-4
我试图获得一个网站的学校信息,并希望将它保存为excel表格,并在每一列中填写详细信息,以下代码帮助我进一步学习。 栏目标题:学校名称,吉祥物,地址,类型,电话,传真等等。例如,我使用了一个链接。这可以使代码更好,更正确的网页抓取?
Imports System.IO.StreamReader
Imports System.Text.RegularExpressions
Public Class Form1
Private Sub Button1_Click(ByVal sender As System.Object, ByVal e As System.EventArgs) Handles Button1.Click
Dim request As System.Net.HttpWebRequest = System.Net.WebRequest.Create("http://www.maxpreps.com/high-schools/abbeville-yellowjackets-(abbeville,al)/home.htm")
Dim response As System.Net.HttpWebResponse = request.GetResponse
Dim sr As System.IO.StreamReader = New System.IO.StreamReader(response.GetResponseStream())
Dim rsssource As String = sr.ReadToEnd
Dim r As New System.Text.RegularExpressions.Regex("<h1 id=""ctl00_NavigationWithContentOverRelated_ContentOverRelated_Header_Header"">.*</h1>")
Dim r1 As New System.Text.RegularExpressions.Regex("<span id=""ctl00_NavigationWithContentOverRelated_ContentOverRelated_Header_Mascot"">.*</span>")
Dim r3 As New System.Text.RegularExpressions.Regex("<span id=""ctl00_NavigationWithContentOverRelated_ContentOverRelated_Header_Colors"">.*</span>")
Dim r4 As New System.Text.RegularExpressions.Regex("<span id=""ctl00_NavigationWithContentOverRelated_ContentOverRelated_Header_GenderType"">.*</span>")
Dim r5 As New System.Text.RegularExpressions.Regex("<span id=""ctl00_NavigationWithContentOverRelated_ContentOverRelated_Header_AthleteDirectorGenericControl"">.*</span>")
Dim r6 As New System.Text.RegularExpressions.Regex("<address>.*</address>")
Dim r7 As New System.Text.RegularExpressions.Regex("<span id=""ctl00_NavigationWithContentOverRelated_ContentOverRelated_Header_Phone"">.*</span>")
Dim r8 As New System.Text.RegularExpressions.Regex("<span id=""ctl00_NavigationWithContentOverRelated_ContentOverRelated_Header_Fax"">.*</span>")
Dim matches As MatchCollection = r.Matches(rsssource)
Dim matches1 As MatchCollection = r1.Matches(rsssource)
Dim matches3 As MatchCollection = r3.Matches(rsssource)
Dim matches4 As MatchCollection = r4.Matches(rsssource)
Dim matches5 As MatchCollection = r5.Matches(rsssource)
Dim matches6 As MatchCollection = r6.Matches(rsssource)
Dim matches7 As MatchCollection = r7.Matches(rsssource)
Dim matches8 As MatchCollection = r8.Matches(rsssource)
For Each itemcode As Match In matches
ListBox1.Items.Add(itemcode.Value.Split("_").GetValue(4))
ListBox1.Items.Add(itemcode.Value.Split("><").GetValue(1))
Next
For Each itemcode As Match In matches1
ListBox1.Items.Add(itemcode.Value.Split("_").GetValue(4))
ListBox1.Items.Add(itemcode.Value.Split("><").GetValue(1))
Next
End Sub
End Class