🔍 robots and other optimizations

.gitignore

@@ -2,4 +2,5 @@
 .venv
 
 # This should be generated on deploy
-static/feed.rss
+static/feed.rss
+static/sitemap.xml

CLAUDE.md

@@ -32,6 +32,12 @@ python scripts/generate_rss.py
 ```
 Run this after adding/updating comics to regenerate `static/feed.rss`.
 
+**Generate sitemap:**
+```bash
+python scripts/generate_sitemap.py
+```
+Run this after adding/updating comics to regenerate `static/sitemap.xml` for search engines.
+
 ## Architecture
 
 ### Data Layer: comics_data.py
@@ -134,6 +140,7 @@ Global context variables injected into all templates:
 - `static/images/icons/`: Navigation icons (first.png, previous.png, next.png, latest.png) used when `USE_ICON_NAV` is True
 - `static/images/`: Header images and other site graphics
 - `static/feed.rss`: Generated RSS feed (run `scripts/generate_rss.py`)
+- `static/sitemap.xml`: Generated sitemap (run `scripts/generate_sitemap.py`)
 
 ## Important Implementation Details
 

app.py

@@ -232,6 +232,30 @@ def api_comic(comic_id):
     return jsonify(comic)
 
 
+@app.route('/sitemap.xml')
+def sitemap():
+    """Serve the static sitemap.xml file"""
+    from flask import send_from_directory
+    return send_from_directory('static', 'sitemap.xml', mimetype='application/xml')
+
+
+@app.route('/robots.txt')
+def robots():
+    """Generate robots.txt dynamically with correct SITE_URL"""
+    from flask import Response
+    robots_txt = f"""# Sunday Comics - Robots.txt
+User-agent: *
+Allow: /
+
+# Sitemap location
+Sitemap: {SITE_URL}/sitemap.xml
+
+# Disallow API endpoints from indexing
+Disallow: /api/
+"""
+    return Response(robots_txt, mimetype='text/plain')
+
+
 @app.errorhandler(404)
 def page_not_found(e):
     """404 error handler"""

scripts/generate_sitemap.py

@@ -0,0 +1,88 @@
+#!/usr/bin/env python3
+# Sunday Comics - Sitemap generator
+# Copyright (c) 2025 Tomasita Cabrera
+# Licensed under the MIT License - see LICENSE file for details
+
+"""
+Script to generate a sitemap.xml file for the comic
+"""
+import sys
+import os
+from xml.etree.ElementTree import Element, SubElement, tostring
+from xml.dom import minidom
+
+# Add parent directory to path so we can import comics_data
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+from comics_data import COMICS, SITE_URL
+
+
+def generate_sitemap():
+    """Generate sitemap.xml from COMICS data"""
+    # Create sitemap root
+    urlset = Element('urlset', xmlns='http://www.sitemaps.org/schemas/sitemap/0.9')
+
+    # Add homepage
+    if COMICS:
+        latest_date = COMICS[-1]['date']
+        url = SubElement(urlset, 'url')
+        SubElement(url, 'loc').text = f'{SITE_URL}/'
+        SubElement(url, 'lastmod').text = latest_date
+        SubElement(url, 'changefreq').text = 'weekly'
+        SubElement(url, 'priority').text = '1.0'
+
+    # Add archive page
+    if COMICS:
+        latest_date = COMICS[-1]['date']
+        url = SubElement(urlset, 'url')
+        SubElement(url, 'loc').text = f'{SITE_URL}/archive'
+        SubElement(url, 'lastmod').text = latest_date
+        SubElement(url, 'changefreq').text = 'weekly'
+        SubElement(url, 'priority').text = '0.9'
+
+    # Add about page
+    url = SubElement(urlset, 'url')
+    SubElement(url, 'loc').text = f'{SITE_URL}/about'
+    SubElement(url, 'changefreq').text = 'monthly'
+    SubElement(url, 'priority').text = '0.7'
+
+    # Add all individual comic pages
+    for comic in COMICS:
+        url = SubElement(urlset, 'url')
+        SubElement(url, 'loc').text = f"{SITE_URL}/comic/{comic['number']}"
+        SubElement(url, 'lastmod').text = comic['date']
+        SubElement(url, 'changefreq').text = 'never'
+        SubElement(url, 'priority').text = '0.8'
+
+    # Convert to pretty XML
+    xml_str = minidom.parseString(tostring(urlset)).toprettyxml(indent='  ')
