很多时候我们在对网站进行数据抓取的时候,可以抓取一部分页面或者接口,这部分可能没有设置登录限制。但是如果要抓取大规模数据的时候,没有登录进行爬取会出现一些弊端。对于一些设置登录限制的页面,无法爬取对于一些没有设置登录的页面或者接口,一旦IP访问频繁,会触发网站的反爬虫,相比较代理池通过改变IP地址来避免被网站封禁,但是现在的有的网站已经不封IP地址,开始封账号的反爬措施,如果做大规模爬虫怎么办呢,一个账号有可能被封,如果像代理池一样提供不同IP,我有多个账号轮流爬取是不是可以避免被封。所有就需要维护多个账号,这个时候就要用到cookies池了,通过获取每个账号模拟登录后的cookies信息,保存到数据库,定时检测cookies有效性。
1.相关工具
安装Redis数据库,redis-py库,reuqests,selenium,Flask 库,还有Google Chrome浏览器 安装好ChromeDriver,购买要爬取的网站账号,比如我购买的微博小号(卖号网站随机百度,有些网站不固定容易404,最好买免验证码登录的) 这里我们搭建微博的Cookies池
2.cookies实现
需要下图几大模块
存储模块负责存储每个账号的用户名,密码已经每个账号对应的Cookies信息,同时提供方法对数据的存储操作
生成模块 负责获取登录之后的Cookies,这个模块要从数据库中取账号密码,再模拟登录目标页面,如果登陆成功,就获取Cookies保存到数据库
检测模块负责定时检测数据库中的Cookies是否有效,使用Cookies请求链接,如果登录状态成功,则是有效的,否则失效并删除,接下来等待生产模块重新登录生成Cookies
接口模块是通过Api提供对外服务的接口,Cookies越多越好,被检测到的概率越小,越不容易被封
接下来实现存储模块:存储部分有两部分:1.账号和密码 2.账号和Cookies 这两部分是一对一对应的,所以可以使用Redis的hash ,hash存储结构是key-value 也就是键值对的形式,和我们所需的是符合的,所以就有两组映射,账号密码 ,账号Cookies, key是账号
import random import redis
# Redis数据库地址
REDIS_HOST = 'localhost'
# Redis端口
REDIS_PORT = 6379
# Redis密码,如无填None
REDIS_PASSWORD = None
class RedisClient(object): def __init__(self, type, website, host=REDIS_HOST, port=REDIS_PORT, password=REDIS_PASSWORD): """ 初始化Redis连接 :param host: 地址 :param port: 端口 :param password: 密码 """ self.db = redis.StrictRedis(host=host, port=port, password=password, decode_responses=True) self.type = type self.website = website def name(self): """ 获取Hash的名称 :return: Hash名称 """ return "{type}:{website}".format(type=self.type, website=self.website) def set(self, username, value): """ 设置键值对 :param username: 用户名 :param value: 密码或Cookies :return: """ return self.db.hset(self.name(), username, value) def get(self, username): """ 根据键名获取键值 :param username: 用户名 :return: """ return self.db.hget(self.name(), username) def delete(self, username): """ 根据键名删除键值对 :param username: 用户名 :return: 删除结果 """ return self.db.hdel(self.name(), username) def count(self): """ 获取数目 :return: 数目 """ return self.db.hlen(self.name()) def random(self): """ 随机得到键值,用于随机Cookies获取 :return: 随机Cookies """ return random.choice(self.db.hvals(self.name())) def usernames(self): """ 获取所有账户信息 :return: 所有用户名 """ return self.db.hkeys(self.name()) def all(self): """ 获取所有键值对 :return: 用户名和密码或Cookies的映射表 """ return self.db.hgetall(self.name()) if __name__ == '__main__': conn = RedisClient('accounts', 'weibo') result = conn.set('wert', 'ssdsdsf') print(result)
我们可以看见name()方法,返回值就是存储key-value 的hash名称 比如accounts:weibo 存储的就是账号和密码,通过这种方式可以把账号密码添加进数据库
生成模块的实现
要获取微博登录信息的Cookies,肯定要登录微博,但是微博这网站的登录接口需要填写验证码 或者手机号验证比较复杂,比较好的是微博登录站点有三个 1.https://weibo.cn 2.https://m.weibo.com
3.https://weibo.com 我们选择第二个站点比较合适,类似于手机客户端的界面,而且登录的时候不需要验证码(前提购买免验证码账号才可以)登录界面是这样
import json from selenium import webdriver from selenium.webdriver import DesiredCapabilities from cookiespool.db import RedisClient from login.weibo.cookies import WeiboCookies
# 产生器使用的浏览器
BROWSER_TYPE = 'PhantomJS'
class CookiesGenerator(object): def __init__(self, website='default'): """ 父类, 初始化一些对象 :param website: 名称 :param browser: 浏览器, 若不使用浏览器则可设置为 None """ self.website = website self.cookies_db = RedisClient('cookies', self.website) self.accounts_db = RedisClient('accounts', self.website) self.init_browser() def __del__(self): self.close() def init_browser(self): """ 通过browser参数初始化全局浏览器供模拟登录使用 :return: """ if BROWSER_TYPE == 'PhantomJS': caps = DesiredCapabilities.PHANTOMJS caps[ "phantomjs.page.settings.userAgent"] = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.133 Safari/537.36' self.browser = webdriver.PhantomJS(desired_capabilities=caps) self.browser.set_window_size(1400, 500) elif BROWSER_TYPE == 'Chrome': self.browser = webdriver.Chrome() def new_cookies(self, username, password): """ 新生成Cookies,子类需要重写 :param username: 用户名 :param password: 密码 :return: """ raise NotImplementedError def process_cookies(self, cookies): """ 处理Cookies :param cookies: :return: """ dict = {} for cookie in cookies: dict[cookie['name']] = cookie['value'] return dict def run(self): """ 运行, 得到所有账户, 然后顺次模拟登录 :return: """ accounts_usernames = self.accounts_db.usernames() cookies_usernames = self.cookies_db.usernames() for username in accounts_usernames: if not username in cookies_usernames: password = self.accounts_db.get(username) print('正在生成Cookies', '账号', username, '密码', password) result = self.new_cookies(username, password) # 