import logging
import re
from django import http
from django.conf import settings
from django.core import urlresolvers
from django.core.exceptions import PermissionDenied
from django.core.mail import mail_managers
from django.utils.cache import get_conditional_response, set_response_etag
from django.utils.encoding import force_text
from django.utils.http import unquote_etag
from django.utils.six.moves.urllib.parse import urlparse
logger = logging.getLogger('django.request')
class CommonMiddleware(object):
"""
"Common" middleware for taking care of some basic operations:
- Forbids access to User-Agents in settings.DISALLOWED_USER_AGENTS
- URL rewriting: Based on the APPEND_SLASH and PREPEND_WWW settings,
this middleware appends missing slashes and/or prepends missing
"www."s.
- If APPEND_SLASH is set and the initial URL doesn't end with a
slash, and it is not found in urlpatterns, a new URL is formed by
appending a slash at the end. If this new URL is found in
urlpatterns, then an HTTP-redirect is returned to this new URL;
otherwise the initial URL is processed as usual.
This behavior can be customized by subclassing CommonMiddleware and
overriding the response_redirect_class attribute.
- ETags: If the USE_ETAGS setting is set, ETags will be calculated from
the entire page content and Not Modified responses will be returned
appropriately.
"""
response_redirect_class = http.HttpResponsePermanentRedirect
def process_request(self, request):
"""
Check for denied User-Agents and rewrite the URL based on
settings.APPEND_SLASH and settings.PREPEND_WWW
"""
# Check for denied User-Agents
if 'HTTP_USER_AGENT' in request.META:
for user_agent_regex in settings.DISALLOWED_USER_AGENTS:
if user_agent_regex.search(request.META['HTTP_USER_AGENT']):
raise PermissionDenied('Forbidden user agent')
# Check for a redirect based on settings.PREPEND_WWW
host = request.get_host()
must_prepend = settings.PREPEND_WWW and host and not host.startswith('www.')
redirect_url = ('%s://www.%s' % (request.scheme, host)) if must_prepend else ''
# Check if a slash should be appended
if self.should_redirect_with_slash(request):
path = self.get_full_path_with_slash(request)
else:
path = request.get_full_path()
# Return a redirect if necessary
if redirect_url or path != request.get_full_path():
redirect_url += path
return self.response_redirect_class(redirect_url)
def should_redirect_with_slash(self, request):
"""
Return True if settings.APPEND_SLASH is True and appending a slash to
the request path turns an invalid path into a valid one.
"""
if settings.APPEND_SLASH and not request.get_full_path().endswith('/'):
urlconf = getattr(request, 'urlconf', None)
return (
not urlresolvers.is_valid_path(request.path_info, urlconf)
and urlresolvers.is_valid_path('%s/' % request.path_info, urlconf)
)
return False
def get_full_path_with_slash(self, request):
"""
Return the full path of the request with a trailing slash appended.
Raise a RuntimeError if settings.DEBUG is True and request.method is
POST, PUT, or PATCH.
"""
new_path = request.get_full_path(force_append_slash=True)
if settings.DEBUG and request.method in ('POST', 'PUT', 'PATCH'):
raise RuntimeError(
"You called this URL via %(method)s, but the URL doesn't end "
"in a slash and you have APPEND_SLASH set. Django can't "
"redirect to the slash URL while maintaining %(method)s data. "
"Change your form to point to %(url)s (note the trailing "
"slash), or set APPEND_SLASH=False in your Django settings." % {
'method': request.method,
'url': request.get_host() + new_path,
}
)
return new_path
def process_response(self, request, response):
"""
Calculate the ETag, if needed.
When the status code of the response is 404, it may redirect to a path
with an appended slash if should_redirect_with_slash() returns True.
"""
# If the given URL is "Not Found", then check if we should redirect to
# a path with a slash appended.
if response.status_code == 404:
if self.should_redirect_with_slash(request):
return self.response_redirect_class(self.get_full_path_with_slash(request))
if settings.USE_ETAGS:
if not response.has_header('ETag'):
set_response_etag(response)
if response.has_header('ETag'):
return get_conditional_response(
request,
etag=unquote_etag(response['ETag']),
response=response,
)
return response
class BrokenLinkEmailsMiddleware(object):
def process_response(self, request, response):
"""
Send broken link emails for relevant 404 NOT FOUND responses.
"""
if response.status_code == 404 and not settings.DEBUG:
domain = request.get_host()
path = request.get_full_path()
referer = force_text(request.META.get('HTTP_REFERER', ''), errors='replace')
if not self.is_ignorable_request(request, path, domain, referer):
ua = force_text(request.META.get('HTTP_USER_AGENT', '<none>'), errors='replace')
ip = request.META.get('REMOTE_ADDR', '<none>')
mail_managers(
"Broken %slink on %s" % (
('INTERNAL ' if self.is_internal_request(domain, referer) else ''),
domain
),
"Referrer: %s\nRequested URL: %s\nUser agent: %s\n"
"IP address: %s\n" % (referer, path, ua, ip),
fail_silently=True)
return response
def is_internal_request(self, domain, referer):
"""
Returns True if the referring URL is the same domain as the current request.
"""
# Different subdomains are treated as different domains.
return bool(re.match("^https?://%s/" % re.escape(domain), referer))
def is_ignorable_request(self, request, uri, domain, referer):
"""
Return True if the given request *shouldn't* notify the site managers
according to project settings or in three specific situations:
- If the referer is empty.
- If a '?' in referer is identified as a search engine source.
- If the referer is equal to the current URL, ignoring the scheme
(assumed to be a poorly implemented bot).
"""
if not referer:
return True
if not self.is_internal_request(domain, referer) and '?' in referer:
return True
parsed_referer = urlparse(referer)
if parsed_referer.netloc in ['', domain] and parsed_referer.path == uri:
return True
return any(pattern.search(uri) for pattern in settings.IGNORABLE_404_URLS)