feat(website): add CollectionPage JSON-LD to category, group, and subcategory pages

Co-Authored-By: Claude <noreply@anthropic.com>

website/build.py

@@ -118,14 +118,11 @@ def build_robots_txt() -> str:
     return f"User-agent: *\nContent-Signal: search=yes, ai-input=yes, ai-train=yes\nAllow: /\n\nSitemap: {SITEMAP_URL}\n"
 
 
-def build_homepage_json_ld(entries: Sequence[TemplateEntry], total_categories: int) -> dict:
+WEBSITE_ID = f"{SITE_URL}#website"
-    description = (
+
-        "An opinionated guide to the best Python frameworks, libraries, and tools. "
+
-        f"Explore {len(entries)} curated projects across {total_categories} categories, "
+def _item_list_payload(entries: Sequence[TemplateEntry]) -> dict:
-        "from AI and agents to data science and web development."
+    return {
-    )
-    website_id = f"{SITE_URL}#website"
-    item_list = {
         "@type": "ItemList",
         "numberOfItems": len(entries),
         "itemListElement": [
@@ -138,12 +135,20 @@ def build_homepage_json_ld(entries: Sequence[TemplateEntry], total_categories: i
             for i, entry in enumerate(entries, start=1)
         ],
     }
+
+
+def build_homepage_json_ld(entries: Sequence[TemplateEntry], total_categories: int) -> dict:
+    description = (
+        "An opinionated guide to the best Python frameworks, libraries, and tools. "
+        f"Explore {len(entries)} curated projects across {total_categories} categories, "
+        "from AI and agents to data science and web development."
+    )
     return {
         "@context": "https://schema.org",
         "@graph": [
             {
                 "@type": "WebSite",
-                "@id": website_id,
+                "@id": WEBSITE_ID,
                 "name": "Awesome Python",
                 "url": SITE_URL,
             },
@@ -153,13 +158,30 @@ def build_homepage_json_ld(entries: Sequence[TemplateEntry], total_categories: i
                 "name": "Awesome Python",
                 "url": SITE_URL,
                 "description": description,
-                "isPartOf": {"@id": website_id},
+                "isPartOf": {"@id": WEBSITE_ID},
-                "mainEntity": item_list,
+                "mainEntity": _item_list_payload(entries),
             },
         ],
     }
 
 
+def category_meta_description(name: str, entry_count: int, description: str) -> str:
+    suffix = description if description else "Part of the Awesome Python catalog."
+    return f"Explore {entry_count} curated Python projects in {name}. {suffix}"
+
+
+def build_category_json_ld(name: str, url: str, description: str, entries: Sequence[TemplateEntry]) -> dict:
+    return {
+        "@context": "https://schema.org",
+        "@type": "CollectionPage",
+        "name": f"{name} Python Libraries",
+        "url": url,
+        "description": description,
+        "isPartOf": {"@id": WEBSITE_ID},
+        "mainEntity": _item_list_payload(entries),
+    }
+
+
 def category_path(category: ParsedSection) -> str:
     return f"/categories/{category['slug']}/"
 
@@ -458,6 +480,15 @@ def build(repo_root: Path) -> None:
         group_categories: Sequence[ParsedSection] | None = None,
     ) -> None:
         page_dir.mkdir(parents=True, exist_ok=True)
+        category_description = category_meta_description(
+            category["name"], len(entries), category["description"]
+        )
+        category_json_ld = json.dumps(
+            build_category_json_ld(
+                category["name"], category_url, category_description, entries
+            ),
+            ensure_ascii=False,
+        ).replace("</", "<\\/")
         (page_dir / "index.html").write_text(
             tpl_category.render(
                 category=category,
@@ -470,6 +501,7 @@ def build(repo_root: Path) -> None:
                 filter_urls_json=filter_urls_json,
                 parent_category=parent_category,
                 group_categories=group_categories,
+                category_json_ld=category_json_ld,
             ),
             encoding="utf-8",
         )

