2 from __future__ import unicode_literals
8 from .common import InfoExtractor
9 from ..compat import compat_urlparse
17 def _decrypt_url(png):
18 encrypted_data = base64.b64decode(png)
19 text_index = encrypted_data.find(b'tEXt')
20 text_chunk = encrypted_data[text_index - 4:]
21 length = struct_unpack('!I', text_chunk[:4])[0]
22 # Use bytearray to get integers when iterating in both python 2.x and 3.x
23 data = bytearray(text_chunk[8:8 + length])
24 data = [chr(b) for b in data if b != 0]
25 hash_index = data.index('#')
26 alphabet_data = data[:hash_index]
27 url_data = data[hash_index + 1:]
32 for l in alphabet_data:
42 for letter in url_data:
59 class RTVEALaCartaIE(InfoExtractor):
60 IE_NAME = 'rtve.es:alacarta'
61 IE_DESC = 'RTVE a la carta'
62 _VALID_URL = r'http://www\.rtve\.es/(m/)?alacarta/videos/[^/]+/[^/]+/(?P<id>\d+)'
65 'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
66 'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43',
70 'title': 'Balonmano - Swiss Cup masculina. Final: EspaƱa-Suecia',
74 'note': 'Live stream',
75 'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/',
81 'skip': 'The f4m manifest can\'t be used yet',
83 'url': 'http://www.rtve.es/m/alacarta/videos/cuentame-como-paso/cuentame-como-paso-t16-ultimo-minuto-nuestra-vida-capitulo-276/2969138/?media=tve',
84 'only_matching': True,
87 def _real_extract(self, url):
88 mobj = re.match(self._VALID_URL, url)
89 video_id = mobj.group('id')
90 info = self._download_json(
91 'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
92 video_id)['page']['items'][0]
93 png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % video_id
94 png = self._download_webpage(png_url, video_id, 'Downloading url information')
95 video_url = _decrypt_url(png)
96 if not video_url.endswith('.f4m'):
97 auth_url = video_url.replace(
98 'resources/', 'auth/resources/'
99 ).replace('.net.rtve', '.multimedia.cdn.rtve')
100 video_path = self._download_webpage(
101 auth_url, video_id, 'Getting video url')
102 # Use mvod1.akcdn instead of flash.akamaihd.multimedia.cdn to get
103 # the right Content-Length header and the mp4 format
104 video_url = compat_urlparse.urljoin(
105 'http://mvod1.akcdn.rtve.es/', video_path)
108 if info.get('sbtFile') is not None:
109 subtitles = self.extract_subtitles(video_id, info['sbtFile'])
113 'title': info['title'],
115 'thumbnail': info.get('image'),
117 'subtitles': subtitles,
118 'duration': float_or_none(info.get('duration'), scale=1000),
121 def _get_subtitles(self, video_id, sub_file):
122 subs = self._download_json(
123 sub_file + '.json', video_id,
124 'Downloading subtitles info')['page']['items']
126 (s['lang'], [{'ext': 'vtt', 'url': s['src']}])
129 class RTVEInfantilIE(InfoExtractor):
130 IE_NAME = 'rtve.es:alacarta'
131 IE_DESC = 'RTVE a la carta'
132 _VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/(?P<show>[^/]*)/video/(?P<short_tittle>[^/]*)/(?P<id>[0-9]+)/'
135 'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/',
136 'md5': '915319587b33720b8e0357caaa6617e6',
140 'title': 'Maneras de vivir',
141 'thumbnail': 'http://www.rtve.es/resources/jpg/6/5/1426182947956.JPG',
146 def _real_extract(self, url):
147 mobj = re.match(self._VALID_URL, url)
148 video_id = mobj.group('id')
149 short_tittle = mobj.group('short_tittle')
150 info = self._download_json(
151 'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
152 video_id)['page']['items'][0]
154 webpage = self._download_webpage(url, video_id)
155 vidplayer_id = self._search_regex(
156 r' id="vidplayer([0-9]+)"', webpage, 'internal video ID')
158 png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % vidplayer_id
159 png = self._download_webpage(png_url, video_id, 'Downloading url information')
160 video_url = _decrypt_url(png)
165 'title': info['title'],
167 'thumbnail': info.get('image'),
168 'duration': float_or_none(info.get('duration'), scale=1000),
173 class RTVELiveIE(InfoExtractor):
174 IE_NAME = 'rtve.es:live'
175 IE_DESC = 'RTVE.es live streams'
176 _VALID_URL = r'http://www\.rtve\.es/(?:deportes/directo|noticias|television)/(?P<id>[a-zA-Z0-9-]+)'
179 'url': 'http://www.rtve.es/noticias/directo-la-1/',
181 'id': 'directo-la-1',
183 'title': 're:^La 1 de TVE [0-9]{4}-[0-9]{2}-[0-9]{2}Z[0-9]{6}$',
186 'skip_download': 'live stream',
190 def _real_extract(self, url):
191 mobj = re.match(self._VALID_URL, url)
192 start_time = time.gmtime()
193 video_id = mobj.group('id')
195 webpage = self._download_webpage(url, video_id)
196 player_url = self._search_regex(
197 r'<param name="movie" value="([^"]+)"/>', webpage, 'player URL')
198 title = remove_end(self._og_search_title(webpage), ' en directo')
199 title += ' ' + time.strftime('%Y-%m-%dZ%H%M%S', start_time)
201 vidplayer_id = self._search_regex(
202 r' id="vidplayer([0-9]+)"', webpage, 'internal video ID')
203 png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % vidplayer_id
204 png = self._download_webpage(png_url, video_id, 'Downloading url information')
205 video_url = _decrypt_url(png)
212 'app': 'rtve-live-live?ovpfv=2.1.2',
213 'player_url': player_url,