request-headers-checker/reqhead

#!/usr/bin/env python3

""" Status Checker to detect response codes and server information """
# full source: https://github.com/angela-d/request-headers-checker
# license:     GPLv3
# author:      angela-d

import pprint
from json import dumps, loads
import sys
from ssl import create_default_context
import socket
from argparse import ArgumentParser
from requests import get, exceptions

# font colors
GREEN = '\033[32m'
YELLOW = '\033[33m'
CLR_COLOR = '\033[m' # reset color to default


def startup(entered_url):
    """ Startup """

    try:

        if entered_url is None:
            print(
                GREEN
                + "\t\tEnter the url you wish to investigate, including the http(s)://"
                + CLR_COLOR
            )

            entered_url = input("URL: ")

        get_http_info(entered_url)

    # if a user chooses to cancel their session before processing a url
    except KeyboardInterrupt:
        print('\nExiting..')
        sys.exit(0)
    except EOFError:
        print('\nExiting..')
        sys.exit(0)


def get_http_info(check_url):
    """ Parse the user-entered URL """
    # try & circumvent user agent blocking for python requests
    spoof_agent = {
        'Accept-Language': 'en-US,en;q=0.5',
        'User-Agent'     : 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Mozilla/5.0 (Windows NT 6.1; WOW64; rv:40.0) Gecko/20100101 Firefox/66.0', # pylint: disable=C0301
        'Accept'         : 'text/html,application/xhtml+xml,application/xml;q =0.9,*/*;q=0.8',
        'Referrer'       : 'https://www.startpage.com'
    }

    try:
        access_url = get(check_url, headers=spoof_agent)
        if len(access_url.history) < 1:
            # normal request
            print(GREEN + '\n\t\t----- Headers for', check_url, ' -----' + CLR_COLOR)
            print("\nHTTP Response: " + str(access_url.status_code))

            request_header = dumps(dict(access_url.headers))
            format_headers = pprint.PrettyPrinter(indent=2)
            format_headers.pprint(loads(request_header))

            # obtain ssl issuer information (if https)
            if 'https:' in check_url:
                print(GREEN + '\n\t\t----- SSL Headers for', check_url, ' -----' + CLR_COLOR)
                hostname = check_url.split("//")[-1].split("/")[0].split('?')[0]

                context = create_default_context()
                server  = context.wrap_socket(socket.socket(), server_hostname=hostname) #pylint: disable=C0326
                server.connect((hostname, 443))
                cert = server.getpeercert()

                issued = dict(extract[0] for extract in cert['subject'])
                issuer = dict(extract[0] for extract in cert['issuer'])

                print('SSL cert issued to', issued['commonName'], 'by', issuer['commonName'],\
                'on', cert['notBefore'], 'expires', cert['notAfter'])

        else:
            # redirects detected
            print(YELLOW + '\n\t\t----- Redirect(s) detected for', check_url, ' -----' + CLR_COLOR)

            redirect_status = get(check_url, allow_redirects=False)
            print(redirect_status.status_code, ' detected from', check_url, \
            'to', redirect_status.headers['Location'], \
            '\n\t\x1B[3mRun a check on ' + redirect_status.headers['Location'] \
            + ' instead.\x1B[23m\n\n')
            startup(entered_url=None)

    # some errors encountered
    except exceptions.InvalidSchema as show_error:
        print(show_error)
        startup(entered_url=None)
    except exceptions.MissingSchema as show_error:
        print(show_error)
        startup(entered_url=None)
    except exceptions.ConnectionError:
        print("Took too long to connect; ensure the URL is valid and try again.")
        sys.exit(1)
    except exceptions.Timeout:
        print("Timeout.  Server might be offline or not responding.")
        sys.exit(1)
    except exceptions.TooManyRedirects:
        print("Infinite Redirects.  Site is poorly configured.")
        sys.exit(1)

if __name__ == '__main__':
    PARSE = ArgumentParser(description='A Python tool to get header \
    information from a website.\nhttp:// or https:// are required.')
    PARSE.add_argument(
        '--version', '-v',
        action='version',
        version='%(prog)s 2.0.0'
        )
    PARSE.add_argument(
        '--url', '-url',
        action='store_true'
        )

    NAMESPACE = PARSE.parse_known_args()

    if len(NAMESPACE[1]) == 1:
        ARGTUP = NAMESPACE[1]
        startup(ARGTUP[0])
    else:
        startup(entered_url=None)