext(video_url)
 130
 131         formats = []
 132         if not video_url.endswith('.f4m') and ext != 'm3u8':
 133             if '?' not in video_url:
 134                 video_url = video_url.replace('resources/', 'auth/resources/')
 135             video_url = video_url.replace('.net.rtve', '.multimedia.cdn.rtve')
 136
 137         if ext == 'm3u8':
 138             formats.extend(self._extract_m3u8_formats(
 139                 video_url, video_id, ext='mp4', entry_protocol='m3u8_native',
 140                 m3u8_id='hls', fatal=False))
 141         elif ext == 'f4m':
 142             formats.extend(self._extract_f4m_formats(
 143                 video_url, video_id, f4m_id='hds', fatal=False))
 144         else:
 145             formats.append({
 146                 'url': video_url,
 147             })
 148         self._sort_formats(formats)
 149
 150         subtitles = None
 151         if info.get('sbtFile') is not None:
 152             subtitles = self.extract_subtitles(video_id, info['sbtFile'])
 153
 154         return {
 155             'id': video_id,
 156             'title': title,
 157             'formats': formats,
 158             'thumbnail': info.get('image'),
 159             'page_url': url,
 160             'subtitles': subtitles,
 161             'duration': float_or_none(info.get('duration'), scale=1000),
 162         }
 163
 164     def _get_subtitles(self, video_id, sub_file):
 165         subs = self._download_json(
 166             sub_file + '.json', video_id,
 167             'Downloading subtitles info')['page']['items']
 168         return dict(
 169             (s['lang'], [{'ext': 'vtt', 'url': s['src']}])
 170             for s in subs)
 171
 172
 173 class RTVEInfantilIE(InfoExtractor):
 174     IE_NAME = 'rtve.es:infantil'
 175     IE_DESC = 'RTVE infantil'
 176     _VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/(?P<show>[^/]*)/video/(?P<short_title>[^/]*)/(?P<id>[0-9]+)/'
 177
 178     _TESTS = [{
 179         'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/',
 180         'md5': '915319587b33720b8e0357caaa6617e6',
 181         'info_dict': {
 182             'id': '3040283',
 183             'ext': 'mp4',
 184             'title': 'Maneras de vivir',
 185             'thumbnail': 'http://www.rtve.es/resources/jpg/6/5/1426182947956.JPG',
 186             'duration': 357.958,
 187         },
 188     }]
 189
 190     def _real_extract(self, url):
 191         video_id = self._match_id(url)
 192         info = self._download_json(
 193             'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
 194             video_id)['page']['items'][0]
 195
 196         webpage = self._download_webpage(url, video_id)
 197         vidplayer_id = self._search_regex(
 198             r' id="vidplayer([0-9]+)"', webpage, 'internal video ID')
 199
 200         png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % vidplayer_id
 201         png = self._download_webpage(png_url, video_id, 'Downloading url information')
 202         video_url = _decrypt_url(png)
 203
 204         return {
 205             'id': video_id,
 206             'ext': 'mp4',
 207             'title': info['title'],
 208             'url': video_url,
 209             'thumbnail': info.get('image'),
 210             'duration': float_or_none(info.get('duration'), scale=1000),
 211         }
 212
 213
 214 class RTVELiveIE(InfoExtractor):
 215     IE_NAME = 'rtve.es:live'
 216     IE_DESC = 'RTVE.es live streams'
 217     _VALID_URL = r'https?://(?:www\.)?rtve\.es/directo/(?P<id>[a-zA-Z0-9-]+)'
 218
 219     _TESTS = [{
 220         'url': 'http://www.rtve.es/directo/la-1/',
 221         'info_dict': {
 222             'id': 'la-1',
 223             'ext': 'mp4',
 224             'title': 're:^La 1 [0-9]{4}-[0-9]{2}-[0-9]{2}Z[0-9]{6}$',
 225         },
 226         'params': {
 227             'skip_download': 'live stream',
 228         }
 229     }]
 230
 231     def _real_extract(self, url):
 232         mobj = re.match(self._VALID_URL, url)
 233         start_time = time.gmtime()
 234         video_id = mobj.group('id')
 235
 236         webpage = self._download_webpage(url, video_id)
 237         title = remove_end(self._og_search_title(webpage), ' en directo en RTVE.es')
 238         title = remove_start(title, 'Estoy viendo ')
 239         title += ' ' + time.strftime('%Y-%m-%dZ%H%M%S', start_time)
 240
 241         vidplayer_id = self._search_regex(
 242             (r'playerId=player([0-9]+)',
 243              r'class=["\'].*?\blive_mod\b.*?["\'][^>]+data-assetid=["\'](\d+)',
 244              r'data-id=["\'](\d+)'),
 245             webpage, 'internal video ID')
 246         png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/amonet/videos/%s.png' % vidplayer_id
 247         png = self._download_webpage(png_url, video_id, 'Downloading url information')
 248         m3u8_url = _decrypt_url(png)
 249         formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
 250         self._sort_formats(formats)
 251
 252         return {
 253             'id': video_id,
 254             'title': title,
 255             'formats': formats,
 256             'is_live': True,
 257         }
 258
 259
 260 class RTVETelevisionIE(InfoExtractor):
 261     IE_NAME = 'rtve.es:television'
 262     _VALID_URL = r'https?://(?:www\.)?rtve\.es/television/[^/]+/[^/]+/(?P<id>\d+).shtml'
 263
 264     _TEST = {
 265         'url': 'http://www.rtve.es/television/20160628/revolucion-del-movil/1364141.shtml',
 266         'info_dict': {
 267             'id': '3069778',
 268             'ext': 'mp4',
 269             'title': 'Documentos TV - La revolución del móvil',
 270             'duration': 3496.948,
 271         },
 272         'params': {
 273             'skip_download': True,
 274         },
 275     }
 276
 277     def _real_extract(self, url):
 278         page_id = self._match_id(url)
 279         webpage = self._download_webpage(url, page_id)
 280
 281         alacarta_url = self._search_regex(
 282             r'data-location="alacarta_videos"[^<]+url&quot;:&quot;(http://www\.rtve\.es/alacarta.+?)&',
 283             webpage, 'alacarta url', default=None)
 284         if alacarta_url is None:
 285             raise ExtractorError(
 286                 'The webpage doesn\'t contain any video', expected=True)
 287
 288         return self.url_result(alacarta_url, ie=RTVEALaCartaIE.ie_key())