def handle_cert_install(self, env):
if env['pywb.proxy_req_uri'] in ('/', '/index.html', '/index.html'):
available = (self.ca is not None)
if self.proxy_cert_dl_view:
return (self.proxy_cert_dl_view.
render_response(available=available,
pem_path=self.CERT_DL_PEM,
p12_path=self.CERT_DL_P12))
elif env['pywb.proxy_req_uri'] == self.CERT_DL_PEM:
if not self.ca:
return None
buff = ''
with open(self.ca.ca_file, 'rb') as fh:
buff = fh.read()
content_type = 'application/x-x509-ca-cert'
return WbResponse.text_response(buff,
content_type=content_type)
elif env['pywb.proxy_req_uri'] == self.CERT_DL_P12:
if not self.ca:
return None
buff = self.ca.get_root_PKCS12()
content_type = 'application/x-pkcs12'
return WbResponse.text_response(buff,
content_type=content_type)
def handle_cert_install(self, env):
if env['pywb.proxy_req_uri'] in ('/', '/index.html', '/index.html'):
available = (self.ca is not None)
if self.proxy_cert_dl_view:
return (self.proxy_cert_dl_view.render_response(
available=available,
pem_path=self.CERT_DL_PEM,
p12_path=self.CERT_DL_P12))
elif env['pywb.proxy_req_uri'] == self.CERT_DL_PEM:
if not self.ca:
return None
buff = ''
with open(self.ca.ca_file) as fh:
buff = fh.read()
content_type = 'application/x-x509-ca-cert'
return WbResponse.text_response(buff, content_type=content_type)
elif env['pywb.proxy_req_uri'] == self.CERT_DL_P12:
if not self.ca:
return None
buff = self.ca.get_root_PKCS12()
content_type = 'application/x-pkcs12'
return WbResponse.text_response(buff, content_type=content_type)
def render_home_page(self):
# render the homepage!
if self.home_view:
return self.home_view.render_response(routes = self.routes)
else:
# default home page template
text = '\n'.join(map(str, self.routes))
return WbResponse.text_response(text)
def render_home_page(self, env):
# render the homepage!
if self.home_view:
return self.home_view.render_response(env=env, routes=self.routes)
else:
# default home page template
text = '\n'.join(map(str, self.routes))
return WbResponse.text_response(text)
def make_redir_response(self, url, headers=None):
if not headers:
headers = []
if self.extra_headers:
for name, value in self.extra_headers.iteritems():
headers.append((name, value))
return WbResponse.redir_response(url, headers=headers)
def make_redir_response(self, url, headers=None):
if not headers:
headers = []
if self.extra_headers:
for name, value in self.extra_headers.iteritems():
headers.append((name, value))
return WbResponse.redir_response(url, headers=headers)
def __call__(self, env, routes):
referrer = env.get('HTTP_REFERER')
# ensure there is a referrer
if referrer is None:
return None
# get referrer path name
ref_split = urlparse.urlsplit(referrer)
# ensure referrer starts with one of allowed hosts
if not any (referrer.startswith(i) for i in self.match_prefixs):
if ref_split.netloc != env.get('HTTP_HOST'):
return None
path = ref_split.path
app_path = env['SCRIPT_NAME']
if app_path:
# must start with current app name, if not root
if not path.startswith(app_path):
return None
path = path[len(app_path):]
for route in routes:
ref_request = route.parse_request(env, False, request_uri = path)
if ref_request:
break
# must have matched one of the routes
if not ref_request:
return None
# must have a rewriter
if not ref_request.urlrewriter:
return None
rewriter = ref_request.urlrewriter
rel_request_uri = env['REL_REQUEST_URI']
timestamp_path = '/' + rewriter.wburl.timestamp + '/'
# check if timestamp is already part of the path
if rel_request_uri.startswith(timestamp_path):
