Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/teamcoco.py

   1 import re
   2 import xml.etree.ElementTree
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     ExtractorError,
   7 )
   8
   9
  10 class TeamcocoIE(InfoExtractor):
  11     _VALID_URL = r'http://teamcoco\.com/video/(?P<url_title>.*)'
  12     _TEST = {
  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',
  16         u'info_dict': {
  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"
  19         }
  20     }
  21
  22     def _real_extract(self, url):
  23         mobj = re.match(self._VALID_URL, url)
  24         if mobj is None:
  25             raise ExtractorError(u'Invalid URL: %s' % url)
  26         url_title = mobj.group('url_title')
  27         webpage = self._download_webpage(url, url_title)
  28
  29         video_id = self._html_search_regex(r'<article class="video" data-id="(\d+?)"',
  30             webpage, u'video id')
  31
  32         self.report_extraction(video_id)
  33
  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'))
  37
  38
  39         qualities = ['500k', '480p', '1000k', '720p', '1080p']
  40         formats = []
  41         for file in data.findall('files/file'):
  42             if file.attrib.get('playmode') == 'all':
  43                 # it just duplicates one of the entries
  44                 break
  45             file_url = file.text
  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)
  49             else:
  50                 format_id = file.attrib['bitrate']
  51             formats.append({
  52                 'url': file_url,
  53                 'ext': 'mp4',
  54                 'format_id': format_id,
  55             })
  56         def sort_key(f):
  57             try:
  58                 return qualities.index(f['format_id'])
  59             except ValueError:
  60                 return -1
  61         formats.sort(key=sort_key)
  62         if not formats:
  63             raise RegexNotFoundError(u'Unable to extract video URL')
  64
  65         return {
  66             'id':          video_id,
  67             'formats': formats,
  68             'title':       self._og_search_title(webpage),
  69             'thumbnail':   self._og_search_thumbnail(webpage),
  70             'description': self._og_search_description(webpage),
  71         }