readabilite: run the new cleaning code

2018-10-25 01:08:25 +02:00
parent 58fe5243af
commit 7d005e9a65
1 changed files with 8 additions and 0 deletions
--- a/morss/readabilite.py
+++ b/morss/readabilite.py
@@ -132,6 +132,12 @@ def write_score_all(root, grades):
        node.attrib['score'] = str(int(grades.get(node, 0)))


+def clean_root(root):
+    for node in list(root):
+        clean_root(node)
+        clean_node(node)
+
+
 def clean_node(node):
    parent = node.getparent()

@@ -277,4 +283,6 @@ def get_article(data, url=None, encoding=None):
    if url:
        best.make_links_absolute(url)

+    clean_root(best)
+
    return lxml.etree.tostring(best, pretty_print=True)