extract code, text as list

sopython · Nov 24, 2014 · 61b933c · 61b933c
1 parent 413b238
commit 61b933c
Show file tree

Hide file tree

Showing 2 changed files with 8 additions and 10 deletions.
diff --git a/nidaba/core/objects.py b/nidaba/core/objects.py
@@ -1,6 +1,4 @@
-from pyparsing import makeHTMLTags, SkipTo
-
-from .parser import strip_tags
+from bs4 import BeautifulSoup
 
 
 class Base(object):
@@ -72,9 +70,13 @@ def __init__(self, data, answers=None, comments=None):
 
     @classmethod
     def _get_code(cls, html):
-        code_start, code_end = makeHTMLTags('code')
-        code = code_start + SkipTo(code_end).setResultsName('body') + code_end
-        return [token.body for token, start, end in code.scanString(html)]
+        return [i.get_text() for i in BeautifulSoup(html).find_all('code')]
+
+    @classmethod
+    def _get_text(cls, html):
+        soup = BeautifulSoup(html)
+        [s.extract() for s in soup('code')]
+        return soup.get_text()
 
 
 class User(object):

diff --git a/nidaba/core/parser.py b/nidaba/core/parser.py