Some test text!

menu
search

Read elements across all PDF pages in Swift

Sample Swift code for using PDFTron SDK to traverse the page display list using ElementReader. Learn more about our PDF Parsing & Content Extraction Library.

Get StartedSamplesDownload

To run this sample, get started with a free trial of PDFTron SDK.

//---------------------------------------------------------------------------------------
// Copyright (c) 2001-2019 by PDFTron Systems Inc. All Rights Reserved.
// Consult legal.txt regarding legal and license information.
//---------------------------------------------------------------------------------------

import PDFNet
import Foundation

func ProcessReaderTestElements(reader: PTElementReader) {
    while let element = reader.next() {
        switch element.getType() {
        case e_ptpath:  // Process path data...
            let data: PTPathData = element.getPathData()
            let _ = data.getPoints()    // points
        case e_pttext_obj:  // Process text strings...
            let textData: Data = element.getTextData()
            let text = String(data: textData, encoding: .utf8)
            print("\(text ?? "")")
        case e_ptform:  // Process form XObjects
            reader.formBegin()
            ProcessReaderTestElements(reader: reader)
            reader.end()
        default:
            break
        }
    }
}

func runElementReaderTest() -> Int {
    return autoreleasepool {
        var ret: Int = 0
        
        
        do {    // Extract text data from all pages in the document
            try PTPDFNet.catchException {
                print("__________________________________________________")
                print("Sample 1 - Extract text data from all pages in the document.")
                print("Opening the input pdf...")
                
                let doc: PTPDFDoc = PTPDFDoc(filepath: Bundle.main.path(forResource: "newsletter", ofType: "pdf"))
                doc.initSecurityHandler()
                
                let page_reader: PTElementReader = PTElementReader()
                
                let itr: PTPageIterator = doc.getPageIterator(1)
                while itr.hasNext() {  // Read every page
                    page_reader.begin(itr.current())
                    ProcessReaderTestElements(reader: page_reader)
                    page_reader.end()
                    itr.next()
                
                }
                print("Done.")
            }
        } catch let e as NSError {
            print("Caught PDFNet exception: \(e)")
            ret = 1
        }
        
        return ret
    }
}
close

Free Trial

Get unlimited trial usage of PDFTron SDK to bring accurate, reliable, and fast document processing capabilities to any application or workflow.

Select a platform to get started with your free trial.

Unlimited usage. No email address required.

PDFTron Receives USD$71 Million Growth Investment Led By Silversmith Capital Partners

Learn More
close