"""Checks the internal links (pages and anchors) of a book built by mdBook. Usage: check_links.py . Exits with 1 if any link is broken. """ import pathlib import posixpath import re import sys import urllib.parse def main(): out = pathlib.Path(sys.argv[1]) pages = {p.relative_to(out).as_posix(): p.read_text() for p in out.rglob("*.html")} ids = {name: set(re.findall(r'id="([^"]+)"', html)) for name, html in pages.items()} broken = 0 for name, html in pages.items(): content = html[html.find("
") : html.find("
")] for link, anchor in re.findall(r'href="([^"#:]*\.html)(?:#([^"]*))?"', content): page = posixpath.normpath(posixpath.join(posixpath.dirname(name), link)) if page not in ids: print(f"{name}: missing page {page}") broken += 1 elif anchor and urllib.parse.unquote(anchor) not in ids[page]: print(f"{name}: missing anchor {page}#{urllib.parse.unquote(anchor)}") broken += 1 for anchor in re.findall(r'href="#([^"]+)"', content): if urllib.parse.unquote(anchor) not in ids[name]: print(f"{name}: missing anchor #{anchor}") broken += 1 print(f"{broken} broken links") sys.exit(1 if broken else 0) if __name__ == "__main__": main()