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             'md5': '3f7746aa0dc86de18df7539903d399ea',
  14             'info_dict': {
  15                 'id': '80187',
  16                 'ext': 'mp4',
  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.',
  19                 'age_limit': 0,
  20             }
  21         }, {
  22             'url': 'http://teamcoco.com/video/louis-ck-interview-george-w-bush',
  23             'md5': 'cde9ba0fa3506f5f017ce11ead928f9a',
  24             'info_dict': {
  25                 'id': '19705',
  26                 'ext': 'mp4',
  27                 "description": "Louis C.K. got starstruck by George W. Bush, so what? Part one.",
  28                 "title": "Louis C.K. Interview Pt. 1 11/3/11",
  29                 'age_limit': 0,
  30             }
  31         }
  32     ]
  33     _VIDEO_ID_REGEXES = (
  34         r'"eVar42"\s*:\s*(\d+)',
  35         r'Ginger\.TeamCoco\.openInApp\("video",\s*"([^"]+)"',
  36         r'"id_not"\s*:\s*(\d+)'
  37     )
  38
  39     def _real_extract(self, url):
  40         mobj = re.match(self._VALID_URL, url)
  41
  42         display_id = mobj.group('display_id')
  43         webpage = self._download_webpage(url, display_id)
  44
  45         video_id = mobj.group("video_id")
  46         if not video_id:
  47             video_id = self._html_search_regex(
  48                 self._VIDEO_ID_REGEXES, webpage, 'video id')
  49
  50         data_url = 'http://teamcoco.com/cvp/2.0/%s.xml' % video_id
  51         data = self._download_xml(
  52             data_url, display_id, 'Downloading data webpage')
  53
  54         qualities = ['500k', '480p', '1000k', '720p', '1080p']
  55         formats = []
  56         for filed in data.findall('files/file'):
  57             if filed.attrib.get('playmode') == 'all':
  58                 # it just duplicates one of the entries
  59                 break
  60             file_url = filed.text
  61             m_format = re.search(r'(\d+(k|p))\.mp4', file_url)
  62             if m_format is not None:
  63                 format_id = m_format.group(1)
  64             else:
  65                 format_id = filed.attrib['bitrate']
  66             tbr = (
  67                 int(filed.attrib['bitrate'])
  68                 if filed.attrib['bitrate'].isdigit()
  69                 else None)
  70
  71             try:
  72                 quality = qualities.index(format_id)
  73             except ValueError:
  74                 quality = -1
  75             formats.append({
  76                 'url': file_url,
  77                 'ext': 'mp4',
  78                 'tbr': tbr,
  79                 'format_id': format_id,
  80                 'quality': quality,
  81             })
  82
  83         self._sort_formats(formats)
  84
  85         return {
  86             'id': video_id,
  87             'display_id': display_id,
  88             'formats': formats,
  89             'title': self._og_search_title(webpage),
  90             'thumbnail': self._og_search_thumbnail(webpage),
  91             'description': self._og_search_description(webpage),
  92             'age_limit': self._family_friendly_search(webpage),
  93         }