Go 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. Go

    success := false

    //  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

    pdf := chilkat.NewPdf()
    success = pdf.LoadFile("qa_data/pdf/search_context.pdf")
    if success == false {
        fmt.Println(pdf.LastErrorText())
        pdf.DisposePdf()
        return
    }

    json := chilkat.NewJsonObject()
    jsonOut := chilkat.NewJsonObject()

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

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

    success = pdf.ExtractText("search",json,jsonOut)
    if success == false {
        fmt.Println(pdf.LastErrorText())
        pdf.DisposePdf()
        json.DisposeJsonObject()
        jsonOut.DisposeJsonObject()
        return
    }

    //  "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.
    fmt.Println("Matches: ", jsonOut.IntOf("count"))

    i := 0
    count_i := jsonOut.SizeOfArray("matches")
    for i < count_i {
        jsonOut.SetI(i)
        fmt.Println("page ", jsonOut.IntOf("matches[i].page"), ": ...", *jsonOut.StringOf("matches[i].before"), "[", *jsonOut.StringOf("matches[i].text"), "]", *jsonOut.StringOf("matches[i].after")
            , "...")
        i = i + 1
    }

    //  The search ignores case by default.  Set caseSensitive to find only the exact spelling.
    json.UpdateBool("caseSensitive",true)
    json.UpdateString("query","Chilkat")
    success = pdf.ExtractText("search",json,jsonOut)
    if success == false {
        fmt.Println(pdf.LastErrorText())
        pdf.DisposePdf()
        json.DisposeJsonObject()
        jsonOut.DisposeJsonObject()
        return
    }

    fmt.Println("Case-sensitive matches for Chilkat: ", 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

    pdf.DisposePdf()
    json.DisposeJsonObject()
    jsonOut.DisposeJsonObject()