def __call__(self, url):
url = normalize_url(url)
if not url:
return
if not url.startswith(self.public_url):
return
if '++plone++production' in url:
front, end = url.rsplit('/', 1)
# check blacklist
for black_listed in self._blacklisted_content:
if url.startswith(front + black_listed):
return
# since we're looking at plone here... let's try fixing up urls...
if '++plone++' in url:
# can always be from site root
url = self.public_url + '/++plone++' + url.rsplit('++plone++',
1)[-1] # noqa
parsed = urlparse(url)
vhm_path = self.vhm_base + parsed.path
resp = subrequest(vhm_path)
if resp.getStatus() == 404:
return
return {
'data': resp.getBody(),
'headers': resp.headers,
'code': resp.getStatus()
}
def __call__(self, url):
url = normalize_url(url)
if not url:
return
resp = requests.get(url)
if resp.status_code in (404, 403, 401, 500, 501, 502):
return
if len(resp.history) > 0:
# if it was a redirect and came_from in the url
if (resp.history[-1].status_code in (301, 302)
and 'came_from' in resp.url):
return
return {
'data': resp.content,
'headers': resp.headers,
'code': resp.status_code
}