1 # Copyright 2015 The Chromium Authors. All rights reserved. 2 # Use of this source code is governed by a BSD-style license that can be 3 # found in the LICENSE file. 4 5 """Code for parsing HTML. 6 7 The purpose of this module is to ensure consistency of HTML parsing 8 in catapult_build. 9 """ 10 11 import bs4 12 13 14 def BeautifulSoup(contents): 15 # html5lib is a lenient parser; compared with the default parser, 16 # it is more similar to how a web browser parses. See: 17 # http://www.crummy.com/software/BeautifulSoup/bs4/doc/#installing-a-parser 18 return bs4.BeautifulSoup(markup=contents, features='html5lib') 19
