zoukankan      html  css  js  c++  java
  • C#用HttpWebRequest通过代理服务器验证后抓取网页内容

    内网用户或代理上网的用户使用

    using System.IO;
    using System.Net;

    public string get_html()

    {

    string urlStr = "http://www.domain.com";                              //設定要獲取的地址
    HttpWebRequest hwr = (HttpWebRequest)HttpWebRequest.Create(urlStr);      //建立HttpWebRequest對象
    hwr.Timeout = 60000;                                                  //定義服務器超時時間
    WebProxy proxy = new WebProxy();                                      //定義一個網關對象
    proxy.Address = new Uri("http://proxy.domain.com:3128");              //網關服務器:端口
    proxy.Credentials = new NetworkCredential("f3210316", "6978233");      //用戶名,密碼
    hwr.UseDefaultCredentials = true;                                      //啟用網關認証
    hwr.Proxy = proxy;                                                      //設置網關

    try
    {

            HttpWebResponse hwrs = (HttpWebResponse)hwr.GetResponse();              //取得回應

    }

    catch
    {
             MessageBox.Show("无法连接代理!");
             return;
    }

    //判断HTTP响应状态
    if(hwrs.StatusCode != HttpStatusCode.OK)
    {
             MessageBox.Show("访问失败!");
             hwrs.Close();
             return;
    }
    else

    {
            Stream s = hwrs.GetResponseStream();                                  //得到回應的流對象
            StreamReader sr = new StreamReader(s, Encoding.UTF8);                  //以UTF-8編碼讀取流
            StringBuilder content = new StringBuilder();                          //
        while (sr.Peek() != -1)                                                  //每次讀取一行,直到
        {                                                                      //下一個字節沒有內容
            content.Append(sr.ReadLine()+""r"n");                              //返回為止
        }                                                                      //
            //return content.ToString() ;

    }

    //输出所有的Header(当然包括服务器输出的Cookie)
    //for(int ii=0;ii<hwrs.Headers.Count;ii++)
    //{
    //MessageBox.Show(hwrs.Headers.GetKey(ii)+":"+res.Headers[ii]);
    //}

    }

    C#用HttpWebRequest通过代理服务器验证后抓取网页内容

    大家知道,用HttpWebRequest可以通过Http对网页进行抓取,但是如果是内网,而且是通过代理上网的用户,如果直接进行操作是行不通的。
    那有没有什么办法呢?
    当然有,呵呵,见以下代码:

    "http://www.domain.com";                            //設定要獲取的地址
    HttpWebRequest hwr = (HttpWebRequest)HttpWebRequest.Create(urlStr);    //建立HttpWebRequest對象
    hwr.Timeout 60000;                                                //定義服務器超時時間
    WebProxy proxy new WebProxy();                                    //定義一個網關對象
    proxy.Address new Uri("http://proxy.domain.com:3128");            //網關服務器:端口
    proxy.Credentials new NetworkCredential("f3210316""6978233");    //用戶名,密碼
    hwr.UseDefaultCredentials true;                                    //啟用網關認証
    hwr.Proxy = proxy;                                                    //設置網關
    HttpWebResponse hwrs = (HttpWebResponse)hwr.GetResponse();            //取得回應
    Stream s = hwrs.GetResponseStream();                                //得到回應的流對象
    StreamReader sr new StreamReader(s, Encoding.UTF8);                //以UTF-8編碼讀取流
    StringBuilder content new StringBuilder();                        //
    while (sr.Peek() != -1)                                                //每次讀取一行,直到
    {                                                                    //下一個字節沒有內容
        content.Append(sr.ReadLine()+""r"n");                            //返回為止
    }                                                                    //
    return content.ToString() ;                                            //返回得到的字符串
  • 相关阅读:
    iOS开发-NSOperation与GCD区别
    FMDB数据库升级
    Xcode自动选择证书
    asp.net常用函数表
    JS操作文件
    Json转换插件
    SpringCloud分布式事务-Seata
    SpringCloud应对高并发的思路
    SpringCloud-Greenwich版本新特性探索(1)---SpringCloudGateway
    如何热更新线上的Java服务器代码
  • 原文地址:https://www.cnblogs.com/cuihongyu3503319/p/14084379.html
Copyright © 2011-2022 走看看