readabilite: avoid double parsing of html

morss/readabilite.py

@@ -19,19 +19,13 @@ import re
 
 import lxml.etree
 import lxml.html
+import lxml.html.soupparser
 from bs4 import BeautifulSoup
 
 
 def parse(data, encoding=None):
-    if encoding:
+    kwargs = {'from_encoding': encoding} if encoding else {}
-        data = BeautifulSoup(data, 'lxml', from_encoding=encoding).prettify('utf-8')
+    return lxml.html.soupparser.fromstring(data, **kwargs)
-
-    else:
-        data = BeautifulSoup(data, 'lxml').prettify('utf-8')
-
-    parser = lxml.html.HTMLParser(remove_comments=True, encoding='utf-8')
-
-    return lxml.html.fromstring(data, parser=parser)
 
 
 def count_words(string):