2 from __future__ import unicode_literals
8 from .common import InfoExtractor
9 from ..compat import compat_urllib_request, compat_urlparse
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:]
34 for l in alphabet_data:
44 for letter in url_data:
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+)'
67 'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
68 'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43',
72 'title': 'Balonmano - Swiss Cup masculina. Final: EspaƱa-Suecia',
76 'note': 'Live stream',
77 'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/',
83 'skip': 'The f4m manifest can\'t be used yet',
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,
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']
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)
121 if info.get('sbtFile') is not None:
122 subtitles = self.extract_subtitles(video_id, info['sbtFile'])
126 'title': info['title'],
128 'thumbnail': info.get('image'),
130 'subtitles': subtitles,
131 'duration': float_or_none(info.get('duration'), scale=1000),
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']
139 (s['lang'], [{'ext': 'vtt', 'url': s['src']}])
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]+)/'
149 'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/',
150 'md5': '915319587b33720b8e0357caaa6617e6',
154 'title': 'Maneras de vivir',
155 'thumbnail': 'http://www.rtve.es/resources/jpg/6/5/1426182947956.JPG',
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]
166 webpage = self._download_webpage(url, video_id)
167 vidplayer_id = self._search_regex(
168 r' id="vidplayer([0-9]+)"', webpage, 'internal video ID')
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)
177 'title': info['title'],
179 'thumbnail': info.get('image'),
180 'duration': float_or_none(info.get('duration'), scale=1000),
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-]+)'
190 'url': 'http://www.rtve.es/noticias/directo-la-1/',
192 'id': 'directo-la-1',
194 'title': 're:^La 1 de TVE [0-9]{4}-[0-9]{2}-[0-9]{2}Z[0-9]{6}$',
197 'skip_download': 'live stream',
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')
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)
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)
223 'app': 'rtve-live-live?ovpfv=2.1.2',
224 'player_url': player_url,