改编版，没有封装函数# -*- coding: utf-8 -*-
from urllib import request
from urllib import parse
from http import cookiejar
import re
import os
url = 'https://accounts.douban.com/login'
form_data = {'source':'index_nav',
'redir':'https://www.douban.com/',
'form_email':'你的用户名',
'form_password':'你的密码'}
cookie = cookiejar.CookieJar()
opener = request.build_opener(request.HTTPCookieProcessor(cookie))
opener.addheaders = [('User-Agent',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/63.0.3239.84 Safari/537.36')]
# 获取验证码
html = request.urlopen(url).read().decode('utf-8')
src = re.findall('<img id="captcha_image" src="(.+?)" alt=',html)[0]
if len(src) > 0:
request.urlretrieve(src,'1.png')
os.startfile('1.png')
solution = input('请输入验证码：')
id = re.findall('id=(.+?)&',src)[0]
form_data = {'source': 'index_nav',
'redir': 'https://www.douban.com/',
'form_email': '你的用户名',
'form_password': '你的用户名',
'captcha-solution':solution,
'captcha-id':id,
'login':'登录'}
# 披着cookie马甲向服务器发起请求
data = parse.urlencode(form_data).encode()
r = opener.open(url,data)
# 登陆后解析网页找到正则匹配自己的帐号
r = opener.open('https://www.douban.com').read().decode('utf-8')
pattern = re.compile('<span>(.+?)的帐号</span>')
result = re.findall(pattern,r)
print(result)
| 
( 粤ICP备18085999号-1 | 粤公网安备 44051102000585号)
狗仔卡
发表于 2017-12-21 10:16:54
显身卡
发表于 2018-3-30 22:19:23
