模拟登录这块一直没搞过，主要是对 模拟登陆的流程不太熟悉，网上找了好多资料，感觉熟悉个大概，就先用豆瓣 试试。
验证码这一块，现在主要是先把验证码的图片保存下来，手动输入验证码，后期研究下python自动识别验证码。
但是验证码保存成本地图片，看的不不太清楚（有时间在改下），可以把验证码的 url 地址在浏览器中打开，就可以看清楚验证码了。
主要实现 登录豆瓣，并发表一句话
# -*- coding:utf-8 -*-
import re
import requests
from bs4 import BeautifulSoup
class DouBan(object):
def __init__(self):
self.__username = "豆瓣帐号" # 豆瓣帐号
self.__password = "豆瓣密码" # 豆瓣密码
self.__main_url = "https://www.douban.com"
self.__login_url = "https://www.douban.com/accounts/login"
self.__proxies = {
"http": "http://172.17.18.80:8080",
"https": "https://172.17.18.80:8080"
}
self.__headers = {
"Host": "www.douban.com",
"Origin": self.__main_url,
"Referer": self.__main_url,
"Upgrade-Insecure-Requests": "1",
"User-Agent": 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'
}
self.__data = {
"source": "index_nav",
"redir": "https://www.douban.com",
"form_email": self.__username,
"form_password": self.__password,
"login": u"登录"
}
self.__session = requests.session()
self.__session.headers = self.__headers
self.__session.proxies = self.__proxies
pass
def login(self):
r = self.__session.post(self.__login_url, self.__data)
if r.status_code == 200:
html = r.content
soup = BeautifulSoup(html, "lxml")
captcha_address = soup.find('img', id='captcha_image')['src']
print captcha_address
# 验证码存在
if captcha_address:
# 利用正则表达式获取captcha的ID
re_captcha_id = r'<input type="hidden" name="captcha-id" value="(.*?)"/'
captcha_id = re.findall(re_captcha_id, html)
print captcha_id
# 保存到本地
with open('captcha.jpg', 'w') as f:
f.write(requests.get(captcha_address, proxies=self.__proxies).content)
captcha = raw_input('please input the captcha:')
self.__data['captcha-solution'] = captcha
self.__data['captcha-id'] = captcha_id
r = self.__session.post(self.__login_url, data=self.__data)
if r.status_code == 200:
print "login success"
data = {
"ck": "NBJ2",
"comment": "模拟登录"
}
r = self.__session.post(self.__main_url, data=data)
print r.status_code
else:
print "登录不需要验证码"
# 不需要验证码的逻辑 和 上面输入验证码之后 的 逻辑 一样
# 此处代码省略
else:
print "login fail", r.status_code
pass
if __name__ == "__main__":
t = DouBan()
t.login()
pass
登录豆瓣帐号，可以看到说了一句话 “模拟登录”
时间： 2024-10-13 16:10:22