概述
public class app { // 获取指定网页的HTML代码 public static string GetPageSource(string URL) { Uri uri = new Uri(URL); HttpWebRequest hwReq = (HttpWebRequest)WebRequest.Create(uri); HttpWebResponse hwRes = (HttpWebResponse)hwReq.GetResponse(); hwReq.Method = "Get"; hwReq.KeepAlive = false; StreamReader reader = new StreamReader(hwRes.GetResponseStream(), System.Text.Encoding.GetEncoding("GB2312")); return reader.ReadToEnd(); } // 提取HTML代码中的网址 public static ArrayList GetHyperLinks(string htmlCode) { ArrayList al = new ArrayList(); string strRegex = @"http://([w-]+.)+[w-]+(/[w- ./?%&=]*)?"; Regex r = new Regex(strRegex, RegexOptions.IgnoreCase); MatchCollection m = r.Matches(htmlCode); for (int i = 0; i <= m.Count - 1; i++) { bool rep = false; string strNew = m[i].ToString(); // 过滤重复的URL foreach (string str in al) { if (strNew == str) { rep = true; break; } } if (!rep) al.Add(strNew); } al.Sort(); return al; } // 把网址写入xml文件 public static void WriteToXml(string strURL, ArrayList alHyperLinks) { XmlTextWriter writer = new XmlTextWriter("HyperLinks.xml", Encoding.UTF8); writer.Formatting = Formatting.Indented; writer.WriteStartDocument(false); writer.WriteDocType("HyperLinks", null, "urls.dtd", null); writer.WriteComment("提取自" + strURL + "的超链接"); writer.WriteStartElement("HyperLinks"); writer.WriteStartElement("HyperLinks", null); writer.WriteAttributeString("DateTime", DateTime.Now.ToString()); foreach (string str in alHyperLinks) { string title = GetDomain(str); string body = str; writer.WriteElementString(title, null, body); } writer.WriteEndElement(); writer.WriteEndElement(); writer.Flush(); writer.Close(); } // 获取网址的域名后缀 static string GetDomain(string strURL) { string retVal; string strRegex = @"(.com/|.net/|.cn/|.org/|.gov/)"; Regex r = new Regex(strRegex, RegexOptions.IgnoreCase); Match m = r.Match(strURL); retVal = m.ToString(); strRegex = @".|/$"; retVal = Regex.Replace(retVal, strRegex, "").ToString(); if (retVal == "") retVal = "other"; return retVal; } }
private void btnkaishi_Click(object sender, EventArgs e) { string strCode; ArrayList alLinks; if (txtapi.Text == "") { MessageBox.Show("请输入网址"); return; } string strURL = txtapi.Text.ToString().Trim(); if (strURL.Substring(0, 7) != @"http://") { strURL = @"http://" + strURL; } MessageBox.Show("正在获取页面代码,请稍后..."); strCode = app.GetPageSource(strURL); MessageBox.Show("正在提取超链接,请稍侯..."); alLinks = app.GetHyperLinks(strCode); MessageBox.Show("正在写入文件,请稍侯..."); app.WriteToXml(strURL, alLinks); }
最后
以上就是贤惠睫毛膏为你收集整理的C# 抓取并导出网页里面所有超链接方法的全部内容,希望文章能够帮你解决C# 抓取并导出网页里面所有超链接方法所遇到的程序开发问题。
如果觉得靠谱客网站的内容还不错,欢迎将靠谱客网站推荐给程序员好友。
本图文内容来源于网友提供,作为学习参考使用,或来自网络收集整理,版权属于原作者所有。
发表评论 取消回复