Merge pull request #1723 from getnikola/prettier-html

ralsina · ralsina · commit abdc591eb9d3 · 2015-05-19T17:07:31.000-03:00
make lxml reformat HTML
diff --git a/CHANGES.txt b/CHANGES.txt
@@ -4,6 +4,7 @@ New in master
 Features
 --------
 
+* Cleaner formatting of HTML output
 * Allowing category hierarchies via new option CATEGORY_ALLOW_HIERARCHIES
   (Issue #1520)
 
diff --git a/nikola/nikola.py b/nikola/nikola.py
@@ -969,7 +969,8 @@ def render_template(self, template_name, output_name, context):
         src = "/".join(src.split(os.sep))
 
         utils.makedirs(os.path.dirname(output_name))
-        doc = lxml.html.document_fromstring(data)
+        parser = lxml.html.HTMLParser(remove_blank_text=True)
+        doc = lxml.html.document_fromstring(data, parser)
         doc.rewrite_links(lambda dst: self.url_replacer(src, dst, context['lang']))
         data = b'<!DOCTYPE html>\n' + lxml.html.tostring(doc, encoding='utf8', method='html', pretty_print=True)
         with open(output_name, "wb+") as post_file:
