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: fix html rewriting, if forcing end </script>, </style>,

Browse Source 
don't actually output to preserve original
wombat: copy over all Location settings
wburl: convert :/ -> :// if 2nd slash missing, only check for <scheme>:/
and ignore subsequent slashes
This commit is contained in:
Ilya Kreymer 2014-03-08 15:10:35 -08:00
parent 541c076b77
commit 584d826f05
5 changed files with 48 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
pywb/rewrite/html_rewriter.py
View File

@ -196,7 +196,10 @@ class HTMLRewriter(HTMLParser):
# HTMLParser overrides below
def close(self):
if (self._wb_parse_context):
result = self.rewrite('</' + self._wb_parse_context + '>')
end_tag = '</' + self._wb_parse_context + '>'
result = self.rewrite(end_tag)
if result.endswith(end_tag):
result = result[:-len(end_tag)]
self._wb_parse_context = None
else:
result = ''

8
pywb/rewrite/test/test_rewrite.py
View File

@ -53,9 +53,9 @@ r"""
>>> parse('<script>window.location = "http://example.com/a/b/c.html"</script>')
<script>window.WB_wombat_location = "/web/20131226101010/http://example.com/a/b/c.html"</script>
# Unterminated script tag auto-terminate
# Unterminated script tag, handle but don't auto-terminate
>>> parse('<script>window.location = "http://example.com/a/b/c.html"</sc>')
<script>window.WB_wombat_location = "/web/20131226101010/http://example.com/a/b/c.html"</sc></script>
<script>window.WB_wombat_location = "/web/20131226101010/http://example.com/a/b/c.html"</sc>
>>> parse('<script>/*<![CDATA[*/window.location = "http://example.com/a/b/c.html;/*]]>*/"</script>')
<script>/*<![CDATA[*/window.WB_wombat_location = "/web/20131226101010/http://example.com/a/b/c.html;/*]]>*/"</script>
@ -66,9 +66,9 @@ r"""
>>> parse('<style>@import "styles.css" .a { font-face: url(\'myfont.ttf\') }</style>')
<style>@import "/web/20131226101010/http://example.com/some/path/styles.css" .a { font-face: url('/web/20131226101010/http://example.com/some/path/myfont.ttf') }</style>
# Unterminated style tag auto-terminate
# Unterminated style tag, handle but don't auto-terminate
>>> parse('<style>@import url(styles.css)')
<style>@import url(/web/20131226101010/http://example.com/some/path/styles.css)</style>
<style>@import url(/web/20131226101010/http://example.com/some/path/styles.css)
# Head Insertion
>>> parse('<html><head><script src="other.js"></script></head><body>Test</body></html>', head_insert = '<script src="cool.js"></script>')

2
pywb/rewrite/url_rewriter.py
View File

@ -57,7 +57,7 @@ class UrlRewriter:
NO_REWRITE_URI_PREFIX = ['#', 'javascript:', 'data:', 'mailto:', 'about:']
PROTOCOLS = ['http://', 'https://', '//', 'ftp://', 'mms://', 'rtsp://', 'wais://']
PROTOCOLS = ['http:/', 'https:/', '//', 'ftp:/', 'mms:/', 'rtsp:/', 'wais:/']
def __init__(self, wburl, prefix):
self.wburl = wburl if isinstance(wburl, WbUrl) else WbUrl(wburl)

20
pywb/rewrite/wburl.py
View File

@ -71,6 +71,9 @@ class WbUrl(BaseWbUrl):
>>> repr(WbUrl('20130102im_/https://example.com'))
"('replay', '20130102', 'im_', 'https://example.com', '20130102im_/https://example.com')"
>>> repr(WbUrl('20130102im_/https:/example.com'))
"('replay', '20130102', 'im_', 'https://example.com', '20130102im_/https://example.com')"
# Protocol agnostic convert to http
>>> repr(WbUrl('20130102im_///example.com'))
"('replay', '20130102', 'im_', 'http://example.com', '20130102im_/http://example.com')"
@ -81,6 +84,9 @@ class WbUrl(BaseWbUrl):
>>> repr(WbUrl('https://example.com/xyz'))
"('latest_replay', '', '', 'https://example.com/xyz', 'https://example.com/xyz')"
>>> repr(WbUrl('https:/example.com/xyz'))
"('latest_replay', '', '', 'https://example.com/xyz', 'https://example.com/xyz')"
>>> repr(WbUrl('https://example.com/xyz?a=%2f&b=%2E'))
"('latest_replay', '', '', 'https://example.com/xyz?a=%2f&b=%2E', 'https://example.com/xyz?a=%2f&b=%2E')"
@ -125,6 +131,11 @@ class WbUrl(BaseWbUrl):
>>> x = WbUrl('/http://example.com:abc/')
Traceback (most recent call last):
Exception: Bad Request Url: http://example.com:abc/
# considered blank
>>> x = WbUrl('https:/')
>>> x = WbUrl('https:///')
>>> x = WbUrl('http://')
"""
# Regexs
@ -148,11 +159,14 @@ class WbUrl(BaseWbUrl):
raise Exception('Invalid WbUrl: ', url)
# protocol agnostic url -> http://
#if self.url.startswith('//'):
# self.url = self.DEFAULT_SCHEME + self.url[2:]
# no protocol -> http://
if not '://' in self.url:
inx = self.url.find(':/')
if inx < 0:
self.url = self.DEFAULT_SCHEME + self.url
else:
inx += 2
if inx < len(self.url) and self.url[inx] != '/':
self.url = self.url[:inx] + '/' + self.url[inx:]
# BUG?: adding upper() because rfc3987 lib rejects lower case %-encoding
# %2F is fine, but %2f -- standard supports either

24
pywb/static/wombat.js
View File

@ -138,7 +138,26 @@ function WB_CopyLocationObj(loc)
newLoc.replace = function(url) { this._origLoc.replace(WB_RewriteUrl(url)); }
newLoc.assign = function(url) { this._origLoc.assign(WB_RewriteUrl(url)); }
newLoc.reload = loc.reload;
newLoc.href = WB_ExtractOrig(newLoc._origHref);
// Adapted from:
// https://gist.github.com/jlong/2428561
var parser = document.createElement('a');
parser.href = WB_ExtractOrig(newLoc._origHref);
newLoc.hash = parser.hash;
newLoc.host = parser.host;
newLoc.hostname = parser.hostname;
newLoc.href = parser.href;
if (newLoc.origin) {
newLoc.origin = parser.origin;
}
newLoc.pathname = parser.pathname;
newLoc.port = parser.port
newLoc.protocol = parser.protocol;
newLoc.search = parser.search;
newLoc.toString = function() { return this.href; }
return newLoc;
@ -148,7 +167,8 @@ function WB_wombat_updateLoc(reqHref, origHref, location)
{
if (reqHref && (WB_ExtractOrig(origHref) != WB_ExtractOrig(reqHref))) {
var finalHref = WB_RewriteUrl(reqHref);
console.log("Rewrite: " + reqHref + " => " + origHref);
location.href = finalHref;
}
}