本文介绍了一种利用正则表达式从HTML页面中抓取并解析城市列表的方法，通过实例展示了如何创建XML文档并使用正则表达式提取特定格式的城市代码。
Imports System.XmlImports System.Text.RegularExpressions
Public Class Form1Class Form1
Private Sub Button1_Click()Sub Button1_Click(ByVal sender As System.Object, ByVal e As System.EventArgs) Handles Button1.Click Try Dim objXml As New XmlDataDocument Dim objXmlElementCity As New XmlDataDocument Dim Content As String = "" objXml.LoadXml("<root />") '抓取所有城市列表 Content = GetContent("http://localhost/CMA/index.htm", "gb2312") '抓到内容后,?始分析数据 Dim regex As System.Text.RegularExpressions.Regex Dim mc As System.Text.RegularExpressions.Match Dim objXmlCityList As XmlElement Dim partten As String = "" Dim cityUrl As String = "" Dim parttenCity As String = "" Dim i As Long = 1 Dim j As Long = 1 'Dim mcCity As System.Text.RegularExpressions.Match objXmlCityList = objXml.CreateElement("citylist") Dim s As String s = "2005-2-21" 'Regex reg = new Regex(@"(?<y>d{4})-(?<m>d{1,2})-(?<d>d{1,2})",RegexOptions.Compiled); 'Match match = reg.Match(s); 'int year = int.Parse(match.Groups["y"].Value); 'int month = int.Parse(match.Groups["m"].Value); 'int day = int .Parse(match.Groups["d"].Value); 'DateTime time = new DateTime(year,month,day); 'Console.WriteLine(time); 'Console.ReadLine(); 'partten = "^c[1] = new Array(" + """" + "6" + ";" ' c[1] = new Array(" 'partten = "" + "(?<citycode>[0-9]{5,})" + """" 'partten = "(?<citycode>[0-9]{5,})" '<citycode> 'partten = "c[[0-9]{1,2}].*;" ' = new Array" + ".*" + ");" 'partten = "^[0-9]{2,3}.[0-9]{2,3}.[0-9]{2,3}.[0-9]{2,3}" partten = "(?<citycode>" & """" & "[0-9]{5}" & """" & ")" regex = New System.Text.RegularExpressions.Regex(partten, RegexOptions.Compiled Or RegexOptions.IgnoreCase) objXmlCityList.SetAttribute("vdatetime", DateTime.Now.ToShortDateString()) mc = regex.Match(Content, 0) MsgBox(mc.Groups("citycode").Value) 'c.Groups( 'Do While mc.Success ' 'MsgBox(mc.Groups("citycode").Value) ' MsgBox(mc.ToString) ' 'MsgBox(mc.Index) ' 'objXmlCityList.AppendChild( ' mc = regex.Match(Content, mc.Index + mc.Length) ' mc.NextMatch() 'Loop Catch ex As Exception End Try
End Sub Private Function GetContent()Function GetContent(ByVal url As String, ByVal encoding As String) As String Dim str As String = "" Dim client As New Net.WebClient client.Headers.Add("Accept", "image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, application/x-shockwave-flash, application/vnd.ms-excel, application/vnd.ms-powerpoint, application/msword, */*") client.Headers.Add("Accept-Language", "zh-cn") client.Headers.Add("UA-CPU", "x86") client.Headers.Add("User-Agent", "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; SV1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)") Try Dim buffer As Byte() buffer = client.DownloadData(url) If (encoding = "utf-8") Then str = System.Text.Encoding.GetEncoding("utf-8").GetString(buffer, 0, buffer.Length) Else str = System.Text.Encoding.GetEncoding("gb2312").GetString(buffer, 0, buffer.Length) End If Return str Return str Catch ex As Exception Return "" End Try End Function
End Class
扫一扫
585
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
