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 ..utils import (
   8     compat_urllib_parse,
   9     remove_start,
  10 )
  11
  12
  13 class VideoMegaIE(InfoExtractor):
  14     _VALID_URL = r'''(?x)https?://
  15         (?:www\.)?videomega\.tv/
  16         (?:iframe\.php)?\?ref=(?P<id>[A-Za-z0-9]+)
  17         '''
  18     _TEST = {
  19         'url': 'http://videomega.tv/?ref=GKeGPVedBe',
  20         'md5': '240fb5bcf9199961f48eb17839b084d6',
  21         'info_dict': {
  22             'id': 'GKeGPVedBe',
  23             'ext': 'mp4',
  24             'title': 'XXL - All Sports United',
  25             'thumbnail': 're:^https?://.*\.jpg$',
  26         }
  27     }
  28
  29     def _real_extract(self, url):
  30         mobj = re.match(self._VALID_URL, url)
  31         video_id = mobj.group('id')
  32
  33         url = 'http://videomega.tv/iframe.php?ref={0:}'.format(video_id)
  34         webpage = self._download_webpage(url, video_id)
  35
  36         escaped_data = self._search_regex(
  37             r'unescape\("([^"]+)"\)', webpage, 'escaped data')
  38         playlist = compat_urllib_parse.unquote(escaped_data)
  39
  40         thumbnail = self._search_regex(
  41             r'image:\s*"([^"]+)"', playlist, 'thumbnail', fatal=False)
  42         url = self._search_regex(r'file:\s*"([^"]+)"', playlist, 'URL')
  43         title = remove_start(self._html_search_regex(
  44             r'<title>(.*?)</title>', webpage, 'title'), 'VideoMega.tv - ')
  45
  46         formats = [{
  47             'format_id': 'sd',
  48             'url': url,
  49         }]
  50         self._sort_formats(formats)
  51
  52         return {
  53             'id': video_id,
  54             'title': title,
  55             'formats': formats,
  56             'thumbnail': thumbnail,
  57         }