/*
* Author:Sunjoy at CCNU
* 如果您改进了这个类请发一份代码给我(ccnusjy 在gmail.com)
*/
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;
/// <summary>
/// 网页类
/// </summary>
public class WebPage
{
#region 私有成员
private Uri m_uri; //网址
private List<Link> m_links; //此网页上的链接
private string m_title; //此网页的标题
private string m_html; //此网页的HTML代码
private string m_outstr; //此网页可输出的纯文本
private bool m_good; //此网页是否可用
private int m_pagesize; //此网页的大小
private static Dictionary<string, CookieContainer> webcookies = new Dictionary<string, CookieContainer>();//存放所有网页的Cookie
private string m_post; //此网页的登陆页需要的POST数据
private string m_loginurl; //此网页的登陆页
#endregion
#region 私有方法
/// <summary>
/// 这私有方法从网页的HTML代码中分析出链接信息
/// </summary>
/// <returns>List<Link></returns>
private List<Link> getLinks()
{
if (m_links.Count == 0)
{
Regex[] regex = new Regex[2];
regex[0] = new Regex("(?m)<a[^><]+href=(\"|')?(?<url>([^>\"'\\s)])+)(\"|')?[^>]*>(?<text>(\\w|\\W)*?)</", RegexOptions.Multiline | RegexOptions.IgnoreCase);
regex[1] = new Regex("<[i]*frame[^><]+src=(\"|')?(?<url>([^>\"'\\s)])+)(\"|')?[^>]*>", RegexOptions.Multiline | RegexOptions.IgnoreCase);
for (int i = 0; i < 2; i++)
{
Match match = regex[i].Match(m_html);
while (match.Success)
{
try
{
string url = new Uri(m_uri, match.Groups["url"].Value).AbsoluteUri;
string text = "";
if (i == 0) text = new Regex("(<[^>]+>)|(\\s)|( )|&|\"", RegexOptions.Multiline | RegexOptions.IgnoreCase).Replace(match.Groups["text"].Value, "");
Link link = new Link(url, text);
m_links.Add(link);
}
