PowerBuilder Requires Chilkat v11.7.0+

Search for Text in a PDF

See more PDF Text Extraction Examples

Demonstrates the "search" operation, which finds every occurrence of a string in a PDF and returns each match with its page number and the text around it. Matching ignores case unless caseSensitive is true. PowerBuilder

integer li_rc
long li_Success
oleobject loo_Pdf
oleobject loo_Json
oleobject loo_JsonOut
long i
long li_Count_i

li_Success = 0

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

//  The three-page PDF used in this example is available at search_context.pdf

loo_Pdf = create oleobject
li_rc = loo_Pdf.ConnectToNewObject("Chilkat.Pdf")
if li_rc < 0 then
    destroy loo_Pdf
    MessageBox("Error","Connecting to COM object failed")
    return
end if
li_Success = loo_Pdf.LoadFile("qa_data/pdf/search_context.pdf")
if li_Success = 0 then
    Write-Debug loo_Pdf.LastErrorText
    destroy loo_Pdf
    return
end if

loo_Json = create oleobject
li_rc = loo_Json.ConnectToNewObject("Chilkat.JsonObject")

loo_JsonOut = create oleobject
li_rc = loo_JsonOut.ConnectToNewObject("Chilkat.JsonObject")

//  The string to find.
loo_Json.UpdateString("query","chilkat")

//  The number of characters returned before and after each match.  The default is 40.
loo_Json.UpdateInt("context",30)

li_Success = loo_Pdf.ExtractText("search",loo_Json,loo_JsonOut)
if li_Success = 0 then
    Write-Debug loo_Pdf.LastErrorText
    destroy loo_Pdf
    destroy loo_Json
    destroy loo_JsonOut
    return
end if

//  "count" is the number of matches.  Each match has the page, the matched text as it appears
//  in the PDF, and the text before and after it.
Write-Debug "Matches: " + string(loo_JsonOut.IntOf("count"))

i = 0
li_Count_i = loo_JsonOut.SizeOfArray("matches")
do while i < li_Count_i
    loo_JsonOut.I = i
    Write-Debug "page " + string(loo_JsonOut.IntOf("matches[i].page")) + ": ..." + loo_JsonOut.StringOf("matches[i].before") + "[" + loo_JsonOut.StringOf("matches[i].text") + "]" + loo_JsonOut.StringOf("matches[i].after") + "..."
    i = i + 1
loop

//  The search ignores case by default.  Set caseSensitive to find only the exact spelling.
loo_Json.UpdateBool("caseSensitive",1)
loo_Json.UpdateString("query","Chilkat")
li_Success = loo_Pdf.ExtractText("search",loo_Json,loo_JsonOut)
if li_Success = 0 then
    Write-Debug loo_Pdf.LastErrorText
    destroy loo_Pdf
    destroy loo_Json
    destroy loo_JsonOut
    return
end if

Write-Debug "Case-sensitive matches for Chilkat: " + string(loo_JsonOut.IntOf("count"))

//  Sample output:

//  Matches: 5
//  page 1: ...[Chilkat] River Field Notes The Chilkat...
//  page 1: ...Chilkat River Field Notes The [Chilkat] River runs for about fifty mi...
//  page 2: ...DAY ONE: UPPER [CHILKAT] FLATS Clear and cold, minus e...
//  page 2: ...he river is sometimes spelled [chilkat] in older records, and the val...
//  page 3: ...y because the fish run on the [Chilkat] was thinning. Two tagged bird...
//  Case-sensitive matches for Chilkat: 3


destroy loo_Pdf
destroy loo_Json
destroy loo_JsonOut