2 from __future__ import unicode_literals
8 from .common import InfoExtractor
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:]
38 for l in alphabet_data:
48 for letter in url_data:
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+)'
71 'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
72 'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43',
76 'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia',
80 'note': 'Live stream',
81 'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/',
87 'skip': 'The f4m manifest can\'t be used yet',
89 'url': 'http://www.rtve.es/alacarta/videos/servir-y-proteger/servir-proteger-capitulo-104/4236788/',
90 'md5': 'e55e162379ad587e9640eda4f7353c0f',
94 'title': 'Servir y proteger - Capítulo 104 ',
98 'skip_download': True, # requires ffmpeg
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,
104 'url': 'http://www.rtve.es/filmoteca/no-do/not-1-introduccion-primer-noticiario-espanol/1465256/',
105 'only_matching': True,
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']
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)
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')
138 formats.extend(self._extract_m3u8_formats(
139 video_url, video_id, ext='mp4', entry_protocol='m3u8_native',
140 m3u8_id='hls', fatal=False))
142 formats.extend(self._extract_f4m_formats(
143 video_url, video_id, f4m_id='hds', fatal=False))
148 self._sort_formats(formats)
151 if info.get('sbtFile') is not None:
152 subtitles = self.extract_subtitles(video_id, info['sbtFile'])
158 'thumbnail': info.get('image'),
160 'subtitles': subtitles,
161 'duration': float_or_none(info.get('duration'), scale=1000),
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']
169 (s['lang'], [{'ext': 'vtt', 'url': s['src']}])
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]+)/'
179 'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/',
180 'md5': '915319587b33720b8e0357caaa6617e6',
184 'title': 'Maneras de vivir',
185 'thumbnail': 'http://www.rtve.es/resources/jpg/6/5/1426182947956.JPG',
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]
196 webpage = self._download_webpage(url, video_id)
197 vidplayer_id = self._search_regex(
198 r' id="vidplayer([0-9]+)"', webpage, 'internal video ID')
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)
207 'title': info['title'],
209 'thumbnail': info.get('image'),
210 'duration': float_or_none(info.get('duration'), scale=1000),
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-]+)'
220 'url': 'http://www.rtve.es/directo/la-1/',
224 'title': 're:^La 1 [0-9]{4}-[0-9]{2}-[0-9]{2}Z[0-9]{6}$',
227 'skip_download': 'live stream',
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')
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)
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)
260 class RTVETelevisionIE(InfoExtractor):
261 IE_NAME = 'rtve.es:television'
262 _VALID_URL = r'https?://(?:www\.)?rtve\.es/television/[^/]+/[^/]+/(?P<id>\d+).shtml'
265 'url': 'http://www.rtve.es/television/20160628/revolucion-del-movil/1364141.shtml',
269 'title': 'Documentos TV - La revolución del móvil',
270 'duration': 3496.948,
273 'skip_download': True,
277 def _real_extract(self, url):
278 page_id = self._match_id(url)
279 webpage = self._download_webpage(url, page_id)
281 alacarta_url = self._search_regex(
282 r'data-location="alacarta_videos"[^<]+url":"(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)
288 return self.url_result(alacarta_url, ie=RTVEALaCartaIE.ie_key())