我正在尝试使用MSXML2和IHTMLDocument 处理HTML网页的iframe部分。
我想使用MSXML2并将其保存以更好地“捕获”数据,认为它比仅使用VBA菜单支持的InternetExplorer或VBA硒参考要快。 (我不想尽可能避免使用IE或硒)
但是我无法找到如何将文档另存为XML格式(以利用其速度),并且同时在没有浏览器(即硒)的帮助下单击文档中的元素。
而且即使单击this web page上的某些标签(id =“ cns_Tab21”),我也很难检索数据。
所以我的问题是..
1>是否可以最大程度地减少使用浏览器的点击次数?
2>即使单击(使用Selenium)后,它也会在VBA编辑器中引发与xpath相关的错误。
预先感谢您的回答,为此使用的网址是 http://bitly.kr/finance 并且链接内的iframe为http://bitly.kr/LT0aCb
'I declared objects
Dim XMLReq As New MSXML2.XMLHTTP60
Dim HTMLDoc As New MSHTML.HTMLDocument
Dim iframeDoc As IHTMLDocument
'and saved XML data to HTML format
HTMLDoc.body.innerHTML = XMLReq.responseText
'and trying to save this HTML to iframe...
Set iframeDoc = HTMLDoc.getElementById("coinfo_cp")
'I tried .contentDocument but it maybe HTMLdoc doesn't have this property.
and I don't know how to access information I saved to iframeDoc above.
'And after I use Selenium I can't figure out why it throw an error
For Each ele In selenium.FindElementsByTag("th")
If ele.Attribute("innerText") = "CAPEX" Then
Debug.Print ele.FindElementsByXPath("./../td").Attribute("innerText")
由于我试图使用XML处理iframe元素并且在VBA Excel中没有InternetExplorer引用,因此这篇文章不是重复的。(p.document)
答案 0 :(得分:1)
当选择该标签(而非iframe)时,您可以复制该页面发出的xhr请求。我使用剪贴板将表格复制到Excel。注意:我使用的网址来自我们的讨论。此信息应反映在问题中。
Option Explicit
Public Sub GetTable()
'VBE > Tools > References > Microsoft HTML Object Library
Dim html As HTMLDocument, hTable As HTMLTable, clipboard As Object
Set html = New HTMLDocument
With CreateObject("MSXML2.XMLHTTP")
.Open "GET", "https://navercomp.wisereport.co.kr/v2/company/ajax/cF1001.aspx?cmp_cd=005930&fin_typ=0&freq_typ=Y&encparam=ZXR1cWFjeGJnS1lWOHhCYmNScmJXUT09&id=bG05RlB6cn", False
.setRequestHeader "User-Agent", "Mozilla/5.0"
.send
html.body.innerHTML = .responseText
End With
Set hTable = html.querySelector(".hbG05RlB6cn + .gHead01")
Set clipboard = GetObject("New:{1C3B4210-F441-11CE-B9EA-00AA006B1A69}") ' New DataObject
clipboard.SetText hTable.outerHTML
clipboard.PutInClipboard
ThisWorkbook.Worksheets("Sheet1").Cells(1, 1).PasteSpecial
End Sub
您可以在页面的脚本中找到用于标签内容更新的ajax url的参数
连同更新目标:
这需要整理:
Option Explicit
Public Sub GetTable()
'https://navercomp.wisereport.co.kr/v2/company/c1010001.aspx?cmp_cd=005930
'VBE > Tools > References > Microsoft HTML Object Library
Dim html As HTMLDocument, hTable As HTMLTable, clipboard As Object, ws As Worksheet
Set ws = ThisWorkbook.Worksheets("Sheet1")
Set html = New HTMLDocument
With CreateObject("MSXML2.XMLHTTP")
.Open "GET", "https://navercomp.wisereport.co.kr/v2/company/ajax/cF1001.aspx?cmp_cd=005930&fin_typ=0&freq_typ=Y&encparam=ZXR1cWFjeGJnS1lWOHhCYmNScmJXUT09&id=bG05RlB6cn", False
.setRequestHeader "User-Agent", "Mozilla/5.0"
.send
html.body.innerHTML = .responseText
End With
Set hTable = html.querySelector(".hbG05RlB6cn + .gHead01") '2nd tab. CAPEX row
Dim html2 As HTMLDocument, i As Long
Set html2 = New HTMLDocument
html2.body.innerHTML = hTable.outerHTML
Dim tableBodyRows As Object, tableBodyRowLength As Long, tableHeaderRowLength As Long, tableHeaderRows As Object, targetRow As Long
Set tableBodyRows = html2.querySelectorAll("tbody tr .bg")
tableBodyRowLength = tableBodyRows.Length
tableHeaderRowLength = html2.querySelectorAll("thead tr").Length + 2
For i = 0 To tableBodyRowLength - 1
If Trim$(tableBodyRows.item(i).innerText) = "CAPEX" Then
targetRow = i + tableHeaderRowLength + 1
Exit For
End If
Next
Set clipboard = GetObject("New:{1C3B4210-F441-11CE-B9EA-00AA006B1A69}") ' New DataObject
clipboard.SetText hTable.outerHTML
clipboard.PutInClipboard
ws.Cells(1, 1).PasteSpecial
Dim unionRng As Range
For i = (tableHeaderRowLength + 1) To (tableBodyRowLength + tableHeaderRowLength)
If i <> targetRow Then
If Not unionRng Is Nothing Then
Set unionRng = Union(ws.rows(i), unionRng)
Else
Set unionRng = ws.rows(i)
End If
End If
Next
If Not unionRng Is Nothing Then unionRng.Delete
End Sub