Export Plone site into a directory tree of PDFs.

export.py

# spin up a local instance
# portal_workflows, allow everything for Anonymous, click update portal security
# bin/instance debug
# >>> for brain in app.Plone.portal_catalog():
# >>>    print brain.getURL().split('http://nohost/Plone/')[1]
# Paste paths into paths.txt
# More info on https://blog.niteo.co/export-plone-to-pdfs/

from subprocess import check_output
import os.path

f = open("paths.txt", "r")
for path in f.readlines():
    path = path[:-1]  # remove \n
    filename = path.split("/")[-1]
    folder = "/".join(path.split("/")[:-1])

    if os.path.isfile(f"output/{folder}/{filename}") or os.path.isfile(
        f"output/{folder}/{filename}.pdf"
    ):
        print(f"skipping: {folder}/{filename}")
        continue
    else:
        print(f"processing: {path}")
    cmd = f"mkdir -p output/{folder}"
    output = check_output(cmd, shell=True).decode()

    if filename.endswith(("pdf", "jpg", "jpeg", "png")):
        cmd = f"wget http://localhost:8080/Plone/{path}"
    else:
        cmd = (
            "/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome "
            "--headless --disable-gpu --no-margins --run-all-compositor-stages-before-draw "
            f"--print-to-pdf={filename}.pdf "
            f"http://localhost:8080/Plone/{path}"
        )
    check_output(cmd, shell=True, cwd=f"output/{folder}")