# remove timestamp but leave / to make host relative url
# 2013/path.html -> /path.html
rel_request_uri = rel_request_uri[len(timestamp_path) - 1:]
final_url = urlparse.urlunsplit((ref_split.scheme, ref_split.netloc, rewriter.rewrite(rel_request_uri), '', ''))
return WbResponse.redir_response(final_url)
def select_coll_response(self, env):
proxy_msg = 'Basic realm="{0}"'.format(self.auth_msg)
headers = [('Content-Type', 'text/plain'),
('Proxy-Authenticate', proxy_msg)]
status_headers = StatusAndHeaders('407 Proxy Authentication', headers)
value = self.auth_msg
return WbResponse(status_headers, value=[value])
def handle_exception(self, env, exc, print_trace):
error_view = None
if hasattr(self.wb_router, "error_view"):
error_view = self.wb_router.error_view
if hasattr(exc, "status"):
status = exc.status()
else:
status = "500 Internal Server Error"
if hasattr(exc, "url"):
err_url = exc.url
else:
err_url = None
err_msg = exc.message
if print_trace:
import traceback
err_details = traceback.format_exc(exc)
print err_details
else:
logging.info(err_msg)
err_details = None
if error_view:
if err_url and isinstance(err_url, str):
err_url = err_url.decode("utf-8", "ignore")
if err_msg and isinstance(err_msg, str):
err_msg = err_msg.decode("utf-8", "ignore")
return error_view.render_response(
exc_type=type(exc).__name__,
err_msg=err_msg,
err_details=err_details,
status=status,
env=env,
err_url=err_url,
)
else:
msg = status + " Error: "
if err_msg:
msg += err_msg
msg = msg.encode("utf-8", "ignore")
return WbResponse.text_response(msg, status=status)
def make_pac_response(self, env):
server_hostport = env['SERVER_NAME'] + ':' + env['SERVER_PORT']
buff = 'function FindProxyForURL (url, host) {\n'
direct_cond =' if (shExpMatch(host, "{0}")) {{ return "DIRECT"; }}\n'
for hostpath in self.hostpaths:
parts = urlparse.urlsplit(hostpath).netloc.split(':')
buff += direct_cond.format(parts[0])
buff += direct_cond.format(env['SERVER_NAME'])
#buff += '\n return "PROXY {0}";\n}}\n'.format(self.hostpaths[0])
buff += '\n return "PROXY {0}";\n}}\n'.format(server_hostport)
return WbResponse.text_response(buff, content_type = 'application/x-ns-proxy-autoconfig')
def handle_exception(self, env, exc, print_trace):
error_view = None
if hasattr(self.wb_router, 'error_view'):
error_view = self.wb_router.error_view
if hasattr(exc, 'status'):
status = exc.status()
else:
status = '400 Bad Request'
if hasattr(exc, 'url'):
err_url = exc.url
else:
err_url = None
err_msg = exc.message
if print_trace:
import traceback
err_details = traceback.format_exc(exc)
print err_details
else:
logging.info(err_msg)
err_details = None
if error_view:
if err_url and isinstance(err_url, str):
err_url = err_url.decode('utf-8', 'ignore')
if err_msg and isinstance(err_msg, str):
err_msg = err_msg.decode('utf-8', 'ignore')
return error_view.render_response(exc_type=type(exc).__name__,
err_msg=err_msg,
err_details=err_details,
status=status,
env=env,
err_url=err_url)
else:
msg = status + ' Error: '
if err_msg:
msg += err_msg
msg = msg.encode('utf-8', 'ignore')
return WbResponse.text_response(msg,
status=status)
def handle_exception(self, env, exc, print_trace):
error_view = None
if hasattr(self.wb_router, 'error_view'):
error_view = self.wb_router.error_view
if hasattr(exc, 'status'):
status = exc.status()
else:
status = '500 Internal Server Error'
if hasattr(exc, 'url'):
err_url = exc.url
else:
err_url = None
err_msg = exc.message
if print_trace:
import traceback
err_details = traceback.format_exc(exc)
print err_details
else:
logging.info(err_msg)
err_details = None
if error_view:
