From 2b6a2d3db4a5d923b964b604c9f41938b0b9e7f6 Mon Sep 17 00:00:00 2001 From: gfxmonk Date: Sat, 1 May 2010 00:08:23 +1000 Subject: [PATCH] removing empty paragraphs is not very useful, and can break some (stupid) websites --- readability/readability.py | 5 ----- 1 file changed, 5 deletions(-) diff --git a/readability/readability.py b/readability/readability.py index 3b4dcbd..9c5f5c6 100755 --- a/readability/readability.py +++ b/readability/readability.py @@ -231,11 +231,6 @@ class Document: for elem in self.tags(node, "form", "iframe"): elem.extract() - # remove empty

tags - for elem in node.findAll("p"): - if not (elem.string or elem.contents): - elem.extract() - # Conditionally clean s,