#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Date    : 2017-08-26 22:48:40
# @Word    : python can change world!
# @Version : python3.6
import requests
import re
def main():
    url='http://www.heibanke.com/lesson/crawler_ex01/'
    num=0
    a=30
    while a >0:
        data={'username':'admin','password':num}
        res=requests.post(url,data=data).text
        if u'错误' in res:
            print(num,'错误')
            num=num+1
            a=a+1
        else:
            print(num,'正确')
            title=re.findall("<title>(.*?)</title>",res)
            word=re.findall("<h1>(.*?)</h1>",res)
            word2=re.findall("<h3>(.*?)</h3>",res)
            html=re.findall('<a href="(.*?)" class="btn btn-primary">下一关</a>',res)
            print('\n'.join([title[0], word[0], word2[0],'下一关地址是','http://www.heibanke.com'+html[0]]))
            break

if __name__ == '__main__':
    main()

import requests
import re
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Date    : 2017-08-26 22:48:40
# @Word    : python can change world!
# @Version : python3.6

def main():
    login_data={'username':'user','password':'password'}
    url='http://www.heibanke.com/lesson/crawler_ex02/'
    login_url='http://www.heibanke.com/accounts/login/?next=/lesson/crawler_ex02/'
    r2=requests.get(login_url)
    c2=r2.cookies
    login_data['csrfmiddlewaretoken']=c2['csrftoken']
    r3=requests.post(login_url,data=login_data,allow_redirects=False,cookies=c2)
    c3=r3.cookies
    pass_data={'username':'user','csrfmiddlewaretoken':c3['csrftoken']}
    for passwd in range(31):
        pass_data['password']=pas
        swd
        r5=requests.post(url,pass_data,cookies=c3)
        text=r5.text
        result=re.findall(r'密码错误',text)
        if u'密码错误' in text:
            print("%s密码错误"%passwd)
        else:
            print("%s密码正确"%passwd)
            title=re.findall("<title>(.*?)</title>",text)
            word=re.findall("<h1>(.*?)</h1>",text)
            word2=re.findall("<h3>(.*?)</h3>",text)
            html=re.findall('<a href="(.*?)" class="btn btn-primary">下一关</a>',text)
            print('\n'.join([title[0], word[0], word2[0],'下一关地址是','http://www.heibanke.com'+html[0]]))
            break
      
if __name__ == '__main__':
    main()

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Date    : 2017-09-02 22:25:21
# @Word    : python can change world!
# @Version : python3.6
import requests
from bs4 import BeautifulSoup
import threading
from queue import Queue


dict1={}
vlauess=[]
web1="http://www.heibanke.com/accounts/login"
web2="http://www.heibanke.com/lesson/crawler_ex03/pw_list/"
web3="http://www.heibanke.com/lesson/crawler_ex03/"
global queuewz
global queuemm
queuewz=Queue()
queuemm=Queue()


class mythreads(threading.Thread):

    def __init__(self):
        threading.Thread.__init__(self)

    def run(self):
        work()
        while not queuemm.empty():
            try:
                dict1[str(queuewz.get())]=queuemm.get()
                print(dict1)
                print("字典长度为%s"%len(dict1))
                if int(len(dict1)) ==100:
                    print("凑到100啦！")
                    for i in range(1,101):
                        vlauess.append(dict1[str(i)])
                    c=vlauess[:100]
                    zzmm=''.join(c)
                    print("密码为%s"%zzmm)
                    print("正在登录.......")
                    dataWebsite1 = {'username': 'user','password': zzmm}
                    s=login_get()
                    res=s.post(web3, data=dataWebsite1).text
                    if u'恭喜' in res:
                        title=re.findall("<title>(.*?)</title>",res)
                        word=re.findall("<h1>(.*?)</h1>",res)
                        word2=re.findall("<h3>(.*?)</h3>",res)
                        html=re.findall('<a href="(.*?)" class="btn btn-primary">下一关</a>',res)
                        print('\n'.join([title[0], word[0], word2[0],'下一关地址是','http://www.heibanke.com'+html[0]]))
                        break
                    else:
                        print("网页有问题哦！可以尝试手动将获得的正确密码登入进去哦！")
                        break
                else:
                    main()
            except IndexError:
                print("例表空了,下一页！")


