def translate_headers(self, url, env):
headers = {}
splits = urlsplit(url)
for name, value in env.iteritems():
if name == 'HTTP_HOST':
name = 'Host'
value = splits.netloc
elif name == 'HTTP_ORIGIN':
name = 'Origin'
value = (splits.scheme + '://' + splits.netloc)
elif name == 'HTTP_X_CSRFTOKEN':
name = 'X-CSRFToken'
cookie_val = extract_client_cookie(env, 'csrftoken')
if cookie_val:
value = cookie_val
elif name.startswith('HTTP_'):
name = name[5:].title().replace('_', '-')
elif name in ('CONTENT_LENGTH', 'CONTENT_TYPE'):
name = name.title().replace('_', '-')
elif name == 'REL_REFERER':
name = 'Referer'
else:
continue
if value:
headers[name] = value
return headers
def translate_headers(self, url, env):
headers = {}
splits = urlsplit(url)
for name, value in env.iteritems():
if name == 'HTTP_HOST':
name = 'Host'
value = splits.netloc
elif name == 'HTTP_ORIGIN':
name = 'Origin'
value = (splits.scheme + '://' + splits.netloc)
elif name == 'HTTP_X_CSRFTOKEN':
name = 'X-CSRFToken'
cookie_val = extract_client_cookie(env, 'csrftoken')
if cookie_val:
value = cookie_val
elif name.startswith('HTTP_'):
name = name[5:].title().replace('_', '-')
elif name in ('CONTENT_LENGTH', 'CONTENT_TYPE'):
name = name.title().replace('_', '-')
elif name == 'REL_REFERER':
name = 'Referer'
else:
continue
if value:
headers[name] = value
return headers
def translate_headers(self, url, urlkey, env):
headers = {}
splits = urlsplit(url)
has_cookies = False
for name, value in six.iteritems(env):
if name == 'HTTP_HOST':
name = 'Host'
value = splits.netloc
elif name == 'HTTP_ORIGIN':
name = 'Origin'
value = (splits.scheme + '://' + splits.netloc)
elif name == 'HTTP_X_CSRFTOKEN':
name = 'X-CSRFToken'
cookie_val = extract_client_cookie(env, 'csrftoken')
if cookie_val:
value = cookie_val
elif name == 'HTTP_REFERER':
continue
elif name == 'HTTP_X_PYWB_REQUESTED_WITH':
continue
elif name == 'HTTP_X_FORWARDED_PROTO':
name = 'X-Forwarded-Proto'
value = splits.scheme
elif name == 'HTTP_COOKIE':
name = 'Cookie'
value = self._req_cookie_rewrite(urlkey, value)
has_cookies = True
elif name.startswith('HTTP_'):
name = name[5:].title().replace('_', '-')
elif name in ('CONTENT_LENGTH', 'CONTENT_TYPE'):
name = name.title().replace('_', '-')
elif name == 'REL_REFERER':
name = 'Referer'
else:
value = None
if value:
headers[name] = value
if not has_cookies:
value = self._req_cookie_rewrite(urlkey, '')
if value:
headers['Cookie'] = value
return headers
def translate_headers(self, url, urlkey, env):
headers = {}
splits = urlsplit(url)
has_cookies = False
for name, value in six.iteritems(env):
if name == 'HTTP_HOST':
name = 'Host'
value = splits.netloc
elif name == 'HTTP_ORIGIN':
name = 'Origin'
value = (splits.scheme + '://' + splits.netloc)
elif name == 'HTTP_X_CSRFTOKEN':
name = 'X-CSRFToken'
cookie_val = extract_client_cookie(env, 'csrftoken')
if cookie_val:
value = cookie_val
elif name == 'HTTP_REFERER':
continue
elif name == 'HTTP_X_PYWB_REQUESTED_WITH':
continue
elif name == 'HTTP_X_FORWARDED_PROTO':
name = 'X-Forwarded-Proto'
value = splits.scheme
elif name == 'HTTP_COOKIE':
name = 'Cookie'
value = self._req_cookie_rewrite(urlkey, value)
has_cookies = True
elif name.startswith('HTTP_'):
name = name[5:].title().replace('_', '-')
elif name in ('CONTENT_LENGTH', 'CONTENT_TYPE'):
name = name.title().replace('_', '-')
elif name == 'REL_REFERER':
name = 'Referer'
else:
