_ Git - youtube-dl/blob - youtube_dl/extractor/sockshare.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from ..utils import (
   5     ExtractorError,
   6     compat_urllib_parse,
   7     compat_urllib_request,
   8 )
   9 import re
  10
  11 from .common import InfoExtractor
  12
  13
  14 class SockshareIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?sockshare\.com/file/(?P<id>[0-9A-Za-z]+)'
  16     _FILE_DELETED_REGEX = r'This file doesn\'t exist, or has been removed\.</div>'
  17     _TEST = {
  18         'url': 'http://www.sockshare.com/file/437BE28B89D799D7',
  19         'md5': '9d0bf1cfb6dbeaa8d562f6c97506c5bd',
  20         'info_dict': {
  21             'id': '437BE28B89D799D7',
  22             'title': 'big_buck_bunny_720p_surround.avi',
  23             'ext': 'avi',
  24             'thumbnail': 're:^http://.*\.jpg$',
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         mobj = re.match(self._VALID_URL, url)
  30         video_id = mobj.group('id')
  31
  32         url = 'http://sockshare.com/file/%s' % video_id
  33         webpage = self._download_webpage(url, video_id)
  34
  35         if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
  36             raise ExtractorError('Video %s does not exist' % video_id,
  37                                  expected=True)
  38
  39         confirm_hash = self._html_search_regex(r'''(?x)<input\s+
  40             type="hidden"\s+
  41             value="([^"]*)"\s+
  42             name="hash"
  43             ''', webpage, 'hash')
  44
  45         fields = {
  46             "hash": confirm_hash,
  47             "confirm": "Continue as Free User"
  48         }
  49
  50         post = compat_urllib_parse.urlencode(fields)
  51         req = compat_urllib_request.Request(url, post)
  52         # Apparently, this header is required for confirmation to work.
  53         req.add_header('Host', 'www.sockshare.com')
  54         req.add_header('Content-type', 'application/x-www-form-urlencoded')
  55
  56         webpage = self._download_webpage(
  57             req, video_id, 'Downloading video page')
  58
  59         video_url = self._html_search_regex(
  60             r'<a href="([^"]*)".+class="download_file_link"',
  61             webpage, 'file url')
  62         video_url = "http://www.sockshare.com" + video_url
  63         title = self._html_search_regex(r'<h1>(.+)<strong>', webpage, 'title')
  64         thumbnail = self._html_search_regex(
  65             r'<img\s+src="([^"]*)".+?name="bg"',
  66             webpage, 'thumbnail')
  67
  68         formats = [{
  69             'format_id': 'sd',
  70             'url': video_url,
  71         }]
  72
  73         return {
  74             'id': video_id,
  75             'title': title,
  76             'thumbnail': thumbnail,
  77             'formats': formats,
  78         }