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

minor tweaks: rewrite 'crossorigin' -> '_crossorigin' param to disable

Browse Source 
crossorigin as it may interfere with loading rewritten content, add
tests for html and lxml parsers
add server_cls as optional param to QueryHandler.init_from_config()
for easier customization
views: dont create template if empty template file specified
This commit is contained in:
Ilya Kreymer 2014-04-19 12:04:43 -07:00
parent 23bb5bd175
commit e1e55ac061
5 changed files with 27 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
pywb/rewrite/html_rewriter.py
View File

@ -167,6 +167,11 @@ class HTMLRewriterMixin(object):
elif attr_name == 'style': elif attr_name == 'style':
attr_value = self._rewrite_css(attr_value) attr_value = self._rewrite_css(attr_value)
# special case: disable crossorigin attr
# as they may interfere with rewriting semantics
elif attr_name == 'crossorigin':
attr_name = '_crossorigin'
# special case: meta tag # special case: meta tag
elif (tag == 'meta') and (attr_name == 'content'): elif (tag == 'meta') and (attr_name == 'content'):
if self.has_attr(tag_attrs, ('http-equiv', 'refresh')): if self.has_attr(tag_attrs, ('http-equiv', 'refresh')):

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

@ -56,6 +56,10 @@ ur"""
>>> parse('<script>window.location = "http://example.com/a/b/c.html"</script>') >>> parse('<script>window.location = "http://example.com/a/b/c.html"</script>')
<script>window.WB_wombat_location = "/web/20131226101010em_/http://example.com/a/b/c.html"</script> <script>window.WB_wombat_location = "/web/20131226101010em_/http://example.com/a/b/c.html"</script>
# Script tag + crossorigin
>>> parse('<script src="/js/scripts.js" crossorigin="anonymous"></script>')
<script src="/web/20131226101010js_/http://example.com/js/scripts.js" _crossorigin="anonymous"></script>
# Unterminated script tag, handle and auto-terminate # Unterminated script tag, handle and auto-terminate
>>> parse('<script>window.location = "http://example.com/a/b/c.html"</sc>') >>> parse('<script>window.location = "http://example.com/a/b/c.html"</sc>')
<script>window.WB_wombat_location = "/web/20131226101010em_/http://example.com/a/b/c.html"</sc></script> <script>window.WB_wombat_location = "/web/20131226101010em_/http://example.com/a/b/c.html"</sc></script>

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

@ -51,6 +51,10 @@ ur"""
>>> parse('<script>window.location = "http://example.com/a/b/c.html"</script>') >>> parse('<script>window.location = "http://example.com/a/b/c.html"</script>')
<html><head><script>window.WB_wombat_location = "/web/20131226101010em_/http://example.com/a/b/c.html"</script></head></html> <html><head><script>window.WB_wombat_location = "/web/20131226101010em_/http://example.com/a/b/c.html"</script></head></html>
# Script tag + crossorigin
>>> parse('<script src="/js/scripts.js" crossorigin="anonymous"></script>')
<html><head><script src="/web/20131226101010js_/http://example.com/js/scripts.js" _crossorigin="anonymous"></script></head></html>
# Unterminated script tag, will auto-terminate # Unterminated script tag, will auto-terminate
>>> parse('<script>window.location = "http://example.com/a/b/c.html"</sc>') >>> parse('<script>window.location = "http://example.com/a/b/c.html"</sc>')
<html><head><script>window.WB_wombat_location = "/web/20131226101010em_/http://example.com/a/b/c.html"</sc></script></head></html> <html><head><script>window.WB_wombat_location = "/web/20131226101010em_/http://example.com/a/b/c.html"</sc></script></head></html>

21
pywb/webapp/query_handler.py
View File

@ -33,14 +33,14 @@ class QueryHandler(object):
@staticmethod @staticmethod
def init_from_config(config, def init_from_config(config,
ds_rules_file=DEFAULT_RULES_FILE, ds_rules_file=DEFAULT_RULES_FILE,
html_view=None): html_view=None,
server_cls=None):
perms_policy = None perms_policy = None
server_cls = None
if hasattr(config, 'get'): if hasattr(config, 'get'):
perms_policy = config.get('perms_policy') perms_policy = config.get('perms_policy')
server_cls = config.get('server_cls') server_cls = config.get('server_cls', server_cls)
cdx_server = create_cdx_server(config, ds_rules_file, server_cls) cdx_server = create_cdx_server(config, ds_rules_file, server_cls)
@ -62,13 +62,6 @@ class QueryHandler(object):
# init standard params # init standard params
params = self.get_query_params(wb_url) params = self.get_query_params(wb_url)
# add any custom filter from the request
if wbrequest.query_filter:
params['filter'].extend(wbrequest.query_filter)
if wbrequest.custom_params:
params.update(wbrequest.custom_params)
params['allowFuzzy'] = True params['allowFuzzy'] = True
params['url'] = wb_url.url params['url'] = wb_url.url
params['output'] = output params['output'] = output
@ -81,6 +74,14 @@ class QueryHandler(object):
return self.make_cdx_response(wbrequest, params, cdx_iter) return self.make_cdx_response(wbrequest, params, cdx_iter)
def load_cdx(self, wbrequest, params): def load_cdx(self, wbrequest, params):
if wbrequest:
# add any custom filter from the request
if wbrequest.query_filter:
params['filter'].extend(wbrequest.query_filter)
if wbrequest.custom_params:
params.update(wbrequest.custom_params)
if self.perms_policy: if self.perms_policy:
perms_op = make_perms_cdx_filter(self.perms_policy, wbrequest) perms_op = make_perms_cdx_filter(self.perms_policy, wbrequest)
if perms_op: if perms_op:

3
pywb/webapp/views.py
View File

@ -104,6 +104,9 @@ class J2TemplateView:
@staticmethod @staticmethod
def create_template(filename, desc='', view_class=None): def create_template(filename, desc='', view_class=None):
if not filename:
return None
if not view_class: if not view_class:
view_class = J2TemplateView view_class = J2TemplateView