website/templates/category.html

@@ -3,6 +3,9 @@
 {% block description %}Explore {{ entries | length }} curated Python projects in {{ category.name }}. {% if category.description %}{{ category.description }}{% else %}Part of the Awesome Python catalog.{% endif %}{% endblock %}
 {% block canonical_url %}{{ category_url }}{% endblock %}
 {% block alternate_links %}{% endblock %}
+{% block extra_head %}
+<script type="application/ld+json">{{ category_json_ld | safe }}</script>
+{% endblock %}
 {% block header %}
 <header class="category-hero">
   <div class="hero-sheen" aria-hidden="true"></div>

website/tests/test_build.py

@@ -518,6 +518,88 @@ class TestBuild:
         assert rendered_names == {e["name"] for e in entries}
         assert rendered_urls == {e["url"] for e in entries}
 
+    def test_category_page_contains_json_ld(self, tmp_path):
+        readme = textwrap.dedent("""\
+            # Awesome Python
+
+            Intro.
+
+            ---
+
+            **Tools**
+
+            ## Widgets
+
+            _Widget libraries._
+
+            - [w1](https://example.com/w1) - A widget.
+            - [w2](https://github.com/owner/w2) - A starred widget.
+
+            # Contributing
+
+            Help!
+        """)
+        (tmp_path / "README.md").write_text(readme, encoding="utf-8")
+        self._copy_real_templates(tmp_path)
+        build(tmp_path)
+
+        category_html = (tmp_path / "website" / "output" / "categories" / "widgets" / "index.html").read_text(encoding="utf-8")
+        marker = '<script type="application/ld+json">'
+        assert marker in category_html
+        start = category_html.index(marker) + len(marker)
+        end = category_html.index("</script>", start)
+        block = category_html[start:end]
+        assert "</script>" not in block
+        data = json.loads(block)
+
+        assert data["@context"] == "https://schema.org"
+        assert data["@type"] == "CollectionPage"
+        assert data["name"] == "Widgets Python Libraries"
+        assert data["url"] == "https://awesome-python.com/categories/widgets/"
+        assert data["description"] == "Explore 2 curated Python projects in Widgets. Widget libraries."
+        assert data["isPartOf"] == {"@id": "https://awesome-python.com/#website"}
+
+        item_list = data["mainEntity"]
+        assert item_list["@type"] == "ItemList"
+        assert item_list["numberOfItems"] == 2
+        names = {item["name"] for item in item_list["itemListElement"]}
+        urls = {item["url"] for item in item_list["itemListElement"]}
+        assert names == {"w1", "w2"}
+        assert urls == {"https://example.com/w1", "https://github.com/owner/w2"}
+        positions = sorted(item["position"] for item in item_list["itemListElement"])
+        assert positions == [1, 2]
+
+    def test_group_page_falls_back_to_default_description_in_json_ld(self, tmp_path):
+        readme = textwrap.dedent("""\
+            # T
+
+            ---
+
+            **AI & ML**
+
+            ## Deep Learning
+
+            - [dl1](https://example.com/dl1) - DL.
+
+            # Contributing
+
+            Done.
+        """)
+        self._copy_real_templates(tmp_path)
+        (tmp_path / "README.md").write_text(readme, encoding="utf-8")
+        build(tmp_path)
+
+        group_html = (tmp_path / "website" / "output" / "categories" / "ai-ml" / "index.html").read_text(encoding="utf-8")
+        marker = '<script type="application/ld+json">'
+        start = group_html.index(marker) + len(marker)
+        end = group_html.index("</script>", start)
+        data = json.loads(group_html[start:end])
+
+        assert data["@type"] == "CollectionPage"
+        assert data["name"] == "AI & ML Python Libraries"
+        assert data["url"] == "https://awesome-python.com/categories/ai-ml/"
+        assert data["description"] == "Explore 1 curated Python projects in AI & ML. Part of the Awesome Python catalog."
+
     def test_build_creates_subcategory_pages(self, tmp_path):
         readme = textwrap.dedent("""\
             # T