黑板客爬虫闯关的第四关

最新推荐文章于 2019-08-12 09:36:00 发布

Test_C.

最新推荐文章于 2019-08-12 09:36:00 发布

阅读量185

点赞数

分类专栏： Python

本文链接：https://blog.csdn.net/weixin_42544006/article/details/92989941

版权

Python 专栏收录该内容

110 篇文章 3 订阅

订阅专栏

import requests
import re

def passwd():
    headers = {
        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3",
        "Accept-Encoding": "gzip, deflate",
        "Accept-Language": "zh,zh-CN;q=0.9,en;q=0.8",
        "Cookie": "Hm_lvt_74e694103cf02b31b28db0a346da0b6b=1560757431; sessionid=8b68mgloyia36ecle55lbupcr4ifairx; csrftoken=oragp4ndPhp1reUDGBgRzzHO70FwYp6n; Hm_lpvt_74e694103cf02b31b28db0a346da0b6b=1560991699",
        "Host": "www.heibanke.com",
        "Proxy-Connection": "keep-alive",
        "Referer": "http://www.heibanke.com/lesson/crawler_ex03/pw_list/?page=5",
        "Upgrade-Insecure-Requests": "1",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.80 Safari/537.36",

    }
    all_list = []
    gz = re.compile(r'password_pos">(.*?)</td>.*?password_val">(.*?)</td>',re.S)
    for i in range(1,14):
        url = 'http://www.heibanke.com/lesson/crawler_ex03/pw_list/?page={}'.format(i)
        html = requests.get(url,headers=headers,timeout=(20,20))

        find_all = gz.findall(html.text)
        all_list += find_all
    print(all_list)
    print(len(all_list))
    return all_list



def test(b=None):
    a = passwd()
    for _ in a:
        index = int(_[0])-1
        val = int(_[1])
        b[index] = val
    print('---',b)
    if b.count(None) >= 1:
        test(b)
    else:
        print('密码:',''.join([str(i) for i in a]))

test(b=[None for _ in range(100)])
# print(b)

6952443295489461364799039487432604843713487766181369634491632647064899367028310525338190161357943396