if err_url and isinstance(err_url, str):
err_url = err_url.decode('utf-8', 'ignore')
if err_msg and isinstance(err_msg, str):
err_msg = err_msg.decode('utf-8', 'ignore')
return error_view.render_response(exc_type=type(exc).__name__,
err_msg=err_msg,
err_details=err_details,
status=status,
env=env,
err_url=err_url)
else:
msg = status + ' Error: '
if err_msg:
msg += err_msg
msg = msg.encode('utf-8', 'ignore')
return WbResponse.text_response(msg, status=status)
def handle_exception(env, error_view, exc, print_trace):
if hasattr(exc, 'status'):
status = exc.status()
else:
status = '400 Bad Request'
if print_trace:
import traceback
err_details = traceback.format_exc(exc)
print err_details
else:
logging.info(str(exc))
err_details = None
if error_view:
import traceback
return error_view.render_response(err_msg = str(exc), err_details = err_details, status = status)
else:
return WbResponse.text_response(status + ' Error: ' + str(exc), status = status)
def __call__(self, wbrequest):
full_path = self.static_path + wbrequest.wb_url_str
try:
if full_path.startswith(".") or full_path.startswith("file://"):
data = open(full_path, "rb")
else:
data = pkgutil.get_data(self.pkg, full_path)
if "wsgi.file_wrapper" in wbrequest.env:
reader = wbrequest.env["wsgi.file_wrapper"](data)
else:
reader = iter(lambda: data.read(), "")
content_type, _ = mimetypes.guess_type(full_path)
return WbResponse.text_stream(data, content_type=content_type)
except IOError:
raise NotFoundException("Static File Not Found: " + wbrequest.wb_url_str)
def __call__(self, wbrequest):
if wbrequest.referrer is None:
return None
if not any (wbrequest.referrer.startswith(i) for i in self.match_prefixs):
return None
try:
ref_split = urlparse.urlsplit(wbrequest.referrer)
path = ref_split.path
script_name = wbrequest.env['SCRIPT_NAME']
if not path.startswith(script_name):
return None
ref_path = path[len(script_name) + 1:].split('/', 1)
# No match on any exception
try:
rewriter = UrlRewriter(ref_path[1], script_name + '/' + ref_path[0] + '/')
except Exception:
return None
rel_request_uri = wbrequest.request_uri[1:]
#ref_wb_url = archiveurl('/' + ref_path[1])
#ref_wb_url.url = urlparse.urljoin(ref_wb_url.url, wbrequest.request_uri[1:])
#ref_wb_url.url = ref_wb_url.url.replace('../', '')
#final_url = urlparse.urlunsplit((ref_split.scheme, ref_split.netloc, ref_path[0] + str(ref_wb_url), '', ''))
final_url = urlparse.urlunsplit((ref_split.scheme, ref_split.netloc, rewriter.rewrite(rel_request_uri), '', ''))
except Exception as e:
raise e
return WbResponse.redir_response(final_url)
def render_search_page(self, wbrequest):
if self.search_view:
return self.search_view.render_response(wbrequest=wbrequest)
else:
return WbResponse.text_response("No Lookup Url Specified")
def handle_magic_page(self, env):
coll, ts = self.get_proxy_coll_ts(env)
ip = self._get_ip(env)
res = json.dumps({'ip': ip, 'coll': coll, 'ts': ts})
return WbResponse.text_response(res, content_type='application/json')
def __call__(self, env, the_router):
referrer = env.get('HTTP_REFERER')
routes = the_router.routes
# ensure there is a referrer
if referrer is None:
return None
# get referrer path name
ref_split = urlparse.urlsplit(referrer)
# require that referrer starts with current Host, if any
curr_host = env.get('HTTP_HOST')
if curr_host and curr_host != ref_split.netloc:
return None
path = ref_split.path
app_path = env.get('SCRIPT_NAME', '')
if app_path:
# must start with current app name, if not root
if not path.startswith(app_path):
return None
path = path[len(app_path):]
