Improved remove_unlikely_candidates following an advice from issue #102

buriy · buriy · commit 537de2b8f6ac · 2018-05-07T12:28:25.000+07:00
diff --git a/readability/readability.py b/readability/readability.py
@@ -395,7 +395,7 @@ def score_node(self, elem):
         }
 
     def remove_unlikely_candidates(self):
-        for elem in self.html.iter():
+        for elem in self.html.findall('.//*'):
             s = "%s %s" % (elem.get('class', ''), elem.get('id', ''))
             if len(s) < 2:
                 continue

Original file line number	Diff line number	Diff line change
`@@ -395,7 +395,7 @@ def score_node(self, elem):`
`395`	`395`	`}`
`396`	`396`
`397`	`397`	`def remove_unlikely_candidates(self):`
`398`		`- for elem in self.html.iter():`
	`398`	`+ for elem in self.html.findall('.//*'):`
`399`	`399`	`s = "%s %s" % (elem.get('class', ''), elem.get('id', ''))`
`400`	`400`	`if len(s) < 2:`
`401`	`401`	`continue`