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

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     int_or_none,
   7     parse_filesize,
   8     unified_strdate,
   9 )
  10
  11
  12 class MegavideozeuIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?megavideoz\.eu/video/(?P<id>.*)(?:.*)'
  14     _TESTS = [
  15         {
  16             'url': 'http://megavideoz.eu/video/WM6UB919XMXH/SMPTE-Universal-Film-Leader',
  17             'info_dict': {
  18                 'id': '48723',
  19                 'ext': 'mp4',
  20                 'duration': '10',
  21                 'title': 'SMPTE Universal Film Leader',
  22             }
  23         }
  24     ]
  25
  26
  27     def _real_extract(self, url):
  28         tmp_video_id = self._match_id(url)
  29
  30         webpage = self._download_webpage(url, tmp_video_id)
  31
  32         config_php = self._html_search_regex(
  33             r'var cnf = \'([^\']+)\'', webpage, 'config.php url')
  34
  35         configpage = self._download_webpage(config_php, tmp_video_id)
  36
  37         video_id = self._html_search_regex(
  38             r'<mediaid>([^<]+)', configpage, 'video id')
  39         video_url = self._html_search_regex(
  40             r'<file>([^<]+)', configpage, 'video URL')
  41         title = self._html_search_regex(
  42             r'<title><!\[CDATA\[([^\]]+)', configpage, 'title')
  43         duration = int_or_none(self._html_search_regex(
  44             r'<duration>([0-9\.]+)', configpage, 'duration', fatal=False))
  45
  46         return {
  47             'id': video_id,
  48             'url': video_url,
  49             'title': title,
  50             'duration': duration
  51         }