前往小程序,Get更优阅读体验!
立即前往
首页
学习
活动
专区
工具
TVP
发布
社区首页 >专栏 >VB.NET 网络爬取数据(以爬取上海海事大学录取分数线为例)

VB.NET 网络爬取数据(以爬取上海海事大学录取分数线为例)

作者头像
一线编程
发布2019-07-22 15:06:26
2.4K0
发布2019-07-22 15:06:26
举报
文章被收录于专栏:办公魔盒办公魔盒

VB.NET 爬虫,网抓,代码写得比较差;望见谅!

(以爬取上海海事大学录取分数线为例)

代码语言:javascript
复制
Imports System.IO
Imports System.Net
Imports System.Text.RegularExpressions

Public Class Form1
    Private Sub Button1_Click(sender As Object, e As EventArgs) Handles Button1.Click
        On Error Resume Next
        For Each dm In ListBox1.Items
            For Each XL In ListBox2.Items
                Dim STR As String
                STR = NET_WZ.GET_DATA("http://admission.shmtu.edu.cn/score/" & XL & "/" & dm)
                Dim TMP As Object
                TMP = NET_WZ.GET_TABLE(STR)
                If TMP <> Nothing Then

                    For I As Integer = 0 To UBound(NET_WZ.GET_TABLE(STR))
                        If TMP(I) <> "" Then
                            Dim item As New ListViewItem With {
                             .Text = dm
                         }
                            item.SubItems.Add(XL)
                            item.SubItems.Add(TMP(I))
                            item.SubItems.Add(TMP(I + 1))
                            item.SubItems.Add(TMP(I + 2))
                            item.SubItems.Add(TMP(I + 3))
                            item.SubItems.Add(TMP(I + 4))
                            ListView1.Items.Add(item)
                            I += 4
                        End If
                        Application.DoEvents()
                    Next
                End If
                Application.DoEvents()
            Next
            Application.DoEvents()
        Next
    End Sub

End Class

Public Class NET_WZ
    Public Shared Function GET_DATA(ByVal _URL As String) As String
        Dim contents As Object = Nothing
        Dim request As WebRequest
        Dim response As WebResponse
        Try
            request = WebRequest.Create(_URL)
            response = request.GetResponse()
            Dim reader As New StreamReader(response.GetResponseStream())
            contents = reader.ReadToEnd()
        Catch ex As Exception
            MsgBox(ex.Message)
        End Try
        GET_DATA = contents
    End Function

    Public Shared Function GET_TABLE(ByVal STR As String) As Object
        Dim strReg, sReg As String
        Dim TMP(1000) As Object
        Dim I As Integer = 0
        Try
            strReg = "(?is)(?<=<table class=).+?(?=</table>)"
            sReg = "(?<=<td>).+?(?=</td>)"
            Dim mc, mth As MatchCollection
            mc = Regex.Matches(STR, strReg)
            For Each m As Match In mc
                Dim temp As String = Replace(m.Value, "<td></td><td>" & vbCr & "</td>", "<td>0</td><td>0</td>")
                mth = Regex.Matches(temp, sReg)
                For Each h As Match In mth
                    TMP(I) = h.Value
                    I += 1
                Next
            Next
        Catch ex As Exception
            MsgBox(ex.Message)
        End Try
        GET_TABLE = TMP
    End Function

End Class

需要把数据导出请自行写代码!

本文参与 腾讯云自媒体分享计划,分享自微信公众号。
原始发表:2019-03-26,如有侵权请联系 cloudcommunity@tencent.com 删除

本文分享自 办公魔盒 微信公众号,前往查看

如有侵权,请联系 cloudcommunity@tencent.com 删除。

本文参与 腾讯云自媒体分享计划  ,欢迎热爱写作的你一起参与!

评论
登录后参与评论
0 条评论
热度
最新
推荐阅读
领券
问题归档专栏文章快讯文章归档关键词归档开发者手册归档开发者手册 Section 归档