]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/karrierevideos.py
2 from __future__
import unicode_literals
4 from .common
import InfoExtractor
5 from ..compat
import compat_urlparse
14 class KarriereVideosIE(InfoExtractor
):
15 _VALID_URL
= r
'https?://(?:www\.)?karrierevideos\.at(?:/[^/]+)+/(?P<id>[^/]+)'
17 'url': 'http://www.karrierevideos.at/berufsvideos/mittlere-hoehere-schulen/altenpflegerin',
21 'title': 'AltenpflegerIn',
22 'description': 'md5:dbadd1259fde2159a9b28667cb664ae2',
23 'thumbnail': r
're:^http://.*\.png',
27 'skip_download': True,
31 'url': 'http://www.karrierevideos.at/orientierung/vaeterkarenz-und-neue-chancen-fuer-muetter-baby-was-nun',
35 'title': 'Väterkarenz und neue Chancen für Mütter - "Baby - was nun?"',
36 'description': 'md5:97092c6ad1fd7d38e9d6a5fdeb2bcc33',
37 'thumbnail': r
're:^http://.*\.png',
41 'skip_download': True,
45 def _real_extract(self
, url
):
46 video_id
= self
._match
_id
(url
)
48 webpage
= self
._download
_webpage
(url
, video_id
)
50 title
= (self
._html
_search
_meta
('title', webpage
, default
=None)
51 or self
._search
_regex
(r
'<h1 class="title">([^<]+)</h1>', webpage
, 'video title'))
53 video_id
= self
._search
_regex
(
54 r
'/config/video/(.+?)\.xml', webpage
, 'video id')
55 # Server returns malformed headers
56 # Force Accept-Encoding: * to prevent gzipped results
57 playlist
= self
._download
_xml
(
58 'http://www.karrierevideos.at/player-playlist.xml.php?p=%s' % video_id
,
59 video_id
, transform_source
=fix_xml_ampersands
,
60 headers
={'Accept-Encoding': '*'})
63 'jwplayer': 'http://developer.longtailvideo.com/trac/wiki/FlashFormats'
67 return xpath_with_ns(path
, NS_MAP
)
69 item
= playlist
.find('./tracklist/item')
70 video_file
= xpath_text(
71 item
, ns('./jwplayer:file'), 'video url', fatal
=True)
72 streamer
= xpath_text(
73 item
, ns('./jwplayer:streamer'), 'streamer', fatal
=True)
75 uploader
= xpath_text(
76 item
, ns('./jwplayer:author'), 'uploader')
77 duration
= float_or_none(
78 xpath_text(item
, ns('./jwplayer:duration'), 'duration'))
80 description
= self
._html
_search
_regex
(
81 r
'(?s)<div class="leadtext">(.+?)</div>',
82 webpage
, 'description')
84 thumbnail
= self
._html
_search
_meta
(
85 'thumbnail', webpage
, 'thumbnail')
87 thumbnail
= compat_urlparse
.urljoin(url
, thumbnail
)
91 'url': streamer
.replace('rtmpt', 'rtmp'),
92 'play_path': 'mp4:%s' % video_file
,
95 'description': description
,
96 'thumbnail': thumbnail
,