Question

我试图从网站获取一些特定内容并将其放在文本文件中。我使用了一个列表框来循环我想要处理的网址，另一个用于查看数据的输出。现在我想要文本文件中的所有数据，每个项目由“〜”sysmbol分隔。

我在my.txt文件中使用的Exmaple Link：http://www.maxpreps.com/high-schools/abbeville-yellowjackets-(abbeville,al)/basketball/previous_seasons.htm

文本文件中预期的数据：
阿布维尔高中篮球统计〜球队：校队11-12岁〜颜色：栗色，灰色，白色....

Imports System.IO.StreamReader
Imports System.Text.RegularExpressions
Imports System.IO


Public Class Form1
    Private Sub Button1_Click(ByVal sender As System.Object, ByVal e As System.EventArgs) Handles Button1.Click
        Dim abc As String = My.Computer.FileSystem.ReadAllText("C:\Documents and Settings\Santosh\Desktop\my.txt")
        Dim pqr As String() = abc.Split(vbNewLine)
        ListBox2.Items.AddRange(pqr)

    End Sub
    Private Sub Button2_Click(ByVal sender As System.Object, ByVal e As System.EventArgs) Handles Button2.Click
        For Each item In ListBox2.Items
            Dim request As System.Net.HttpWebRequest = System.Net.WebRequest.Create(item)
            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
                Dim W As New IO.StreamWriter("C:\" & FileName.Text & ".txt")
                W.Write(itemcode.Value.Split("""").GetValue(2))
                W.Close()

                'ListBox1.Items.Add(itemcode.Value.Split("""").GetValue(2))
            Next
            For Each itemcode As Match In matches1
                ListBox1.Items.Add(itemcode.Value.Split("""").GetValue(2))
            Next
        Next item

    End Sub
End Class

Answer 1

只需将它附加到Write语句的末尾，就像这样。

W.Write(itemcode.Value.Split("""").GetValue(2) & " ~ ")

以格式将数据写入文本文件

1 个答案: