1
0
Fork 0
mirror of https://github.com/tldr-pages/tldr.git synced 2025-04-22 09:22:07 +02:00
tldr/scripts/pdf/render.py
K.B.Dharun Krishna e35b482300
scripts: build and deploy PDF pages for translations (#10969)
* scripts: build and deploy PDF pages for translations

Signed-off-by: K.B.Dharun Krishna <kbdharunkrishna@gmail.com>

* render.py: fix typo in filename description

---------

Signed-off-by: K.B.Dharun Krishna <kbdharunkrishna@gmail.com>
2023-10-22 02:34:22 +05:30

102 lines
3.7 KiB
Python

#!/usr/bin/env python3
# SPDX-License-Identifier: MIT
"""
A Python script to generate a single PDF document with all the `tldr` pages. It works by generating
intermediate HTML files from existing md files using Python-markdown, applying desired formatting
through CSS, and finally rendering them as PDF. There is no LaTeX dependency for generating the PDF.
"""
import os
import sys
import glob
import markdown
import argparse
from datetime import datetime
from weasyprint import HTML
def main(loc, colorscheme, output_filename):
# Checking correctness of path
if not os.path.isdir(loc):
print("Invalid directory. Please try again!", file=sys.stderr)
sys.exit(1)
# Set up css style sheets
csslist = ["basic.css"]
if colorscheme != "basic":
csslist.append(f"{colorscheme}.css")
# A string that stores all pages in HTML format
html = (
'<!doctype html><html><head><meta charset="utf-8"></head>'
+ "<body><h1 class=title-main>tldr pages book</h1>"
+ "<div class=title-sub>Simplified and community-driven man pages</div>"
+ "<div class=title-sub><em><small>Generated on "
+ datetime.now().strftime("%c")
+ "</small></em></div><br><br>"
+ "<div class=title-sub>Website: <a href=https://tldr.sh>https://tldr.sh</a></div><br>"
+ "<div class=title-sub>GitHub: <a href=https://github.com/tldr-pages/tldr>https://github.com/tldr-pages/tldr</a></div><br>"
+ '<p style="page-break-before: always" ></p>'
)
# Writing names of all directories inside 'pages' to a list
for operating_sys in sorted(os.listdir(loc)):
# Required string to create directory title pages
html += (
"<h1 class=title-dir>"
+ operating_sys.capitalize()
+ "</h1>"
+ '<p style="page-break-before: always" ></p>'
)
# Conversion of Markdown to HTML string
for page_number, md in enumerate(
sorted(glob.glob(os.path.join(loc, operating_sys, "*.md"))), start=1
):
with open(md, "r") as inp:
text = inp.readlines()
# modify our page to have an H2 header, so that it is grouped under
# the H1 header for the directory
text[0] = "<h2 class='title-page'>" + text[0][2:] + "</h2>"
for line in text:
if line.startswith(">"):
line = "####" + line[1:]
html += markdown.markdown(line)
html += '<p style="page-break-before: always" ></p>'
print(f"Rendered page {page_number} of the directory {operating_sys}")
html += "</body></html>"
# Writing the PDF to disk
print("\nConverting all pages to PDF...")
HTML(string=html).write_pdf(output_filename, stylesheets=csslist)
if os.path.exists(output_filename):
print(f"\nCreated {output_filename} in the current directory!\n")
if __name__ == "__main__":
# Parsing the arguments
parser = argparse.ArgumentParser(
prog="tldr-pages-to-pdf",
description="A Python script to generate a single PDF document with all the `tldr` pages.",
)
parser.add_argument("dir_path", help="Path to the 'pages' directory")
parser.add_argument(
"-c",
"--color",
choices=["solarized-light", "solarized-dark", "basic"],
default="basic",
help="Color scheme of the PDF",
)
parser.add_argument(
"-o",
"--output",
default="tldr-book.pdf",
help="Custom filename for the output PDF (default is 'tldr-book.pdf')",
)
args = parser.parse_args()
main(args.dir_path, args.color, args.output)