1 from __future__ import unicode_literals
5 from .common import InfoExtractor
8 class TeamcocoIE(InfoExtractor):
9 _VALID_URL = r'http://teamcoco\.com/video/(?P<video_id>[0-9]+)?/?(?P<display_id>.*)'
12 'url': 'http://teamcoco.com/video/80187/conan-becomes-a-mary-kay-beauty-consultant',
13 'md5': '3f7746aa0dc86de18df7539903d399ea',
17 'title': 'Conan Becomes A Mary Kay Beauty Consultant',
18 'description': 'Mary Kay is perhaps the most trusted name in female beauty, so of course Conan is a natural choice to sell their products.'
21 'url': 'http://teamcoco.com/video/louis-ck-interview-george-w-bush',
22 'md5': 'cde9ba0fa3506f5f017ce11ead928f9a',
26 "description": "Louis C.K. got starstruck by George W. Bush, so what? Part one.",
27 "title": "Louis C.K. Interview Pt. 1 11/3/11"
32 def _real_extract(self, url):
33 mobj = re.match(self._VALID_URL, url)
35 display_id = mobj.group('display_id')
36 webpage = self._download_webpage(url, display_id)
38 video_id = mobj.group("video_id")
40 video_id = self._html_search_regex(
41 r'<div\s+class="player".*?data-id="(\d+?)"',
44 data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
45 data = self._download_xml(
46 data_url, display_id, 'Downloading data webpage')
48 qualities = ['500k', '480p', '1000k', '720p', '1080p']
50 for filed in data.findall('files/file'):
51 if filed.attrib.get('playmode') == 'all':
52 # it just duplicates one of the entries
55 m_format = re.search(r'(\d+(k|p))\.mp4', file_url)
56 if m_format is not None:
57 format_id = m_format.group(1)
59 format_id = filed.attrib['bitrate']
61 int(filed.attrib['bitrate'])
62 if filed.attrib['bitrate'].isdigit()
66 quality = qualities.index(format_id)
73 'format_id': format_id,
77 self._sort_formats(formats)
81 'display_id': display_id,
83 'title': self._og_search_title(webpage),
84 'thumbnail': self._og_search_thumbnail(webpage),
85 'description': self._og_search_description(webpage),