ASP.NET采集系统万能正则表达式

由于经常要写一些采集的程序，下面的三个函数是采集中的很常用的函数。姑且叫采集系统万能正则表达式吧。

第一个：//获取页面的html源码
public string GetHtmlSource(string Url, string charset)
{
if (charset == "" || charset == null) charset = "gb2312";
string text1 = "";
try
{
HttpWebRequest request1 = (HttpWebRequest)WebRequest.Create(Url);
HttpWebResponse response1 = (HttpWebResponse)request1.GetResponse();
Stream stream1 = response1.GetResponseStream();
StreamReader reader1 = new StreamReader(stream1, Encoding.GetEncoding(charset));
text1 = reader1.ReadToEnd();
stream1.Close();
response1.Close();
}
catch (Exception exception1)
{
}
return text1;
}

第二个：截取字符串

public string SniffwebCode(string code, string wordsBegin, string wordsEnd)
{
string NewsTitle = "";
Regex regex1 = new Regex("" + wordsBegin + @"(?<title>[/s/S]+?)" + wordsEnd + "", RegexOptions.Compiled | RegexOptions.IgnoreCase);
for (Match match1 = regex1.Match(code); match1.Success; match1 = match1.NextMatch())
{
NewsTitle = match1.Groups["title"].ToString();
}
return NewsTitle;

}

第三个：截取网址

public ArrayList SniffwebCodeReturnList(string code, string wordsBegin, string wordsEnd)
{
ArrayList urlList = new ArrayList();
//string NewsTitle = "";
Regex regex1 = new Regex("" + wordsBegin + @"(?<title>[/s/S]+?)" + wordsEnd + "", RegexOptions.Compiled | RegexOptions.IgnoreCase);
for (Match match1 = regex1.Match(code); match1.Success; match1 = match1.NextMatch())
{
urlList.Add(match1.Groups["title"].ToString());
}
return urlList;

}

全部代码如下：

using System;
using System.Collections.Generic;
using System.Text;
using System.Data;
using System.Data.OleDb;
using System.IO;
using System.Text.RegularExpressions;
using System.Text;
using System.Collections;
using System.Net;
namespace getWeb
{
public class DBconn
{
// public string dbConnString = @"User ID=sa;Data Source=.;Password=sa;Initial Catalog=GetWeb;Provider=SQLOLEDB.1";
public string dbConnString = @"provider=microsoft.jet.oledb.4.0;data source=Getweb.mdb";
public static string GetSource(string Url, string charset)
{
if (charset == "" || charset == null) charset = "gb2312";
string text1 = "";
try
{
Stream stream1 = new WebClient().OpenRead(Url);
text1 = new StreamReader(stream1, Encoding.GetEncoding(charset)).ReadToEnd();
stream1.Close();
}
catch (Exception exception1)
{
}
return text1;
}

public string GetHtmlSource(string Url, string charset)
{
if (charset == "" || charset == null) charset = "gb2312";
string text1 = "";
try
{
HttpWebRequest request1 = (HttpWebRequest)WebRequest.Create(Url);
HttpWebResponse response1 = (HttpWebResponse)request1.GetResponse();
Stream stream1 = response1.GetResponseStream();
StreamReader reader1 = new StreamReader(stream1, Encoding.GetEncoding(charset));
text1 = reader1.ReadToEnd();
stream1.Close();
response1.Close();
}
catch (Exception exception1)
{
}
return text1;
}

public string Get_Http(string a_strUrl, int timeout)
{
string strResult;

try
{
HttpWebRequest myReq = (HttpWebRequest)HttpWebRequest.Create(a_strUrl);
myReq.Timeout = timeout;
HttpWebResponse HttpWResp = (HttpWebResponse)myReq.GetResponse();

Stream myStream = HttpWResp.GetResponseStream();

StreamReader sr = new StreamReader(myStream, Encoding.Default);
StringBuilder strBuilder = new StringBuilder();
while (-1 != sr.Peek())
{
strBuilder.Append(sr.ReadLine() + "/r/n");
}

strResult = strBuilder.ToString();
}
catch (Exception exp)
{
strResult = "错误：" + exp.Message;
}

return strResult;

}

//获取页面内容后，分析页面中连接地址取到要抓取的url：
//处理页面标题和链接
public string SniffwebCode(string code, string wordsBegin, string wordsEnd)
{
string NewsTitle = "";
Regex regex1 = new Regex("" + wordsBegin + @"(?<title>[/s/S]+?)" + wordsEnd + "", RegexOptions.Compiled | RegexOptions.IgnoreCase);
for (Match match1 = regex1.Match(code); match1.Success; match1 = match1.NextMatch())
{
NewsTitle = match1.Groups["title"].ToString();
}
return NewsTitle;

}

public ArrayList SniffwebCodeReturnList(string code, string wordsBegin, string wordsEnd)
{
ArrayList urlList = new ArrayList();
//string NewsTitle = "";
Regex regex1 = new Regex("" + wordsBegin + @"(?<title>[/s/S]+?)" + wordsEnd + "", RegexOptions.Compiled | RegexOptions.IgnoreCase);
for (Match match1 = regex1.Match(code); match1.Success; match1 = match1.NextMatch())
{
urlList.Add(match1.Groups["title"].ToString());
}
return urlList;

}

}
}