blob: 4d34cd7079741d94e49f6ce5b93cba3715f9924a (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
|
#!/usr/bin/env python3
"""Generate sitemap.xml from local HTML files."""
from __future__ import annotations
from pathlib import Path
from datetime import datetime, timezone
import re
ROOT = Path(__file__).resolve().parents[1]
SITE = "https://www.sillylaird.ca"
EXCLUDE_FILES = {
"404.html",
"50x.html",
}
EXCLUDE_DIRS = {"partials", ".git"}
def should_skip(path: Path) -> bool:
if any(part in EXCLUDE_DIRS for part in path.parts):
return True
if path.name.endswith("~"):
return True
if path.name in EXCLUDE_FILES:
return True
return False
def url_for_path(path: Path) -> str:
rel = path.relative_to(ROOT).as_posix()
if rel == "index.html":
return SITE + "/"
if rel.endswith("/index.html"):
return SITE + "/" + rel[:-len("index.html")]
return SITE + "/" + rel
def lastmod_for_path(path: Path) -> str:
ts = path.stat().st_mtime
dt = datetime.fromtimestamp(ts, tz=timezone.utc)
return dt.strftime("%Y-%m-%d")
def main() -> int:
urls = []
for html in ROOT.rglob("*.html"):
if should_skip(html):
continue
urls.append((url_for_path(html), lastmod_for_path(html)))
urls.sort(key=lambda item: item[0])
lines = [
"<?xml version=\"1.0\" encoding=\"UTF-8\"?>",
'<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">',
]
for loc, lastmod in urls:
lines.append(" <url>")
lines.append(f" <loc>{loc}</loc>")
lines.append(f" <lastmod>{lastmod}</lastmod>")
lines.append(" </url>")
lines.append("</urlset>")
(ROOT / "sitemap.xml").write_text("\n".join(lines) + "\n", encoding="utf-8")
return 0
if __name__ == "__main__":
raise SystemExit(main())
|