value = None
if value:
headers[name] = value
if not has_cookies:
value = self._req_cookie_rewrite(urlkey, '')
if value:
headers['Cookie'] = value
return headers
def get_coll(self, env):
sesh_id = extract_client_cookie(env, self.cookie_name)
coll = None
ts = None
if sesh_id:
coll = self.cache[sesh_id + ':c']
ts = self.cache[sesh_id + ':t']
return coll, ts, sesh_id
def get_coll(self, env):
sesh_id = extract_client_cookie(env, self.cookie_name)
coll = None
ts = None
if sesh_id:
coll = self.cache[sesh_id + ':c']
ts = self.cache[sesh_id + ':t']
return coll, ts, sesh_id
def get_req_headers(self):
headers = {}
has_cookies = False
for name, value in iteritems(self.env):
if name == 'HTTP_HOST':
name = 'Host'
value = self.splits.netloc
elif name == 'HTTP_ORIGIN':
name = 'Origin'
value = (self.splits.scheme + '://' + self.splits.netloc)
elif name == 'HTTP_X_CSRFTOKEN':
name = 'X-CSRFToken'
cookie_val = extract_client_cookie(self.env, 'csrftoken')
if cookie_val:
value = cookie_val
elif name == 'HTTP_X_PYWB_REQUESTED_WITH':
continue
elif name == 'HTTP_X_FORWARDED_PROTO':
name = 'X-Forwarded-Proto'
value = self.splits.scheme
elif name == 'HTTP_COOKIE':
name = 'Cookie'
value = self._req_cookie_rewrite(value)
has_cookies = True
elif name.startswith('HTTP_'):
name = name[5:].title().replace('_', '-')
elif name in ('CONTENT_LENGTH', 'CONTENT_TYPE'):
name = name.title().replace('_', '-')
else:
value = None
if value:
headers[name] = value
if not has_cookies:
value = self._req_cookie_rewrite('')
if value:
headers['Cookie'] = value
if self.extra_cookie:
headers['Cookie'] = self.extra_cookie + ';' + headers.get('Cookie', '')
print('Cookie', headers['Cookie'])
return headers
def get_req_headers(self):
headers = {}
has_cookies = False
for name, value in iteritems(self.env):
if name == 'HTTP_HOST':
name = 'Host'
if self.splits:
value = self.splits.netloc
elif name == 'HTTP_ORIGIN':
name = 'Origin'
if self.splits:
value = (self.splits.scheme + '://' + self.splits.netloc)
elif name == 'HTTP_X_CSRFTOKEN':
name = 'X-CSRFToken'
if self.splits:
cookie_val = extract_client_cookie(self.env, 'csrftoken')
if cookie_val:
value = cookie_val
elif name == 'HTTP_X_PYWB_REQUESTED_WITH':
continue
elif name in ('HTTP_CONNECTION', 'HTTP_PROXY_CONNECTION'):
continue
elif name in ('HTTP_IF_MODIFIED_SINCE', 'HTTP_IF_UNMODIFIED_SINCE'):
continue
elif name == 'HTTP_X_FORWARDED_PROTO':
name = 'X-Forwarded-Proto'
if self.splits:
value = self.splits.scheme
elif name.startswith('HTTP_'):
name = name[5:].title().replace('_', '-')
elif name in ('CONTENT_LENGTH', 'CONTENT_TYPE'):
name = name.title().replace('_', '-')
else:
value = None
if value:
headers[name] = value
if self.extra_cookie:
headers['Cookie'] = self.extra_cookie + ';' + headers.get('Cookie', '')
return headers
def get_coll(self, env):
sesh_id = extract_client_cookie(env, self.cookie_name)
coll = None
ts = None
if sesh_id:
coll = self.cache[sesh_id + ':c']
try:
ts = self.cache[sesh_id + ':t']
except KeyError:
pass
return coll, ts, sesh_id
def get_coll(self, env):
sesh_id = extract_client_cookie(env, self.cookie_name)
coll = None
ts = None
if sesh_id:
coll = self.cache[sesh_id + ':c']
try:
ts = self.cache[sesh_id + ':t']
except KeyError:
pass
return coll, ts, sesh_id
def handle_magic_page(self, env):
request_url = env['REL_REQUEST_URI']
parts = urlparse.urlsplit(request_url)
server_name = env['pywb.proxy_host']
