Add sitemap generation

Initially the rel="alternate" hreflang="xx" links in the sitemap caused the
size of the file to increase exponentially as additional languages were added.
The current implementation has a single sitemap.xml for each language, with a
sitemap_index.xml at the root.

i2p2www/__init__.py

@@ -15,10 +15,26 @@ CANONICAL_DOMAIN = 'www.i2p2.de'
 BLOG_ENTRIES_PER_PAGE = 20
 MEETINGS_PER_PAGE = 20
 
+SUPPORTED_LANGS = [
+    'en',
+    'es',
+    'zh',
+    'de',
+    'fr',
+    'it',
+    'nl',
+    'ru',
+    'sv',
+    'cs',
+    'ar',
+    'el',
+    ]
+
 TEMPLATE_DIR = os.path.join(os.path.dirname(__file__), 'pages')
 STATIC_DIR = os.path.join(os.path.dirname(__file__), 'static')
 BLOG_DIR = os.path.join(os.path.dirname(__file__), 'blog')
 MEETINGS_DIR = os.path.join(os.path.dirname(__file__), 'meetings/logs')
+SITE_DIR = os.path.join(TEMPLATE_DIR, 'site')
 MIRRORS_FILE = os.path.join(TEMPLATE_DIR, 'downloads/mirrors')
 
 

i2p2www/sitemap.py

@@ -0,0 +1,86 @@
+from flask import make_response, render_template, request, safe_join
+import os.path
+
+from i2p2www import SITE_DIR, SUPPORTED_LANGS
+from i2p2www.blog.helpers import get_blog_slugs
+from i2p2www.meetings.helpers import get_meetings_ids
+
+
+##########
+# Sitemaps
+
+def render_sitemap_index():
+    # Include the / at the end, so the language can be
+    # sandwiched between url_root and /sitemap.xml in
+    # the template.
+    url_root = request.url_root
+
+    # Render and return the sitemap index
+    response = make_response(render_template('global/sitemap_index.xml', url_root=url_root, langs=SUPPORTED_LANGS))
+    response.headers['Content-Type'] = 'application/xml'
+    return response
+
+def render_sitemap():
+    # Include the / at the end, so the language can be
+    # sandwiched between url_root and url.path in the
+    # template.
+    url_root = request.url_root
+    urls = []
+
+    # --------------
+    # Main site urls
+    # --------------
+    # walk over all directories/files
+    for v in os.walk(SITE_DIR):
+        # iterate over all files
+        pathbase = os.path.relpath(v[0], SITE_DIR)
+        for f in v[2]:
+            # ignore all non-.html files
+            if not f.endswith('.html'):
+                continue
+            path = pathbase
+            if f != 'index.html':
+                path = safe_join(pathbase, f[:-5])
+            if path.startswith('.'):
+                path = path[1:]
+            if not path.startswith('/'):
+                path = '/%s' % path
+            urls.append({
+                'path': path,
+                })
+
+    # ---------
+    # Blog urls
+    # ---------
+    urls.append({
+        'path': '/blog/',
+        })
+    blog_slugs = get_blog_slugs()
+    for slug in blog_slugs:
+        urls.append({
+            'path': '/blog/entry/%s' % slug,
+            })
+
+    # -------------
+    # Meetings urls
+    # -------------
+    urls.append({
+        'path': '/meetings/',
+        })
+    meetings = get_meetings_ids()
+    for id in meetings:
+        urls.append({
+            'path': '/meetings/%d' % id,
+            })
+
+    # --------------
+    # Downloads urls
+    # --------------
+    urls.append({
+        'path': '/download',
+        })
+
+    # Render and return the sitemap
+    response = make_response(render_template('global/sitemap.xml', url_root=url_root, langs=SUPPORTED_LANGS, urls=urls))
+    response.headers['Content-Type'] = 'application/xml'
+    return response

i2p2www/urls.py

@@ -68,3 +68,6 @@ url('/<string:f>.html', 'legacy.legacy_show')
 url('/hosts.txt', 'views.hosts')
 url('/robots.txt', 'views.robots')
 url('/favicon.ico', 'views.favicon')
+
+url('/sitemap_index.xml', 'sitemap.render_sitemap_index')
+url('/<lang:lang>/sitemap.xml', 'sitemap.render_sitemap')