youtube_dl/extractor/vice.py

   1 from __future__ import unicode_literals
   2 import re
   3
   4 from .common import InfoExtractor
   5 from .ooyala import OoyalaIE
   6 from ..utils import ExtractorError
   7
   8
   9 class ViceIE(InfoExtractor):
  10     _VALID_URL = r'https?://(.+?\.)?vice\.com/.*?/(?P<name>.+)'
  11
  12     _TESTS = [
  13         {
  14             'url': 'http://www.vice.com/Fringes/cowboy-capitalists-part-1',
  15             'info_dict': {
  16                 'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp',
  17                 'ext': 'mp4',
  18                 'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov',
  19             },
  20             'params': {
  21                 # Requires ffmpeg (m3u8 manifest)
  22                 'skip_download': True,
  23             },
  24         }, {
  25             'url': 'https://news.vice.com/video/experimenting-on-animals-inside-the-monkey-lab',
  26             'info_dict': {
  27                 'id': 'N2bzkydjraWDGwnt8jAttCF6Y0PDv4Zj',
  28                 'ext': 'mp4',
  29                 'title': 'VICE News - Inside the Monkey Lab',
  30                 'description': 'md5:1f660d467d3515f29d11e5ef742a4b82',
  31             },
  32             'params': {
  33                 # Requires ffmpeg (m3u8 manifest)
  34                 'skip_download': True,
  35             },
  36         }
  37     ]
  38
  39     def _real_extract(self, url):
  40         mobj = re.match(self._VALID_URL, url)
  41         name = mobj.group('name')
  42         webpage = self._download_webpage(url, name)
  43         try:
  44             embed_code = self._search_regex(
  45                 r'embedCode=([^&\'"]+)', webpage,
  46                 'ooyala embed code')
  47             ooyala_url = OoyalaIE._url_for_embed_code(embed_code)
  48         except ExtractorError:
  49             raise ExtractorError('The page doesn\'t contain a video', expected=True)
  50         return self.url_result(ooyala_url, ie='Ooyala')