import base64 import datetime import itertools import netrc import os import re import socket import time import email.utils import xml.etree.ElementTree import random import math import operator import hashlib import binascii import urllib from .utils import * from .extractor.common import InfoExtractor, SearchInfoExtractor from .extractor.ard import ARDIE from .extractor.arte import ArteTvIE from .extractor.bliptv import BlipTVIE, BlipTVUserIE from .extractor.comedycentral import ComedyCentralIE from .extractor.dailymotion import DailymotionIE from .extractor.gametrailers import GametrailersIE from .extractor.generic import GenericIE from .extractor.googleplus import GooglePlusIE from .extractor.googlesearch import GoogleSearchIE from .extractor.metacafe import MetacafeIE from .extractor.myvideo import MyVideoIE from .extractor.statigram import StatigramIE from .extractor.photobucket import PhotobucketIE from .extractor.soundcloud import SoundcloudIE, SoundcloudSetIE from .extractor.vimeo import VimeoIE from .extractor.yahoo import YahooIE, YahooSearchIE from .extractor.youtube import YoutubeIE, YoutubePlaylistIE, YoutubeSearchIE, YoutubeUserIE, YoutubeChannelIE from .extractor.zdf import ZDFIE class DepositFilesIE(InfoExtractor): """Information extractor for depositfiles.com""" _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)' def _real_extract(self, url): file_id = url.split('/')[-1] # Rebuild url in english locale url = 'http://depositfiles.com/en/files/' + file_id # Retrieve file webpage with 'Free download' button pressed free_download_indication = { 'gateway_result' : '1' } request = compat_urllib_request.Request(url, compat_urllib_parse.urlencode(free_download_indication)) try: self.report_download_webpage(file_id) webpage = compat_urllib_request.urlopen(request).read() except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: raise ExtractorError(u'Unable to retrieve file webpage: %s' % compat_str(err)) # Search for the real file URL mobj = re.search(r'