[转]正则表达式相关:C# 抓取网页类(获取网页中所有信息)
using System;
using System.Data;
using System.Configuration;
using System.Net;
using System.IO;
using System.Text;
using System.Collections.Generic;
using System.Text.RegularExpressions;
using System.Threading;
using System.Web;
using System.Web.UI.MobileControls;
/// <summary>
/// 网页类
/// </summary>
public class WebPage
{
#region 私有成员
private Uri m_uri; //url
private List<Link> m_links; //此网页上的链接
private string m_title; //标题
private string m_html; //HTML代码
private string m_outstr; //网页可输出的纯文本
private bool m_good; //网页是否可用
private int m_pagesize; //网页的大小
private static Dictionary<string, CookieContainer> webcookies = new Dictionary<string, CookieContainer>();//存放所有网页的Cookie
#endregion
#region 属性
/// <summary>
/// 通过此属性可获得本网页的网址,只读
/// </summary>
public string URL
{
get
{
return m_uri.AbsoluteUri;
}
}
/// <summary>
/// 通过此属性可获得本网页的标题,只读
/// </summary>
public string Title
{
get
{
if (m_title == "")
{
温馨提示: 本文由Jm博客推荐,转载请保留链接: https://www.jmwww.net/file/68502.html