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|filmoteca)/[^/]+/[^/]+/(?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: España-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,
91 'url': 'http://www.rtve.es/filmoteca/no-do/not-1-introduccion-primer-noticiario-espanol/1465256/',
92 'only_matching': True,
95 def _real_initialize(self
):
96 user_agent_b64
= base64
.b64encode(std_headers
['User-Agent'].encode('utf-8')).decode('utf-8')
97 manager_info
= self
._download
_json
(
98 'http://www.rtve.es/odin/loki/' + user_agent_b64
,
99 None, 'Fetching manager info')
100 self
._manager
= manager_info
['manager']
102 def _real_extract(self
, url
):
103 mobj
= re
.match(self
._VALID
_URL
, url
)
104 video_id
= mobj
.group('id')
105 info
= self
._download
_json
(
106 'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id
,
107 video_id
)['page']['items'][0]
108 if info
['state'] == 'DESPU':
109 raise ExtractorError('The video is no longer available', expected
=True)
110 png_url
= 'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self
._manager
, video_id
)
111 png_request
= sanitized_Request(png_url
)
112 png_request
.add_header('Referer', url
)
113 png
= self
._download
_webpage
(png_request
, video_id
, 'Downloading url information')
114 video_url
= _decrypt_url(png
)
115 if not video_url
.endswith('.f4m'):
116 if '?' not in video_url
:
117 video_url
= video_url
.replace('resources/', 'auth/resources/')
118 video_url
= video_url
.replace('.net.rtve', '.multimedia.cdn.rtve')
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
'https?://(?:www\.)?rtve\.es/directo/(?P<id>[a-zA-Z0-9-]+)'
190 'url': 'http://www.rtve.es/directo/la-1/',
194 'title': 're:^La 1 [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 title
= remove_end(self
._og
_search
_title
(webpage
), ' en directo en RTVE.es')
208 title
= remove_start(title
, 'Estoy viendo ')
209 title
+= ' ' + time
.strftime('%Y-%m-%dZ%H%M%S', start_time
)
211 vidplayer_id
= self
._search
_regex
(
212 (r
'playerId=player([0-9]+)',
213 r
'class=["\'].*?
\blive
_mod
\b.*?
["\'][^>]+data-assetid=["\'](\d
+)',
214 r'data
-id=["\'](\d+)'),
215 webpage, 'internal video ID')
216 png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/amonet/videos/%s.png' % vidplayer_id
217 png = self._download_webpage(png_url, video_id, 'Downloading url information')
218 m3u8_url = _decrypt_url(png)
219 formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
220 self._sort_formats(formats)
230 class RTVETelevisionIE(InfoExtractor):
231 IE_NAME = 'rtve.es:television'
232 _VALID_URL = r'https?://(?:www\.)?rtve\.es/television/[^/]+/[^/]+/(?P<id>\d+).shtml'
235 'url': 'http://www.rtve.es/television/20160628/revolucion-del-movil/1364141.shtml',
239 'title': 'Documentos TV - La revolución del móvil',
240 'duration': 3496.948,
243 'skip_download': True,
247 def _real_extract(self, url):
248 page_id = self._match_id(url)
249 webpage = self._download_webpage(url, page_id)
251 alacarta_url = self._search_regex(
252 r'data-location="alacarta_videos
"[^<]+url":"(http://www\.rtve\.es/alacarta.+?)&',
253 webpage, 'alacarta url', default=None)
254 if alacarta_url is None:
255 raise ExtractorError(
256 'The webpage doesn\'t contain any video', expected=True)
258 return self.url_result(alacarta_url, ie=RTVEALaCartaIE.ie_key())