PDF文本内容提取到TXT文件

时　间:2011-10-08 09:40:10
作　者:叶海峰   ID：31  城市：广州
摘　要:提取PDF文件的文本内容,并可以设定需要提取的页码翻页,生成为TXT文件
正　文:

点击下载此附件

      提取PDF文件的文本内容,需要引用Acrobat库,Acrobat7.0,9.0测试通过,大部分代码在网上收集回来,并非原创,如运行过程中出现ActiveX部件不能创建对象的提示,则有可能是Acrobat库引用失败,请重新安装完整版的Acrobat

Sub PdfToTxT()
    Dim MyPdf  As AcroPDDoc
    Dim MyPageHilite As AcroHiliteList
    Dim PageSelect As AcroPDTextSelect
    Dim i      As Integer
    Dim pdfdata As String
    Dim OpenResult, HiliteResult
    Dim pagenumber As Integer
    Dim myPDFPage As AcroPDPage
    Open "c:\1.txt" For Output As #1
    Set MyPdf = CreateObject("acroexch.pddoc")
    OpenResult = MyPdf.Open("c:\2007年半年报摘要.pdf")
    For pagenumber = 0 To MyPdf.GetNumPages - 1
        Set myPDFPage = MyPdf.AcquirePage(pagenumber)
        Set MyPageHilite = CreateObject("acroexch.hilitelist")
        HiliteResult = MyPageHilite.Add(0, 9000)
        Set PageSelect = myPDFPage.CreatePageHilite(MyPageHilite)
        For i = 0 To PageSelect.GetNumText - 1
            pdfdata = pdfdata & PageSelect.GetText(i)
        Next
        Print #1, pdfdata
        pdfdata = ""
        Set myPDFPage = Nothing
        Set MyPageHilite = Nothing
        Set PageSelect = Nothing
    Next
    Set MyPdf = Nothing
    Close #1
End Sub