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'https?://(?:www\.)?videomega\.tv/(?:(?:view|iframe|cdn)\.php)?\?ref=(?P<id>[A-Za-z0-9]+)'
  12     _TEST = {
  13         'url': 'http://videomega.tv/cdn.php?ref=AOSQBJYKIDDIKYJBQSOA',
  14         'md5': 'cc1920a58add3f05c6a93285b84fb3aa',
  15         'info_dict': {
  16             'id': 'AOSQBJYKIDDIKYJBQSOA',
  17             'ext': 'mp4',
  18             'title': '1254207',
  19             'thumbnail': 're:^https?://.*\.jpg$',
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         video_id = self._match_id(url)
  25
  26         iframe_url = 'http://videomega.tv/cdn.php?ref=%s' % video_id
  27         req = compat_urllib_request.Request(iframe_url)
  28         req.add_header('Referer', url)
  29         req.add_header('Cookie', 'noadvtday=0')
  30         webpage = self._download_webpage(req, video_id)
  31
  32         title = self._html_search_regex(
  33             r'<title>(.+?)</title>', webpage, 'title')
  34         title = re.sub(
  35             r'(?:^[Vv]ideo[Mm]ega\.tv\s-\s*|\s*-\svideomega\.tv$)', '', title)
  36         thumbnail = self._search_regex(
  37             r'<video[^>]+?poster="([^"]+)"', webpage, 'thumbnail', fatal=False)
  38         video_url = self._search_regex(
  39             r'<source[^>]+?src="([^"]+)"', webpage, 'video URL')
  40
  41         return {
  42             'id': video_id,
  43             'title': title,
  44             'url': video_url,
  45             'thumbnail': thumbnail,
  46             'http_headers': {
  47                 'Referer': iframe_url,
  48             },
  49         }