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

   1 # encoding: 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 compat_urllib_request, compat_urlparse
  10 from ..utils import (
  11     ExtractorError,
  12     float_or_none,
  13     remove_end,
  14     std_headers,
  15     struct_unpack,
  16 )
  17
  18
  19 def _decrypt_url(png):
  20     encrypted_data = base64.b64decode(png.encode('utf-8'))
  21     text_index = encrypted_data.find(b'tEXt')
  22     text_chunk = encrypted_data[text_index - 4:]
  23     length = struct_unpack('!I', text_chunk[:4])[0]
  24     # Use bytearray to get integers when iterating in both python 2.x and 3.x
  25     data = bytearray(text_chunk[8:8 + length])
  26     data = [chr(b) for b in data if b != 0]
  27     hash_index = data.index('#')
  28     alphabet_data = data[:hash_index]
  29     url_data = data[hash_index + 1:]
  30
  31     alphabet = []
  32     e = 0
  33     d = 0
  34     for l in alphabet_data:
  35         if d == 0:
  36             alphabet.append(l)
  37             d = e = (e + 1) % 4
  38         else:
  39             d -= 1
  40     url = ''
  41     f = 0
  42     e = 3
  43     b = 1
  44     for letter in url_data:
  45         if f == 0:
  46             l = int(letter) * 10
  47             f = 1
  48         else:
  49             if e == 0:
  50                 l += int(letter)
  51                 url += alphabet[l]
  52                 e = (b + 3) % 4
  53                 f = 0
  54                 b += 1
  55             else:
  56                 e -= 1
  57
  58     return url
  59
  60
  61 class RTVEALaCartaIE(InfoExtractor):
  62     IE_NAME = 'rtve.es:alacarta'
  63     IE_DESC = 'RTVE a la carta'
  64     _VALID_URL = r'http://www\.rtve\.es/(m/)?alacarta/videos/[^/]+/[^/]+/(?P<id>\d+)'
  65
  66     _TESTS = [{
  67         'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
  68         'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43',
  69         'info_dict': {
  70             'id': '2491869',
  71             'ext': 'mp4',
  72             'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia',
  73             'duration': 5024.566,
  74         },
  75     }, {
  76         'note': 'Live stream',
  77         'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/',
  78         'info_dict': {
  79             'id': '1694255',
  80             'ext': 'flv',
  81             'title': 'TODO',
  82         },
  83         'skip': 'The f4m manifest can\'t be used yet',
  84     }, {
  85         'url': 'http://www.rtve.es/m/alacarta/videos/cuentame-como-paso/cuentame-como-paso-t16-ultimo-minuto-nuestra-vida-capitulo-276/2969138/?media=tve',
  86         'only_matching': True,
  87     }]
  88
  89     def _real_initialize(self):
  90         user_agent_b64 = base64.b64encode(std_headers['User-Agent'].encode('utf-8')).decode('utf-8')
  91         manager_info = self._download_json(
  92             'http://www.rtve.es/odin/loki/' + user_agent_b64,
  93             None, 'Fetching manager info')
  94         self._manager = manager_info['manager']
  95
  96     def _real_extract(self, url):
  97         mobj = re.match(self._VALID_URL, url)
  98         video_id = mobj.group('id')
  99         info = self._download_json(
 100             'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
 101             video_id)['page']['items'][0]
 102         if info['state'] == 'DESPU':
 103             raise ExtractorError('The video is no longer available', expected=True)
 104         png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id)
 105         png_request = compat_urllib_request.Request(png_url)
 106         png_request.add_header('Referer', url)
 107         png = self._download_webpage(png_request, video_id, 'Downloading url information')
 108         video_url = _decrypt_url(png)
 109         if not video_url.endswith('.f4m'):
 110             auth_url = video_url.replace(
 111                 'resources/', 'auth/resources/'
 112             ).replace('.net.rtve', '.multimedia.cdn.rtve')
 113             video_path = self._download_webpage(
 114                 auth_url, video_id, 'Getting video url')
 115             # Use mvod1.akcdn instead of flash.akamaihd.multimedia.cdn to get
 116             # the right Content-Length header and the mp4 format
 117             video_url = compat_urlparse.urljoin(
 118                 'http://mvod1.akcdn.rtve.es/', video_path)
 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'http://www\.rtve\.es/(?:deportes/directo|noticias|television)/(?P<id>[a-zA-Z0-9-]+)'
 188
 189     _TESTS = [{
 190         'url': 'http://www.rtve.es/noticias/directo-la-1/',
 191         'info_dict': {
 192             'id': 'directo-la-1',
 193             'ext': 'flv',
 194             'title': 're:^La 1 de TVE [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         player_url = self._search_regex(
 208             r'<param name="movie" value="([^"]+)"/>', webpage, 'player URL')
 209         title = remove_end(self._og_search_title(webpage), ' en directo')
 210         title += ' ' + time.strftime('%Y-%m-%dZ%H%M%S', start_time)
 211
 212         vidplayer_id = self._search_regex(
 213             r' id="vidplayer([0-9]+)"', webpage, 'internal video ID')
 214         png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % vidplayer_id
 215         png = self._download_webpage(png_url, video_id, 'Downloading url information')
 216         video_url = _decrypt_url(png)
 217
 218         return {
 219             'id': video_id,
 220             'ext': 'flv',
 221             'title': title,
 222             'url': video_url,
 223             'app': 'rtve-live-live?ovpfv=2.1.2',
 224             'player_url': player_url,
 225             'rtmp_live': True,
 226         }