最近写了批量get网站title的脚本，脚本很慢不实用，bug很多，慎用！主要是总结踩得坑，就当模块练习了。
源码如下：
import requests
import argparse
import re
class bcolors:
HEADER = ‘\033[95m‘
OKBLUE = ‘\033[94m‘
OKGREEN = ‘\033[92m‘
WARNING = ‘\033[93m‘
FAIL = ‘\033[91m‘
ENDC = ‘\033[0m‘
BOLD = ‘\033[1m‘
UNDERLINE = ‘\033[4m‘
def parser_args():
parser = argparse.ArgumentParser()
parser.add_argument("-f","--file",help="指定domain文件")
# parser.add_argument("-f","--file",help="指定domain文件",action="store_true") 不可控
return parser.parse_args()
def httpheaders(url):
proxies = {
‘http‘: ‘http://127.0.0.1:8080‘
}
headers = {
‘Connection‘: ‘close‘,
‘Upgrade-Insecure-Requests‘: ‘1‘,
‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.110 Safari/537.36‘,
‘Accept‘: ‘text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8‘,
‘Accept-Encoding‘: ‘gzip, deflate, sdch, br‘,
‘Accept-Language‘: ‘zh-CN,zh;q=0.8‘,
}
requests.packages.urllib3.disable_warnings()
res = requests.get(url, proxies=proxies, headers=headers, timeout=10, verify=False)
res.encoding = res.apparent_encoding
head = res.headers
# print(‘[+]url:‘+url,‘ ‘+‘Content-Type:‘+head[‘Content-Type‘])
title = re.findall("<title>(.*)</title>", res.text, re.IGNORECASE)[0].strip()
print(bcolors.OKGREEN+‘[+]url:‘+url,‘ ‘+‘title:‘+title+‘ length:‘+head[‘Content-Length‘]+bcolors.ENDC)
def fileopen(filename):
with open(filename,‘r‘) as obj:
for adomain in obj.readlines():
adomain = adomain.rstrip(‘\n‘)
try:
httpheaders(adomain)
except Exception as e:
print(bcolors.WARNING +‘[+]‘+adomain+" Connect refuse"+bcolors.ENDC)
if __name__ == "__main__":
try:
abc = vars(parser_args())
a = abc[‘file‘]
fileopen(a)
except FileNotFoundError as e:
print(‘目录下无该文件‘+a)
本次踩到的坑：
1.使用Python3 requests发送HTTPS请求，已经关闭认证（verify=False）情况下，控制台会输出以下错误：
InsecureRequestWarning: Unverified HTTPS request is being made. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings
命令行看到此消息，强迫症会很难受。
解决办法：在执行code前加入 requests.packages.urllib3.disable_warnings()
2.关于argparse模块的用法：
def parser_args():
parser = argparse.ArgumentParser() #创建ArgumentParser()对象
parser.add_argument("-f","--file",help="指定domain文件") #主要看第二个参数，--file将file传作key值，例如：-f aaa,那么file的value为‘aaa‘
# parser.add_argument("-f","--file",help="指定domain文件",action="store_true") 不可控
return parser.parse_args()
原文：https://www.cnblogs.com/devapath/p/12446259.html