path_url = parts.path[1:]
if parts.query:
path_url += '?' + parts.query
if server_name.startswith('auto'):
coll, ts, sesh_id = self.get_coll(env)
if coll:
return self.make_sethost_cookie_response(sesh_id,
path_url,
env)
else:
return self.make_magic_response('select', path_url, env)
elif server_name.startswith('query.'):
wb_url = WbUrl(path_url)
# only dealing with specific timestamp setting
if wb_url.is_query():
return None
coll, ts, sesh_id = self.get_coll(env)
if not coll:
return self.make_magic_response('select', path_url, env)
self.set_ts(sesh_id, wb_url.timestamp)
return self.make_redir_response(wb_url.url)
elif server_name.endswith(self.set_prefix):
old_sesh_id = extract_client_cookie(env, self.cookie_name)
sesh_id = self.create_renew_sesh_id(old_sesh_id)
if sesh_id != old_sesh_id:
headers = self.make_cookie_headers(sesh_id, self.magic_name)
else:
headers = None
coll = server_name[:-len(self.set_prefix)]
# set sesh value
self.set_coll(sesh_id, coll)
return self.make_sethost_cookie_response(sesh_id, path_url, env,
headers=headers)
elif self.sethost_prefix in server_name:
inx = server_name.find(self.sethost_prefix)
sesh_id = server_name[:inx]
domain = server_name[inx + len(self.sethost_prefix):]
headers = self.make_cookie_headers(sesh_id, domain)
full_url = env['pywb.proxy_scheme'] + '://' + domain
full_url += '/' + path_url
return self.make_redir_response(full_url, headers=headers)
elif 'select.' in server_name:
coll, ts, sesh_id = self.get_coll(env)
route_temp = '-set.' + self.magic_name + '/' + path_url
return (self.proxy_select_view.
render_response(routes=self.routes,
route_temp=route_temp,
coll=coll,
url=path_url))
def handle_magic_page(self, env):
request_url = env['REL_REQUEST_URI']
parts = urlsplit(request_url)
server_name = env['pywb.proxy_host']
path_url = parts.path[1:]
if parts.query:
path_url += '?' + parts.query
if server_name.startswith('auto'):
coll, ts, sesh_id = self.get_coll(env)
if coll:
return self.make_sethost_cookie_response(sesh_id,
path_url,
env)
else:
return self.make_magic_response('select', path_url, env)
elif server_name.startswith('query.'):
wb_url = WbUrl(path_url)
# only dealing with specific timestamp setting
if wb_url.is_query():
return None
coll, ts, sesh_id = self.get_coll(env)
if not coll:
return self.make_magic_response('select', path_url, env)
self.set_ts(sesh_id, wb_url.timestamp)
return self.make_redir_response(wb_url.url)
elif server_name.endswith(self.set_prefix):
old_sesh_id = extract_client_cookie(env, self.cookie_name)
sesh_id = self.create_renew_sesh_id(old_sesh_id)
if sesh_id != old_sesh_id:
headers = self.make_cookie_headers(sesh_id, self.magic_name)
else:
headers = None
coll = server_name[:-len(self.set_prefix)]
# set sesh value
self.set_coll(sesh_id, coll)
return self.make_sethost_cookie_response(sesh_id, path_url, env,
headers=headers)
elif self.sethost_prefix in server_name:
inx = server_name.find(self.sethost_prefix)
sesh_id = server_name[:inx]
domain = server_name[inx + len(self.sethost_prefix):]
headers = self.make_cookie_headers(sesh_id, domain)
full_url = env['pywb.proxy_scheme'] + '://' + domain
full_url += '/' + path_url
return self.make_redir_response(full_url, headers=headers)
elif 'select.' in server_name:
coll, ts, sesh_id = self.get_coll(env)
route_temp = '-set.' + self.magic_name + '/' + path_url
return (self.proxy_select_view.