def login_get():
    try:
        s = requests.Session()
        r=s.get(web1)     # 访问登录页面获取登录要用的csrftoken
        token1 = r.cookies['csrftoken']      # 保存csrftoken
        # 将csrftoekn存入字段csrfmiddlewaretoken
        dataWebsite1 = {'username': 'user',
                        'password': 'password',
                        'csrfmiddlewaretoken': token1
                    }
        res=s.post(web1, data=dataWebsite1)
    except KeyError as e:
        pass

    return s

def get_html(s):
    r=s.get(web2)
    res=r.text
    return res

def get_dict(res):

    soup=BeautifulSoup(res,"html.parser")
    for a in soup.find_all('td',attrs={'title':'password_pos'}):
        wz=(a.string)
        queuewz.put(wz)
    for b in soup.find_all('td',attrs={'title':'password_val'}):
        mm=(b.string)
        queuemm.put(mm)

def work():
    res=get_html(s)
    get_dict(res)


def main():
    global s
    s=login_get()
    threads=[]
    threads_count=10

    for i in range(threads_count):
        threads.append(mythreads())

    for t in threads:
        t.start()

    for t in threads:
        t.join()


if __name__ == '__main__':
    main()

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Date    : 2017-09-11 12:25:25
# @word : python will change the world!
# @Version : 3.6

import requests
import re
import urllib.request
import pytesseract
from PIL import Image
import sys
web_login="http://www.heibanke.com/accounts/login/?next=/lesson/crawler_ex04/"
web_ex04="http://www.heibanke.com/lesson/crawler_ex04/"

def get_s():
    s=requests.Session()
    s.get(web_login)
    token1 = s.cookies['csrftoken']      # 保存csrftoken
    dataWebsite1 = {'username': 'user',
                    'password': 'password',
                    'csrfmiddlewaretoken': token1
                    }
    s.post(web_login, data=dataWebsite1)
    return s

def cleanyzm(yzm,s,num):
    a=yzm
    if len(a.replace(' ',''))!=4:
        print("打回")
        get_img(s,num)
    else:
        yzm=a.upper()
        print(yzm)
        return yzm

def get_img(s,num):
    res=s.get(web_ex04).text
    img=re.findall('![]((.*?))',res)
    img_html='http://www.heibanke.com'+str(img[0])
    print("验证码下载完毕")
    urllib.request.urlretrieve(img_html,"yzm.png")
    yzm=pytesseract.image_to_string(Image.open('yzm.png'),lang='num')
    cshu=re.findall(r'img src="/captcha/image/(.*)/" alt="captcha"', res)[0]
    token1 = s.cookies['csrftoken']
    yzm=cleanyzm(yzm,s,num)
    dataWebsite1 = {'username': 'user',
                        'password': num,
                        'csrfmiddlewaretoken': token1,
                        'captcha_0':cshu,
                        'captcha_1':yzm
                        }
    res=s.post(web_ex04, data=dataWebsite1).text
    if u'密码错误' in res:
        print(num,"密码错误")
        num=num+1
        get_img(s,num)
    else:
        if u'验证码输入错误' in res:
            print(num,"验证码输入错误！")
            get_img(s,num)
        else:
            print(num,"成功！")
            title=re.findall("<title>(.*?)</title>",res)
            word=re.findall("<h1>(.*?)</h1>",res)
            word2=re.findall("<h3>(.*?)</h3>",res)
            print('\n'.join([title[0],word[0],word2[0]]))
            sys.exit(0)

def main():
    s=get_s()
    #global num
    num=0             ########设置开始运行的密码，直到成功程序退出！
    get_img(s,num)


if __name__ == '__main__':
    main()