博客
关于我
强烈建议你试试无所不能的chatGPT,快点击我
发现的一个好的socket网页抓取源码
阅读量:4323 次
发布时间:2019-06-06

本文共 3276 字,大约阅读时间需要 10 分钟。

C#使用Socket获取网页源代码的代码,需要的朋友可以参考下

 

WebToolkit类:

using System;
using System.Net.Sockets;
using System.Text;

namespace ConsoleApplication1

{
class WebToolkit
{
/// <summary>
/// Url结构
/// </summary>
struct UrlInfo
{
public string Host;
public int Port;
public string File;
public string Body;
}

/// <summary>

/// 解析URL
/// </summary>
/// <param name="url"></param>
/// <returns></returns>
private static UrlInfo ParseURL(string url)
{
UrlInfo urlInfo = new UrlInfo();
string[] strTemp = null;
urlInfo.Host = "";
urlInfo.Port = 80;
urlInfo.File = "/";
urlInfo.Body = "";
int intIndex = url.ToLower().IndexOf("http://");
if (intIndex != -1)
{
url = url.Substring(7);
intIndex = url.IndexOf("/");
if (intIndex == -1)
{
urlInfo.Host = url;
}
else
{
urlInfo.Host = url.Substring(0, intIndex);
url = url.Substring(intIndex);
intIndex = urlInfo.Host.IndexOf(":");
if (intIndex != -1)
{
strTemp = urlInfo.Host.Split(':');
urlInfo.Host = strTemp[0];
int.TryParse(strTemp[1], out urlInfo.Port);
}
intIndex = url.IndexOf("?");
if (intIndex == -1)
{
urlInfo.File = url;
}
else
{
strTemp = url.Split('?');
urlInfo.File = strTemp[0];
urlInfo.Body = strTemp[1];
}
}
}
return urlInfo;
}

/// <summary>

/// 发出请求并获取响应
/// </summary>
/// <param name="host"></param>
/// <param name="port"></param>
/// <param name="body"></param>
/// <param name="encode"></param>
/// <returns></returns>
private static string GetResponse(string host, int port, string body, Encoding encode)
{
string strResult = string.Empty;
byte[] bteSend = Encoding.ASCII.GetBytes(body);
byte[] bteReceive = new byte[1024];
int intLen = 0;

using (Socket socket = new Socket(AddressFamily.InterNetwork, SocketType.Stream, ProtocolType.Tcp))

{
try
{
socket.Connect(host, port);
if (socket.Connected)
{
socket.Send(bteSend, bteSend.Length, 0);
while ((intLen = socket.Receive(bteReceive, bteReceive.Length, 0)) > 0)
{
strResult += encode.GetString(bteReceive, 0, intLen);
}
}
socket.Close();
}
catch { }
}

return strResult;

}

/// <summary>

/// GET请求
/// </summary>
/// <param name="url"></param>
/// <param name="encode"></param>
/// <returns></returns>
public static string Get(string url, Encoding encode)
{
UrlInfo urlInfo = ParseURL(url);
string strRequest = string.Format("GET {0}?{1} HTTP/1.1\r\nHost:{2}:{3}\r\nConnection:Close\r\n\r\n", urlInfo.File, urlInfo.Body, urlInfo.Host, urlInfo.Port.ToString());
return GetResponse(urlInfo.Host, urlInfo.Port, strRequest, encode);
}

/// <summary>

/// POST请求
/// </summary>
/// <param name="url"></param>
/// <param name="encode"></param>
/// <returns></returns>
public static string Post(string url, Encoding encode)
{
UrlInfo urlInfo = ParseURL(url);
string strRequest = string.Format("POST {0} HTTP/1.1\r\nHost:{1}:{2}\r\nContent-Length:{3}\r\nContent-Type:application/x-www-form-urlencoded\r\nConnection:Close\r\n\r\n{4}", urlInfo.File, urlInfo.Host, urlInfo.Port.ToString(), urlInfo.Body.Length, urlInfo.Body);
return GetResponse(urlInfo.Host, urlInfo.Port, strRequest, encode);
}
}
}

调用示例:

using System;

using System.Text;

namespace ConsoleApplication1

{
//调用示例
class Program
{
public static void Main(string[] args)
{
Console.WriteLine(WebToolkit.Get("", Encoding.Default));
Console.ReadKey();
}
}
}

详细出处参考:

转载于:https://www.cnblogs.com/lijinchang/archive/2011/10/11/2207021.html

你可能感兴趣的文章
第五天站立会议内容
查看>>
最短路径(SP)问题相关算法与模板
查看>>
js算法之最常用的排序
查看>>
Python——交互式图形编程
查看>>
经典排序——希尔排序
查看>>
团队编程项目作业2-团队编程项目代码设计规范
查看>>
英特尔公司将停止910GL、915GL和915PL芯片组的生产
查看>>
Maven配置
查看>>
HttpServletRequest /HttpServletResponse
查看>>
SAM4E单片机之旅——24、使用DSP库求向量数量积
查看>>
从远程库克隆库
查看>>
codeforces Unusual Product
查看>>
hdu4348 - To the moon 可持久化线段树 区间修改 离线处理
查看>>
正则表达式的搜索和替换
查看>>
个人项目:WC
查看>>
地鼠的困境SSL1333 最大匹配
查看>>
flume+elasticsearch+kibana遇到的坑
查看>>
【MM系列】在SAP里查看数据的方法
查看>>
C#——winform
查看>>
CSS3 transform制作的漂亮的滚动式导航
查看>>