Xbase++ 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. Xbase++

LOCAL nSuccess
LOCAL oPdf
LOCAL oJson
LOCAL oJsonOut
LOCAL i
LOCAL nCount_i

nSuccess := 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

oPdf := CreateObject("Chilkat.Pdf")
nSuccess := oPdf:LoadFile("qa_data/pdf/search_context.pdf")
IF (nSuccess == 0)
    ? oPdf:LastErrorText
    oPdf:destroy()
    RETURN
ENDIF

oJson := CreateObject("Chilkat.JsonObject")
oJsonOut := CreateObject("Chilkat.JsonObject")

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

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

nSuccess := oPdf:ExtractText("search", oJson, oJsonOut)
IF (nSuccess == 0)
    ? oPdf:LastErrorText
    oPdf:destroy()
    oJson:destroy()
    oJsonOut:destroy()
    RETURN
ENDIF

//  "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.
? "Matches: " + Str(oJsonOut:IntOf("count"))

i := 0
nCount_i := oJsonOut:SizeOfArray("matches")
DO WHILE i < nCount_i
    oJsonOut:I := i
    ? "page " + Str(oJsonOut:IntOf("matches[i].page")) + ": ..." + oJsonOut:StringOf("matches[i].before") + "[" + oJsonOut:StringOf("matches[i].text") + "]" + oJsonOut:StringOf("matches[i].after") + "..."
    i := i + 1
ENDDO

//  The search ignores case by default.  Set caseSensitive to find only the exact spelling.
oJson:UpdateBool("caseSensitive", 1)
oJson:UpdateString("query", "Chilkat")
nSuccess := oPdf:ExtractText("search", oJson, oJsonOut)
IF (nSuccess == 0)
    ? oPdf:LastErrorText
    oPdf:destroy()
    oJson:destroy()
    oJsonOut:destroy()
    RETURN
ENDIF

? "Case-sensitive matches for Chilkat: " + Str(oJsonOut: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

oPdf:destroy()
oJson:destroy()
oJsonOut:destroy()