# Single file
pdftotext document.pdf output.txt
pdftotext -layout document.pdf output.txt  # Preserve layout

import subprocess
from concurrent.futures import ProcessPoolExecutor

def extract_text(pdf_path: str, timeout: int = 30) -> str | None:
    """Extract text via pdftotext subprocess — killable on timeout."""
    try:
        result = subprocess.run(
            ["pdftotext", pdf_path, "-"],
            capture_output=True, text=True, timeout=timeout
        )
        return result.stdout if result.returncode == 0 else None
    except subprocess.TimeoutExpired:
        return None  # Process killed cleanly by OS

# 8 workers, chunksize=50 — sustained ~49 files/second
with ProcessPoolExecutor(max_workers=8) as pool:
    results = list(pool.map(extract_text, pdf_paths, chunksize=50))

# Merge PDFs
qpdf --empty --pages file1.pdf file2.pdf -- merged.pdf

# Split pages
qpdf document.pdf --pages . 1-5 -- first_five.pdf

# Decrypt
qpdf --decrypt encrypted.pdf decrypted.pdf

# Merge
pdftk file1.pdf file2.pdf cat output merged.pdf

# Split
pdftk document.pdf burst output page_%02d.pdf

# Rotate
pdftk document.pdf cat 1-endeast output rotated.pdf