youtube_dl/extractor/firedrive.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_parse,
  10     compat_urllib_request,
  11 )
  12
  13
  14 class FiredriveIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?firedrive\.com/' + \
  16                  '(?:file|embed)/(?P<id>[0-9a-zA-Z]+)'
  17     _FILE_DELETED_REGEX = r'<div class="removed_file_image">'
  18
  19     _TESTS = [{
  20         'url': 'https://www.firedrive.com/file/FEB892FA160EBD01',
  21         'md5': 'd5d4252f80ebeab4dc2d5ceaed1b7970',
  22         'info_dict': {
  23             'id': 'FEB892FA160EBD01',
  24             'ext': 'flv',
  25             'title': 'bbb_theora_486kbit.flv',
  26             'thumbnail': 're:^http://.*\.jpg$',
  27         },
  28     }]
  29
  30     def _real_extract(self, url):
  31         mobj = re.match(self._VALID_URL, url)
  32         video_id = mobj.group('id')
  33
  34         url = 'http://firedrive.com/file/%s' % video_id
  35
  36         webpage = self._download_webpage(url, video_id)
  37
  38         if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
  39             raise ExtractorError('Video %s does not exist' % video_id,
  40                                  expected=True)
  41
  42         fields = dict(re.findall(r'''(?x)<input\s+
  43             type="hidden"\s+
  44             name="([^"]+)"\s+
  45             value="([^"]*)"
  46             ''', webpage))
  47
  48         post = compat_urllib_parse.urlencode(fields)
  49         req = compat_urllib_request.Request(url, post)
  50         req.add_header('Content-type', 'application/x-www-form-urlencoded')
  51
  52         # Apparently, this header is required for confirmation to work.
  53         req.add_header('Host', 'www.firedrive.com')
  54
  55         webpage = self._download_webpage(req, video_id,
  56                                          'Downloading video page')
  57
  58         title = self._search_regex(r'class="external_title_left">(.+)</div>',
  59                                    webpage, 'title')
  60         thumbnail = self._search_regex(r'image:\s?"(//[^\"]+)', webpage,
  61                                        'thumbnail', fatal=False)
  62         if thumbnail is not None:
  63             thumbnail = 'http:' + thumbnail
  64
  65         ext = self._search_regex(r'type:\s?\'([^\']+)\',',
  66                                  webpage, 'extension', fatal=False)
  67         video_url = self._search_regex(
  68             r'file:\s?loadURL\(\'(http[^\']+)\'\),', webpage, 'file url')
  69
  70         formats = [{
  71             'format_id': 'sd',
  72             'url': video_url,
  73             'ext': ext,
  74         }]
  75
  76         return {
  77             'id': video_id,
  78             'title': title,
  79             'thumbnail': thumbnail,
  80             'formats': formats,
  81         }