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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6
   7
   8 class BloombergIE(InfoExtractor):
   9     _VALID_URL = r'https?://www\.bloomberg\.com/video/(?P<name>.+?)\.html'
  10
  11     _TEST = {
  12         'url': 'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html',
  13         # The md5 checksum changes
  14         'info_dict': {
  15             'id': 'qurhIVlJSB6hzkVi229d8g',
  16             'ext': 'flv',
  17             'title': 'Shah\'s Presentation on Foreign-Exchange Strategies',
  18             'description': 'md5:0681e0d30dcdfc6abf34594961d8ea88',
  19         },
  20     }
  21
  22     def _real_extract(self, url):
  23         mobj = re.match(self._VALID_URL, url)
  24         name = mobj.group('name')
  25         webpage = self._download_webpage(url, name)
  26         f4m_url = self._search_regex(
  27             r'<source src="(https?://[^"]+\.f4m.*?)"', webpage,
  28             'f4m url')
  29         title = re.sub(': Video$', '', self._og_search_title(webpage))
  30
  31         return {
  32             'id': name.split('-')[-1],
  33             'title': title,
  34             'formats': self._extract_f4m_formats(f4m_url, name),
  35             'description': self._og_search_description(webpage),
  36             'thumbnail': self._og_search_thumbnail(webpage),
  37         }