Public Access
twislaandClaude Sonnet 5.5
8f4b5e0ddc
A Zola site in site/, from the design: both themes on the device's palette, notched shapes, self-hosted fonts, the wordmark and icons, two generated hero drawings, nine App cards (the mesh messenger marked planned), real screenshots, the updates and build sections. The Install page builds ESP Web Tools' manifest in the browser from the Gitea API (it needs Caddy to allow the origin), refuses any download that isn't on the project's server, and falls back to the esptool steps. Downloads lists the releases. The focus ring shows on notched controls. A page checker fails the build if a page loads from another origin. Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01EhqxQ49eCju4CzKYNjZzwT
91 lines
3.5 KiB
Python
Executable File
91 lines
3.5 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
"""Checks a built site (docs/milestones/W1.md): what the pages promise, kept.
|
|
|
|
Usage: site/tools/check_site.py <built site folder>
|
|
|
|
- No page loads anything from another origin: no script, stylesheet, image, font, frame or preload
|
|
from elsewhere (links a visitor follows are fine).
|
|
- Every page has a title, a description and a language, and every image has an alt attribute.
|
|
- Every file a page references on this site exists.
|
|
"""
|
|
import html.parser
|
|
import os
|
|
import re
|
|
import sys
|
|
import urllib.parse
|
|
|
|
ROOT = sys.argv[1] if len(sys.argv) > 1 else "public"
|
|
HERE = os.path.dirname(os.path.abspath(__file__))
|
|
BASE = re.search(r'base_url\s*=\s*"([^"]+)"', open(os.path.join(HERE, "..", "config.toml")).read()).group(1)
|
|
HOST = urllib.parse.urlparse(BASE).netloc
|
|
|
|
|
|
class Page(html.parser.HTMLParser):
|
|
def __init__(self):
|
|
super().__init__()
|
|
self.title = False
|
|
self.has_title = False
|
|
self.has_description = False
|
|
self.lang = None
|
|
self.loads = [] # (tag, url) of everything the page fetches by itself
|
|
self.images_without_alt = 0
|
|
|
|
def handle_starttag(self, tag, attrs):
|
|
a = dict(attrs)
|
|
if tag == "html":
|
|
self.lang = a.get("lang")
|
|
if tag == "title":
|
|
self.title = True
|
|
if tag == "meta" and a.get("name") == "description" and a.get("content"):
|
|
self.has_description = True
|
|
if tag in ("script", "img", "iframe", "frame", "embed", "source", "video", "audio") and a.get("src"):
|
|
self.loads.append((tag, a["src"]))
|
|
if tag == "link" and a.get("href") and a.get("rel", "") in ("stylesheet", "preload", "icon", "modulepreload", "prefetch"):
|
|
self.loads.append(("link " + a["rel"], a["href"]))
|
|
if tag == "img" and "alt" not in a:
|
|
self.images_without_alt += 1
|
|
|
|
def handle_data(self, data):
|
|
if self.title and data.strip():
|
|
self.has_title = True
|
|
|
|
def handle_endtag(self, tag):
|
|
if tag == "title":
|
|
self.title = False
|
|
|
|
|
|
problems = []
|
|
pages = 0
|
|
for folder, _, files in os.walk(ROOT):
|
|
for name in files:
|
|
if not name.endswith(".html"):
|
|
continue
|
|
path = os.path.join(folder, name)
|
|
shown = os.path.relpath(path, ROOT)
|
|
p = Page()
|
|
p.feed(open(path, encoding="utf-8").read())
|
|
pages += 1
|
|
if not p.has_title: problems.append(f"{shown}: no title")
|
|
if not p.has_description: problems.append(f"{shown}: no description")
|
|
if not p.lang: problems.append(f"{shown}: no language")
|
|
if p.images_without_alt: problems.append(f"{shown}: {p.images_without_alt} image(s) without alt")
|
|
for tag, url in p.loads:
|
|
u = urllib.parse.urlparse(url)
|
|
if u.netloc and u.netloc != HOST:
|
|
problems.append(f"{shown}: {tag} loads {url} from another origin")
|
|
elif not u.netloc and not u.scheme:
|
|
target = os.path.join(ROOT, u.path.lstrip("/")) if u.path.startswith("/") else os.path.join(folder, u.path)
|
|
if u.path and not os.path.exists(target):
|
|
problems.append(f"{shown}: {tag} {url} does not exist")
|
|
elif u.netloc == HOST:
|
|
target = os.path.join(ROOT, u.path.lstrip("/"))
|
|
if not os.path.exists(target):
|
|
problems.append(f"{shown}: {tag} {url} does not exist")
|
|
|
|
if not pages:
|
|
problems.append(f"no pages found in {ROOT}")
|
|
for p in problems:
|
|
print("site check:", p)
|
|
print(f"site check: {pages} pages, {len(problems)} problem(s)")
|
|
sys.exit(1 if problems else 0)
|