Python urllib.request 模块，getproxies() 实例源码

def proxyurllib():
    print(COLOR_GREEN+'-'*30+COLOR_NONE)
    #TODO proxy
    handler=request.ProxyHandler({'http':'http://10.112.5.173:49908'})
    '''
    proxy_auth_handler = urllib.request.ProxyBasicAuthHandler()
    proxy_auth_handler.add_password('realm', 'host', 'username', 'password')
    '''
    opener=request.build_opener(handler)
    request.install_opener(opener)
    #??opener??urlopen()?????URL opener??????urlopen()????????opener???response=
    google = request.urlopen('http://www.google.com')
    print(google.read())

    print("?????",request.getproxies())

#proxyurllib()

#FIXME ROBOT.TXT??

def make_soup(url):  # pragma: no cover
    """Make soup, that is basically parsing the html document."""
    response = requests.get(
        url,
        headers={'User-agent': 'UIP'},
        # gets system proxy (if it is currently using one)
        proxies=getproxies())

    html = response.content
    return BeautifulSoup(html, "html.parser")

def make_json(url):  # pragma: no cover
    """Make a dictionary out of a json file."""
    response = requests.get(
        url,
        headers={'User-agent': 'UIP'},
        # gets system proxy (if it is currently using one)
        proxies=getproxies())

    json_file = response.text
    data = json.loads(json_file)
    return data

def get_proxies():
    proxies = getproxies()
    filtered_proxies = {}
    for key, value in proxies.items():
        if key.startswith('http'):
            if not value.startswith('http'):
                filtered_proxies[key] = 'http://%s' % value
            else:
                filtered_proxies[key] = value
    return filtered_proxies