from pypdf import PdfWriter, PdfReader writer = PdfWriter() for pdf_path in list_of_pdfs: reader = PdfReader(pdf_path) for page in reader.pages: writer.add_page(page) writer.add_metadata(reader.metadata) # preserves source metadata
pdfplumber builds on pdfminer.six but adds intelligent layout analysis. Its secret weapon: and page objects as context managers . from pypdf import PdfWriter, PdfReader writer = PdfWriter()
from pathlib import Path from jinja2 import Environment, FileSystemLoader from weasyprint import HTML def generate_invoice(data: dict) -> bytes: template_dir = Path("templates") env = Environment(loader=FileSystemLoader(template_dir)) template = env.get_template("invoice.html") rendered = template.render(**data) return HTML(string=rendered).write_pdf() from pypdf import PdfWriter
with open("merged.pdf", "wb") as f: writer.write(f) attach_output_intent=True ) pdf.save("archival.pdf"
Modern Python (2025+) uses uv (blazing-fast package manager) with workspaces:
import pikepdf with pikepdf.open("document.pdf") as pdf: pdf.convert_to_pdfa( version="2b", output_intent=srgb_intent, attach_output_intent=True ) pdf.save("archival.pdf", compress_streams=True)