模拟登陆豆瓣，发帖和回复code

from bs4 import BeautifulSoup
import requests
from html.parser import HTMLParser
from PIL import Image

#模拟登陆豆瓣

class MomNi():
#初始化
def init(self):
self.header = {
‘User-Agent’:’Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36’
}
self.session = requests.session()
#seession方法

#登录code
def longin(self,form_email,form_password,):

    login_url = 'https://accounts.douban.com/login'
    #登录url

    response = self.session.get(login_url)
    #get获取网址信息

    (captch_id,captch_url) = _get_captcha(response.content.decode('utf-8'))
    # 传入验证码的图片和标签

    print(captch_id)

    if captch_id:
        r = self.session.get(captch_url)
        with open('captcha.jpg','wb') as f:
            f.write(r.content)
        #如果ID 存在获取图片链接并写入
        try:
            img = Image.open('captch.jpg',mode="r")
            img.show()
            img.close()
        except:
            print('请输入验证码')

        captcha_solution = input('please input solution for captcha[{}:'.format(captch_url))
        #输入验证码

    #没有验证码的参数
    data = {
        'form_email':form_email,
        'form_password':form_password,
        'source': 'index_nav',
        'user_login': '登录',
        'redir':'https: // www.douban.com /'
    }
     #验证码参数                                           }
    if captch_id:
        data['captcha-id'] = captch_id
        data['captcha-solution'] = captcha_solution

    self.session.post(login_url,data=data,headers=self.header)
    # print(self.session.get('https://www.douban.com').content.decode('utf-8'))   登陆后内容


#发帖
def get_content(self,comment,ck = '6_29',):
    data = {
        'ck' : ck,
        'comment':comment
    }
    self.session.post('https://www.douban.com/',data=data,headers=self.header)

#定义_attr方法，解析式调用

def _attr(attrs,attrname):
    for attr in attrs:
        if attr[0] == attrname:
            return attr[1]
    return None

def _get_captcha(content):
    # 继承HTMLParser解析方法
    class Captchaparser(HTMLParser):
        def __init__(self):
            HTMLParser.__init__(self)
            self.captch_id = None
            self.captch_url = None

        #使用HTMLparser解析标签和属性
        def handle_starttag(self, tag, attrs):
            #验证码图片
            if tag == 'img' and _attr(attrs, 'id') == 'captcha_image' and _attr(attrs, 'class') == 'captcha_image':
                self.captch_url = _attr(attrs,'src')

            #验证码输入框
            if tag == 'input' and _attr(attrs, 'type') == 'hidden' and _attr(attrs,'name') == 'captcha-id':
                self.captch_id = _attr(attrs,'value')


    p = Captchaparser()
    # 实例化这个类
    p.feed(content)
    # 传入要解析的文本
    return p.captch_id,p.captch_url
    #将匹配到的数据返回

if __name__ == '__main__':
    form_email = input('plase your email:')
    form_password = input('plase your password:')
    #输入用户名密码
    Run = MomNi()
    #调用方法
    Run.longin(form_email,form_password)
    #传入用户名和方法
    comment = input('plase input comment:')
    #发帖
    Run.get_content(comment)
    #调用发帖函数

code中没有回复发帖函数。

    是因为在回复已发帖内容时，每个内容的代码ID都是唯一的。  不同发帖内容的ID各不相同。