diff --git a/pywb/indexreader.py b/pywb/indexreader.py
index 95453c9f..66bde98a 100644
--- a/pywb/indexreader.py
+++ b/pywb/indexreader.py
@@ -19,7 +19,8 @@ class RemoteCDXServer:
'statuscode': '200',
'timestamp': '20020120142510',
'urlkey': 'com,example)/'}
- """
+
+ """
def __init__(self, serverUrl):
self.serverUrl = serverUrl
diff --git a/pywb/regexmatch.py b/pywb/regexmatch.py
index 53102f21..9f3d4242 100644
--- a/pywb/regexmatch.py
+++ b/pywb/regexmatch.py
@@ -148,6 +148,9 @@ class CSSRewriter(RegexRewriter):
"""
+ CSS_URL_REGEX = "url\\s*\\(\\s*[\\\\\"']*([^'\"]+)[\\\\\"']*\\s*\\)"
+ CSS_IMPORT_NO_URL_REGEX = "@import\\s+(?!url)\\(?\\s*['\"]?(?!url[\\s\\(])([\w.:/\\\\-]+)"
+
def __init__(self, rewriter):
rules = self._createRules(rewriter)
@@ -156,8 +159,8 @@ class CSSRewriter(RegexRewriter):
def _createRules(self, rewriter):
return [
- ("url\\s*\\(\\s*[\\\\\"']*([^'\"]+)[\\\\\"']*\\s*\\)", RegexRewriter.archivalRewrite(rewriter), 1),
- ("@import\\s+(?!url)\\(?\\s*['\"]?(?!url[\\s\\(])([\w.:/\\\\-]+)", RegexRewriter.archivalRewrite(rewriter), 1),
+ (CSSRewriter.CSS_URL_REGEX, RegexRewriter.archivalRewrite(rewriter), 1),
+ (CSSRewriter.CSS_IMPORT_NO_URL_REGEX, RegexRewriter.archivalRewrite(rewriter), 1),
]
diff --git a/pywb/wbhtml.py b/pywb/wbhtml.py
index 325b4892..946715da 100644
--- a/pywb/wbhtml.py
+++ b/pywb/wbhtml.py
@@ -10,30 +10,38 @@ from regexmatch import JSRewriter, CSSRewriter
#=================================================================
class WBHtml(HTMLParser):
r"""
- >>> WBHtml(rewriter).feed('Text')
+ >>> parse('Text')
Text
- >>> WBHtml(rewriter).feed('
')
+ >>> parse('
')
- >>> WBHtml(rewriter).feed('
')
+ >>> parse('
')
- >>> WBHtml(rewriter).feed('')
+ >>> parse('')
- >>> WBHtml(rewriter).feed('')
+ >>> parse('')
- >>> WBHtml(rewriter).feed('')
+ # Unterminated script tag auto-terminate
+ >>> parse('
+
+ >>> parse('')
- >>> WBHtml(rewriter).feed('')
+ >>> parse('')
- >>> WBHtml(rewriter).feed('')
+ >>> parse('')
- """
+
+ # Unterminated style tag auto-terminate
+ >>> parse('
+ """
REWRITE_TAGS = {
'a': {'href': ''},
@@ -77,6 +85,14 @@ class WBHtml(HTMLParser):
self.cssRewriter = CSSRewriter(rewriter)
+ def close(self):
+ if (self._wbParseContext):
+ self.feed('')
+ self._wbParseContext = None
+
+ HTMLParser.close(self)
+
+
# ===========================
META_REFRESH_REGEX = re.compile('^[\\d.]+\\s*;\\s*url\\s*=\\s*(.+?)\\s*$', re.IGNORECASE | re.MULTILINE)
@@ -217,4 +233,9 @@ if __name__ == "__main__":
rewriter = ArchivalUrlRewriter('/20131226101010/http://example.com/some/path/index.html', '/web/')
+ def parse(data):
+ parser = WBHtml(rewriter)
+ parser.feed(data)
+ parser.close()
+
doctest.testmod()
diff --git a/pywb/wburlrewriter.py b/pywb/wburlrewriter.py
index 41370ef4..751d3b4c 100644
--- a/pywb/wburlrewriter.py
+++ b/pywb/wburlrewriter.py
@@ -41,7 +41,7 @@ class ArchivalUrlRewriter:
NO_REWRITE_URI_PREFIX = ['javascript:', 'data:', 'mailto:', 'about:']
- PROTOCOLS = ['http://', 'https://', '//', 'mms://', 'rtsp://', 'wais://']
+ PROTOCOLS = ['http://', 'https://', '//', 'ftp://', 'mms://', 'rtsp://', 'wais://']
def __init__(self, wburl_str, prefix):
self.wburl = ArchivalUrl(wburl_str)