C#教程

关注公众号 jb51net

关闭
首页 > 软件编程 > C#教程 > C#网页信息采集方法

C#网页信息采集方法汇总

投稿:shichen2014

这篇文章主要介绍了C#网页信息采集方法,实例汇总了三种常用的方法,是非常实用的技巧,需要的朋友可以参考下

本文实例总结了三种常用的C#网页信息采集方法。分享给大家供大家参考。具体实现方法如下:

一、通过HttpWebResponse 来获取

复制代码 代码如下:
public static string CheckTeamSiteUrl(string url) 

        string response = ""; 
        HttpWebResponse httpResponse = null; 
 
        //assert: user have access to URL  
        try 
        { 
            HttpWebRequest httpRequest = (HttpWebRequest)WebRequest.Create(url); 
            httpRequest.Headers.Set("Pragma", "no-cache"); 
 
                // request.Headers.Set("KeepAlive", "true"); 
 
                httpRequest.CookieContainer = new CookieContainer(); 
 
 
 
                httpRequest.Referer = url; 
 
                httpRequest.UserAgent = "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; .NET CLR 1.1.4322; .NET CLR 2.0.50727)"; 
 
               
 
            httpRequest.Credentials = System.Net.CredentialCache.DefaultCredentials; 
            httpResponse = (HttpWebResponse)httpRequest.GetResponse(); 
             
        } 
        catch (Exception ex) 
        { 
            throw new ApplicationException("HTTP 403 Access denied, URL: " + url, ex); 
        } 
 
        //if here, the URL is correct and the user has access  
        try 
        { 
            string strEncod = httpResponse.ContentType; 
            StreamReader stream; 
            if (strEncod.ToLower().IndexOf("utf") != -1) 
            { 
                stream = new StreamReader(httpResponse.GetResponseStream(), System.Text.Encoding.UTF8); 
            } 
            else 
            { 
                stream = new StreamReader(httpResponse.GetResponseStream(), System.Text.Encoding.Default); 
            } 
            
            char[] buff = new char[4000]; 
            stream.ReadBlock(buff,0,4000); 
            response = new string(buff); 
            stream.Close(); 
            httpResponse.Close(); 
        } 
        catch (Exception ex) 
        { 
            throw new ApplicationException("HTTP 404 Page not found, URL: " + url, ex); 
        } 
        return response; 
}

 
二、通过 WebResponse 来获取

复制代码 代码如下:
public static string getPage(String url) 
{
        WebResponse result = null; 
        string resultstring = ""; 
        try 
        { 
            WebRequest req = WebRequest.Create(url); 
            req.Timeout = 30000; 
            result = req.GetResponse(); 
            Stream ReceiveStream = result.GetResponseStream(); 
 
            //read the stream into a string 
            //StreamReader sr = new StreamReader(ReceiveStream, System.Text.Encoding.UTF8); 
            string strEncod = result.ContentType; 
            StreamReader sr; 
            if (strEncod.ToLower().IndexOf("utf") != -1) 
            { 
                sr = new StreamReader(ReceiveStream, System.Text.Encoding.UTF8); 
            } 
            else 
            { 
                sr = new StreamReader(ReceiveStream, System.Text.Encoding.Default); 
            } 
            resultstring = sr.ReadToEnd(); 
            js.alert(resultstring); 
            //Console.WriteLine(resultstring); 
        } 
        catch 
        { 
            throw new Exception(); 
        } 
        finally 
        { 
            if (result != null) 
            { 
                result.Close(); 
            } 
        } 
        return resultstring; 
}

 
三、通过WebClient来获取

复制代码 代码如下:
public string get(int length) 

        try 
        { 
            getEncodeing(); 
            WebClient wb = new WebClient(); 
            Stream response = wb.OpenRead(url); 
            StreamReader reader = new StreamReader(response, this.encoding, true, 256000); 
            char[] a = new char[length]; 
            int i  = reader.Read(a,0,length); 
            reader.Close(); 
            return new string(a); 
        } 
        catch (Exception e) 
        { 
            return e.Message; 
            //return null; 
        } 

private void getEncodeing() 
{
        switch (this.encode) 
        { 
            case "UTF-8": encoding = Encoding.UTF8; break; 
            case "GB2312": encoding = Encoding.GetEncoding("GB2312"); break; 
            case "ASCII": encoding = Encoding.ASCII; break; 
            default: encoding = Encoding.GetEncoding(encode); break; 
        } 
}

希望本文所述对大家的C#程序设计有所帮助。

您可能感兴趣的文章:
阅读全文