ElementReader

Sample code in Swift and Obj-C for using Apryse iOS SDK to traverse the page display list using ElementReader available. Learn more about our full PDF Data Extraction SDK Capabilities.

To start your free trial, get stated with iOS SDK.

Obj-C

//---------------------------------------------------------------------------------------
// Copyright (c) 2001-2024 by Apryse Software Inc. All Rights Reserved.
// Consult legal.txt regarding legal and license information.
//---------------------------------------------------------------------------------------

#import <OBJC/PDFNetOBJC.h>
#import <Foundation/Foundation.h>

void ProcessReaderTestElements(PTElementReader *reader)
{
    PTElement *element;
    for (element=[reader Next]; element != NULL; element = [reader Next])     // Read page contents
    {
        switch ([element GetType])
        {
        case e_ptpath:                        // Process path data...
            {
                PTPathData *data = [element GetPathData];
                NSArray *points = [data GetPoints];
            }
             break;
        case e_pttext_obj:                 // Process text strings...
            {
                NSString* nsdata = [element GetTextString];
                unsigned char* data = (unsigned char *)[nsdata UTF8String];
                printf("%s\n", data);
            }
            break;
        case e_ptform:                // Process form XObjects
            {
                [reader FormBegin]; 
                ProcessReaderTestElements(reader);
                [reader End]; 
            }
            break;
        default:
                ;
        }
    }
}

int main(int argc, char *argv[])
{
    @autoreleasepool {
        int ret = 0;
        [PTPDFNet Initialize: 0];
        
        @try    // Extract text data from all pages in the document
        {
            printf("-------------------------------------------------\n");
            printf("Sample 1 - Extract text data from all pages in the document.\n");
            printf("Opening the input pdf...\n");

            PTPDFDoc *doc = [[PTPDFDoc alloc] initWithFilepath: @"../../TestFiles/newsletter.pdf"];
            [doc InitSecurityHandler];
            
            PTPageIterator *itr;
            PTElementReader *page_reader = [[PTElementReader alloc] init];

            for (itr = [doc GetPageIterator: 1]; [itr HasNext]; [itr Next])        //  Read every page
            {                
                [page_reader Begin: [itr Current]];
                ProcessReaderTestElements(page_reader);
                [page_reader End];
            }

            printf("Done.\n");
        }
        @catch(NSException *e)
        {
            NSLog(@"%@", e.reason);
            ret = 1;
        }
        [PTPDFNet Terminate: 0];        
        return ret;
    }

}

Swift

//---------------------------------------------------------------------------------------
// 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
    }
}