backup/pywb
1
0
Fork 0
mirror of https://github.com/webrecorder/pywb.git synced 2025-03-24 06:59:52 +01:00
Code Issues Projects Releases Activity

rewrite fixes: html_rewriter do not unescape attrs!

Browse Source 
rules: don't rewrite past end of block or line
This commit is contained in:
Ilya Kreymer 2014-03-06 02:29:52 -08:00
parent 673ff35d15
commit 3718e1d21b
3 changed files with 9 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
pywb/rewrite/html_rewriter.py
View File

@ -208,6 +208,10 @@ class HTMLRewriter(HTMLParser):
return result return result
# called to unescape attrs -- do not unescape!
def unescape(self, s):
return s
def handle_starttag(self, tag, attrs): def handle_starttag(self, tag, attrs):
if not self.rewrite_tag_attrs(tag, attrs, False): if not self.rewrite_tag_attrs(tag, attrs, False):
self.out.write(self.get_starttag_text()) self.out.write(self.get_starttag_text())

4
pywb/rewrite/test/test_rewrite.py
View File

@ -31,6 +31,10 @@ r"""
>>> parse('<HTML><A Href="#abc">Text</a></hTmL>') >>> parse('<HTML><A Href="#abc">Text</a></hTmL>')
<HTML><a href="#abc">Text</a></html> <HTML><a href="#abc">Text</a></html>
# Ensure attr values are not unescaped
>>> parse('<input value="&quot;X&quot;">X</input>')
<input value="&quot;X&quot;">X</input>
# Unicode # Unicode
>>> parse('<a href="http://испытание.испытание/">испытание</a>') >>> parse('<a href="http://испытание.испытание/">испытание</a>')
<a href="/web/20131226101010/http://испытание.испытание/">испытание</a> <a href="/web/20131226101010/http://испытание.испытание/">испытание</a>

2
pywb/rules.yaml
View File

@ -23,7 +23,7 @@ rules:
- url_prefix: 'com,facebook)/' - url_prefix: 'com,facebook)/'
rewrite: rewrite:
js_regexs: js_regexs:
- match: 'Bootloader\.configurePage.*' - match: 'Bootloader\.configurePage[^}$]+'
replace: '/* {0} */' replace: '/* {0} */'