Raphaël G. Git Repositories - youtubedl/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 ..utils import (
   8     ExtractorError,
   9     compat_urllib_parse,
  10     compat_urllib_request,
  11     determine_ext,
  12 )
  13
  14
  15 class FiredriveIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?firedrive\.com/' + \
  17                  '(?:file|embed)/(?P<id>[0-9a-zA-Z]+)'
  18     _FILE_DELETED_REGEX = r'<div class="removed_file_image">'
  19
  20     _TESTS = [{
  21         'url': 'https://www.firedrive.com/file/FEB892FA160EBD01',
  22         'md5': 'd5d4252f80ebeab4dc2d5ceaed1b7970',
  23         'info_dict': {
  24             'id': 'FEB892FA160EBD01',
  25             'ext': 'flv',
  26             'title': 'bbb_theora_486kbit.flv',
  27             'thumbnail': 're:^http://.*\.jpg$',
  28         },
  29     }]
  30
  31     def _real_extract(self, url):
  32         mobj = re.match(self._VALID_URL, url)
  33         video_id = mobj.group('id')
  34
  35         url = 'http://firedrive.com/file/%s' % video_id
  36
  37         webpage = self._download_webpage(url, video_id)
  38
  39         if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
  40             raise ExtractorError('Video %s does not exist' % video_id,
  41                                  expected=True)
  42
  43         fields = dict(re.findall(r'''(?x)<input\s+
  44             type="hidden"\s+
  45             name="([^"]+)"\s+
  46             (?:id="[^"]+"\s+)?
  47             value="([^"]*)"
  48             ''', webpage))
  49
  50         post = compat_urllib_parse.urlencode(fields)
  51         req = compat_urllib_request.Request(url, post)
  52         req.add_header('Content-type', 'application/x-www-form-urlencoded')
  53
  54         # Apparently, this header is required for confirmation to work.
  55         req.add_header('Host', 'www.firedrive.com')
  56
  57         webpage = self._download_webpage(req, video_id,
  58                                          'Downloading video page')
  59
  60         title = self._search_regex(r'class="external_title_left">(.+)</div>',
  61                                    webpage, 'title')
  62         thumbnail = self._search_regex(r'image:\s?"(//[^\"]+)', webpage,
  63                                        'thumbnail', fatal=False)
  64         if thumbnail is not None:
  65             thumbnail = 'http:' + thumbnail
  66
  67         ext = self._search_regex(r'type:\s?\'([^\']+)\',',
  68                                  webpage, 'extension', fatal=False)
  69         video_url = self._search_regex(
  70             r'file:\s?\'(http[^\']+)\',', webpage, 'file url')
  71
  72         formats = [{
  73             'format_id': 'sd',
  74             'url': video_url,
  75             'ext': ext,
  76         }]
  77
  78         return {
  79             'id': video_id,
  80             'title': title,
  81             'thumbnail': thumbnail,
  82             'formats': formats,
  83         }