批量抓取title keywords descrip【seo工具】

前两天帮朋友写个小工具。思路很简单实现也不是太难。写了这么个小工具。

实现功能：通过搜索引擎自动换页抓取记录页面中的属性值。贴代码：

using System;
using System.Collections.Generic;
using System.ComponentModel;
using System.Data;
using System.Drawing;
using System.Text;
using System.Windows.Forms;
using System.IO;
using System.Net;
using System.Text.RegularExpressions;
using System.Collections;
// 作者：CppCoding 最后编辑 2011 5 6 特征码：yschttl spt 这个是在雅虎中用的 换搜索引擎的话 针对不同的搜索引擎会有不同 测试了 nike puma 均是该特征码
// 目前可能运行缓慢
// 报错原因：网络速度，网页响应时间 由于是国外网站 读取源代码可能失败 所以报错
// Ver0.0.2
// 实现了导出、自动翻页、设置搜索页面数量等功能。
namespace 获取html_控制截取
{
public partial class Form1 : Form
{
public Form1()
{
InitializeComponent();
}
private static string GetStringByUrl( string strUrl)
{
WebRequest wrt = System.Net.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;
}
private void button1_Click( object sender, EventArgs e)
{
string url = txt_Url.Text;
int j = 0 ;
int want = Convert.ToInt32(txtWant.Text);
while ( j < want && url != null )
{
string herf = GetStringByUrl(url);

// string[] splitHerf = Regex.Split(herf, "yschttl spt", RegexOptions.IgnoreCase);
string [] splitHerf = herf.Split( new string [] { " \"yschttl spt\" " },StringSplitOptions.None);
for ( int i = 1 ; i < splitHerf.Length; i ++ )
{
// string[] splitWant = Regex.Split(splitHerf[i], "data-", RegexOptions.IgnoreCase);

string [] splitWount = splitHerf[i].Split( new string [] { " \" " }, StringSplitOptions.None);
// for (int t = 0; t < 1; t++)
// {

// // Regex reg = new Regex(@"(?is)<a(?:(?!href=).)*href=(['""]?)(?<url>[^""\s>]*)\1[^>]*>(?<text>(?:(?!</?a\b).)*)</a>");
// // MatchCollection mc = reg.Matches(splitWount[1]);
// // foreach (Match m in mc)
// // {
// // txtEnd.Text += m.Groups["url"].Value + "\n";

// // }
// txtEnd.Text += sR;
// }
string title = "" ;
string key = "" ;
string des = "" ;
// string[] st= splitWount[0].Split(new string[]{"href=\""},StringSplitOptions.None);
// string[] go = st[1].Split('"');
string nextUrl = splitWount[ 1 ];
string code = GetStringByUrl(nextUrl);
string checkTitle = " <title> " ;
string checkKey = " \"Keywords\" content=\" " ;
string checkDes = " \"Description\" content=\" " ;
if (code.IndexOf(checkTitle) > - 1 )
{
string [] fistTitle = code.Split( new string [] { " <title> " }, StringSplitOptions.None);
string [] secTitle = fistTitle[ 1 ].Split( new string [] { " < " }, StringSplitOptions.None);
title = secTitle[ 0 ];


}
else
continue ;
if (code.IndexOf(checkKey) > - 1 )
{
string [] fistKey = code.Split( new string [] { " ds\" content=\" " }, StringSplitOptions.None);
string [] secKey = fistKey[ 1 ].Split( new string [] { " \" " }, StringSplitOptions.None);
key = secKey[ 0 ];

}
else
continue ;
if (code.IndexOf(checkDes) > - 1 )
{
string [] fistDes = code.Split( new string [] { " \"Description\" content=\" " }, StringSplitOptions.RemoveEmptyEntries);
string [] secDes = fistDes[ 1 ].Split( new string [] { " \" " }, StringSplitOptions.RemoveEmptyEntries);
des = secDes[ 0 ];
}
else
continue ; //

txtEnd.Text += j + " ..目前扫描到的网页为： " + url + " \n " ;

txtEnd.Text += des + " | " + key + " | " + des + " \n " ;
// sw.WriteLine(txtEnd.Text);

}
j ++ ;
string [] fistNext = herf.Split( new string []{ " \">Next & " },StringSplitOptions.None);
string [] secNext = fistNext[ 0 ].Split( new string []{ " xt\" href=\" " },StringSplitOptions.None);
if (secNext.Length < 1 )
{
url = null ;
}
url = secNext[ 1 ];

}

}

private void button2_Click( object sender, EventArgs e)
{
StreamWriter sw = new StreamWriter( @" C:\Documents and Settings\Administrator\桌面\获取字符串.doc " , true , Encoding.UTF8);
sw.WriteLine(txtEnd.Text);
sw.Close();
}
}




}

由于本人是菜鸟，里面代码基本没有优化，大家就当看着娱乐吧。希望各位尽情批评指导。

附截图

转载于:https://www.cnblogs.com/Evilhx/archive/2011/05/07/2039768.html