_ Git - youtube-dl/blob - youtube_dl/extractor/wayofthemaster.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import determine_ext
   7
   8
   9 class WayOfTheMasterIE(InfoExtractor):
  10     _VALID_URL = r'https?://www\.wayofthemaster\.com/([^/?#]*/)*(?P<id>[^/?#]+)\.s?html(?:$|[?#])'
  11
  12     _TEST = {
  13         'url': 'http://www.wayofthemaster.com/hbks.shtml',
  14         'md5': '5316b57487ada8480606a93cb3d18d24',
  15         'info_dict': {
  16             'id': 'hbks',
  17             'ext': 'mp4',
  18             'title': 'Intelligent Design vs. Evolution',
  19         },
  20     }
  21
  22     def _real_extract(self, url):
  23         mobj = re.match(self._VALID_URL, url)
  24         video_id = mobj.group('id')
  25
  26         webpage = self._download_webpage(url, video_id)
  27
  28         title = self._search_regex(
  29             r'<img src="images/title_[^"]+".*?alt="([^"]+)"',
  30             webpage, 'title', default=None)
  31         if title is None:
  32             title = self._html_search_regex(
  33                 r'<title>(.*?)</title>', webpage, 'page title')
  34
  35         url_base = self._search_regex(
  36             r'<param\s+name="?movie"?\s+value=".*?/wotm_videoplayer_highlow[0-9]*\.swf\?vid=([^"]+)"',
  37             webpage, 'URL base')
  38         formats = [{
  39             'format_id': 'low',
  40             'quality': 1,
  41             'url': url_base + '_low.mp4',
  42         }, {
  43             'format_id': 'high',
  44             'quality': 2,
  45             'url': url_base + '_high.mp4',
  46         }]
  47         self._sort_formats(formats)
  48
  49         return {
  50             'id': video_id,
  51             'title': title,
  52             'formats': formats,
  53         }