进程与线程

开发平台：
Visual C++

Form1.cs：源码内容
							﻿using System;
using System.Collections.Generic;
using System.ComponentModel;
using System.Data;
using System.Drawing;
using System.Linq;
using System.Text;
using System.Windows.Forms;
using System.Net;
using System.IO;
using System.Text.RegularExpressions;
namespace WebCrawler
{
    public partial class Form1 : Form
    {
        public Form1()
        {
            InitializeComponent();
        }
        private void Form1_Load(object sender, EventArgs e)
        {
        }
        //1、获取对应url的html源文件
        private string GetWebContent(string Url)
        {
            string strResult = "";
            try
            {
                //声明一个HttpWebRequest请求
                HttpWebRequest request = (HttpWebRequest)WebRequest.Create(Url);
                //设置连接超时时间
                request.Timeout = 30000; 
              
                request.Headers.Set("Pragma", "no-cache");
                HttpWebResponse response = (HttpWebResponse)request.GetResponse();
                Stream streamReceive = response.GetResponseStream();
                Encoding encoding = Encoding.GetEncoding("GB2312");
                StreamReader streamReader = new StreamReader(streamReceive, encoding);
                strResult = streamReader.ReadToEnd();
            }
            catch
            {
                MessageBox.Show("出错");
            }
            return strResult;
        }
        private void button1_Click(object sender, EventArgs e)
        {
            //要抓取的URL地址   
            string Url = "http://society.people.com.cn/GB/1062/10693940.html";
            //得到指定Url的源码   
            string strWebContent = GetWebContent(Url);
            string s = "";
            /*写法一*/
            //Regex patternTitle =new Regex("<DIV id="p_title">(.*?)</div>");　//C#正则表达式提取匹配URL的模式，              
           //MatchCollection mc = patternTitle.Match.Matches(strWebContent);//满足pattern的匹配集合               
            //foreach (Match match in mc)
            //{
            //    s = match.Value.ToString();
            //}
            //int Counter = mc.Count;
            //for (int i = 0; i < Counter; i++)
            //{
            //    s = s + "Title" + mc[i].ToString();
            //}
            /*写法二*/
            //2、从源文件中匹配出需要的特定文本内容
            string patternTitle = "<DIV id="p_title">(.*?)</div>";
            Match mc=Regex.Match(strWebContent,patternTitle);
            if (mc.Success)
            {
                 s = mc.Groups[0].ToString();
            }
           int start= s.IndexOf(">");
           int end = s.IndexOf("</");
           s = s.Substring(start+1,end-start-1);
           richTextBox1.Text = s;
        }
    }
}

						