]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/rtve.py
2 from __future__
import unicode_literals
8 from .common
import InfoExtractor
24 def _decrypt_url(png
):
25 encrypted_data
= compat_b64decode(png
)
26 text_index
= encrypted_data
.find(b
'tEXt')
27 text_chunk
= encrypted_data
[text_index
- 4:]
28 length
= compat_struct_unpack('!I', text_chunk
[:4])[0]
29 # Use bytearray to get integers when iterating in both python 2.x and 3.x
30 data
= bytearray(text_chunk
[8:8 + length
])
31 data
= [chr(b
) for b
in data
if b
!= 0]
32 hash_index
= data
.index('#')
33 alphabet_data
= data
[:hash_index
]
34 url_data
= data
[hash_index
+ 1:]
35 if url_data
[0] == 'H' and url_data
[3] == '%':
36 # remove useless HQ%% at the start
37 url_data
= url_data
[4:]
42 for l
in alphabet_data
:
52 for letter
in url_data
:
69 class RTVEALaCartaIE(InfoExtractor
):
70 IE_NAME
= 'rtve.es:alacarta'
71 IE_DESC
= 'RTVE a la carta'
72 _VALID_URL
= r
'https?://(?:www\.)?rtve\.es/(m/)?(alacarta/videos|filmoteca)/[^/]+/[^/]+/(?P<id>\d+)'
75 'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
76 'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43',
80 'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia',
84 'note': 'Live stream',
85 'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/',
91 'skip': 'The f4m manifest can\'t be used yet',
93 'url': 'http://www.rtve.es/alacarta/videos/servir-y-proteger/servir-proteger-capitulo-104/4236788/',
94 'md5': 'e55e162379ad587e9640eda4f7353c0f',
98 'title': 'Servir y proteger - Capítulo 104 ',
102 'skip_download': True, # requires ffmpeg
105 'url': 'http://www.rtve.es/m/alacarta/videos/cuentame-como-paso/cuentame-como-paso-t16-ultimo-minuto-nuestra-vida-capitulo-276/2969138/?media=tve',
106 'only_matching': True,
108 'url': 'http://www.rtve.es/filmoteca/no-do/not-1-introduccion-primer-noticiario-espanol/1465256/',
109 'only_matching': True,
112 def _real_initialize(self
):
113 user_agent_b64
= base64
.b64encode(std_headers
['User-Agent'].encode('utf-8')).decode('utf-8')
114 manager_info
= self
._download
_json
(
115 'http://www.rtve.es/odin/loki/' + user_agent_b64
,
116 None, 'Fetching manager info')
117 self
._manager
= manager_info
['manager']
119 def _real_extract(self
, url
):
120 mobj
= re
.match(self
._VALID
_URL
, url
)
121 video_id
= mobj
.group('id')
122 info
= self
._download
_json
(
123 'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id
,
124 video_id
)['page']['items'][0]
125 if info
['state'] == 'DESPU':
126 raise ExtractorError('The video is no longer available', expected
=True)
127 title
= info
['title']
128 png_url
= 'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self
._manager
, video_id
)
129 png_request
= sanitized_Request(png_url
)
130 png_request
.add_header('Referer', url
)
131 png
= self
._download
_webpage
(png_request
, video_id
, 'Downloading url information')
132 video_url
= _decrypt_url(png
)
133 ext
= determine_ext(video_url
)
136 if not video_url
.endswith('.f4m') and ext
!= 'm3u8':
137 if '?' not in video_url
:
138 video_url
= video_url
.replace('resources/', 'auth/resources/')
139 video_url
= video_url
.replace('.net.rtve', '.multimedia.cdn.rtve')
142 formats
.extend(self
._extract
_m
3u8_formats
(
143 video_url
, video_id
, ext
='mp4', entry_protocol
='m3u8_native',
144 m3u8_id
='hls', fatal
=False))
146 formats
.extend(self
._extract
_f
4m
_formats
(
147 video_url
, video_id
, f4m_id
='hds', fatal
=False))
152 self
._sort
_formats
(formats
)
155 if info
.get('sbtFile') is not None:
156 subtitles
= self
.extract_subtitles(video_id
, info
['sbtFile'])
162 'thumbnail': info
