Swift 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. Swift

func chilkatTest() {
    var success: Bool = 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

    let pdf = CkoPdf()!
    success = pdf.loadFile(filePath: "qa_data/pdf/search_context.pdf")
    if success == false {
        print("\(pdf.lastErrorText!)")
        return
    }

    let json = CkoJsonObject()!
    let jsonOut = CkoJsonObject()!

    //  The string to find.
    json.updateString(jsonPath: "query", value: "chilkat")

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

    success = pdf.extractText(op: "search", jsonIn: json, jsonOut: jsonOut)
    if success == false {
        print("\(pdf.lastErrorText!)")
        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.
    print("Matches: \(jsonOut.int(of: "count").intValue)")

    var i: Int = 0
    var count_i: Int = jsonOut.size(ofArray: "matches").intValue
    while i < count_i {
        jsonOut.i = i
        print("page \(jsonOut.int(of: "matches[i].page").intValue): ...\(jsonOut.string(of: "matches[i].before")!)[\(jsonOut.string(of: "matches[i].text")!)]\(jsonOut.string(of: "matches[i].after")!)...")
        i = i + 1
    }

    //  The search ignores case by default.  Set caseSensitive to find only the exact spelling.
    json.updateBool(jsonPath: "caseSensitive", value: true)
    json.updateString(jsonPath: "query", value: "Chilkat")
    success = pdf.extractText(op: "search", jsonIn: json, jsonOut: jsonOut)
    if success == false {
        print("\(pdf.lastErrorText!)")
        return
    }

    print("Case-sensitive matches for Chilkat: \(jsonOut.int(of: "count").intValue)")

    //  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

}