roucheng 通过本文主要向大家介绍了马桶c的个人空间,欲情 c max,维生素c,奔驰c200,85度c等相关知识,希望对您有所帮助,也希望大家支持linkedu.com www.linkedu.com
本文实例讲述了C#基于正则表达式实现获取网页中所有信息的网页抓取类。分享给大家供大家参考，具体如下：
类的代码：
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 == "")
{
Regex reg = new Regex(@"(?m)<title[^>]*>(?<title>(?:\w|\W)*?)</title[^>]*>", RegexOptions.Multiline | RegexOptions.IgnoreCase);
Match mc = reg.Match(m_html);
if (mc.Success)
m_title = mc.Groups["title"].Value.Trim();
}
return m_title;
}
}
public string M_html
{
get
{
if (m_html == null)
{
m_html = "";
}
return m_html;
}
}
/// <summary>
/// 此属性获得本网页的所有链接信息，只读
/// </summary>
public List<Link> Links
{
get
{
if (m_links.Count == 0) getLinks();
return m_links;
}
}
/// <summary>
/// 此属性返回本网页的全部纯文本信息，只读
/// </summary>
public string Context
{
get
{
if (m_outstr == "") getContext(Int16.MaxValue);
return m_outstr;
}
}
/// <summary>
/// 此属性获得本网页的大小
/// </summary>
public int PageSize
{
get
{
return m_pagesize;
}
}
/// <summary>
/// 此属性获得本网页的所有站内链接
/// </summary>
public List<Link> InsiteLinks
{
get
{
return getSpecialLinksByUrl("^http://" + m_uri.Host, Int16.MaxValue);
}
}
/// <summary>
/// 此属性表示本网页是否可用
/// </summary>
public bool IsGood
{
get
{
return m_good;
}
}
/// <summary>
/// 此属性表示网页的所在的网站
/// </summary>
public string Host
{
get
{
return m_uri.Host;
}
}
#endregion
/// <summary>
/// 从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(@"<a\shref\s*=""(?<URL>[^""]*).*?>(?<title>[^<]*)</a>", RegexOptions.IgnoreCase | RegexOptions.Singleline);
regex[1] = new Regex("<[i]*frame[^><]+src=(\"|')?(?<url>([^>\"'\\s)])+)(\"|')?[^>]*>", RegexOptions.IgnoreCase);
for (int i = 0; i < 2; i++)
{
Match match = regex[i].Match(m_html);
while (match.Success)
{
try
{
string url = HttpUtility.UrlDecode(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();
link.Text = text;
link.NavigateUrl = url;
m_links.Add(link);
}
catch (Exception ex) { Console.WriteLine(ex.Message); };
match = match.NextMatch();
}
}
}
return m_links;
}
/// <summary>
/// 此私有方法从一段HTML文本中提取出一定字数的纯文本
/// </summary>
/// <param name="instr">HTML代码</param>
/// <param name="firstN">提取从头数多少个字</param>
/// <param name="withLink">是否要链接里面的字</param>
/// <returns>纯文本</returns>
private string getFirstNchar(string instr, int firstN, bool withLink)
{
if (m_outstr == "")
{
m_outstr = instr.Clone() as string;
m_outstr = new Regex(@"(?m)<script[^>]*>(\w|\W)*?</script[^>]*>", RegexOptions.Multiline | RegexOptions.IgnoreCase).Replace(m_outstr, "");
m_outstr = new Regex(@"(?m)<style[^>]*>(\w|\W)*?</style[^>]*>", RegexOptions.Multiline | RegexOptions.IgnoreCase).Replace(m_outstr, "");
m_outstr = new Regex(@"(?m)<select[^>]*>(\w|\W)*?</select[^>]*>", RegexOptions.Multiline | RegexOptions.IgnoreCase).Replace(m_outstr, "");
if (!withLink) m_outstr = new Regex(@"(?m)<a[^>]*>(\w|\W)*?</a[^>]*>", RegexOptions.Multiline | RegexOptions.IgnoreCase).Replace(m_outstr, "");
Regex objReg = new System.Text.RegularExpressions.Regex("(<[^>]+?>)| ", RegexOptions.Multiline | RegexOptions.IgnoreCase);
m_outstr = objReg.Replace(m_outstr, "");
Regex objReg2 = new System.Text.RegularExpressions.Regex("(\\s)+", RegexOptions.Multiline | RegexOptions.IgnoreCase);
m_outstr = objReg2.Replace(m_outstr, " ");
}
return m_outstr.Length > firstN ? m_outstr.Substring(0, firstN) : m_outstr;
}
#region 公有文法
/// <summary>
/// 此公有方法提取网页中一定字数的纯文本，包括链接文字
/// </summary>
/// <param name="firstN">字数</param>
/// <returns></returns>
public string getContext(int firstN)
{
return getFirstNchar(m_html, firstN, true);
}
/// <summary>
/// 此公有方法从本网页的链接中提取一定数量的链接，该链接的URL满足某正则式
/// </summary>
/// <param name="pattern">正则式</param>
/// <param name="count">返回的链接的个数</param>
/// <returns>List<Link></returns>
public List<Link> getSpecialLinksByUrl(string pattern, int count)
{
if (m_links.Count == 0) getLinks();
List<Link> SpecialLinks = new List<Link>();
List<Link>.Enumerator i;
i = m_links.GetEnumerator();
int cnt = 0;
while (i.MoveNext() && cnt < count)
{
if (new Regex(pattern, RegexOptions.Multiline | RegexOptions.IgnoreCase).Match(i.Current.NavigateUrl).Success)
{
SpecialLinks.Add(i.Current);
cnt++;
}
}
return SpecialLinks;
}
/// <summary>
/// 此公有方法从本网页的链接中提取一定数量的链接，该链接的文字满足某正则式
/// </summary>
/// <param name="pattern">正则式</param>
/// <param name="count">返回的链接的个数</param>
/// <returns>List<Link></returns>
public List<Link> getSpecialLinksByText(string pattern