render_response(routes=self.routes,
route_temp=route_temp,
coll=coll,
url=path_url))
def get_req_headers(self):
headers = {}
has_cookies = False
for name, value in iteritems(self.env):
if name == 'HTTP_HOST':
name = 'Host'
if self.splits:
value = self.splits.netloc
elif name == 'HTTP_ORIGIN':
name = 'Origin'
referrer = self.env.get('HTTP_REFERER')
if referrer:
splits = urlsplit(referrer)
else:
splits = self.splits
if splits:
value = (splits.scheme + '://' + splits.netloc)
elif name == 'HTTP_X_CSRFTOKEN':
name = 'X-CSRFToken'
if self.splits:
cookie_val = extract_client_cookie(self.env, 'csrftoken')
if cookie_val:
value = cookie_val
elif name == 'HTTP_X_PYWB_REQUESTED_WITH':
continue
elif name in ('HTTP_CONNECTION', 'HTTP_PROXY_CONNECTION'):
continue
elif name in ('HTTP_IF_MODIFIED_SINCE', 'HTTP_IF_UNMODIFIED_SINCE'):
continue
elif name == 'HTTP_X_FORWARDED_PROTO':
name = 'X-Forwarded-Proto'
if self.splits:
value = self.splits.scheme
elif not has_brotli and name == 'HTTP_ACCEPT_ENCODING' and 'br' in value:
# if brotli not available, remove 'br' from accept-encoding to avoid
# capture brotli encoded content
name = 'Accept-Encoding'
value = ','.join([enc for enc in value.split(',') if enc.strip() != 'br'])
elif name.startswith('HTTP_'):
name = name[5:].title().replace('_', '-')
elif name in ('CONTENT_LENGTH', 'CONTENT_TYPE'):
name = name.title().replace('_', '-')
else:
value = None
if value:
headers[name] = value
if self.extra_cookie:
headers['Cookie'] = self.extra_cookie + ';' + headers.get('Cookie', '')
return headers
def get_req_headers(self):
headers = {}
has_cookies = False
for name, value in iteritems(self.env):
if name == 'HTTP_HOST':
name = 'Host'
if self.splits:
value = self.splits.netloc
elif name == 'HTTP_ORIGIN':
name = 'Origin'
referrer = self.env.get('HTTP_REFERER')
if referrer:
splits = urlsplit(referrer)
else:
splits = self.splits
if splits:
value = (splits.scheme + '://' + splits.netloc)
elif name == 'HTTP_X_CSRFTOKEN':
name = 'X-CSRFToken'
if self.splits:
cookie_val = extract_client_cookie(self.env, 'csrftoken')
if cookie_val:
value = cookie_val
elif name == 'HTTP_X_PYWB_REQUESTED_WITH':
continue
elif name in ('HTTP_CONNECTION', 'HTTP_PROXY_CONNECTION'):
continue
elif name in ('HTTP_IF_MODIFIED_SINCE',
'HTTP_IF_UNMODIFIED_SINCE'):
continue
elif name == 'HTTP_X_FORWARDED_PROTO':
name = 'X-Forwarded-Proto'
if self.splits:
value = self.splits.scheme
elif not has_brotli and name == 'HTTP_ACCEPT_ENCODING' and 'br' in value:
# if brotli not available, remove 'br' from accept-encoding to avoid
# capture brotli encoded content
name = 'Accept-Encoding'
value = ','.join(
[enc for enc in value.split(',') if enc.strip() != 'br'])
elif name.startswith('HTTP_'):
name = name[5:].title().replace('_', '-')
elif name in ('CONTENT_LENGTH', 'CONTENT_TYPE'):
name = name.title().replace('_', '-')
else:
value = None
if value:
headers[name] = value
if self.extra_cookie:
headers['Cookie'] = self.extra_cookie + ';' + headers.get(
'Cookie', '')
return headers
