1
0
Fork 0
www/build.py

83 lines
2.4 KiB
Python
Raw Normal View History

2023-09-11 22:38:24 +00:00
#!/usr/bin/env python
import argparse
import copy
import os
import pathlib
import shutil
import bs4
import markdown
def main():
parser = argparse.ArgumentParser()
parser.add_argument("src", help="source directory", nargs="?", default="./src")
parser.add_argument("out", help="output directory", nargs="?", default="./out")
args = parser.parse_args()
2023-09-12 00:15:40 +00:00
src = pathlib.Path(args.src)
out = pathlib.Path(args.out)
2023-09-11 22:38:24 +00:00
2023-09-11 23:17:14 +00:00
md = markdown.Markdown(extensions=["attr_list", "footnotes", "meta"])
2023-09-11 22:38:24 +00:00
# Clean the output directory
if out.exists():
print("Removing ", out)
shutil.rmtree(out)
# Load the template
template = bs4.BeautifulSoup(
(src / ".template.html").read_text(encoding="utf8"),
features="html.parser")
2023-09-11 23:17:14 +00:00
count = 0
2023-09-12 00:15:40 +00:00
for dirpath, _, filenames in os.walk(src):
dirpath = pathlib.Path(dirpath).relative_to(src)
2023-09-11 22:38:24 +00:00
for filename in filenames:
if filename[0] == ".":
continue # Skip dotfiles
2023-09-11 23:17:14 +00:00
count += 1
2023-09-11 22:38:24 +00:00
# Future-proofing
if not filename.endswith(".html") and not filename.endswith(".md"):
raise Exception("Support for this filetype is not yet supported:", filename)
path = src / dirpath / filename
dest = out / dirpath / filename
os.makedirs(dest.parent, exist_ok=True)
content = path.read_text(encoding="utf8")
meta = {}
# Preprocess markdown into html
if dest.name.endswith(".md"):
print("Converting", path)
2023-09-11 23:17:14 +00:00
md.reset()
2023-09-11 22:38:24 +00:00
dest = dest.with_suffix(".html")
content = md.convert(content)
meta = md.Meta
# Inject content into the template
page_content = bs4.BeautifulSoup(content, features="html.parser")
page = copy.copy(template)
article = page.new_tag("article")
article.append(page_content)
page.article.replace_with(article)
# Apply metadata to the template
if meta_title := meta.get("title"):
title = "".join(meta_title)
page.title.string = title
page.header.h1.string = title
# Write the destination file
print("Writing ", dest)
dest.write_text(str(page))
2023-09-11 23:17:14 +00:00
print("Processed", count, "files")
2023-09-11 22:38:24 +00:00
if __name__ == "__main__":
main()