1
0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-29 19:47:54 +01:00
youtube-dl/youtube_dl/extractor/teamcoco.py
2013-07-12 22:12:04 +02:00

47 lines
1.6 KiB
Python

import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
)
class TeamcocoIE(InfoExtractor):
_VALID_URL = r'http://teamcoco\.com/video/(?P<url_title>.*)'
_TEST = {
u'url': u'http://teamcoco.com/video/louis-ck-interview-george-w-bush',
u'file': u'19705.mp4',
u'md5': u'27b6f7527da5acf534b15f21b032656e',
u'info_dict': {
u"description": u"Louis C.K. got starstruck by George W. Bush, so what? Part one.",
u"title": u"Louis C.K. Interview Pt. 1 11/3/11"
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
url_title = mobj.group('url_title')
webpage = self._download_webpage(url, url_title)
video_id = self._html_search_regex(r'<article class="video" data-id="(\d+?)"',
webpage, u'video id')
self.report_extraction(video_id)
data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
data = self._download_webpage(data_url, video_id, 'Downloading data webpage')
video_url = self._html_search_regex(r'<file type="high".*?>(.*?)</file>',
data, u'video URL')
return [{
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': self._og_search_title(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'description': self._og_search_description(webpage),
}]