+
+    # Remove extra blank lines
+    xml_str = '\n'.join([line for line in xml_str.split('\n') if line.strip()])
+
+    return xml_str
+
+
+def main():
+    """Generate and save sitemap"""
+    # Get path to static folder
+    script_dir = os.path.dirname(os.path.abspath(__file__))
+    parent_dir = os.path.dirname(script_dir)
+    static_dir = os.path.join(parent_dir, 'static')
+
+    # Create static directory if it doesn't exist
+    os.makedirs(static_dir, exist_ok=True)
+
+    # Generate sitemap
+    sitemap_content = generate_sitemap()
+
+    # Save to file
+    sitemap_file = os.path.join(static_dir, 'sitemap.xml')
+    with open(sitemap_file, 'w', encoding='utf-8') as f:
+        f.write(sitemap_content)
+
+    print(f"Sitemap generated: {sitemap_file}")
+    print(f"Total URLs: {len(COMICS) + 3}")  # comics + homepage + archive + about
+
+
+if __name__ == '__main__':
+    main()

templates/archive.html

@@ -24,7 +24,8 @@
                 <a href="{{ url_for('comic', comic_id=comic.number) }}">
                     <img src="{{ url_for('static', filename='images/thumbs/' + comic.filename) }}"
                          onerror="this.onerror=null; this.src='{{ url_for('static', filename='images/thumbs/default.jpg') }}';"
-                         alt="{{ comic.title if comic.title else '#' ~ comic.number }}">
+                         alt="{{ comic.title if comic.title else '#' ~ comic.number }}"
+                         loading="lazy">
                     <div class="archive-info">
                         {% if not archive_full_width %}
                         <h3>#{{ comic.number }}{% if comic.title %}: {{ comic.title }}{% endif %}</h3>

templates/base.html

@@ -7,6 +7,7 @@
 
     <!-- SEO Meta Tags -->
     <meta name="description" content="{% block meta_description %}A webcomic about life, the universe, and everything{% endblock %}">
+    <link rel="canonical" href="{% block canonical %}{{ site_url }}{{ request.path }}{% endblock %}">
 
     <!-- Open Graph / Facebook -->
     <meta property="og:type" content="website">

templates/comic.html

@@ -4,6 +4,27 @@
 
 {% block og_image %}{{ site_url }}/static/images/thumbs/{{ comic.filename }}{% endblock %}
 
+{% block extra_css %}
+<script type="application/ld+json">
+{
+  "@context": "https://schema.org",
+  "@type": "ComicStory",
+  "name": "{{ comic.title if comic.title else '#' ~ comic.number }}",
+  "datePublished": "{{ comic.date }}",
+  "image": "{{ site_url }}/static/images/comics/{{ comic.filename }}",
+  "thumbnailUrl": "{{ site_url }}/static/images/thumbs/{{ comic.filename }}",
+  "description": "{{ comic.alt_text }}",
+  "isPartOf": {
+    "@type": "ComicSeries",
+    "name": "{{ comic_name }}",
+    "url": "{{ site_url }}"
+  },
+  "position": "{{ comic.number }}",
+  "url": "{{ site_url }}/comic/{{ comic.number }}"
+}
+</script>
+{% endblock %}
+
 {% block content %}
 <!-- ARIA live region for screen reader announcements -->
 <div aria-live="polite" aria-atomic="true" class="sr-only" id="comic-announcer"></div>
@@ -29,7 +50,8 @@
             {% else %}
             <img src="{{ url_for('static', filename='images/comics/' + comic.filename) }}"
                  alt="{{ comic.title if comic.title else '#' ~ comic.number }}"
-                 title="{{ comic.alt_text }}">
+                 title="{{ comic.alt_text }}"
+                 loading="eager">
             {% endif %}
         </a>
         {% else %}
@@ -43,7 +65,8 @@
             {% else %}
             <img src="{{ url_for('static', filename='images/comics/' + comic.filename) }}"
                  alt="{{ comic.title if comic.title else '#' ~ comic.number }}"
-                 title="{{ comic.alt_text }}">
+                 title="{{ comic.alt_text }}"
+                 loading="eager">
             {% endif %}
         {% endif %}
     </div>