正则抓取网页所有href和src
2024-09-20 14:14:30
根据抓取的页面,用正则来匹配页面href和src
string UserAgent = "Mozilla/5.0 (Windows NT 5.2; rv:29.0) Gecko/20100101 Firefox/29.0";
string ContentType = ""; Uri strReqUrl = new Uri("http://m.lhrb.ufstone.net/");
protected void Application_BeginRequest(object sender, EventArgs e)
{ Uri u = new Uri(strReqUrl, Request.RawUrl);
byte[] b = getVerificationCode(u); //MemoryStream ms = new MemoryStream(b);
//Response.ClearContent();
//Response.ContentType = ContentType;
//Response.BinaryWrite(b); StringBuilder strHtml = new StringBuilder(Encoding.GetEncoding("gb2312").GetString(b));
StringBuilder sb = new StringBuilder();
GetHtmlUrl(ref strHtml);
Response.Write(strHtml.ToString());
Response.End();
}
public byte[] getVerificationCode(Uri url)
{
WebClient MyWebClient = new WebClient();
MyWebClient.Headers.Add("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8");
MyWebClient.Headers.Add("Accept-Language", " zh-cn,zh;q=0.8,en-us;q=0.5,en;q=0.3");
MyWebClient.Headers.Add("User-Agent", this.UserAgent);
MyWebClient.Credentials = CredentialCache.DefaultCredentials;
try
{
Byte[] pageData = MyWebClient.DownloadData(url.AbsoluteUri);
ContentType = MyWebClient.ResponseHeaders["Content-Type"];
return (pageData);
}
catch
{
return null;
}
}
void GetHtmlUrl(ref StringBuilder strHtml)
{
//string headstr = "(src|href)=", endstr = "(\")";
//string reg = @"(?<=" + headstr + ")(.*?)(?=" + endstr + ")"; string reg = "(src|href)\\s*=\\s*(?:\"(?<1>[^\"]*)\"|(?<1>\\S+))";
Regex r = new Regex(reg, RegexOptions.None);
Match match = r.Match(strHtml.ToString());
StringBuilder sb = new StringBuilder();
while (match.Success)
{
//sb.Append(match.Groups["url"].Value + "\n");//得到href值
//sb.Append(match.Groups["text"].Value + "\n");//得到<a><a/>中间的内容 sb.Append(match + "\n");//得到href值
match = match.NextMatch();
//try
//{
// Uri u = new Uri(strReqUrl, match.Value.Replace("\"", "").Replace("'", ""));
// strHtml.Replace(match.Value, @"/" + u.ToString().Replace(strReqUrl.ToString(), ""));
//}
//catch
//{
//}
}
}
最新文章
- Undefined symbols for architecture arm64解决方案
- BZOJ 1030: [JSOI2007]文本生成器 [AC自动机 DP]
- 安装zookeeper遇到的问题以及解决方案
- 【C语言】C语言函数
- 关于IOS应用程序视图
- Java线程池应用
- ie10中元素超出父元素的宽度时不能自动隐藏
- 字符流缓冲区BufferedReader之readLine方法的原理
- Stage3D学习笔记(六):旋转动画效果
- JavaScript高级程序设计(六):关键字 void 和 delete 使用
- Gartner 如何看 RASP 和 WAF?
- CodeForces 158C - Cd and pwd commands(模拟)
- partial类修饰符
- Android适配难题全面总结
- dev控件 xtraTabbedMdiManager 如何将关闭子窗体改为收回主窗体内
- python 3.5 import theano ::hypot error
- sql优化问题笔记(mysql)
- Codeforces 235E. Number Challenge DP
- elk之elasticsearch 入门
- css3动画属性系列之transform细讲scale缩放