主题：关于读取PDF导入表的问题

Dim reader As New iTextSharp.text.pdf.PdfReader("C:\Users\朱建斌\Documents\Foxtable项目\PDF读取项目\箱单\jnby\5l1611330 1-18.pdf")

Dim n As Integer = reader.NumberOfPages

Dim str As String = ""

Dim str1 As String

Dim str2 As String

Dim str3 As String

For i As Integer = 1 To n

    Dim strategy As object = New iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy()

    Dim currentText As String = iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(Reader, i, strategy)

    currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.[Default], Encoding.UTF8, Encoding.[Default].GetBytes(currentText)))

    str = currentText.Replace("/", "-")

    str1 = System.Text.RegularExpressions.Regex.Replace(str,"^", "/")

    str2 = System.Text.RegularExpressions.Regex.Replace(str1," ", "/")

    str3 = System.Text.RegularExpressions.Regex.Replace(str2,"\n", "/")

Next

Dim mc = System.Text.RegularExpressions.Regex.Matches(str3 ,"/.+?/")

msgbox(mc.Count)

msgbox(Str3)

Dim nw As Integer = mc.Count

For i As Integer = 0 To nw -1

    msgbox("xs:" & mc(i).value)

Next

reader.Close()

不知道为什么里面会缺好几个数据