youtube_dl/extractor/teamcoco.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6
   7
   8 class TeamcocoIE(InfoExtractor):
   9     _VALID_URL = r'http://teamcoco\.com/video/(?P<video_id>[0-9]+)?/?(?P<display_id>.*)'
  10     _TESTS = [
  11     {
  12         'url': 'http://teamcoco.com/video/80187/conan-becomes-a-mary-kay-beauty-consultant',
  13         'file': '80187.mp4',
  14         'md5': '3f7746aa0dc86de18df7539903d399ea',
  15         'info_dict': {
  16             'title': 'Conan Becomes A Mary Kay Beauty Consultant',
  17             'description': 'Mary Kay is perhaps the most trusted name in female beauty, so of course Conan is a natural choice to sell their products.'
  18         }
  19     },
  20     {
  21         'url': 'http://teamcoco.com/video/louis-ck-interview-george-w-bush',
  22         'file': '19705.mp4',
  23         'md5': 'cde9ba0fa3506f5f017ce11ead928f9a',
  24         'info_dict': {
  25             "description": "Louis C.K. got starstruck by George W. Bush, so what? Part one.",
  26             "title": "Louis C.K. Interview Pt. 1 11/3/11"
  27         }
  28     }
  29     ]
  30
  31     def _real_extract(self, url):
  32         mobj = re.match(self._VALID_URL, url)
  33
  34         display_id = mobj.group('display_id')
  35         webpage = self._download_webpage(url, display_id)
  36
  37         video_id = mobj.group("video_id")
  38         if not video_id:
  39             video_id = self._html_search_regex(
  40                 r'data-node-id="(\d+?)"',
  41                 webpage, 'video id')
  42
  43         data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
  44         data = self._download_xml(
  45             data_url, display_id, 'Downloading data webpage')
  46
  47         qualities = ['500k', '480p', '1000k', '720p', '1080p']
  48         formats = []
  49         for filed in data.findall('files/file'):
  50             if filed.attrib.get('playmode') == 'all':
  51                 # it just duplicates one of the entries
  52                 break
  53             file_url = filed.text
  54             m_format = re.search(r'(\d+(k|p))\.mp4', file_url)
  55             if m_format is not None:
  56                 format_id = m_format.group(1)
  57             else:
  58                 format_id = filed.attrib['bitrate']
  59             tbr = (
  60                 int(filed.attrib['bitrate'])
  61                 if filed.attrib['bitrate'].isdigit()
  62                 else None)
  63
  64             try:
  65                 quality = qualities.index(format_id)
  66             except ValueError:
  67                 quality = -1
  68             formats.append({
  69                 'url': file_url,
  70                 'ext': 'mp4',
  71                 'tbr': tbr,
  72                 'format_id': format_id,
  73                 'quality': quality,
  74             })
  75
  76         self._sort_formats(formats)
  77
  78         return {
  79             'id': video_id,
  80             'display_id': display_id,
  81             'formats': formats,
  82             'title': self._og_search_title(webpage),
  83             'thumbnail': self._og_search_thumbnail(webpage),
  84             'description': self._og_search_description(webpage),
  85         }