youtube_dl/extractor/wayofthemaster.py

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