gpt4 book ai didi

excel - 使用 getElementsByTagName() 进行网页抓取

转载 作者:行者123 更新时间:2023-12-04 21:50:00 25 4
gpt4 key购买 nike

我想将餐厅名称、电话号码、网站和地址等餐厅数据导入 Excel,但不幸的是我收到了广告和垃圾数据。我使用 http://automatetheweb.net/vba-getelementsbytagname-method/ 创建了一个代码网站,但它没有帮助。请纠正我的代码中的问题。
网址:https://www.yellowpages.com/atlanta-ga/attorneys
请不要引用 json,因为它不适用于其他网站。

Sub Yellowcom()
'Dim ieObj As InternetExplorer
Dim htmlELe As IHTMLElement
Dim HTML As HTMLDocument
Dim i As Integer

Dim URL As String
Dim URLParameter As String
Dim page As Long
Dim links As Object
Dim IE As Object


i = 1

Set IE = CreateObject("InternetExplorer.Application")
'Set ieObj = New InternetExplorer
IE.Visible = True
URL = "https://www.yellowpages.com/atlanta-ga/attorneys"
'Application.Wait Now + TimeValue("00:00:05")

For page = 2 To 4

If page > 1 Then URLParameter = "?page=" & page

IE.navigate URL & URLParameter

' Wait for the browser to load the page
Do Until IE.readyState = 4

DoEvents

Loop

Set HTML = IE.document
Set links = HTML.getElementsByClassName("info")

For Each htmlELe In links

With ActiveSheet
.Range("A" & i).Value = htmlELe.Children(0).textContent
.Range("B" & i).Value = htmlELe.getElementsByTagName("a")(0).href
.Range("C" & i).Value = htmlELe.Children(2).textContent
.Range("D" & i).Value = htmlELe.Children(2).querySelector("a[href]")
'links2 = htmlELe.getElementsByClassName("links")(1)
' .Range("D" & i).Value = links2.href


End With
i = i + 1

Next htmlELe

Next page

IE.Quit
Set IE = Nothing

End Sub

所需的输出应该是这样的
enter image description here

最佳答案

我会使用 xhr 而不是浏览器,并将每个页面的数据存储在一个数组中,然后将其写入工作表。您真的可以根据每页结果和页数预先确定一个数组以保存所有结果,但以下仍然有效

Option Explicit
Public Sub GetListings()
Dim html As HTMLDocument, page As Long, html2 As HTMLDocument
Dim results As Object, headers(), ws As Worksheet, i As Long

Const START_PAGE As Long = 1
Const END_PAGE As Long = 2

Set ws = ThisWorkbook.Worksheets("Sheet1")
headers = Array("Name", "Phone", "Website", "Address")
Application.ScreenUpdating = False
Set html = New HTMLDocument
Set html2 = New HTMLDocument
ws.Cells(1, 1).Resize(1, UBound(headers) + 1) = headers

With CreateObject("MSXML2.XMLHTTP")
For page = START_PAGE To END_PAGE
.Open "GET", "https://www.yellowpages.com/atlanta-ga/attorneys?page=" & page, False
.send
html.body.innerHTML = .responseText
Set results = html.querySelectorAll(".organic .result")
Dim output(), r As Long
ReDim output(1 To results.Length, 1 To 4)
r = 1
For i = 0 To results.Length - 1
On Error Resume Next
html2.body.innerHTML = results.item(i).outerHTML
output(r, 1) = html2.querySelector(".business-name").innerText
output(r, 2) = html2.querySelector(".phone").innerText
output(r, 3) = html2.querySelector(".track-visit-website").href
output(r, 4) = html2.querySelector(".street-address").innerText & " " & html2.querySelector(".locality").innerText
On Error GoTo 0
r = r + 1
Next
ws.Cells(GetLastRow(ws, 1) + 1, 1).Resize(UBound(output, 1), UBound(output, 2)) = output
Next
End With
Application.ScreenUpdating = True
End Sub
Public Function GetLastRow(ByVal ws As Worksheet, Optional ByVal columnNumber As Long = 1) As Long
With ws
GetLastRow = .Cells(.rows.Count, columnNumber).End(xlUp).Row
End With
End Function

输出样本:

enter image description here

关于excel - 使用 getElementsByTagName() 进行网页抓取,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/56477125/

25 4 0
Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
广告合作:1813099741@qq.com 6ren.com