Objective-C Requires Chilkat v11.7.0+

Get Every Occurrence of a Label in a PDF

See more PDF Text Extraction Examples

Demonstrates the "labelOccurrence" option. When the same label appears more than once (for example "Total:" on each of several receipts), "first" (the default) uses the first occurrence, "all" returns every occurrence with its page, and a number selects one occurrence. Objective-C

#import <CkoPdf.h>
#import <CkoJsonObject.h>

BOOL success = NO;

//  This example requires the Chilkat API to have been previously unlocked.
//  See Global Unlock Sample for sample code.

//  The PDF used in this example (three receipts, one per page) is available at three_receipts.pdf

CkoPdf *pdf = [[CkoPdf alloc] init];
success = [pdf LoadFile: @"qa_data/pdf/three_receipts.pdf"];
if (success == NO) {
    NSLog(@"%@",pdf.LastErrorText);
    return;
}

CkoJsonObject *json = [[CkoJsonObject alloc] init];
CkoJsonObject *jsonOut = [[CkoJsonObject alloc] init];

//  Each of the three pages is a receipt with a "Total:" line.
[json UpdateString: @"label" value: @"Total"];
[json UpdateString: @"labelValue" value: @"right"];

//  By default only the first occurrence (in reading order) is used.
success = [pdf ExtractText: @"text" jsonIn: json jsonOut: jsonOut];
if (success == NO) {
    NSLog(@"%@",pdf.LastErrorText);
    return;
}

NSLog(@"%@%@",@"First total: ",[jsonOut StringOf: @"text"]);

//  labelOccurrence "all" returns every occurrence.  The "text" member holds the values joined
//  by line breaks, and labelMatches has one entry per occurrence with its page.
[json UpdateString: @"labelOccurrence" value: @"all"];
success = [pdf ExtractText: @"text" jsonIn: json jsonOut: jsonOut];
if (success == NO) {
    NSLog(@"%@",pdf.LastErrorText);
    return;
}

int i = 0;
int count_i = [[jsonOut SizeOfArray: @"labelMatches"] intValue];
while (i < count_i) {
    jsonOut.I = [NSNumber numberWithInt: i];
    NSLog(@"%@%d%@%@",@"Page ",[[jsonOut IntOf: @"labelMatches[i].page"] intValue],@" total: ",[jsonOut StringOf: @"labelMatches[i].text"]);
    i = i + 1;
}

//  A number selects one occurrence: 2 is the second.
[json UpdateInt: @"labelOccurrence" value: [NSNumber numberWithInt: 2]];
success = [pdf ExtractText: @"text" jsonIn: json jsonOut: jsonOut];
if (success == NO) {
    NSLog(@"%@",pdf.LastErrorText);
    return;
}

NSLog(@"%@%@",@"Second total: ",[jsonOut StringOf: @"text"]);

//  The occurrences are counted over the selected pages, so combining "pages" with the label
//  is another way to pick one receipt:
[json UpdateString: @"labelOccurrence" value: @"first"];
[json UpdateString: @"pages" value: @"3"];
[json UpdateString: @"label" value: @"Receipt No."];
success = [pdf ExtractText: @"text" jsonIn: json jsonOut: jsonOut];
if (success == NO) {
    NSLog(@"%@",pdf.LastErrorText);
    return;
}

NSLog(@"%@%@",@"Receipt number on page 3: ",[jsonOut StringOf: @"text"]);

//  Sample output:

//  First total: $19.86
//  Page 1 total: $19.86
//  Page 2 total: $17.34
//  Page 3 total: $23.62
//  Second total: $17.34
//  Receipt number on page 3: 1003