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

   1 import re
   2 import os
   3 import socket
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     compat_http_client,
   8     compat_str,
   9     compat_urllib_error,
  10     compat_urllib_parse,
  11     compat_urllib_request,
  12
  13     ExtractorError,
  14 )
  15
  16
  17 class DepositFilesIE(InfoExtractor):
  18     """Information extractor for depositfiles.com"""
  19
  20     _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)'
  21
  22     def _real_extract(self, url):
  23         file_id = url.split('/')[-1]
  24         # Rebuild url in english locale
  25         url = 'http://depositfiles.com/en/files/' + file_id
  26
  27         # Retrieve file webpage with 'Free download' button pressed
  28         free_download_indication = { 'gateway_result' : '1' }
  29         request = compat_urllib_request.Request(url, compat_urllib_parse.urlencode(free_download_indication))
  30         try:
  31             self.report_download_webpage(file_id)
  32             webpage = compat_urllib_request.urlopen(request).read()
  33         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
  34             raise ExtractorError(u'Unable to retrieve file webpage: %s' % compat_str(err))
  35
  36         # Search for the real file URL
  37         mobj = re.search(r'<form action="(http://fileshare.+?)"', webpage)
  38         if (mobj is None) or (mobj.group(1) is None):
  39             # Try to figure out reason of the error.
  40             mobj = re.search(r'<strong>(Attention.*?)</strong>', webpage, re.DOTALL)
  41             if (mobj is not None) and (mobj.group(1) is not None):
  42                 restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip()
  43                 raise ExtractorError(u'%s' % restriction_message)
  44             else:
  45                 raise ExtractorError(u'Unable to extract download URL from: %s' % url)
  46
  47         file_url = mobj.group(1)
  48         file_extension = os.path.splitext(file_url)[1][1:]
  49
  50         # Search for file title
  51         file_title = self._search_regex(r'<b title="(.*?)">', webpage, u'title')
  52
  53         return [{
  54             'id':       file_id.decode('utf-8'),
  55             'url':      file_url.decode('utf-8'),
  56             'uploader': None,
  57             'upload_date':  None,
  58             'title':    file_title,
  59             'ext':      file_extension.decode('utf-8'),
  60         }]