2 from __future__ import unicode_literals
8 from .common import InfoExtractor
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:]
37 for l in alphabet_data:
47 for letter in url_data:
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/[^/]+/[^/]+/(?P<id>\d+)'
70 'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
71 'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43',
75 'title': 'Balonmano - Swiss Cup masculina. Final: EspaƱa-Suecia',
79 'note': 'Live stream',
80 'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/',
86 'skip': 'The f4m manifest can\'t be used yet',
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,
92 def _real_initialize(self):
93 user_agent_b64 = base64.b64encode(std_headers['User-Agent'].encode('utf-8')).decode('utf-8')
94 manager_info = self._download_json(
95 'http://www.rtve.es/odin/loki/' + user_agent_b64,
96 None, 'Fetching manager info')
97 self._manager = manager_info['manager']
99 def _real_extract(self, url):
100 mobj = re.match(self._VALID_URL, url)
101 video_id = mobj.group('id')
102 info = self._download_json(
103 'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
104 video_id)['page']['items'][0]
105 if info['state'] == 'DESPU':
106 raise ExtractorError('The video is no longer available', expected=True)
107 png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id)
108 png_request = sanitized_Request(png_url)
109 png_request.add_header('Referer', url)
110 png = self._download_webpage(png_request, video_id, 'Downloading url information')
111 video_url = _decrypt_url(png)
112 if not video_url.endswith('.f4m'):
113 video_url = video_url.replace(
114 'resources/', 'auth/resources/'
115 ).replace('.net.rtve', '.multimedia.cdn.rtve')
118 if info.get('sbtFile') is not None:
119 subtitles = self.extract_subtitles(video_id, info['sbtFile'])
123 'title': info['title'],
125 'thumbnail': info.get('image'),
127 'subtitles': subtitles,
128 'duration': float_or_none(info.get('duration'), scale=1000),
131 def _get_subtitles(self, video_id, sub_file):
132 subs = self._download_json(
133 sub_file + '.json', video_id,
134 'Downloading subtitles info')['page']['items']
136 (s['lang'], [{'ext': 'vtt', 'url': s['src']}])
140 class RTVEInfantilIE(InfoExtractor):
141 IE_NAME = 'rtve.es:infantil'
142 IE_DESC = 'RTVE infantil'
143 _VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/(?P<show>[^/]*)/video/(?P<short_title>[^/]*)/(?P<id>[0-9]+)/'
146 'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/',
147 'md5': '915319587b33720b8e0357caaa6617e6',
151 'title': 'Maneras de vivir',
152 'thumbnail': 'http://www.rtve.es/resources/jpg/6/5/1426182947956.JPG',
157 def _real_extract(self, url):
158 video_id = self._match_id(url)
159 info = self._download_json(
160 'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
161 video_id)['page']['items'][0]
163 webpage = self._download_webpage(url, video_id)
164 vidplayer_id = self._search_regex(
165 r' id="vidplayer([0-9]+)"', webpage, 'internal video ID')
167 png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % vidplayer_id
168 png = self._download_webpage(png_url, video_id, 'Downloading url information')
169 video_url = _decrypt_url(png)
174 'title': info['title'],
176 'thumbnail': info.get('image'),
177 'duration': float_or_none(info.get('duration'), scale=1000),
181 class RTVELiveIE(InfoExtractor):
182 IE_NAME = 'rtve.es:live'
183 IE_DESC = 'RTVE.es live streams'
184 _VALID_URL = r'https?://www\.rtve\.es/directo/(?P<id>[a-zA-Z0-9-]+)'
187 'url': 'http://www.rtve.es/directo/la-1/',
191 'title': 're:^La 1 [0-9]{4}-[0-9]{2}-[0-9]{2}Z[0-9]{6}$',
194 'skip_download': 'live stream',
198 def _real_extract(self, url):
199 mobj = re.match(self._VALID_URL, url)
200 start_time = time.gmtime()
201 video_id = mobj.group('id')
203 webpage = self._download_webpage(url, video_id)
204 title = remove_end(self._og_search_title(webpage), ' en directo en RTVE.es')
205 title = remove_start(title, 'Estoy viendo ')
206 title += ' ' + time.strftime('%Y-%m-%dZ%H%M%S', start_time)
208 vidplayer_id = self._search_regex(
209 r'playerId=player([0-9]+)', webpage, 'internal video ID')
210 png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/amonet/videos/%s.png' % vidplayer_id
211 png = self._download_webpage(png_url, video_id, 'Downloading url information')
212 m3u8_url = _decrypt_url(png)
213 formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
214 self._sort_formats(formats)