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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_urllib_request
   8
   9
  10 class VideoMegaIE(InfoExtractor):
  11     _VALID_URL = r'''(?x)https?://
  12         (?:www\.)?videomega\.tv/
  13         (?:iframe\.php|cdn\.php)?\?ref=(?P<id>[A-Za-z0-9]+)
  14         '''
  15     _TEST = {
  16         'url': 'http://videomega.tv/?ref=4GNA688SU99US886ANG4',
  17         'md5': 'bf5c2f95c4c917536e80936af7bc51e1',
  18         'info_dict': {
  19             'id': '4GNA688SU99US886ANG4',
  20             'ext': 'mp4',
  21             'title': 'BigBuckBunny_320x180',
  22             'thumbnail': 're:^https?://.*\.jpg$',
  23         }
  24     }
  25
  26     def _real_extract(self, url):
  27         video_id = self._match_id(url)
  28
  29         iframe_url = 'http://videomega.tv/cdn.php?ref=%s' % video_id
  30         req = compat_urllib_request.Request(iframe_url)
  31         req.add_header('Referer', url)
  32         webpage = self._download_webpage(req, video_id)
  33
  34         title = self._html_search_regex(
  35             r'<title>(.*?)</title>', webpage, 'title')
  36         title = re.sub(
  37             r'(?:^[Vv]ideo[Mm]ega\.tv\s-\s?|\s?-\svideomega\.tv$)', '', title)
  38         thumbnail = self._search_regex(
  39             r'<video[^>]+?poster="([^"]+)"', webpage, 'thumbnail', fatal=False)
  40         video_url = self._search_regex(
  41             r'<source[^>]+?src="([^"]+)"', webpage, 'video URL')
  42
  43         return {
  44             'id': video_id,
  45             'title': title,
  46             'url': video_url,
  47             'thumbnail': thumbnail,
  48             'http_headers': {
  49                 'Referer': iframe_url,
  50             },
  51         }