Creating Accessible PDFs: A Developer’s Guide to WCAG Compliance

from PyPDF2 import PdfWriter, PdfReader  

def add_alt_text(input_pdf, output_pdf, alt_text_dict):  
    reader = PdfReader(input_pdf)  
    writer = PdfWriter()  

    for page_num, page in enumerate(reader.pages):  
        images = page.images  
        for img_idx, img in enumerate(images):  
            # Add alt text to image  
            img_obj = img.indirect_reference.get_object()  
            img_obj.update({  
                "/Alt": PdfString(alt_text_dict.get(f"page{page_num}_img{img_idx}", "")  
            })  
        writer.add_page(page)  

    with open(output_pdf, "wb") as f:  
        writer.write(f)  

# Usage  
alt_texts = {"page0_img0": "Diagram of patient onboarding workflow"}  
add_alt_text("medical_form.pdf", "accessible_medical_form.pdf", alt_texts)

PDDocument doc = new PDDocument();  
PDAccessibility accessibility = doc.getAccessibility();  
accessibility.setAccessible(true);  

// Create tagged structure  
PDStructureTreeRoot treeRoot = new PDStructureTreeRoot();  
PDStructureElement heading = new PDStructureElement(StandardStructureTypes.H1, treeRoot);  
heading.setPage(0);  
heading.appendKid(new PDStructureElement(StandardStructureTypes.P, treeRoot));  

// Add content  
PDPage page = new PDPage();  
doc.addPage(page);  
PDStream stream = new PDStream(doc);  
try (PDPageContentStream content = new PDPageContentStream(doc, page)) {  
    content.beginText();  
    content.setFont(PDType1Font.HELVETICA_BOLD, 12);  
    content.newLineAtOffset(100, 700);  
    content.showText("Accessible PDF Heading");  
    content.endText();  
}  

doc.save("tagged_pdf.pdf");

import { PDFDocument } from 'pdf-lib';  

async function setPdfLanguage(inputPdf, langCode) {  
    const pdfDoc = await PDFDocument.load(inputPdf);  
    pdfDoc.setLanguage(langCode);  
    const pdfBytes = await pdfDoc.save();  
    return pdfBytes;  
}  

// Usage  
const pdfBytes = await setPdfLanguage(fs.readFileSync('report.pdf'), 'en-US');  
fs.writeFileSync('accessible_report.pdf', pdfBytes);

import subprocess  

def run_accessibility_check(pdf_path):  
    result = subprocess.run(  
        ["axe-pdf", pdf_path, "--tags", "wcag2a,wcag2aa"],  
        capture_output=True,  
        text=True  
    )  
    if "0 violations found" not in result.stdout:  
        print(f"Accessibility issues found: {result.stdout}")  
    return result.stdout  

report = run_accessibility_check("invoice.pdf")

from PyPDF2 import PdfReader  

def tag_headings(pdf_path):  
    reader = PdfReader(pdf_path)  
    for page in reader.pages:  
        text = page.extract_text()  
        lines = text.split('\n')  
        for line in lines:  
            if line.isupper() and len(line) < 50:  # Detect headings  
                # Add tag logic here  
                print(f"Heading detected: {line}")

import camelot  

tables = camelot.read_pdf("data.pdf")  
for table in tables:  
    table.df.to_csv("table.csv")  
    # Add table tags via PDFBox