.get('image'),
164 'subtitles': subtitles
,
165 'duration': float_or_none(info
.get('duration'), scale
=1000),
168 def _get_subtitles(self
, video_id
, sub_file
):
169 subs
= self
._download
_json
(
170 sub_file
+ '.json', video_id
,
171 'Downloading subtitles info')['page']['items']
173 (s
['lang'], [{'ext': 'vtt', 'url': s
['src']}])
177 class RTVEInfantilIE(InfoExtractor
):
178 IE_NAME
= 'rtve.es:infantil'
179 IE_DESC
= 'RTVE infantil'
180 _VALID_URL
= r
'https?://(?:www\.)?rtve\.es/infantil/serie/(?P<show>[^/]*)/video/(?P<short_title>[^/]*)/(?P<id>[0-9]+)/'
183 'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/',
184 'md5': '915319587b33720b8e0357caaa6617e6',
188 'title': 'Maneras de vivir',
189 'thumbnail': 'http://www.rtve.es/resources/jpg/6/5/1426182947956.JPG',
194 def _real_extract(self
, url
):
195 video_id
= self
._match
_id
(url
)
196 info
= self
._download
_json
(
197 'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id
,
198 video_id
)['page']['items'][0]
200 webpage
= self
._download
_webpage
(url
, video_id
)
201 vidplayer_id
= self
._search
_regex
(
202 r
' id="vidplayer([0-9]+)"', webpage
, 'internal video ID')
204 png_url
= 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % vidplayer_id
205 png
= self
._download
_webpage
(png_url
, video_id
, 'Downloading url information')
206 video_url
= _decrypt_url(png
)
211 'title': info
['title'],
213 'thumbnail': info
.get('image'),
214 'duration': float_or_none(info
.get('duration'), scale
=1000),
218 class RTVELiveIE(InfoExtractor
):
219 IE_NAME
= 'rtve.es:live'
220 IE_DESC
= 'RTVE.es live streams'
221 _VALID_URL
= r
'https?://(?:www\.)?rtve\.es/directo/(?P<id>[a-zA-Z0-9-]+)'
224 'url': 'http://www.rtve.es/directo/la-1/',
228 'title': 're:^La 1 [0-9]{4}-[0-9]{2}-[0-9]{2}Z[0-9]{6}$',
231 'skip_download': 'live stream',
235 def _real_extract(self
, url
):
236 mobj
= re
.match(self
._VALID
_URL
, url
)
237 start_time
= time
.gmtime()
238 video_id
= mobj
.group('id')
240 webpage
= self
._download
_webpage
(url
, video_id
)
241 title
= remove_end(self
._og
_search
_title
(webpage
), ' en directo en RTVE.es')
242 title
= remove_start(title
, 'Estoy viendo ')
243 title
+= ' ' + time
.strftime('%Y-%m-%dZ%H%M%S', start_time
)
245 vidplayer_id
= self
._search
_regex
(
246 (r
'playerId=player([0-9]+)',
247 r
'class=["\'].*?
\blive
_mod
\b.*?
["\'][^>]+data-assetid=["\'](\d
+)',
248 r'data
-id=["\'](\d+)'),
249 webpage, 'internal video ID')
250 png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/amonet/videos/%s.png' % vidplayer_id
251 png = self._download_webpage(png_url, video_id, 'Downloading url information')
252 m3u8_url = _decrypt_url(png)
253 formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
254 self._sort_formats(formats)
264 class RTVETelevisionIE(InfoExtractor):
265 IE_NAME = 'rtve.es:television'
266 _VALID_URL = r'https?://(?:www\.)?rtve\.es/television/[^/]+/[^/]+/(?P<id>\d+).shtml'
269 'url': 'http://www.rtve.es/television/20160628/revolucion-del-movil/1364141.shtml',
273 'title': 'Documentos TV - La revolución del móvil',
274 'duration': 3496.948,
277 'skip_download': True,
281 def _real_extract(self, url):
282 page_id = self._match_id(url)
283 webpage = self._download_webpage(url, page_id)
285 alacarta_url = self._search_regex(
286 r'data-location="alacarta_videos
"[^<]+url":"(http://www\.rtve\.es/alacarta.+?)&',
287 webpage, 'alacarta url', default=None)
288 if alacarta_url is None:
289 raise ExtractorError(
290 'The webpage doesn\'t contain any video', expected=True)
292 return self.url_result(alacarta_url, ie=RTVEALaCartaIE.ie_key())