Fix for #52: <input type="hidden"> are not counted any more for "form removal" heuristic.

2014-09-22 15:31:31 +07:00 · 2014-09-22 15:31:31 +07:00 · 638f73f6a2
commit 638f73f6a2
parent 2fab5ffa6b
1 changed files with 1 additions and 0 deletions
--- a/readability/readability.py
+++ b/readability/readability.py
@ -452,6 +452,7 @@ class Document:
                for kind in ['p', 'img', 'li', 'a', 'embed', 'input']:
                    counts[kind] = len(el.findall('.//%s' % kind))
                counts["li"] -= 100
+                counts["input"] -= len(el.findall('.//input[@type="hidden"]'))

                # Count the text length excluding any surrounding whitespace
                content_length = text_length(el)