]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/teamcoco.py
2 import xml
.etree
.ElementTree
4 from .common
import InfoExtractor
10 class TeamcocoIE(InfoExtractor
):
11 _VALID_URL
= r
'http://teamcoco\.com/video/(?P<url_title>.*)'
13 u
'url': u
'http://teamcoco.com/video/louis-ck-interview-george-w-bush',
14 u
'file': u
'19705.mp4',
15 u
'md5': u
'cde9ba0fa3506f5f017ce11ead928f9a',
17 u
"description": u
"Louis C.K. got starstruck by George W. Bush, so what? Part one.",
18 u
"title": u
"Louis C.K. Interview Pt. 1 11/3/11"
22 def _real_extract(self
, url
):
23 mobj
= re
.match(self
._VALID
_URL
, url
)
25 raise ExtractorError(u
'Invalid URL: %s' % url
)
26 url_title
= mobj
.group('url_title')
27 webpage
= self
._download
_webpage
(url
, url_title
)
29 video_id
= self
._html
_search
_regex
(r
'<article class="video" data-id="(\d+?)"',
32 self
.report_extraction(video_id
)
34 data_url
= 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
35 data_xml
= self
._download
_webpage
(data_url
, video_id
, 'Downloading data webpage')
36 data
= xml
.etree
.ElementTree
.fromstring(data_xml
.encode('utf-8'))
39 qualities
= ['500k', '480p', '1000k', '720p', '1080p']
41 for file in data
.findall('files/file'):
42 if file.attrib
.get('playmode') == 'all':
43 # it just duplicates one of the entries
46 m_format
= re
.search(r
'(\d+(k|p))\.mp4', file_url
)
47 if m_format
is not None:
48 format_id
= m_format
.group(1)
50 format_id
= file.attrib
['bitrate']
54 'format_id': format_id
,
58 return qualities
.index(f
['format_id'])
61 formats
.sort(key
=sort_key
)
63 raise RegexNotFoundError(u
'Unable to extract video URL')
68 'title': self
._og
_search
_title
(webpage
),
69 'thumbnail': self
._og
_search
_thumbnail
(webpage
),
70 'description': self
._og
_search
_description
(webpage
),