asp.net 抓取网页源码三种实现方法

 更新时间:2013年06月05日 11:14:45   投稿:shangke   我要评论
asp.net 抓取网页源码三种实现方法,需要的朋友可以参考一下

方法1 比较推荐  

/// <summary>  
    /// 用HttpWebRequest取得网页源码  
    /// 对于带BOM的网页很有效,不管是什么编码都能正确识别  
    /// </summary>  
    /// <param name="url">网页地址" </param>  
    /// <returns>返回网页源文件</returns>  
    public static string GetHtmlSource2(string url)
    {
      //处理内容  
      string html = "";
      HttpWebRequest request = (HttpWebRequest)WebRequest.Create(url);
      request.Accept = "*/*"; //接受任意文件
      request.UserAgent = "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; .NET CLR 1.1.4322)"; // 模拟使用IE在浏览 http://www.52mvc.com
      request.AllowAutoRedirect = true;//是否允许302
      //request.CookieContainer = new CookieContainer();//cookie容器,
      request.Referer = url; //当前页面的引用
 
      HttpWebResponse response = (HttpWebResponse)request.GetResponse();
      Stream stream = response.GetResponseStream();
      StreamReader reader = new StreamReader(stream, Encoding.Default);
      html = reader.ReadToEnd();
      stream.Close();
 
      return html;
    }

方法2 

using System;
using System.Collections.Generic;
using System.Linq;
using System.Web;
using System.IO;
using System.Text;
using System.Net;
namespace MySql
{
  public class GetHttpData
  {
    public static string GetHttpData2(string Url)
    {
      string sException = null;
      string sRslt = null;
      WebResponse oWebRps = null;
      WebRequest oWebRqst = WebRequest.Create(Url);
      oWebRqst.Timeout = 50000;
      try
      {
        oWebRps = oWebRqst.GetResponse();
      }
      catch (WebException e)
      {
        sException = e.Message.ToString();
      }
      catch (Exception e)
      {
        sException = e.ToString();
      }
      finally
      {
        if (oWebRps != null)
        {
          StreamReader oStreamRd = new StreamReader(oWebRps.GetResponseStream(), Encoding.GetEncoding("utf-8"));
          sRslt = oStreamRd.ReadToEnd();
          oStreamRd.Close();
          oWebRps.Close();
        }
      }
      return sRslt;
    }
  }
}

方法3

public static string getHtml(string url, params string [] charSets)//url是要访问的网站地址,charSet是目标网页的编码,如果传入的是null或者"",那就自动分析网页的编码
  {
    try
    {
      string charSet = null;
      if (charSets.Length == 1) {
        charSet = charSets[0];
      }
      WebClient myWebClient = new WebClient(); //创建WebClient实例myWebClient
      // 需要注意的:
      //有的网页可能下不下来,有种种原因比如需要cookie,编码问题等等
      //这是就要具体问题具体分析比如在头部加入cookie
      // webclient.Headers.Add("Cookie", cookie);
      //这样可能需要一些重载方法。根据需要写就可以了
 
      //获取或设置用于对向 Internet 资源的请求进行身份验证的网络凭据。
      myWebClient.Credentials = CredentialCache.DefaultCredentials;
      //如果服务器要验证用户名,密码
      //NetworkCredential mycred = new NetworkCredential(struser, strpassword);
      //myWebClient.Credentials = mycred;
      //从资源下载数据并返回字节数组。(加@是因为网址中间有"/"符号)
      byte[] myDataBuffer = myWebClient.DownloadData(url);
      string strWebData = Encoding.Default.GetString(myDataBuffer);
 
      //获取网页字符编码描述信息
      Match charSetMatch = Regex.Match(strWebData, "<meta([^<]*)charset=([^<]*)\"", RegexOptions.IgnoreCase | RegexOptions.Multiline);
      string webCharSet = charSetMatch.Groups[2].Value;
      if (charSet == null || charSet == "")
        charSet = webCharSet;
 
      if (charSet != null && charSet != "" && Encoding.GetEncoding(charSet) != Encoding.Default)
      {
        strWebData = Encoding.GetEncoding(charSet).GetString(myDataBuffer);
      }
      else {
        strWebData = Encoding.GetEncoding("utf-8").GetString(myDataBuffer);
      }
      return strWebData;
    }
    catch (Exception e) { return ""; }
  }

asp.net 获取网页源文件的方法

有时候我们需要获取 网页源文件,所以用以下这个方法很容易完成任务!

private string GetStringByUrl(string strUrl) 
{ 
  WebRequest wrt = WebRequest.Create(strUrl); 
  WebResponse wrse = wrt.GetResponse(); 
  Stream strM = wrse.GetResponseStream(); 
  StreamReader SR = new StreamReader(strM,  Encoding.GetEncoding("utf-8")); 
  string strallstrm = SR.ReadToEnd(); 
  return strallstrm; 
} 

只要传入要下载网页的地址就OK了!
通过这个方法做个源码导出:

private string SaveHTML() 
 {     
string str = RenderPage("Default2.aspx"); 
    Response.ContentEncoding = System.Text.Encoding.GetEncoding("UTF-8"); //解决中文乱码 
    Response.AddHeader("Content-Disposition","attachment;filename=index.html"); //解决中文文件名乱码   
    Response.AddHeader("Content-length",str.Length.ToString()); 
    Response.Write(str); 
    Response.End(); 
} 

以上就是asp.net 抓取网页源码的全部代码了,希望对大家有所帮助。

相关文章

最新评论