# coding=utf-8

import httplib, urllib, urllib2, ssl, time, os

HEADERS = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3298.4 Safari/537.36'}

def show_status_urllib(url):
    function_name = 'urllib'
    try:
        response = urllib.urlopen(url)
    except IOError, e:
        return False, function_name + ' : IOError - ' + e.message
    except ssl.CertificateError, e:
        return False, function_name + ' : CertificateError - ' + e.message
    except httplib.BadStatusLine, e:
        return False, function_name + ' : httplib.BadStatisLine - ' + e.message
    else:
        return return_code(function_name, response)


def show_status_urllib2(url):
    function_name = 'urllib2'
    try:
        # request = urllib2.Request(url)
        request = urllib2.Request(url, '', HEADERS)
        response = urllib2.urlopen(request)
    except urllib2.HTTPError, e:
        return False, function_name + ' : HTTPError code ' + str(e.code)
    except urllib2.URLError, e:
        return False, function_name + ' : URLError - ' + str(e.reason)
    except IOError, e:
        return False, function_name + ' : IOError - ' + e.message
    except ssl.CertificateError, e:
        return False, function_name + ' : CertificateError - ' + e.message
    except httplib.BadStatusLine, e:
        return False, function_name + ' : httplib.BadStatisLine - ' + e.message
    else:
        return return_code(function_name, response)


def return_code(function_name, response):
    code = response.getcode()
    if code == 404:
        return False, function_name + ' : code 404 - Page Not Found !'
    elif code == 403:
        return False, function_name + ' : code 403 - Forbidden !'
    else:
        return True, function_name + ' : code ' + str(code) + ' - OK !'


def return_log(protocol, is_true, url, urllib_log, urllib2_log):
    if is_true:
        return '### ' + protocol + '_YES ### ' + url + ' → （' + urllib_log + ' ）（ ' + urllib2_log + '）'
    else:
        return '### ' + protocol + '_NO ### ' + url + ' → （' + urllib_log + ' ）（ ' + urllib2_log + '）'


def request_url(url):
    url = url.strip().replace(" ", "").replace("\n", "").replace("\r\n", "")

    http_url = 'http://' + url
    is_http_urllib_true, http_urllib_log = show_status_urllib(http_url)
    is_http_urllib2_true, http_urllib2_log = show_status_urllib2(http_url)

    https_url = 'https://' + url
    is_https_urllib_true, https_urllib_log = show_status_urllib(https_url)
    is_https_urllib2_true, https_urllib2_log = show_status_urllib2(https_url)

    line = return_log('HTTP', is_http_urllib_true and is_http_urllib2_true, http_url, http_urllib_log, http_urllib2_log) + return_log('HTTPS', is_https_urllib_true and is_https_urllib2_true, https_url, https_urllib_log, https_urllib2_log)
    print line
    return line


def save_log(log_file, log_http_no_and_https_no_file, log_http_no_but_https_yes_file, log_http_yes_but_https_no_file, line):
    line += '\n'
    log_file.write(line)
    log_file.flush()
    if '### HTTP_NO ###' in line:
        if '### HTTPS_NO ###' in line:
            log_http_no_and_https_no_file.write(line)
            log_http_no_and_https_no_file.flush()
        elif '### HTTPS_YES ###' in line:
            log_http_no_but_https_yes_file.write(line)
            log_http_no_but_https_yes_file.flush()
    elif '### HTTP_YES ###' in line and '### HTTPS_NO ###' in line:
        log_http_yes_but_https_no_file.write(line)
        log_http_yes_but_https_no_file.flush()

def main():
    if not os.path.exists('logs'):
        os.mkdir('logs')

    now_time = time.strftime('%Y-%m-%d-%H-%M-%S', time.localtime(time.time()))
    log_file = open('logs/log-' + now_time + '.txt', 'a')
    log_http_no_and_https_no_file = open('logs/log-' + now_time + '-http-no-and-https-no.txt', 'a')
    log_http_no_but_https_yes_file = open('logs/log-' + now_time + '-http-no-but-https-yes.txt', 'a')
    log_http_yes_but_https_no_file = open('logs/log-' + now_time + '-http-yes-but-https-no.txt', 'a')

    print 'URL Testing For List :\n'

    url_of_list = ['www.baidu.com', 'news.baidu.com/guonei', 'www.qq.com', 'www.taobao.com']
    for url in url_of_list:
        save_log(log_file, log_http_no_and_https_no_file, log_http_no_but_https_yes_file, log_http_yes_but_https_no_file, request_url(url))

    print '\nURL Testing For TXT File :\n'

    url_file = open("url.txt")
    for url in url_file.xreadlines():
        save_log(log_file, log_http_no_and_https_no_file, log_http_no_but_https_yes_file, log_http_yes_but_https_no_file, request_url(url))
    url_file.close()

    log_file.close()
    log_http_no_and_https_no_file.close()
    log_http_no_but_https_yes_file.close()
    log_http_yes_but_https_no_file.close()


if __name__ == "__main__":
    main()