下面是我適合你的情況很常見的例子,它顯示了XHR和正則表達式的使用檢索網頁的HTML內容,從中提取的所有鏈接,並下載各個環節的目標文件:
Option Explicit
Sub Test()
' declare vars
Dim sUrl As String
Dim sReqProt As String
Dim sReqAddr As String
Dim sReqPath As String
Dim sContent As String
Dim oLinks As Object
Dim oMatch As Object
Dim sHref As String
Dim sHrefProt As String
Dim sHrefAddr As String
Dim sHrefPath As String
Dim sHrefFull As String
Dim n As Long
Dim aContent() As Byte
' set source URL
sUrl = "https:\\......\links.html"
' process source URL
SplitUrl sUrl, sReqProt, sReqAddr, sReqPath
If sReqProt = "" Then sReqProt = "http:"
sUrl = sReqProt & "//" & sReqAddr & "/" & sReqPath
' retrieve source page HTML content
With CreateObject("Microsoft.XMLHTTP")
.Open "GET", sUrl, False
.Send
sContent = .ResponseText
End With
' parse source page HTML content to extract all links
Set oLinks = CreateObject("Scripting.Dictionary")
With CreateObject("VBScript.RegExp")
.Global = True
.MultiLine = True
.IgnoreCase = True
.Pattern = "<a.*?href *= *(?:'|"")(.*?)(?:'|"").*?>"
For Each oMatch In .Execute(sContent)
sHref = oMatch.subMatches(0)
SplitUrl sHref, sHrefProt, sHrefAddr, sHrefPath
If sHrefProt = "" Then sHrefProt = sReqProt
If sHrefAddr = "" Then sHrefAddr = sReqAddr
sHrefFull = sHrefProt & "//" & sHrefAddr & "/" & sHrefPath
oLinks(oLinks.Count) = sHrefFull
Next
End With
' save each link target into file
For Each n In oLinks
sHref = oLinks(n)
With CreateObject("Microsoft.XMLHTTP")
.Open "GET", sHref, False
.Send
aContent = .ResponseBody
End With
With CreateObject("ADODB.Stream")
.Type = 1 ' adTypeBinary
.Open
.Write aContent
.SaveToFile "C:\Test\" & n & ".xml", 2 ' adSaveCreateOverWrite
.Close
End With
Next
End Sub
Sub SplitUrl(sUrl, sProt, sAddr, sPath)
' extract protocol, address and path from URL
Dim aSplit
aSplit = Split(sUrl, "//")
If UBound(aSplit) = 0 Then
sProt = ""
sAddr = sUrl
Else
sProt = aSplit(0)
sAddr = aSplit(1)
End If
aSplit = Split(sAddr, "/")
If UBound(aSplit) = 0 Then
sPath = sAddr
sAddr = ""
Else
sPath = Mid(sAddr, Len(aSplit(0)) + 2)
sAddr = aSplit(0)
End If
End Sub
此方法不採用IE自動化。通常情況下,IE的Cookie的過程足以引用當前會話,因此如果您的網站不使用附加程序進行身份驗證並生成鏈接列表,那麼該方法應該適用於您。
這是一個兔子洞,我已經倒了很多次。簡短的回答是停止嘗試讓IE充當代理來下載文件。使用xmlHttp對象通過GetResponseHeader登錄並收集/返回認證,然後使用ADO流保存文件。 – Jeeped
[This](http://stackoverflow.com/a/32429348/2165759)可能會有所幫助。 – omegastripes