]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/mitele.py
1 from __future__
import unicode_literals
6 from .common
import InfoExtractor
9 get_element_by_attribute
,
15 class MiTeleIE(InfoExtractor
):
17 _VALID_URL
= r
'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<episode>[^/]+)/'
20 'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
21 'md5': '6a75fe9d0d3275bead0cb683c616fddb',
25 'title': 'Programa 144 - Tor, la web invisible',
26 'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
27 'display_id': 'programa-144',
32 def _real_extract(self
, url
):
33 mobj
= re
.match(self
._VALID
_URL
, url
)
34 episode
= mobj
.group('episode')
35 webpage
= self
._download
_webpage
(url
, episode
)
36 embed_data_json
= self
._search
_regex
(
37 r
'MSV\.embedData\[.*?\]\s*=\s*({.*?});', webpage
, 'embed data',
40 embed_data
= json
.loads(embed_data_json
)
42 info_url
= embed_data
['flashvars']['host']
43 info_el
= self
._download
_xml
(info_url
, episode
).find('./video/info')
45 video_link
= info_el
.find('videoUrl/link').text
46 token_query
= compat_urllib_parse
.urlencode({'id': video_link}
)
47 token_info
= self
._download
_json
(
48 'http://token.mitele.es/?' + token_query
, episode
,
49 transform_source
=strip_jsonp
53 'id': embed_data
['videoId'],
54 'display_id': episode
,
55 'title': info_el
.find('title').text
,
56 'url': token_info
['tokenizedUrl'],
57 'description': get_element_by_attribute('class', 'text', webpage
),
58 'thumbnail': info_el
.find('thumb').text
,
59 'duration': parse_duration(info_el
.find('duration').text
),