ref_route = None
ref_request = None
for route in routes:
matcher, coll = route.is_handling(path)
if matcher:
ref_request = the_router.parse_request(route, env,
matcher, coll, path)
ref_route = route
break
# must have matched one of the routes with a urlrewriter
if not ref_request or not ref_request.urlrewriter:
return None
rewriter = ref_request.urlrewriter
rel_request_uri = env['REL_REQUEST_URI']
timestamp_path = '/' + rewriter.wburl.timestamp + '/'
# check if timestamp is already part of the path
if rel_request_uri.startswith(timestamp_path):
# remove timestamp but leave / to make host relative url
# 2013/path.html -> /path.html
rel_request_uri = rel_request_uri[len(timestamp_path) - 1:]
rewritten_url = rewriter.rewrite(rel_request_uri)
# if post, can't redirect as that would lost the post data
# (can't use 307 because FF will show confirmation warning)
if ref_request.method == 'POST':
new_wb_url = WbUrl(rewritten_url[len(rewriter.prefix):])
ref_request.wb_url.url = new_wb_url.url
return ref_route.handler(ref_request)
final_url = urlparse.urlunsplit((ref_split.scheme,
ref_split.netloc,
rewritten_url,
'',
''))
return WbResponse.redir_response(final_url, status='302 Temp Redirect')
def handle_connect(self, env):
sock = self.get_request_socket(env)
if not sock:
return WbResponse.text_response('HTTPS Proxy Not Supported',
'405 HTTPS Proxy Not Supported')
sock.send('HTTP/1.0 200 Connection Established\r\n')
sock.send('Server: pywb proxy\r\n')
sock.send('\r\n')
hostname, port = env['REL_REQUEST_URI'].split(':')
if not self.use_wildcard:
_, certfile = self.ca.get_cert_for_host(hostname)
else:
certfile = self.ca.get_wildcard_cert(hostname)
try:
ssl_sock = ssl.wrap_socket(sock,
server_side=True,
certfile=certfile,
#ciphers="ALL",
suppress_ragged_eofs=False,
ssl_version=ssl.PROTOCOL_SSLv23
)
env['pywb.proxy_ssl_sock'] = ssl_sock
buffreader = BufferedReader(ssl_sock, block_size=self.BLOCK_SIZE)
statusline = buffreader.readline().rstrip()
except Exception as se:
raise BadRequestException(se.message)
statusparts = statusline.split(' ')
if len(statusparts) < 3:
raise BadRequestException('Invalid Proxy Request: ' + statusline)
env['REQUEST_METHOD'] = statusparts[0]
env['REL_REQUEST_URI'] = ('https://' +
env['REL_REQUEST_URI'].replace(':443', '') +
statusparts[1])
env['SERVER_PROTOCOL'] = statusparts[2].strip()
env['pywb.proxy_scheme'] = 'https'
env['pywb.proxy_host'] = hostname
env['pywb.proxy_port'] = port
env['pywb.proxy_req_uri'] = statusparts[1]
queryparts = env['REL_REQUEST_URI'].split('?', 1)
env['PATH_INFO'] = queryparts[0]
env['QUERY_STRING'] = queryparts[1] if len(queryparts) > 1 else ''
while True:
line = buffreader.readline()
if line:
line = line.rstrip()
if not line:
break
parts = line.split(':', 1)
if len(parts) < 2:
continue
name = parts[0].strip()
value = parts[1].strip()
name = name.replace('-', '_').upper()
if name not in ('CONTENT_LENGTH', 'CONTENT_TYPE'):
name = 'HTTP_' + name
env[name] = value
remain = buffreader.rem_length()
if remain > 0:
remainder = buffreader.read(self.BLOCK_SIZE)
env['wsgi.input'] = BufferedReader(ssl_sock,
block_size=self.BLOCK_SIZE,
starting_data=remainder)
def __call__(self, wbrequest):
return WbResponse.text_response(str(wbrequest))
def render_home_page(self, env):
if self.home_view:
return self.home_view.render_response(env=env, routes=self.routes)
else:
return WbResponse.text_response('No Home Page')
def __call__(self, env, the_router):
referrer = env.get('HTTP_REFERER')
routes = the_router.routes
# ensure there is a referrer
if referrer is None:
return None
