將Word文檔中的內容提取到SQL數據庫的最佳方法是什麼？

Question

我有一個以文檔形式存在的100,000個問題的問題銀行。這些問題在文字中包含一些包含圖像。是否有任何有效的方法一次提取問題（，包括圖像）並將它們導入到SQL數據庫中？寧願不必將文本轉換爲圖像，因爲這些問題可能需要編輯。謝謝！

Answer 1

這裏是一個開始

分離問題編號，問題文本，每個答案數量以及每個答案文字

然後將它們打印在即時窗口

，請與您的文檔

的一個嘗試

Option Explicit 

Sub parse() 

    Dim rgx As Object 
    Set rgx = CreateObject("vbscript.regexp") 
    rgx.MultiLine = True 
    rgx.Global = True 
    rgx.pattern = "^[\s]+|[\s]+$" 

    Dim s As String 

    Dim i As Integer 

    Dim qNum As Long 
    Dim qest As String 

    Dim aNum As Integer 
    Dim answ As String 

    Dim par As Paragraphs 
    Set par = ActiveDocument.Paragraphs 

    Dim p As Integer 
    For p = 1 To par.Count 
     s = rgx.Replace(par(p).Range.Text, "")     ' trim whitespace (leading and trailing) 
'  Debug.Print "--- "; s 

     Select Case Left(s, 1) 
      Case "0" To "9"          ' question found 
       qNum = CDec(Split(s, ".")(0))     ' number 
       i = 1 

       qest = rgx.Replace(Split(s, ".", 2)(1), "")  ' first line of text 

       Do While True 
        s = rgx.Replace(par(p + i).Range.Text, "") ' check for multiline question 
        If Len(s) > 0 Then 
         If Left(s, 1) = "(" Then 
          p = p + i - 1      ' it is an answer line, so exit 
          Exit Do 
         Else 
          qest = qest & vbNewLine & s   ' assemble multiline question 
         End If 
        End If 
        i = i + 1 
       Loop 

       Debug.Print vbNewLine; "question # "; qNum; vbTab; qest 

      Case "("           ' answer found 
       aNum = CDec(Mid(s, 2, 1))      ' number 
       answ = Split(s, ")", 2)(1)      ' text 
       Debug.Print "answer # "; aNum, answ 
     End Select 
    Next p 


End Sub