黑板客爬虫闯关

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Date    : 2018-04-03 22:34:21
# @Author  : csu_vc(s4ad0w.protonmail.com)
# @Link    : http://blog.csdn.net/csu_vc
# @Version : python3.6

import requests
import re

def add_url(url,num):
    return url+num

def next(url):
    global flag
    content = requests.get(url)
    content = content.text.encode('utf-8')
    pattern = re.compile(r'下一个你需要输入的数字是(.*?)\.')
    num = pattern.findall(content)
    if len(num)>0:
        print num[0]
        return num
    else:
        # flag = 0
        # print flag
        print content
        # return num

def main():
    flag = 1
    url = 'http://www.heibanke.com/lesson/crawler_ex00/'
    content = requests.get(url)
    content = content.text.encode('utf-8')
    pattern = re.compile(r'你需要在网址后输入数字(.*?)</h3>')
    num = pattern.findall(content)
    print num[0]
    while(flag==1):
        try:
            num = next(add_url(url,num[0]))
            # print flag
        except Exception as e:
            flag = 0
            print e
    print '[!]works have already done yet'

if __name__ == '__main__':
    main()

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Date    : 2018-04-04 21:48:19
# @Author  : csu_vc(s4ad0w.protonmail.com)
# @Link    : http://blog.csdn.net/csu_vc
# @Version : python3.6

import requests
import re

url = 'http://www.heibanke.com/lesson/crawler_ex01/'
content = requests.get(url)
content = content.content
pattern = re.compile(r"name='csrfmiddlewaretoken' value='(.*)' />")
result1 = pattern.findall(content)
for i in range(1,30):
    data={
        'csrfmiddlewaretoken':result1[0],
        'username':'aa',
        'password':i,
    }
    content = requests.post(url,data=data)
    if '您输入的密码错误' in content.content:
        print '[*]'+'尝试'+str(i)+'失败'
    else:
        print '[!]'+'尝试'+str(i)+'成功'
        print content.content