问题描述

Python使用urllib2 urlopen打开网页不正确

 #!/usr/bin/python
# -*- coding: utf-8 -*-

import urllib;
import urllib2;
import os;
import sys;
import shutil;

def searchVT():
    VTMainUrl = 'https://www.virustotal.com/en/#search';
    headers = {
    'accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
    'content-type':'application/x-www-form-urlencode',
    'referer':'https://www.virustotal.com/',
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/38.0.2125.101 Safari/537.36'};
    postDict = {'query' : '18092AC0F4F694C60762DC98C9F66BC3',};
    postData = urllib.urlencode(postDict);
    req = urllib2.Request(VTMainUrl, postData, headers);
    try:
        respHtml = urllib2.urlopen(req).read();
    except urllib2.URLError,e:
        if hasattr(e,"reason"):
            print "Failed to reach the server"
            print "The reason:",e.reason
        elif hasattr(e,"code"):
            print "The server couldn't fulfill the request"
            print "Error code:",e.code
            print "Return content:",e.read()
        else:
            pass  #其他异常的处理
    file_object = open('thefile.txt', 'w')
    file_object.write(respHtml)
    file_object.close( )
    print respHtml;
    return respHtml;       

if __name__=="__main__":
    searchVT();

最近使用urllib2 urlopen尝试打开VT网页并进行使用MD5查询，但是不知道为什么返回的网页为空，求大神赐教~

解决方案

怀疑页面是异步方式加载的，所以请求的时候直接返回空页面了，内容是后面在ajax加载的。