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