backup/pywb
1
0
Fork 0
mirror of https://github.com/webrecorder/pywb.git synced 2025-03-15 00:03:28 +01:00
Code Issues Projects Releases Activity

rewrite: default HTMLParser entityref and charref are treated as plain

Browse Source 
data for HTMLRewriter, since they are never rewritten, and to avoid
semicolon ambiguity, since no way to determine if there is a ; or not
at end. Addresses #43
This commit is contained in:
Ilya Kreymer 2014-11-04 12:12:32 -08:00
parent 5e4b830fa7
commit e4bcef1c8b
2 changed files with 21 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
pywb/rewrite/html_rewriter.py
View File

@ -263,10 +263,20 @@ class HTMLRewriterMixin(object):
#=================================================================
class HTMLRewriter(HTMLRewriterMixin, HTMLParser):
PARSETAG = re.compile('[<]')
def __init__(self, *args, **kwargs):
HTMLParser.__init__(self)
super(HTMLRewriter, self).__init__(*args, **kwargs)
def reset(self):
HTMLParser.reset(self)
self.interesting = self.PARSETAG
def clear_cdata_mode(self):
HTMLParser.clear_cdata_mode(self)
self.interesting = self.PARSETAG
def feed(self, string):
try:
HTMLParser.feed(self, string)
@ -311,11 +321,12 @@ class HTMLRewriter(HTMLRewriterMixin, HTMLParser):
def handle_data(self, data):
self.parse_data(data)
def handle_entityref(self, data):
self.out.write('&' + data + ';')
def handle_charref(self, data):
self.out.write('&#' + data + ';')
# overriding regex so that these are no longer called
#def handle_entityref(self, data):
# self.out.write('&' + data + ';')
#
#def handle_charref(self, data):
# self.out.write('&#' + data + ';')
def handle_comment(self, data):
self.out.write('<!--')

7
pywb/rewrite/test/test_html_rewriter.py
View File

@ -28,8 +28,11 @@ ur"""
<base href="/web/20131226101010/http://example.com/some/path/static/"/><img src="/web/20131226101010im_/http://example.com/some/path/static/image.gif"/>
# HTML Entities
>>> parse('<a href="">&rsaquo; &nbsp; &#62;</div>')
<a href="">&rsaquo; &nbsp; &#62;</div>
>>> parse('<a href="">&rsaquo; &nbsp; &#62; &#63</div>')
<a href="">&rsaquo; &nbsp; &#62; &#63</div>
>>> parse('<div>X&Y</div> </div>X&Y;</div>')
<div>X&Y</div> </div>X&Y;</div>
# Don't rewrite anchors
>>> parse('<HTML><A Href="#abc">Text</a></hTmL>')