xmlhttp请求导致的Unicode字符

时间:2018-11-02 18:08:55

标签: excel vba excel-vba xmlhttprequest

在此LINK >> @QHarr中,我们引入了一种解决方案来计算Google搜索的结果,这是代码

Public Sub GetResultsCount()
Dim sResponse As String, html As HTMLDocument
With CreateObject("MSXML2.XMLHTTP")
    .Open "GET", "https://www.google.com/search?q=mitsubishi", False
    .setRequestHeader "If-Modified-Since", "Sat, 1 Jan 2000 00:00:00 GMT"
    .send
    sResponse = StrConv(.responseBody, vbUnicode)
End With
Set html = New HTMLDocument
With html
    .body.innerHTML = sResponse
    Debug.Print .querySelector("#resultStats").innerText
End With

End Sub

代码可以正常工作..但是在立即窗口中,我得到了这个难以理解的字符 enter image description here

该如何解决以阿拉伯字符显示?

感谢高级帮助

1 个答案:

答案 0 :(得分:4)

我找到了这个线程:VBA - Convert string to UNICODE,并设法提出了解决方案(它适用于波兰语字符,不确定阿拉伯语)

Private Const CP_UTF8 = 65001

Private Declare Function MultiByteToWideChar Lib "kernel32" ( _
   ByVal CodePage As Long, ByVal dwFlags As Long, _
   ByVal lpMultiByteStr As Long, ByVal cchMultiByte As Long, _
   ByVal lpWideCharStr As Long, ByVal cchWideChar As Long) As Long

Public Sub GetResultsCount()
Dim sResponse As String 
Dim html      As HTMLDocument
With CreateObject("MSXML2.XMLHTTP")
    .Open "GET", "https://www.google.com/search?q=mitsubishi", False
    .setRequestHeader "If-Modified-Since", "Sat, 1 Jan 2000 00:00:00 GMT"
    .send
    sResponse = StrConv(.responseBody, vbUnicode)
End With
Set html = New HTMLDocument

html.body.innerHTML = sResponse
Debug.Print sUTF8ToUni(StrConv(html.querySelector("#resultStats").innerText, vbFromUnicode))
End Sub

Public Function sUTF8ToUni(bySrc() As Byte) As String
   ' Converts a UTF-8 byte array to a Unicode string
   Dim lBytes As Long, lNC As Long, lRet As Long

   lBytes = UBound(bySrc) - LBound(bySrc) + 1
   lNC = lBytes
   sUTF8ToUni = String$(lNC, Chr(0))
   lRet = MultiByteToWideChar(CP_UTF8, 0, VarPtr(bySrc(LBound(bySrc))), lBytes, StrPtr(sUTF8ToUni), lNC)
   sUTF8ToUni = Left$(sUTF8ToUni, lRet)
End Function