Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/sockshare.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from ..compat import (
   7     compat_urllib_parse,
   8     compat_urllib_request,
   9 )
  10 from ..utils import (
  11     determine_ext,
  12     ExtractorError,
  13 )
  14
  15 from .common import InfoExtractor
  16
  17
  18 class SockshareIE(InfoExtractor):
  19     _VALID_URL = r'https?://(?:www\.)?sockshare\.com/file/(?P<id>[0-9A-Za-z]+)'
  20     _FILE_DELETED_REGEX = r'This file doesn\'t exist, or has been removed\.</div>'
  21     _TEST = {
  22         'url': 'http://www.sockshare.com/file/437BE28B89D799D7',
  23         'md5': '9d0bf1cfb6dbeaa8d562f6c97506c5bd',
  24         'info_dict': {
  25             'id': '437BE28B89D799D7',
  26             'title': 'big_buck_bunny_720p_surround.avi',
  27             'ext': 'avi',
  28         }
  29     }
  30
  31     def _real_extract(self, url):
  32         video_id = self._match_id(url)
  33         url = 'http://sockshare.com/file/%s' % video_id
  34         webpage = self._download_webpage(url, video_id)
  35
  36         if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
  37             raise ExtractorError('Video %s does not exist' % video_id,
  38                                  expected=True)
  39
  40         confirm_hash = self._html_search_regex(r'''(?x)<input\s+
  41             type="hidden"\s+
  42             value="([^"]*)"\s+
  43             name="hash"
  44             ''', webpage, 'hash')
  45
  46         fields = {
  47             "hash": confirm_hash.encode('utf-8'),
  48             "confirm": "Continue as Free User"
  49         }
  50
  51         post = compat_urllib_parse.urlencode(fields)
  52         req = compat_urllib_request.Request(url, post)
  53         # Apparently, this header is required for confirmation to work.
  54         req.add_header('Host', 'www.sockshare.com')
  55         req.add_header('Content-type', 'application/x-www-form-urlencoded')
  56
  57         webpage = self._download_webpage(
  58             req, video_id, 'Downloading video page')
  59
  60         video_url = self._html_search_regex(
  61             r'<a href="([^"]*)".+class="download_file_link"',
  62             webpage, 'file url')
  63         video_url = "http://www.sockshare.com" + video_url
  64         title = self._html_search_regex((
  65             r'<h1>(.+)<strong>',
  66             r'var name = "([^"]+)";'),
  67             webpage, 'title', default=None)
  68         thumbnail = self._html_search_regex(
  69             r'<img\s+src="([^"]*)".+?name="bg"',
  70             webpage, 'thumbnail', default=None)
  71
  72         formats = [{
  73             'format_id': 'sd',
  74             'url': video_url,
  75             'ext': determine_ext(title),
  76         }]
  77
  78         return {
  79             'id': video_id,
  80             'title': title,
  81             'thumbnail': thumbnail,
  82             'formats': formats,
  83         }