GeezerVison

Walltime of each invocation of getproxies_environment() 0.057759761810302734 ms
Walltime of each invocation of getproxies_environment_faster() 0.04382586479187012 ms
Speedup: 24.12388240830176 %

Walltime of each invocation of getproxies_environment() 1.234044075012207 ms
Walltime of each invocation of getproxies_environment_faster() 1.0999860763549805 ms
Speedup: 10.863307184218716 %

import os
import sys
import time


def fill_env_dummy_values(n_proxies=4, n_non_proxies=10):
    for i in range(n_non_proxies):
        os.environ[f'dummy_environ_var_{i}'] = '0' * 50
    for i in range(n_proxies):
        os.environ[f'scheme_{i}_proxy'] = '0' * 20


# https://github.com/python/cpython/blob/f8be2e262c5c2fdbc9721210ae1cb46edc16db82/Lib/urllib/request.py#L2479
def getproxies_environment():
    """Return a dictionary of scheme -> proxy server URL mappings.

    Scan the environment for variables named <scheme>_proxy;
    this seems to be the standard convention.  If you need a
    different way, you can pass a proxies dictionary to the
    [Fancy]URLopener constructor.
    """
    # in order to prefer lowercase variables, process environment in
    # two passes: first matches any, second pass matches lowercase only

    # select only environment variables which end in (after making lowercase) _proxy
    proxies = {}
    environment = []
    for name in os.environ.keys():
        # fast screen underscore position before more expensive case-folding
        if len(name) > 5 and name[-6] == "_" and name[-5:].lower() == "proxy":
            value = os.environ[name]
            proxy_name = name[:-6].lower()
            environment.append((name, value, proxy_name))
            if value:
                proxies[proxy_name] = value
    # CVE-2016-1000110 - If we are running as CGI script, forget HTTP_PROXY
    # (non-all-lowercase) as it may be set from the web server by a "Proxy:"
    # header from the client
    # If "proxy" is lowercase, it will still be used thanks to the next block
    if 'REQUEST_METHOD' in os.environ:
        proxies.pop('http', None)
    for name, value, proxy_name in environment:
        # not case-folded, checking here for lower-case env vars only
        if name[-6:] == '_proxy':
            if value:
                proxies[proxy_name] = value
            else:
                proxies.pop(proxy_name, None)
    return proxies


# Speedup of
# https://github.com/python/cpython/blob/f8be2e262c5c2fdbc9721210ae1cb46edc16db82/Lib/urllib/request.py#L2479
def getproxies_environment_faster():
    """Return a dictionary of scheme -> proxy server URL mappings.

    Scan the environment for variables named <scheme>_proxy;
    this seems to be the standard convention.  If you need a
    different way, you can pass a proxies dictionary to the
    [Fancy]URLopener constructor.
    """
    # in order to prefer lowercase variables, process environment in
    # two passes: first matches any, second pass matches lowercase only

    # select only environment variables which end in (after making lowercase) _proxy
    proxies = {}
    environment = []
    for name in os.environ:  # No .keys() here.
        # fast screen underscore position before more expensive case-folding
        if len(name) > 5 and name[-6] == "_" and name[-5:].lower() == "proxy":
            value = os.environ[name]
            proxy_name = name[:-6].lower()
            environment.append((name, value, proxy_name))
            if value:
                proxies[proxy_name] = value
    # CVE-2016-1000110 - If we are running as CGI script, forget HTTP_PROXY
    # (non-all-lowercase) as it may be set from the web server by a "Proxy:"
    # header from the client
    # If "proxy" is lowercase, it will still be used thanks to the next block
    if 'REQUEST_METHOD' in os.environ:
        proxies.pop('http', None)
    for name, value, proxy_name in environment:
        # not case-folded, checking here for lower-case env vars only
        if name[-6:] == '_proxy':
            if value:
                proxies[proxy_name] = value
            else:
                proxies.pop(proxy_name, None)
    return proxies


if __name__ == '__main__':
    fill_env_dummy_values(n_proxies=4, n_non_proxies=int(sys.argv[1]))

    # Make sure there is no pre-warming effect.
    getproxies_environment()
    getproxies_environment_faster()
    
    num_repeats = 1000
    t0 = time.time()
    for _ in range(num_repeats):
        getproxies_environment()
    getproxies_environment_time_per_call = (time.time() - t0) / num_repeats
    print('Walltime of each invocation of getproxies_environment()',
          getproxies_environment_time_per_call * 1000, 'ms')
    t0 = time.time()
    for _ in range(num_repeats):
        getproxies_environment_faster()
    getproxies_environment_faster_time_per_call = (time.time() - t0) / num_repeats
    print('Walltime of each invocation of getproxies_environment_faster()',
          getproxies_environment_faster_time_per_call * 1000, 'ms')
    print('Speedup:', (getproxies_environment_time_per_call - getproxies_environment_faster_time_per_call) / getproxies_environment_time_per_call * 100, '%')