在一个具网址中抓取内容应该怎么做?

Question

HttpWebRequest loHttp = (HttpWebRequest) WebRequest.Create("http://www.1798.cn/Qybl/ming.asp?id=16606");
HttpWebResponse loWebResponse = (HttpWebResponse) loHttp.GetResponse();
Encoding enc = Encoding.Default;
StreamReader loResponseStream = new StreamReader(loWebResponse.GetResponseStream(),enc);
string download = loResponseStream.ReadToEnd();
string companyName = download.Substring(download.IndexOf("class=t3>")+9,download.IndexOf("</FONT>",download.IndexOf("class=t3>")));//公司名称
string linkman = download.Substring(download.IndexOf("class=t2>")+9,download.IndexOf("&nbsp;",download.IndexOf("class=t2>")));//联系人
string tel = download.Substring(download.IndexOf("<font size=\"2\">电 话：")+19,download.IndexOf("<BR>",download.IndexOf("<font size=\"2\">电 话：")));//电 话
string fax = download.Substring(download.IndexOf("传 真：")+4,download.IndexOf("<BR>",download.IndexOf("传 真：")));//传 真
string code = download.Substring(download.IndexOf("邮 编：")+4,download.IndexOf("<BR>",download.IndexOf("邮 编：")));//邮 编
string url = download.Substring(download.IndexOf("网 址：")+4,download.IndexOf("<BR>",download.IndexOf("网 址：")));//网 址
string email = download.Substring(download.IndexOf("Email：")+6,download.IndexOf("<BR>",download.IndexOf("Email：")));//邮 编
string add = download.Substring(download.IndexOf("地 址：")+4,download.IndexOf("</font>",download.IndexOf("地 址：")));//地 址

Answer 1

http://www.1798.cn/Qybl/search.asp?page=1&sortid=&typeid=&qylb=&title=&cityid=
共1593页，你一页一页读出就

Answer 2

using System;
using System.Net;
using System.Text;
using System.IO;
namespace ConsoleApplication6
{
/// <summary>
/// Class1 的摘要说明。
/// </summary>
class Class1
{
/// <summary>
/// 应用程序的主入口点。
/// </summary>
[STAThread]
static void Main(string[] args)
{
HttpWebRequest loHttp = (HttpWebRequest) WebRequest.Create("http://www.1798.cn/Qybl/ming.asp?id=16606");
HttpWebResponse loWebResponse = (HttpWebResponse) loHttp.GetResponse();
Encoding enc = Encoding.Default;
StreamReader loResponseStream = new StreamReader(loWebResponse.GetResponseStream(),enc);
string download = loResponseStream.ReadToEnd();
string companyName = download.Substring(download.IndexOf("class=t3>")+9,download.IndexOf("</FONT>",download.IndexOf("class=t3>"))-download.IndexOf("class=t3>")-9);//公司名称
string linkman = download.Substring(download.IndexOf("class=t2>")+9,download.IndexOf("&nbsp;",download.IndexOf("class=t2>"))-download.IndexOf("class=t2>")-9);//联系人
string tel = download.Substring(download.IndexOf("<font size=\"2\">电 话：")+19,download.IndexOf("<BR>",download.IndexOf("<font size=\"2\">电 话："))-download.IndexOf("<font size=\"2\">电 话：")-19);//电 话
string fax = download.Substring(download.IndexOf("传 真：")+4,download.IndexOf("<BR>",download.IndexOf("传 真："))-download.IndexOf("传 真：")-4);//传 真
string code = download.Substring(download.IndexOf("邮 编：")+4,download.IndexOf("<BR>",download.IndexOf("邮 编："))-download.IndexOf("邮 编：")-4);//邮 编
string url = download.Substring(download.IndexOf("网 址：")+4,download.IndexOf("<BR>",download.IndexOf("网 址："))-download.IndexOf("网 址：")-4);//网 址
string email = download.Substring(download.IndexOf("Email：")+6,download.IndexOf("<BR>",download.IndexOf("Email："))-download.IndexOf("Email：")-6);//邮 编
string add = download.Substring(download.IndexOf("地 址：")+4,download.IndexOf("</font>",download.IndexOf("地 址："))-download.IndexOf("地 址：")-4);//地 址
Console.WriteLine(companyName);
Console.WriteLine(linkman);
Console.WriteLine(tel);
Console.WriteLine(fax);
Console.WriteLine(code);
Console.WriteLine(url);
Console.WriteLine(email);
Console.WriteLine(add);
Console.ReadLine();
//
// TODO: 在此处添加代码以启动应用程序
//
}
}
}

Answer 3

我前段时间刚写了个通用的抓取程序，多线程的，支持任意页面抓取。
有兴趣可以联系我roket#126.com(把#改为@).

Answer 4

群号码：9978078
群名称：vs.net开发—C#篇
欢迎大家加入~~~~