Text extraction benchmarks

use pdfluent::PdfDocument;

fn extract_all(paths: &[&str]) -> pdfluent::Result<()> {
    for path in paths {
        let doc = PdfDocument::open(path)?;
        for i in 0..doc.page_count() {
            let _text = doc.page(i)?.text()?;
        }
    }
    Ok(())
}

import fitz  # pymupdf

def extract_all(paths):
    for path in paths:
        doc = fitz.open(path)
        for page in doc:
            _ = page.get_text()
        doc.close()