diff --git a/douban/douban.py b/douban/douban.py index d23eb5e..7eb0e7e 100644 --- a/douban/douban.py +++ b/douban/douban.py @@ -1,107 +1,61 @@ #!/usr/bin/env python3 # -*- coding: utf-8 -*- - -''' -Required -- requests (必须) -- bs4 (必选) -- pillow (可选) -''' - -from urllib.request import urlretrieve import requests -from bs4 import BeautifulSoup -from os import remove -try: - import cookielib -except: - import http.cookiejar as cookielib -try: - from PIL import Image -except: - pass +""" +info: +author:CriseLYJ +github:https://github.com/CriseLYJ/ +update_time:2019-04-04 +""" -url = 'https://accounts.douban.com/login' - -datas = {'source': 'index_nav', - 'remember': 'on'} - -headers = {'Host': 'www.douban.com', - 'Referer': 'https://www.douban.com/', - 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:55.0) Gecko/20100101 Firefox/55.0', - 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', - 'Accept-Language': 'zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3', - 'Accept-Encoding': 'gzip, deflate, br'} - -# 尝试使用cookie信息 -session = requests.session() -session.cookies = cookielib.LWPCookieJar(filename='cookies') -try: - session.cookies.load(ignore_discard=True) -except: - print("Cookies未能加载") - # cookies加载不成功，则输入账号密码信息 - datas['form_email'] = input('Please input your account:') - datas['form_password'] = input('Please input your password:') +""" +模拟登陆豆瓣 +""" -def get_captcha(): - ''' - 获取验证码及其ID - ''' - r = requests.post(url, data=datas, headers=headers) - page = r.text - soup = BeautifulSoup(page, "html.parser") - # 利用bs4获得验证码图片地址 - img_src = soup.find('img', {'id': 'captcha_image'}).get('src') - urlretrieve(img_src, 'captcha.jpg') - try: - im = Image.open('captcha.jpg') - im.show() - im.close() - except: - print('到本地目录打开captcha.jpg获取验证码') - finally: - captcha = input('please input the captcha:') - remove('captcha.jpg') - captcha_id = soup.find( - 'input', {'type': 'hidden', 'name': 'captcha-id'}).get('value') - return captcha, captcha_id +class DouBanLogin(object): + def __init__(self, account, password): + self.url = "https://accounts.douban.com/j/mobile/login/basic" + self.headers = { + "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" + } + """初始化数据""" + self.data = { + "ck": "", + "name": account, + "password": password, + "remember": "true", + "ticket": "" + } + self.session = requests.Session() + def get_cookie(self): + """模拟登陆获取cookie""" + html = self.session.post( + url=self.url, + headers=self.headers, + data=self.data + ).json() + if html["status"] == "success": + print("恭喜你，登陆成功") -def isLogin(): - ''' - 通过查看用户个人账户信息来判断是否已经登录 - ''' - url = "https://www.douban.com/accounts/" - login_code = session.get(url, headers=headers, - allow_redirects=False).status_code - if login_code == 200: - return True - else: - return False + def get_user_data(self): + """获取用户数据表明登陆成功""" + # TODO: 这里填写你用户主页的url + url = "这里填写你用户主页的url" + # 获取用户信息页面 + html = self.session.get(url).text + print(html) - -def login(): - captcha, captcha_id = get_captcha() - # 增加表数据 - datas['captcha-solution'] = captcha - datas['captcha-id'] = captcha_id - login_page = session.post(url, data=datas, headers=headers) - page = login_page.text - soup = BeautifulSoup(page, "html.parser") - result = soup.findAll('div', attrs={'class': 'title'}) - # 进入豆瓣登陆后页面，打印热门内容 - for item in result: - print(item.find('a').get_text()) - # 保存 cookies 到文件， - # 下次可以使用 cookie 直接登录，不需要输入账号和密码 - session.cookies.save() + def run(self): + """运行程序""" + self.get_cookie() + self.get_user_data() if __name__ == '__main__': - if isLogin(): - print('Login successfully') - else: - login() + account = input("请输入你的账号:") + password = input("请输入你的密码:") + login = DouBanLogin(account, password) + login.run() diff --git a/douban/douban_spider.py b/douban/douban_spider.py index ba49bed..4472e7a 100644 --- a/douban/douban_spider.py +++ b/douban/douban_spider.py @@ -9,7 +9,7 @@ url = "https://movie.douban.com/j/search_subjects" # 定义请求头 headers = { - "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36" + "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" } # 循环构建请求参数并且发送请求 for page_start in range(0, 100, 20): diff --git a/facebook/facebook.py b/facebook/facebook.py index c41d672..b807a77 100644 --- a/facebook/facebook.py +++ b/facebook/facebook.py @@ -6,26 +6,19 @@ import pyquery def login(session, email, password): - ''' - Attempt to login to Facebook. Returns user ID, xs token and - fb_dtsg token. All 3 are required to make requests to - Facebook endpoints as a logged in user. Returns False if - login failed. - ''' - - # Navigate to Facebook's homepage to load Facebook's cookies. + """ + 获取cookie + """ response = session.get('https://m.facebook.com') - # Attempt to login to Facebook + # 尝试登陆 response = session.post('https://m.facebook.com/login.php', data={ 'email': email, 'pass': password }, allow_redirects=False) - # If c_user cookie is present, login was successful if 'c_user' in response.cookies: - - # Make a request to homepage to get fb_dtsg token + # 说明登陆成功 homepage_resp = session.get('https://m.facebook.com/home.php') dom = pyquery.PyQuery(homepage_resp.text.encode('utf8')) @@ -46,7 +39,7 @@ if __name__ == "__main__": session = requests.session() session.headers.update({ - 'User-Agent': 'Mozilla/5.0 (X11; Linux i686; rv:39.0) Gecko/20100101 Firefox/39.0' + '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' }) fb_dtsg, user_id, xs = login(session, args.email, args.password) diff --git a/webWeixin/webWeixin.py b/webWeixin/webWeixin.py index d9d4eeb..11b7062 100644 --- a/webWeixin/webWeixin.py +++ b/webWeixin/webWeixin.py @@ -16,7 +16,7 @@ update_time:2019-3-6 session = requests.session() headers = { - 'User-Agent': 'Mozilla/5.0 (Windows NT 5.1; rv:33.0) Gecko/20100101 Firefox/33.0' + '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' } QRImgPath = os.path.split(os.path.realpath(__file__))[0] + os.sep + 'webWeixinQr.jpg'