PDF to Markdown with Python

Layout-aware and quick: the PDF to Markdown output keeps headings and ruled tables. PyMuPDF is AGPL-licensed, so check the terms before shipping it inside a closed product.

# pip install pymupdf4llm
import pathlib
import pymupdf4llm

md = pymupdf4llm.to_markdown("report.pdf")
pathlib.Path("report.md").write_text(md, encoding="utf-8")

Best for ruled tables. By default it only finds tables drawn with lines; borderless grids need custom settings. The helper writes each table as a pipe table.

# pip install pdfplumber
import pdfplumber

def table_to_md(rows):
    rows = [[(c or "").replace("|", "\\|").strip() for c in r] for r in rows]
    head, body = rows[0], rows[1:]
    lines = ["| " + " | ".join(head) + " |", "|" + " --- |" * len(head)]
    lines += ["| " + " | ".join(r) + " |" for r in body]
    return "\n".join(lines)

with pdfplumber.open("invoice.pdf") as pdf:
    for page in pdf.pages:
        for table in page.extract_tables():
            print(table_to_md(table), end="\n\n")

A PDF to Markdown loop: it reads every file in a pdfs folder and writes one .md file per input.

# pip install pymupdf4llm
import pathlib
import pymupdf4llm

out = pathlib.Path("markdown")
out.mkdir(exist_ok=True)
for pdf in sorted(pathlib.Path("pdfs").glob("*.pdf")):
    md = pymupdf4llm.to_markdown(str(pdf))
    (out / f"{pdf.stem}.md").write_text(md, encoding="utf-8")
    print("wrote", out / f"{pdf.stem}.md")