VBA如何抓取html标题,VBA HTML数据抓取指南

我以纽约为例,代码如下。

我在2016/6/7重写

Public Declare Sub Sleep Lib "kernel32.dll" (ByVal dwMilliseconds As Long)

Sub CreditUnion()

Dim IE As Object, TableResults As Object, webRow As Object, charterInfo As Variant, page As Long, pageTotal As Long, r As Long

Dim beginTime As Date, i As Long

Set IE = CreateObject("internetexplorer.application")

IE.navigate "http://mapping.ncua.gov/ResearchCreditUnion.aspx"

IE.Visible = True

Do While IE.Busy Or IE.readystate <> 4 '4 = READYSTATE_COMPLETE

DoEvents

Loop

'input city name into form

IE.document.getelementbyid("MainContent_txtCity").Value = "new york"

'click find button

IE.document.getelementbyid("MainContent_btnFind").Click

sleep 5 * 1000

'total pages

pageTotal = IE.document.getelementbyid("MainContent_pager_total").innertext

page = 0

Do Until page = pageTotal

DoEvents

page = IE.document.getelementbyid("MainContent_pager_to").innertext

With IE.document.getelementbyid("MainContent_grid")

For r = 1 To .Rows.Length - 1

If Not IsArray(charterInfo) Then

ReDim charterInfo(7, 0) As Variant

Else

ReDim Preserve charterInfo(7, UBound(charterInfo, 2) + 1) As Variant

End If

charterInfo(0, UBound(charterInfo, 2)) = .Rows(r).Cells(0).innertext

Next r

End With

If page < pageTotal Then

IE.document.getelementbyid("MainContent_pageNext").Click

beginTime = Now

Application.Wait (Now + TimeValue("00:00:05"))

End If

Loop

For r = 0 To UBound(charterInfo, 2)

IE.navigate "http://mapping.ncua.gov/SingleResult.aspx?ID=" & charterInfo(0, r)

Do While IE.Busy Or IE.readystate <> 4 '4 = READYSTATE_COMPLETE

DoEvents

Loop

'wait 5 sec. for screen refresh

sleep 5 * 1000

With IE.document.getelementbyid("MainContent_newDetails")

For i = 0 To .Rows.Length - 1

DoEvents

Select Case .Rows(i).Cells(0).innertext

Case "Credit Union Name:"

charterInfo(1, r) = .Rows(i).Cells(1).innertext

Case "Region:"

charterInfo(2, r) = .Rows(i).Cells(1).innertext

Case "Credit Union Status:"

charterInfo(3, r) = .Rows(i).Cells(1).innertext

Case "Assets:"

charterInfo(4, r) = Replace(Replace(.Rows(i).Cells(1).innertext, ",", ""), "$", "")

Case "Number of Members:"

charterInfo(5, r) = Replace(.Rows(i).Cells(1).innertext, ",", "")

Case "Address:"

charterInfo(6, r) = .Rows(i).Cells(1).innertext

Case "Phone:"

charterInfo(7, r) = "'" & .Rows(i).Cells(1).innertext

End Select

Next i

End With

Next r

IE.Quit

Set IE = Nothing

'post result on Excel cell

Worksheets(1).Range("A1").Resize(UBound(charterInfo, 2) + 1, UBound(charterInfo, 1) + 1).Value = Application.Transpose(charterInfo)

End Sub

  • 0
    点赞
  • 3
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值