Python 简单的爬取网站状态码标题

import requests
import re
import time
import threadpool
import traceback
code_200 = []
code_not200 = []
_REGEX_ = '<title>(.*)</title>'
def getTitle(url):
    try:
        response = requests.get(url)
        pattern = re.compile(_REGEX_, flags=re.IGNORECASE)
        try:
            title = re.findall(pattern, response.text)[0]
        except IndexError:
            title = '无标题'
        if response.status_code == 200:
            code_200.append({'url':url,'title':title,"status_code":response.status_code})
            print({'url':url,'title':title,"status_code":response.status_code})
            return
        else:
            code_not200.append({'url':url,'title':title,"status_code":response.status_code})
            print({'url': url, 'title': title, "status_code": response.status_code})
            return
    except Exception as e:
        traceback.print_exc()
        return 0


if __name__ == '__main__':
    domain = []
    with open('test5.txt','r') as f:
        for i in f.readlines():
            domain.append(i.strip())
        f.close()
    print(domain)
    start_time = time.time()
    pool = threadpool.ThreadPool(100)
    requests_1 = threadpool.makeRequests(getTitle, domain)
    [pool.putRequest(req) for req in requests_1]
    pool.wait()
    with open('test6.txt','w+',encoding='UTF-8') as f:
        for i in code_200:
            f.write(str(i) + '\n')
        for i in code_not200:
            f.write(str(i) + '\n')
    print('%d second' % (time.time() - start_time))