Check redirects and return status of active webpages

check_domain_status.py

#!/usr/bin/env python3

'''
Script to check redirects and return status of contacted page.
Input file should be one domain per line
'''

from urllib.parse import urlparse
import requests

input_file = 'domains.txt'
output_file = 'output.txt'

def get_domain(url):
    parsed_uri = urlparse(url)
    return '{uri.scheme}://{uri.netloc}/'.format(uri=parsed_uri)


def get_domain_status(url):
    try:
        session = requests.Session()
        res = session.get(url, timeout=0.5)
        print("Processing " + url)

        if len(res.history) > 0:
            chain = ""
            code = res.history[0].status_code
            domain = get_domain(res.url)
            for resp in res.history:
                chain += resp.url + ' => '
            return str(code) + ", " + str(len(res.history)) + ", " + domain + ", " + chain + ", " + res.url
        else:
            return str(res.status_code)
    except requests.exceptions.Timeout:
        return '[Timeout]'
    except requests.exceptions.TooManyRedirects:
        return '[TooManyRedirects]'
    except requests.ConnectionError:
        return '[CnnectionError]'


with open(output_file, 'w') as results_file:
    results_file.write('starting_URL, status, redirects, base_URL, chain, final_URL\n')
    domain_list_file = open(input_file, "r")
    urls = domain_list_file.read().splitlines()
    for url in urls:
        check_url = url if url.startswith('http') else "http://%s" % url
        result = get_domain_status(check_url)
        results_file.write(url + ", " + str(result) + "\n")
    domain_list_file.close()