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