URL Scanner in Python

url_scan.py

#!/usr/bin/env python
#
# The requests module is probably already on your system. If it is not
# the run: easy_install requests
#
import sys
import requests

def checkUrl(url):
    try:
        # If you get too many TMO errors try increasing the timeout value.
        resp = requests.head(url, timeout=2, verify=False, allow_redirects=False)
        code = resp.status_code

        if code >= 200 and code <= 299:
            print '2XX: {0}'.format(url)
        elif code >= 300 and code <= 399:
            print '3XX: {0} -> {1}'.format(url, resp.headers['location'])
        elif code >= 400 and code <= 499:
            print '4XX: {0}'.format(url)
        elif code >= 500 and code <= 599:
            print '5XX: {0}'.format(url)
        else:
            print '{0}: {1}'.format(resp.status_code, url)

    except requests.exceptions.ConnectionError:
        print 'CXN: {0}'.format(url)

    except requests.exceptions.Timeout:
        print 'TMO: {0}'.format(url)

    except Exception as e:
        print 'UNK: {0} - {1}'.format(url, str(e))


if __name__ == '__main__':
    if len(sys.argv) != 2:
        print 'Usage: url_scan.py url_file'

    for url in open(sys.argv[1]):
        url = url.rstrip('\r\n')

        # Skip empty lines, comments, and lines that do not begin with http
        if url == '': continue
        if url[0] == '#': continue
        if url[:4] != 'http': continue

        checkUrl(url)