mirror of
https://github.com/webrecorder/pywb.git
synced 2025-03-28 00:25:21 +01:00
f0a0976038
create 'framework' subpackage for general purpose components! contains routing, request/response, exceptions and wsgi wrappers update framework package for pep8 dsrules: using load_config_yaml() (pushed to utils) to init default config
163 lines
4.8 KiB
Python
163 lines
4.8 KiB
Python
from pywb.utils.wbexception import WbException
|
|
from pywb.utils.loaders import load_yaml_config
|
|
|
|
from wbexceptions import NotFoundException, InternalRedirect
|
|
from wbrequestresponse import WbResponse, StatusAndHeaders
|
|
|
|
|
|
import os
|
|
import importlib
|
|
import logging
|
|
|
|
|
|
#=================================================================
|
|
# adapted from wsgiref.request_uri, but doesn't include domain name
|
|
# and allows all characters which are allowed in the path segment
|
|
# according to: http://tools.ietf.org/html/rfc3986#section-3.3
|
|
# explained here:
|
|
# http://stackoverflow.com/questions/4669692/
|
|
# valid-characters-for-directory-part-of-a-url-for-short-links
|
|
|
|
def rel_request_uri(environ, include_query=1):
|
|
"""
|
|
Return the requested path, optionally including the query string
|
|
|
|
# Simple test:
|
|
>>> rel_request_uri({'PATH_INFO': '/web/example.com'})
|
|
'/web/example.com'
|
|
|
|
# Test all unecoded special chars and double-quote
|
|
# (double-quote must be encoded but not single quote)
|
|
>>> rel_request_uri({'PATH_INFO': "/web/example.com/0~!+$&'()*+,;=:\\\""})
|
|
"/web/example.com/0~!+$&'()*+,;=:%22"
|
|
"""
|
|
from urllib import quote
|
|
url = quote(environ.get('PATH_INFO', ''), safe='/~!$&\'()*+,;=:@')
|
|
if include_query and environ.get('QUERY_STRING'):
|
|
url += '?' + environ['QUERY_STRING']
|
|
|
|
return url
|
|
|
|
|
|
#=================================================================
|
|
def create_wb_app(wb_router):
|
|
# Top-level wsgi application
|
|
def application(env, start_response):
|
|
if env.get('SCRIPT_NAME') or not env.get('REQUEST_URI'):
|
|
env['REL_REQUEST_URI'] = rel_request_uri(env)
|
|
else:
|
|
env['REL_REQUEST_URI'] = env['REQUEST_URI']
|
|
|
|
response = None
|
|
|
|
try:
|
|
response = wb_router(env)
|
|
|
|
if not response:
|
|
msg = 'No handler for "{0}"'.format(env['REL_REQUEST_URI'])
|
|
raise NotFoundException(msg)
|
|
|
|
except InternalRedirect as ir:
|
|
response = WbResponse(StatusAndHeaders(ir.status, ir.httpHeaders))
|
|
|
|
except WbException as e:
|
|
response = handle_exception(env, wb_router.error_view, e, False)
|
|
|
|
except Exception as e:
|
|
response = handle_exception(env, wb_router.error_view, e, True)
|
|
|
|
return response(env, start_response)
|
|
|
|
return application
|
|
|
|
|
|
#=================================================================
|
|
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)
|
|
|
|
#=================================================================
|
|
DEFAULT_CONFIG_FILE = 'config.yaml'
|
|
|
|
|
|
#=================================================================
|
|
def init_app(init_func, load_yaml=True, config_file=None):
|
|
logging.basicConfig(format='%(asctime)s: [%(levelname)s]: %(message)s',
|
|
level=logging.DEBUG)
|
|
logging.info('')
|
|
|
|
if load_yaml:
|
|
if not config_file:
|
|
config_file = os.environ.get('PYWB_CONFIG_FILE')
|
|
if not config_file:
|
|
config_file = DEFAULT_CONFIG_FILE
|
|
|
|
config = load_yaml_config(config_file)
|
|
|
|
try:
|
|
if load_yaml:
|
|
wb_router = init_func(config)
|
|
else:
|
|
wb_router = init_func()
|
|
except:
|
|
msg = '*** pywb app init FAILED config from "%s"!\n'
|
|
logging.exception(msg, init_func.__name__)
|
|
raise
|
|
else:
|
|
msg = '*** pywb app inited with config from "%s"!\n'
|
|
logging.info(msg, init_func.__name__)
|
|
|
|
return create_wb_app(wb_router)
|
|
|
|
|
|
#=================================================================
|
|
DEFAULT_PORT = 8080
|
|
|
|
|
|
def start_wsgi_server(the_app):
|
|
from wsgiref.simple_server import make_server
|
|
from optparse import OptionParser
|
|
|
|
opt = OptionParser('%prog [OPTIONS]')
|
|
opt.add_option('-p', '--port', type='int', default=None)
|
|
|
|
options, args = opt.parse_args()
|
|
|
|
port = options.port
|
|
|
|
if port is None:
|
|
try:
|
|
config = load_default_config()
|
|
port = config.get('port', DEFAULT_PORT)
|
|
except:
|
|
port = DEFAULT_PORT
|
|
|
|
logging.debug('Starting CDX Server on port %s', port)
|
|
|
|
try:
|
|
httpd = make_server('', port, the_app)
|
|
httpd.serve_forever()
|
|
except KeyboardInterrupt as ex:
|
|
pass
|
|
|
|
logging.debug('Stopping CDX Server')
|