Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/hostingbulk.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     ExtractorError,
   9     compat_urllib_request,
  10     int_or_none,
  11     urlencode_postdata,
  12 )
  13
  14
  15 class HostingBulkIE(InfoExtractor):
  16     _VALID_URL = r'''(?x)
  17         https?://(?:www\.)?hostingbulk\.com/
  18         (?:embed-)?(?P<id>[A-Za-z0-9]{12})(?:-\d+x\d+)?\.html'''
  19     _FILE_DELETED_REGEX = r'<b>File Not Found</b>'
  20     _TEST = {
  21         'url': 'http://hostingbulk.com/n0ulw1hv20fm.html',
  22         'md5': '6c8653c8ecf7ebfa83b76e24b7b2fe3f',
  23         'info_dict': {
  24             'id': 'n0ulw1hv20fm',
  25             'ext': 'mp4',
  26             'title': 'md5:5afeba33f48ec87219c269e054afd622',
  27             'filesize': 6816081,
  28             'thumbnail': 're:^http://.*\.jpg$',
  29         }
  30     }
  31
  32     def _real_extract(self, url):
  33         mobj = re.match(self._VALID_URL, url)
  34         video_id = mobj.group('id')
  35
  36         url = 'http://hostingbulk.com/{0:}.html'.format(video_id)
  37
  38         # Custom request with cookie to set language to English, so our file
  39         # deleted regex would work.
  40         request = compat_urllib_request.Request(
  41             url, headers={'Cookie': 'lang=english'})
  42         webpage = self._download_webpage(request, video_id)
  43
  44         if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
  45             raise ExtractorError('Video %s does not exist' % video_id,
  46                                  expected=True)
  47
  48         title = self._html_search_regex(r'<h3>(.*?)</h3>', webpage, 'title')
  49         filesize = int_or_none(
  50             self._search_regex(
  51                 r'<small>\((\d+)\sbytes?\)</small>',
  52                 webpage,
  53                 'filesize',
  54                 fatal=False
  55             )
  56         )
  57         thumbnail = self._search_regex(
  58             r'<img src="([^"]+)".+?class="pic"',
  59             webpage, 'thumbnail', fatal=False)
  60
  61         fields = dict(re.findall(r'''(?x)<input\s+
  62             type="hidden"\s+
  63             name="([^"]+)"\s+
  64             value="([^"]*)"
  65             ''', webpage))
  66
  67         request = compat_urllib_request.Request(url, urlencode_postdata(fields))
  68         request.add_header('Content-type', 'application/x-www-form-urlencoded')
  69         response = self._request_webpage(request, video_id,
  70                                          'Submiting download request')
  71         video_url = response.geturl()
  72
  73         formats = [{
  74             'format_id': 'sd',
  75             'filesize': filesize,
  76             'url': video_url,
  77         }]
  78
  79         return {
  80             'id': video_id,
  81             'title': title,
  82             'thumbnail': thumbnail,
  83             'formats': formats,
  84         }