# get referrer path name
ref_split = urlparse.urlsplit(referrer)
# require that referrer starts with current Host, if any
curr_host = env.get('HTTP_HOST')
if curr_host and curr_host != ref_split.netloc:
return None
path = ref_split.path
app_path = env.get('SCRIPT_NAME', '')
if app_path:
# must start with current app name, if not root
if not path.startswith(app_path):
return None
path = path[len(app_path):]
ref_route = None
ref_request = None
for route in routes:
matcher, coll = route.is_handling(path)
if matcher:
ref_request = the_router.parse_request(route, env,
matcher, coll, path)
ref_route = route
break
# must have matched one of the routes with a urlrewriter
if not ref_request or not ref_request.urlrewriter:
return None
rewriter = ref_request.urlrewriter
rel_request_uri = env['REL_REQUEST_URI']
timestamp_path = '/' + rewriter.wburl.timestamp + '/'
# check if timestamp is already part of the path
if rel_request_uri.startswith(timestamp_path):
# remove timestamp but leave / to make host relative url
# 2013/path.html -> /path.html
rel_request_uri = rel_request_uri[len(timestamp_path) - 1:]
rewritten_url = rewriter.rewrite(rel_request_uri)
# if post, can't redirect as that would lost the post data
# (can't use 307 because FF will show confirmation warning)
if ref_request.method == 'POST':
new_wb_url = WbUrl(rewritten_url[len(rewriter.prefix):])
ref_request.wb_url.url = new_wb_url.url
return ref_route.handler(ref_request)
final_url = urlparse.urlunsplit((ref_split.scheme,
ref_split.netloc,
rewritten_url,
'',
''))
return WbResponse.redir_response(final_url, status='302 Temp Redirect')
def handle_connect(self, env):
sock = self.get_request_socket(env)
if not sock:
return WbResponse.text_response('HTTPS Proxy Not Supported',
'405 HTTPS Proxy Not Supported')
sock.send('HTTP/1.0 200 Connection Established\r\n')
sock.send('Server: pywb proxy\r\n')
sock.send('\r\n')
hostname, port = env['REL_REQUEST_URI'].split(':')
if not self.use_wildcard:
_, certfile = self.ca.get_cert_for_host(hostname)
else:
certfile = self.ca.get_wildcard_cert(hostname)
try:
ssl_sock = ssl.wrap_socket(
sock,
server_side=True,
certfile=certfile,
#ciphers="ALL",
suppress_ragged_eofs=False,
ssl_version=ssl.PROTOCOL_SSLv23)
env['pywb.proxy_ssl_sock'] = ssl_sock
buffreader = BufferedReader(ssl_sock, block_size=self.BLOCK_SIZE)
statusline = buffreader.readline().rstrip()
except Exception as se:
raise BadRequestException(se.message)
statusparts = statusline.split(' ')
if len(statusparts) < 3:
raise BadRequestException('Invalid Proxy Request: ' + statusline)
env['REQUEST_METHOD'] = statusparts[0]
env['REL_REQUEST_URI'] = ('https://' +
env['REL_REQUEST_URI'].replace(':443', '') +
statusparts[1])
env['SERVER_PROTOCOL'] = statusparts[2].strip()
env['pywb.proxy_scheme'] = 'https'
env['pywb.proxy_host'] = hostname
env['pywb.proxy_port'] = port
env['pywb.proxy_req_uri'] = statusparts[1]
queryparts = env['REL_REQUEST_URI'].split('?', 1)
env['PATH_INFO'] = queryparts[0]
env['QUERY_STRING'] = queryparts[1] if len(queryparts) > 1 else ''
while True:
line = buffreader.readline()
if line:
line = line.rstrip()
if not line:
break
parts = line.split(':', 1)
if len(parts) < 2:
continue
name = parts[0].strip()
value = parts[1].strip()
name = name.replace('-', '_').upper()
if not name in ('CONTENT_LENGTH', 'CONTENT_TYPE'):
name = 'HTTP_' + name
env[name] = value
remain = buffreader.rem_length()
if remain > 0:
remainder = buffreader.read(self.BLOCK_SIZE)
env['wsgi.input'] = BufferedReader(ssl_sock,
block_size=self.BLOCK_SIZE,
starting_data=remainder)
