]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/daum.py
3 from __future__
import unicode_literals
7 from .common
import InfoExtractor
13 class DaumIE(InfoExtractor
):
14 _VALID_URL
= r
'https?://(?:m\.)?tvpot\.daum\.net/(?:v/|.*?clipid=)(?P<id>[^?#&]+)'
18 'url': 'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
22 'title': 'DOTA 2GETHER 시즌2 6회 - 2부',
23 'description': 'DOTA 2GETHER 시즌2 6회 - 2부',
24 'upload_date': '20130831',
28 'url': 'http://tvpot.daum.net/v/vab4dyeDBysyBssyukBUjBz',
29 'only_matching': True,
31 'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24',
32 'only_matching': True,
35 def _real_extract(self
, url
):
36 mobj
= re
.match(self
._VALID
_URL
, url
)
37 video_id
= mobj
.group('id')
38 canonical_url
= 'http://tvpot.daum.net/v/%s' % video_id
39 webpage
= self
._download
_webpage
(canonical_url
, video_id
)
40 full_id
= self
._search
_regex
(
41 r
'<iframe src="http://videofarm.daum.net/controller/video/viewer/Video.html\?.*?vid=(.+?)[&"]',
43 query
= compat_urllib_parse
.urlencode({'vid': full_id}
)
44 info
= self
._download
_xml
(
45 'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query
, video_id
,
46 'Downloading video info')
47 urls
= self
._download
_xml
(
48 'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query
,
49 video_id
, 'Downloading video formats info')
52 for format_el
in urls
.findall('result/output_list/output_list'):
53 profile
= format_el
.attrib
['profile']
54 format_query
= compat_urllib_parse
.urlencode({
58 url_doc
= self
._download
_xml
(
59 'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query
,
60 video_id
, note
='Downloading video data for %s format' % profile
)
61 format_url
= url_doc
.find('result/url').text
69 'title': info
.find('TITLE').text
,
71 'thumbnail': self
._og
_search
_thumbnail
(webpage
),
72 'description': info
.find('CONTENTS').text
,
73 'duration': int(info
.find('DURATION').text
),
74 'upload_date': info
.find('REGDTTM').text
[:8],