Merge pull request #180 from chripede/patch-2

Add inline_style option
lxml · Jul 24, 2016 · 0a43d0b · 0a43d0b
2 parents b3ffdd9 + c355493
commit 0a43d0b
Show file tree

Hide file tree

Showing 2 changed files with 27 additions and 3 deletions.
diff --git a/src/lxml/html/clean.py b/src/lxml/html/clean.py
@@ -112,7 +112,10 @@ class Cleaner(object):
         Removes any comments.
 
     ``style``:
-        Removes any style tags or attributes.
+        Removes any style tags.
+
+    ``inline_style``
+        Removes any style attributes.
 
     ``links``:
         Removes any ``<link>`` tags
@@ -191,6 +194,7 @@ class Cleaner(object):
     javascript = True
     comments = True
     style = False
+    inline_style = False
     links = True
     meta = True
     page_structure = True
@@ -314,6 +318,7 @@ def __call__(self, doc):
             kill_tags.add(etree.ProcessingInstruction)
         if self.style:
             kill_tags.add('style')
+        if self.inline_style:
             etree.strip_attributes(doc, 'style')
         if self.links:
             kill_tags.add('link')

diff --git a/src/lxml/html/tests/test_clean.txt b/src/lxml/html/tests/test_clean.txt
@@ -122,7 +122,7 @@
   </body>
 </html>
 
->>> print(Cleaner(style=True, links=True, add_nofollow=True, page_structure=False, safe_attrs_only=False).clean_html(doc))
+>>> print(Cleaner(style=True, inline_style=True, links=True, add_nofollow=True, page_structure=False, safe_attrs_only=False).clean_html(doc))
 <html>
   <head>
   </head>
@@ -142,6 +142,26 @@
   </body>
 </html>
 
+>>> print(Cleaner(style=True, inline_style=False, links=True, add_nofollow=True, page_structure=False, safe_attrs_only=False).clean_html(doc))
+<html>
+  <head>
+  </head>
+  <body>
+    <a href="">a link</a>
+    <a href="">a control char link</a>
+    <a href="">data</a>
+    <a href="#">another link</a>
+    <p>a paragraph</p>
+    <div style="display: none">secret EVIL!</div>
+    of EVIL!
+    Password:
+    <a href="evil-site" rel="nofollow">spam spam SPAM!</a>
+    <a href="http://example.com" rel="author nofollow">Author</a>
+    <a href="http://example.com" rel="nofollow">Text</a>
+    <img src="evil!">
+  </body>
+</html>
+
 >>> print(Cleaner(links=False, page_structure=False, javascript=True, host_whitelist=['example.com'], whitelist_tags=None).clean_html(doc))
 <html>
   <head>
@@ -165,4 +185,3 @@
     <img src="evil!">
   </body>
 </html>
-