]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/aftenposten.py
2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
16 class AftenpostenIE(InfoExtractor
):
17 _VALID_URL
= r
'https?://(?:www\.)?aftenposten\.no/webtv/(?:#!/)?video/(?P<id>\d+)'
20 'url': 'http://www.aftenposten.no/webtv/#!/video/21039/trailer-sweatshop-i-can-t-take-any-more',
21 'md5': 'fd828cd29774a729bf4d4425fe192972',
25 'title': 'TRAILER: "Sweatshop" - I canĀ“t take any more',
26 'description': 'md5:21891f2b0dd7ec2f78d84a50e54f8238',
27 'timestamp': 1416927969,
28 'upload_date': '20141125',
32 def _real_extract(self
, url
):
33 video_id
= self
._match
_id
(url
)
35 data
= self
._download
_xml
(
36 'http://frontend.xstream.dk/ap/feed/video/?platform=web&id=%s' % video_id
, video_id
)
39 'atom': 'http://www.w3.org/2005/Atom',
40 'xt': 'http://xstream.dk/',
41 'media': 'http://search.yahoo.com/mrss/',
44 entry
= data
.find(xpath_with_ns('./atom:entry', NS_MAP
))
47 entry
, xpath_with_ns('./atom:title', NS_MAP
), 'title')
48 description
= xpath_text(
49 entry
, xpath_with_ns('./atom:summary', NS_MAP
), 'description')
50 timestamp
= parse_iso8601(xpath_text(
51 entry
, xpath_with_ns('./atom:published', NS_MAP
), 'upload date'))
54 media_group
= entry
.find(xpath_with_ns('./media:group', NS_MAP
))
55 for media_content
in media_group
.findall(xpath_with_ns('./media:content', NS_MAP
)):
56 media_url
= media_content
.get('url')
59 tbr
= int_or_none(media_content
.get('bitrate'))
60 mobj
= re
.search(r
'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', media_url
)
63 'url': mobj
.group('url'),
64 'play_path': 'mp4:%s' % mobj
.group('playpath'),
65 'app': mobj
.group('app'),
68 'format_id': 'rtmp-%d' % tbr
,
75 self
._sort
_formats
(formats
)
77 link
= find_xpath_attr(
78 entry
, xpath_with_ns('./atom:link', NS_MAP
), 'rel', 'original')
81 'url': link
.get('href'),
82 'format_id': link
.get('rel'),
86 'url': splash
.get('url'),
87 'width': int_or_none(splash
.get('width')),
88 'height': int_or_none(splash
.get('height')),
89 } for splash
in media_group
.findall(xpath_with_ns('./xt:splash', NS_MAP
))]
94 'description': description
,
95 'timestamp': timestamp
,
97 'thumbnails': thumbnails
,