VBScript Requires Chilkat v11.7.0+

Search a PDF with a Regular Expression

See more PDF Text Extraction Examples

Demonstrates searching a PDF with a regular expression (regex: true), limiting the number of results (maxResults), and matching whole words only (wholeWord). VBScript

Dim fso, outFile
Set fso = CreateObject("Scripting.FileSystemObject")
'Create a Unicode (utf-16) output text file.
Set outFile = fso.CreateTextFile("output.txt", True, True)

success = 0

'  This example requires the Chilkat API to have been previously unlocked.
'  See Global Unlock Sample for sample code.

'  The PDF used in this example is available at order_records.pdf

set pdf = CreateObject("Chilkat.Pdf")
success = pdf.LoadFile("qa_data/pdf/order_records.pdf")
If (success = 0) Then
    outFile.WriteLine(pdf.LastErrorText)
    WScript.Quit
End If

set json = CreateObject("Chilkat.JsonObject")
set jsonOut = CreateObject("Chilkat.JsonObject")

'  Find every order number.  With regex set to true, the query is a regular expression.
success = json.UpdateString("query","ORD-[0-9]{4}-[0-9]{4}")
success = json.UpdateBool("regex",1)
'  We only want the matched text, so no context is needed.
success = json.UpdateInt("context",0)

success = pdf.ExtractText("search",json,jsonOut)
If (success = 0) Then
    outFile.WriteLine(pdf.LastErrorText)
    WScript.Quit
End If

outFile.WriteLine("Order numbers found: " & jsonOut.IntOf("count"))
i = 0
count_i = jsonOut.SizeOfArray("matches")
Do While i < count_i
    jsonOut.I = i
    outFile.WriteLine(jsonOut.StringOf("matches[i].text"))
    i = i + 1
Loop

'  Find the e-mail addresses, but stop after the first three.
success = json.UpdateString("query","[a-z0-9._]+@[a-z]+[.][a-z]+")
success = json.UpdateInt("maxResults",3)
success = pdf.ExtractText("search",json,jsonOut)
If (success = 0) Then
    outFile.WriteLine(pdf.LastErrorText)
    WScript.Quit
End If

outFile.WriteLine("First three e-mail addresses:")
i = 0
count_i = jsonOut.SizeOfArray("matches")
Do While i < count_i
    jsonOut.I = i
    outFile.WriteLine(jsonOut.StringOf("matches[i].text"))
    i = i + 1
Loop

'  wholeWord: true matches only whole words.  The word "cat" appears once in the PDF,
'  but it is also inside "catalog" and "category".
success = json.Delete("maxResults")
success = json.UpdateBool("regex",0)
success = json.UpdateString("query","cat")
success = pdf.ExtractText("search",json,jsonOut)
If (success = 0) Then
    outFile.WriteLine(pdf.LastErrorText)
    WScript.Quit
End If

outFile.WriteLine("Occurrences of cat (any): " & jsonOut.IntOf("count"))

success = json.UpdateBool("wholeWord",1)
success = pdf.ExtractText("search",json,jsonOut)
If (success = 0) Then
    outFile.WriteLine(pdf.LastErrorText)
    WScript.Quit
End If

outFile.WriteLine("Occurrences of cat (whole word): " & jsonOut.IntOf("count"))

'  Sample output:

'  Order numbers found: 9
'  ORD-2026-0301
'  ORD-2026-0302
'  ORD-2026-0303
'  ORD-2026-0304
'  ORD-2026-0305
'  ORD-2026-0306
'  ORD-2026-0307
'  ORD-2026-0308
'  ORD-2026-0307
'  First three e-mail addresses:
'  alice.moore@example.com
'  bkumar@example.org
'  carla@example.net
'  Occurrences of cat (any): 3
'  Occurrences of cat (whole word): 1

outFile.Close