|
1 | 1 | #!/usr/bin/env python3 |
2 | 2 | # -*- coding: utf-8 -*- |
3 | | - |
4 | | -''' |
5 | | -Required |
6 | | -- requests (必须) |
7 | | -- bs4 (必选) |
8 | | -- pillow (可选) |
9 | | -''' |
10 | | - |
11 | | -from urllib.request import urlretrieve |
12 | 3 | import requests |
13 | | -from bs4 import BeautifulSoup |
14 | | -from os import remove |
15 | | - |
16 | | -try: |
17 | | - import cookielib |
18 | | -except: |
19 | | - import http.cookiejar as cookielib |
20 | | -try: |
21 | | - from PIL import Image |
22 | | -except: |
23 | | - pass |
24 | | - |
25 | | -url = 'https://accounts.douban.com/login' |
26 | | - |
27 | | -datas = {'source': 'index_nav', |
28 | | - 'remember': 'on'} |
29 | | - |
30 | | -headers = {'Host': 'www.douban.com', |
31 | | - 'Referer': 'https://www.douban.com/', |
32 | | - 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:55.0) Gecko/20100101 Firefox/55.0', |
33 | | - 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', |
34 | | - 'Accept-Language': 'zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3', |
35 | | - 'Accept-Encoding': 'gzip, deflate, br'} |
36 | | - |
37 | | -# 尝试使用cookie信息 |
38 | | -session = requests.session() |
39 | | -session.cookies = cookielib.LWPCookieJar(filename='cookies') |
40 | | -try: |
41 | | - session.cookies.load(ignore_discard=True) |
42 | | -except: |
43 | | - print("Cookies未能加载") |
44 | | - # cookies加载不成功，则输入账号密码信息 |
45 | | - datas['form_email'] = input('Please input your account:') |
46 | | - datas['form_password'] = input('Please input your password:') |
47 | | - |
48 | | - |
49 | | -def get_captcha(): |
50 | | - ''' |
51 | | - 获取验证码及其ID |
52 | | - ''' |
53 | | - r = requests.post(url, data=datas, headers=headers) |
54 | | - page = r.text |
55 | | - soup = BeautifulSoup(page, "html.parser") |
56 | | - # 利用bs4获得验证码图片地址 |
57 | | - img_src = soup.find('img', {'id': 'captcha_image'}).get('src') |
58 | | - urlretrieve(img_src, 'captcha.jpg') |
59 | | - try: |
60 | | - im = Image.open('captcha.jpg') |
61 | | - im.show() |
62 | | - im.close() |
63 | | - except: |
64 | | - print('到本地目录打开captcha.jpg获取验证码') |
65 | | - finally: |
66 | | - captcha = input('please input the captcha:') |
67 | | - remove('captcha.jpg') |
68 | | - captcha_id = soup.find( |
69 | | - 'input', {'type': 'hidden', 'name': 'captcha-id'}).get('value') |
70 | | - return captcha, captcha_id |
71 | | - |
72 | | - |
73 | | -def isLogin(): |
74 | | - ''' |
75 | | - 通过查看用户个人账户信息来判断是否已经登录 |
76 | | - ''' |
77 | | - url = "https://www.douban.com/accounts/" |
78 | | - login_code = session.get(url, headers=headers, |
79 | | - allow_redirects=False).status_code |
80 | | - if login_code == 200: |
81 | | - return True |
82 | | - else: |
83 | | - return False |
84 | | - |
85 | 4 |
|
86 | | -def login(): |
87 | | - captcha, captcha_id = get_captcha() |
88 | | - # 增加表数据 |
89 | | - datas['captcha-solution'] = captcha |
90 | | - datas['captcha-id'] = captcha_id |
91 | | - login_page = session.post(url, data=datas, headers=headers) |
92 | | - page = login_page.text |
93 | | - soup = BeautifulSoup(page, "html.parser") |
94 | | - result = soup.findAll('div', attrs={'class': 'title'}) |
95 | | - # 进入豆瓣登陆后页面，打印热门内容 |
96 | | - for item in result: |
97 | | - print(item.find('a').get_text()) |
98 | | - # 保存 cookies 到文件， |
99 | | - # 下次可以使用 cookie 直接登录，不需要输入账号和密码 |
100 | | - session.cookies.save() |
| 5 | +""" |
| 6 | +info: |
| 7 | +author:CriseLYJ |
| 8 | +github:https://github.com/CriseLYJ/ |
| 9 | +update_time:2019-04-04 |
| 10 | +""" |
| 11 | + |
| 12 | +""" |
| 13 | +模拟登陆豆瓣 |
| 14 | +""" |
| 15 | + |
| 16 | + |
| 17 | +class DouBanLogin(object): |
| 18 | + def __init__(self, account, password): |
| 19 | + self.url = "https://accounts.douban.com/j/mobile/login/basic" |
| 20 | + self.headers = { |
| 21 | + "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36" |
| 22 | + } |
| 23 | + """初始化数据""" |
| 24 | + self.data = { |
| 25 | + "ck": "", |
| 26 | + "name": account, |
| 27 | + "password": password, |
| 28 | + "remember": "true", |
| 29 | + "ticket": "" |
| 30 | + } |
| 31 | + self.session = requests.Session() |
| 32 | + |
| 33 | + def get_cookie(self): |
| 34 | + """模拟登陆获取cookie""" |
| 35 | + html = self.session.post( |
| 36 | + url=self.url, |
| 37 | + headers=self.headers, |
| 38 | + data=self.data |
| 39 | + ).json() |
| 40 | + if html["status"] == "success": |
| 41 | + print("恭喜你，登陆成功") |
| 42 | + |
| 43 | + def get_user_data(self): |
| 44 | + """获取用户数据表明登陆成功""" |
| 45 | + # TODO: 这里填写你用户主页的url |
| 46 | + url = "这里填写你用户主页的url" |
| 47 | + # 获取用户信息页面 |
| 48 | + html = self.session.get(url).text |
| 49 | + print(html) |
| 50 | + |
| 51 | + def run(self): |
| 52 | + """运行程序""" |
| 53 | + self.get_cookie() |
| 54 | + self.get_user_data() |
101 | 55 |
|
102 | 56 |
|
103 | 57 | if __name__ == '__main__': |
104 | | - if isLogin(): |
105 | | - print('Login successfully') |
106 | | - else: |
107 | | - login() |
| 58 | + account = input("请输入你的账号:") |
| 59 | + password = input("请输入你的密码:") |
| 60 | + login = DouBanLogin(account, password) |
| 61 | + login.run() |
0 commit comments