From d23133f6107551b49ff5c2d106efc411333da4c1 Mon Sep 17 00:00:00 2001
From: Zhiming Wang <zmwangx@gmail.com>
Date: Tue, 5 May 2015 23:24:34 -0700
Subject: add sitemap.xml and robots.txt
---
pyblog | 48 ++++++++++++++++++++++++++++++++++++++++++++++--
1 file changed, 46 insertions(+), 2 deletions(-)
(limited to 'pyblog')
diff --git a/pyblog b/pyblog
index ce5c7986..c6945734 100755
--- a/pyblog
+++ b/pyblog
@@ -239,6 +239,48 @@ def generate_index(feed):
os.remove(tmppath)
+def make_sitemap_url_element(atomlink, atomupdated, changefreq, priority):
+ """Make a sitemap <url> element.
+
+ Parameters
+ ----------
+ atomlink : xml.etree.ElementTree.Element
+ atom:link element, e.g., <link href="http://zmwangx.github.io/"/>
+ atomupdated : xml.etree.ElementTree.Element
+ atom:updated element, e.g., <updated>2015-05-05T22:38:42-07:00</updated>
+ changefreq : {"always", "hourly", "daily", "weekly", "monthly", "yearly", "never"}
+ priority : {1.0, 0.9, 0.8, 0.7, 0.6, 0.5, 0.4, 0.3, 0.2, 0.1}
+
+ """
+
+ urlelem = ET.Element("url")
+ loc = ET.Element("loc")
+ loc.text = atomlink.attrib["href"]
+ lastmod = ET.Element("lastmod")
+ lastmod.text = atomupdated.text
+ changefreq_elem = ET.Element("changefreq")
+ changefreq_elem.text = changefreq
+ priority_elem = ET.Element("priority")
+ priority_elem.text = "%.1f" % priority
+ urlelem.append(loc)
+ urlelem.append(lastmod)
+ urlelem.append(changefreq_elem)
+ urlelem.append(priority_elem)
+ return urlelem
+
+
+def generate_sitemap(feed):
+ """Generate sitemap.xml."""
+ sitemap = ET.Element("urlset", xmlns="http://www.sitemaps.org/schemas/sitemap/0.9")
+ sitemap.append(make_sitemap_url_element(feed.links[1], feed.updated, "daily", 1.0))
+ for entry in feed.entries:
+ sitemap.append(make_sitemap_url_element(entry.link, entry.updated, "monthly", 0.9))
+ sitemappath = os.path.join(BUILDDIR, "sitemap.xml")
+ with open(sitemappath, "w", encoding="utf-8") as sitemapfile:
+ sitemapfile.write('<?xml version="1.0" encoding="UTF-8"?>\n%s\n' %
+ ET.tostring(sitemap).decode('utf-8'))
+
+
def generate_index_and_feed():
"""Generate index.html and atom feed."""
sys.stderr.write("generating atom feed\n")
@@ -309,6 +351,8 @@ def generate_index_and_feed():
atom.write("%s\n" % feed.dump_feed())
sys.stderr.write("wrote atom.xml\n")
+ generate_sitemap(feed)
+
def generate_blog(fresh=False, report_total_errors=True):
"""Generate the blog in BUILDDIR.
@@ -371,7 +415,7 @@ def generate_blog(fresh=False, report_total_errors=True):
if name.startswith('.'):
continue
extension = name.split(".")[-1]
- if extension not in ["css", "jpg", "md", "png", "svg", "ico"]:
+ if extension not in ["css", "jpg", "md", "png", "svg", "ico", "txt"]:
continue
relpath = os.path.join(relroot, name)
@@ -387,7 +431,7 @@ def generate_blog(fresh=False, report_total_errors=True):
anything_modified = True
if srcpath == INDEXMD:
continue # index will be processed separately
- if extension in ["css", "jpg", "png", "svg", "ico"]:
+ if extension in ["css", "jpg", "png", "svg", "ico", "txt"]:
sys.stderr.write("copying %s\n" % relpath)
shutil.copy(srcpath, dstpath)
elif extension == "md":
--
cgit v1.2.1