Get_Web_banner(批量获取网站banner)

环境：Python3

get_banner.py：

 

import chardet
import requests,re
from threading import Thread,activeCount
from sys import argv
from queue import Queue


requests.packages.urllib3.disable_warnings()
new_targets = []

def get_banner(url):
        if 'http://' or 'https://' not in url.strip(): #判断有无协议
            target = 'http://' + url.strip()
        try:
            req = requests.get(target,verify=False,allow_redirects=False,timeout=(5,20))
            if 'charset' not in req.headers.get('Content-Type', " "):
                req.encoding = chardet.detect(req.content).get('encoding')  # 解决网页编码问题
            code = req.status_code
            if '30' in str(code):
                if req.headers['Location'] == 'https://' + target.strip('http://') + '/':
                    req_30x = requests.get('https://{}'.format(target.strip('http://')),verify=False,timeout=(5,20))
                    code_30x = str(req_30x.status_code).strip()
                    if 'charset' not in req_30x.headers.get('Content-Type', " "):
                        req_30x.encoding = chardet.detect(req_30x.content).get('encoding')  # 解决网页编码问题
                    try:
                        title_30x = re.findall(r'<title>(.*?)</title>',req_30x.text,re.S)[0].strip()
                    except:
                        title_30x = 'None'
                    if 'Server' in req_30x.headers:
                        server_30x = req_30x.headers['Server'].strip()
                    else:
                        server_30x = ''
                    if 'Content-Type' in req_30x.headers:
                        type_30x = req_30x.headers['Content-Type'].strip()
                    else:
                        type_30x = ''
                    if 'X-Powered-By' in req_30x.headers:
                        x_powered_by_30x = req_30x.headers['X-Powered-By'].strip()
                    else:
                      x_powered_by_30x = ''
                    print('[+] {} {} {} {} {} {} '.format(code_30x,target,title_30x,server_30x,type_30x,x_powered_by_30x))
                    write_info(target,code_30x,title_30x, server_30x, type_30x,x_powered_by_30x)
                else:
                    title = '302_redirection'
                    location = req.headers['Location']
                    print('[+] {} {} {} Location：{}'.format(code,target,title,location))
                    write_info(target,code,title,location=location)
            else:
                try:
                    title = re.findall(r'<title>(.*?)</title>',req.text,re.S)[0].strip()
                except:
                    title = 'None'
                if 'Server' in req.headers:
                    server = req.headers['Server'].strip()
                else:
                    server = ''
                if 'Content-Type' in req.headers:
                    type = req.headers['Content-Type'].strip()
                else:
                    type = ''
                if 'X-Powered-By' in req.headers:
                    x_powered_by = req.headers['X-Powered-By'].strip()
                else:
                    x_powered_by = ''
                write_info(target,code,title,server,type,x_powered_by)
                print('[+] {} {} {} {} {}'.format(code,target,title,server,x_powered_by))
        except Exception as e:
            print('[-]Error {} {} '.format(target,str(e)))


def write_info(url,code,title='',server='',type='',x_power_by='',location=''):
    with open('websites_banner.txt','a+') as f:
        f.write('{} {} {} {} {} {} \n'.format(code,url,title,server,type,x_power_by,location))

if __name__ == '__main__':
    try:
        queue = Queue()
        filename = argv[1]
        new_filename = argv[2]
        with open(filename,'r+') as f:
            for url in f:
                url = url.strip()
                if url not in new_targets:
                    new_targets.append(url)
        for new_url  in new_targets:
            queue.put(new_url)
            with open(new_filename,'a+') as f:
                f.write(new_url + '\n')
        while queue.qsize() > 0:
            if activeCount() <= 10:
                Thread(target=get_banner, args=(queue.get(),)).start()
    except IndexError:
        print('Usage：python3 get_banner.py urls.txt new_urls.txt')

使用方法：

1.在当目录下urls.txt中放入需要获取banner的url(可有http可无http)。

 

update：python3 get_banner.py urls.txt

 

2019.4.24 update：

1.对跳转进行优化，判断如果跳转后为https://加上原域名，则继续获取标题，并且添加上了headers。

2. Referer可根据爬取的情况自行修改。

2019.5.21 update：

加入多线程，修改使用方法。

 

Use：python3 get_banner.py urls.txt new_urls.txt

 

转载于:https://www.cnblogs.com/P1g3/p/10735233.html