diff options
Diffstat (limited to 'pyblog')
| -rwxr-xr-x | pyblog | 63 |
1 files changed, 43 insertions, 20 deletions
@@ -26,6 +26,22 @@ import colorama import dateutil.parser import dateutil.tz +# TODO: put blog configurations in a config file + +############################# BLOG CONFIGURATIONS ############################## +# Safe to customize +BLOG_HOME = "http://zmwangx.github.io" +BLOG_TITLE = "dl? cmplnts?" +AUTHOR = "Zhiming Wang" +AUTHOR_EMAIL = "zmwangx@gmail.com" +ICON_PATH = "img/icon-400.png" # set to None to leave it out +########################## END OF BLOG CONFIGURATIONS ########################## + + +########################### GENERATOR CONFIGURATIONS ########################### +# Do not touch unless you know what you are doing. +GENERATOR_NAME = "pyblog" +GENERATOR_HOME_PAGE = "https://github.com/zmwangx/zmwangx.github.io" ROOTDIR = os.path.dirname(os.path.realpath(__file__)) SOURCEDIR = os.path.join(ROOTDIR, "source") @@ -38,6 +54,7 @@ ATOM = os.path.join(BUILDDIR, "atom.xml") INDEXHTML = os.path.join(BUILDDIR, "index.html") FEED_MAX_ENTRIES = 20 +####################### END OF GENERATOR CONFIGURATIONS ######################## # Hack ET to support CDATA. @@ -275,7 +292,9 @@ def make_sitemap_url_element(atomlink, atomupdated, changefreq, priority): 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)) + # index + sitemap.append(make_sitemap_url_element(BLOG_HOME, feed.updated, "daily", 1.0)) + # blog entries 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") @@ -286,28 +305,30 @@ def generate_sitemap(feed): def generate_index_and_feed(): """Generate index.html and atom feed.""" + # pylint: disable=too-many-statements sys.stderr.write("generating atom feed\n") # initialize feed feed = AtomFeed() - # TODO: Put hard-coded values in a config file - feed.author = ET.fromstring("<author>" - "<name>Zhiming Wang</name>" - "<uri>https://github.com/zmwangx</uri>" - "<email>zmwangx@gmail.com</email>" - "</author>") - feed.generator = ET.Element("generator", uri="https://github.com/zmwangx/zmwangx.github.io") - feed.generator.text = "pyblog" - feed.icon = ET.Element("icon") - feed.icon.text = "http://zmwangx.github.io/img/icon-400.png" - feed.id_text = "http://zmwangx.github.io" + feed.author = ET.fromstring( + "<author>" + "<name>{author}</name>" + "<uri>{home}</uri>" + "<email>{email}</email>" + "</author>".format(author=AUTHOR, home=BLOG_HOME, email=AUTHOR_EMAIL)) + feed.generator = ET.Element("generator", uri=GENERATOR_HOME_PAGE) + feed.generator.text = GENERATOR_NAME + if ICON_PATH is not None: + feed.icon = ET.Element("icon") + feed.icon.text = "{home}/{icon_path}".format(home=BLOG_HOME, icon_path=ICON_PATH) + feed.id_text = BLOG_HOME feed.id = ET.Element("id") feed.id.text = feed.id_text feed.links = [ - ET.Element("link", href="http://zmwangx.github.io/atom.xml", rel="self"), - ET.Element("link", href="http://zmwangx.github.io/"), + ET.Element("link", href="{home}/atom.xml".format(home=BLOG_HOME), rel="self"), + ET.Element("link", href=BLOG_HOME), ] - feed.title_text = "dl? cmplnts?" - feed.title = ET.fromstring("<title>%s</title>" % feed.title_text) + feed.title_text = BLOG_TITLE + feed.title = ET.fromstring("<title>{title}</title>".format(title=BLOG_TITLE)) # update time will be set after everthing finishes for name in os.listdir(os.path.join(BUILDDIR, "blog")): @@ -318,7 +339,7 @@ def generate_index_and_feed(): with open(htmlpath, encoding="utf-8") as htmlfile: soup = bs4.BeautifulSoup(htmlfile.read()) entry.author = feed.author # assume it's always the same author - entry.id_text = "%s/blog/%s" % (feed.id_text, name) + entry.id_text = "%s/blog/%s" % (BLOG_HOME, name) entry.id = ET.Element("id") entry.id.text = entry.id_text entry.relpath = "/blog/%s" % name @@ -333,8 +354,10 @@ def generate_index_and_feed(): entry.updated.text = entry.updated_datetime.isoformat() # extract the article content without header and footer article = soup.article - article.header.extract() - article.footer.extract() + if article.header is not None: + article.header.extract() + if article.footer is not None: + article.footer.extract() entry.content_html = ''.join([str(content) for content in article.contents]) entry.content = ET.Element("content", type="html") @@ -443,7 +466,7 @@ def generate_blog(fresh=False, report_total_errors=True): sys.stderr.write("copying %s\n" % relpath) shutil.copy(srcpath, dstpath) elif extension == "md": - sys.stderr.write("generating %s\n" % relpath) + sys.stderr.write("compiling %s\n" % relpath) pandoc_args = [ "pandoc", srcpath, "--template", HTMLTEMPLATE, |