Site: the posts link to each other wherever they refer to one; check_site.py checks every link of the site

"The last post" and "the first post" in the LoRa, Gemini and S1 posts are
now links. check_site.py follows every link to another page of the site and
the #fragment it names, so a broken one fails the Site job.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EhqxQ49eCju4CzKYNjZzwT

site/tools/check_site.py

@@ -7,6 +7,7 @@ Usage: site/tools/check_site.py <built site folder>
   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.
+- Every link to another page of the site lands on a page that exists, and so does the #fragment it names.
 """
 import html.parser
 import os
@@ -29,9 +30,16 @@ class Page(html.parser.HTMLParser):
         self.lang = None
         self.loads = []  # (tag, url) of everything the page fetches by itself
         self.images_without_alt = 0
+        self.links = []  # href of every <a>
+        self.ids = set()  # every id and name: what a #fragment can name
 
     def handle_starttag(self, tag, attrs):
         a = dict(attrs)
+        for key in ("id", "name"):
+            if a.get(key):
+                self.ids.add(a[key])
+        if tag == "a" and a.get("href"):
+            self.links.append(a["href"])
         if tag == "html":
             self.lang = a.get("lang")
         if tag == "title":
@@ -56,6 +64,7 @@ class Page(html.parser.HTMLParser):
 
 problems = []
 pages = 0
+parsed = {}  # path of a page, from the site's root -> its Page
 for folder, _, files in os.walk(ROOT):
     for name in files:
         if not name.endswith(".html"):
@@ -65,6 +74,7 @@ for folder, _, files in os.walk(ROOT):
         p = Page()
         p.feed(open(path, encoding="utf-8").read())
         pages += 1
+        parsed["/" + shown.replace(os.sep, "/")] = (p, folder)
         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")
@@ -82,6 +92,31 @@ for folder, _, files in os.walk(ROOT):
                 if not os.path.exists(target):
                     problems.append(f"{shown}: {tag} {url} does not exist")
 
+def page_of(url_path):
+    """The built page a path of the site names: /guide/ is /guide/index.html."""
+    if url_path.endswith("/"):
+        return url_path + "index.html"
+    if os.path.isdir(os.path.join(ROOT, url_path.lstrip("/"))):
+        return url_path + "/index.html"
+    return url_path
+
+
+for shown_path, (p, folder) in parsed.items():
+    for href in p.links:
+        u = urllib.parse.urlparse(href)
+        if u.scheme in ("mailto", "tel") or (u.netloc and u.netloc != HOST):
+            continue
+        if not u.path:  # "#fragment": this page
+            target = shown_path
+        elif u.path.startswith("/"):
+            target = page_of(urllib.parse.unquote(u.path))
+        else:
+            target = page_of(os.path.normpath(os.path.join(os.path.dirname(shown_path), urllib.parse.unquote(u.path))).replace(os.sep, "/"))
+        if not os.path.exists(os.path.join(ROOT, target.lstrip("/"))):
+            problems.append(f"{shown_path.lstrip('/')}: link {href} goes nowhere")
+        elif u.fragment and target in parsed and u.fragment not in parsed[target][0].ids:
+            problems.append(f"{shown_path.lstrip('/')}: link {href}: no #{u.fragment} on that page")
+
 if not pages:
     problems.append(f"no pages found in {ROOT}")
 for p in problems: