🔍 sitemap

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()