diff options
| -rw-r--r-- | generators/generators.py | 35 | ||||
| -rwxr-xr-x | pyblog | 33 |
2 files changed, 36 insertions, 32 deletions
diff --git a/generators/generators.py b/generators/generators.py index 06a34743..8887bddb 100644 --- a/generators/generators.py +++ b/generators/generators.py @@ -11,8 +11,12 @@ import dateutil import io import subprocess +import lxml.etree as ET + from config.config import * +from utils import utils + def generate_menu(): """Generate menu.""" @@ -348,3 +352,34 @@ def generate_index(feed): except subprocess.CalledProcessError: sys.stderr.write("error: failed to generate index.html\n") os.remove(tmppath) + +def generate_sitemap(feed): + """Generate sitemap.xml.""" + sitemap = ET.Element("urlset", xmlns="http://www.sitemaps.org/schemas/sitemap/0.9") + # index + sitemap.append(utils.make_sitemap_url_element(BLOG_HOME, feed.updated, "daily", 1.0)) + # other top level pages + for name in os.listdir(BUILDDIR): + if (not name.endswith(".html") or name == "index.html" or + re.match("google[a-z0-9]+\.html", name)): # exclude Google's site ownership verification file + continue + link = urllib.parse.urljoin(BLOG_HOME, name) + fullpath = os.path.join(BUILDDIR, name) + # try to extract updated time + updated = None + with open(fullpath, encoding="utf-8") as htmlobj: + soup = bs4.BeautifulSoup(htmlobj.read(), "lxml") + if soup.footer is not None: + updated_tag = soup.footer.find(attrs={"class": "updated"}) + if updated_tag is not None: + updated = dateutil.parser.parse(updated_tag.text) + sitemap.append(utils.make_sitemap_url_element(link, updated, "monthly", 0.9)) + + # blog entries + for entry in feed.entries: + sitemap.append(utils.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')) + sys.stderr.write("wrote sitemap.xml\n") @@ -51,37 +51,6 @@ from config.config import * from generators import generators -def generate_sitemap(feed): - """Generate sitemap.xml.""" - sitemap = ET.Element("urlset", xmlns="http://www.sitemaps.org/schemas/sitemap/0.9") - # index - sitemap.append(utils.make_sitemap_url_element(BLOG_HOME, feed.updated, "daily", 1.0)) - # other top level pages - for name in os.listdir(BUILDDIR): - if (not name.endswith(".html") or name == "index.html" or - re.match("google[a-z0-9]+\.html", name)): # exclude Google's site ownership verification file - continue - link = urllib.parse.urljoin(BLOG_HOME, name) - fullpath = os.path.join(BUILDDIR, name) - # try to extract updated time - updated = None - with open(fullpath, encoding="utf-8") as htmlobj: - soup = bs4.BeautifulSoup(htmlobj.read(), "lxml") - if soup.footer is not None: - updated_tag = soup.footer.find(attrs={"class": "updated"}) - if updated_tag is not None: - updated = dateutil.parser.parse(updated_tag.text) - sitemap.append(utils.make_sitemap_url_element(link, updated, "monthly", 0.9)) - - # blog entries - for entry in feed.entries: - sitemap.append(utils.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')) - sys.stderr.write("wrote sitemap.xml\n") - def rewrite_title(): """Override the title of some page for a better render""" sys.stderr.write("Overriding some titles\n") @@ -378,7 +347,7 @@ def generate_index_and_feed(): rssxml.write("%s\n" % rss.dump_rss(FEED_MAX_ENTRIES)) sys.stderr.write("wrote rss.xml\n") - generate_sitemap(feed) + generators.generate_sitemap(feed) # exclude_list is only inialized once to avoid constant disk IO |