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 (
   8     compat_urllib_parse,
   9     compat_urllib_request,
  10 )
  11 from ..utils import (
  12     ExtractorError,
  13     remove_start,
  14 )
  15
  16
  17 class VideoMegaIE(InfoExtractor):
  18     _VALID_URL = r'''(?x)https?://
  19         (?:www\.)?videomega\.tv/
  20         (?:iframe\.php)?\?ref=(?P<id>[A-Za-z0-9]+)
  21         '''
  22     _TEST = {
  23         'url': 'http://videomega.tv/?ref=QR0HCUHI1661IHUCH0RQ',
  24         'md5': 'bf5c2f95c4c917536e80936af7bc51e1',
  25         'info_dict': {
  26             'id': 'QR0HCUHI1661IHUCH0RQ',
  27             'ext': 'mp4',
  28             'title': 'Big Buck Bunny',
  29             'thumbnail': 're:^https?://.*\.jpg$',
  30         }
  31     }
  32
  33     def _real_extract(self, url):
  34         video_id = self._match_id(url)
  35
  36         iframe_url = 'http://videomega.tv/iframe.php?ref={0:}'.format(video_id)
  37         req = compat_urllib_request.Request(iframe_url)
  38         req.add_header('Referer', url)
  39         webpage = self._download_webpage(req, video_id)
  40
  41         try:
  42             escaped_data = re.findall(r'unescape\("([^"]+)"\)', webpage)[-1]
  43         except IndexError:
  44             raise ExtractorError('Unable to extract escaped data')
  45
  46         playlist = compat_urllib_parse.unquote(escaped_data)
  47
  48         thumbnail = self._search_regex(
  49             r'image:\s*"([^"]+)"', playlist, 'thumbnail', fatal=False)
  50         video_url = self._search_regex(r'file:\s*"([^"]+)"', playlist, 'URL')
  51         title = remove_start(self._html_search_regex(
  52             r'<title>(.*?)</title>', webpage, 'title'), 'VideoMega.tv - ')
  53
  54         formats = [{
  55             'format_id': 'sd',
  56             'url': video_url,
  57         }]
  58         self._sort_formats(formats)
  59
  60         return {
  61             'id': video_id,
  62             'title': title,
  63             'formats': formats,
  64             'thumbnail': thumbnail,
  65             'http_headers': {
  66                 'Referer': iframe_url,
  67             },
  68         }