成功获取 if result.get('status') == 1: cookies = self.process_cookies(result.get('content')) print('成功获取到Cookies', cookies) if self.cookies_db.set(username, json.dumps(cookies)): print('成功保存Cookies') # 密码错误,移除账号 elif result.get('status') == 2: print(result.get('content')) if self.accounts_db.delete(username): print('成功删除账号') else: print(result.get('content')) else: print('所有账号都已经成功获取Cookies') def close(self): """ 关闭 :return: """ try: print('Closing Browser') self.browser.close() del self.browser except TypeError: print('Browser not opened') class WeiboCookiesGenerator(CookiesGenerator): def __init__(self, website='weibo'): """ 初始化操作 :param website: 站点名称 :param browser: 使用的浏览器 """ CookiesGenerator.__init__(self, website) self.website = website def new_cookies(self, username, password): """ 生成Cookies :param username: 用户名 :param password: 密码 :return: 用户名和Cookies """ return WeiboCookies(username, password, self.browser).main()
这部分是来判断是否登录成功
import time from io import BytesIO from PIL import Image from selenium.common.exceptions import TimeoutException #from selenium.webdriver import ActionChains from selenium.webdriver.common.by import By from selenium.webdriver.support.ui import WebDriverWait from selenium.webdriver.support import expected_conditions as EC from os import listdir from os.path import abspath, dirname TEMPLATES_FOLDER = dirname(abspath(__file__)) + '/templates/' class WeiboCookies(): def __init__(self, username, password, browser): self.url = 'https://passport.weibo.cn/signin/login?entry=mweibo&r=https://m.weibo.cn/' self.browser = browser self.wait = WebDriverWait(self.browser, 20) self.username = username self.password = password def open(self): """ 打开网页输入用户名密码并点击 :return: None """ self.browser.delete_all_cookies() self.browser.get(self.url) username = self.wait.until(EC.presence_of_element_located((By.ID, 'loginName'))) password = self.wait.until(EC.presence_of_element_located((By.ID, 'loginPassword'))) submit = self.wait.until(EC.element_to_be_clickable((By.ID, 'loginAction'))) username.send_keys(self.username) password.send_keys(self.password) time.sleep(1) submit.click() def password_error(self): """ 判断是否密码错误 :return: """ try: return WebDriverWait(self.browser, 5).until( EC.text_to_be_present_in_element((By.ID, 'errorMsg'), '用户名或密码错误')) except TimeoutException: return False def login_successfully(self): """ 判断是否登录成功 :return: """ try: return bool( WebDriverWait(self.browser, 5).until(EC.presence_of_element_located((By.CLASS_NAME, 'lite-iconf-profile')))) except TimeoutException: return False def get_cookies(self): """ 获取Cookies :return: """ return self.browser.get_cookies() def main(self): """ 破解入口 :return: """ self.open() if self.password_error(): return { 'status': 2, 'content': '用户名或密码错误' } # 如果不需要验证码直接登录成功 if self.login_successfully(): cookies = self.get_cookies() return { 'status': 1, 'content': cookies }
检测模块:获取到Cookies信息后还需要对Cookies的有效性进行检测,也就是通过登录返回的Response的状态码判断是否有效
import json import requests from requests.exceptions import ConnectionError from cookiespool.db import * class ValidTester(object): def __init__(self, website='default'): self.website = website self.cookies_db = RedisClient('cookies', self.website) self.accounts_db = RedisClient('accounts', self.website) def test(self, username, cookies): raise NotImplementedError def run(self): cookies_groups = self.cookies_db.all() for username, cookies in cookies_groups.items(): self.test(username, cookies) class WeiboValidTester(ValidTester): def __init__(self, website='weibo'): ValidTester.__init__(self, website) def test(self, username, cookies): print('正在测试Cookies', '用户名', username) try: cookies = json.loads(cookies) except TypeError: print('Cookies不合法', username) self.cookies_db.delete(username) print('删除Cookies', username) return try: test_url = TEST_URL_MAP[self.website] response = requests.get(test_url, cookies=cookies, timeout=5, allow_redirects=False) if response.status_code == 200: print('Cookies有效', username) else: print(response.status_code, response.headers) print('Cookies失效', username) self.cookies_db.delete(username) print('删除Cookies', username) except ConnectionError as e: print('发生异常', e.args)
接口模块驱动其他几个模块的运行
import time from multiprocessing import Process from cookiespool.api import app from cookiespool.generator import * from cookiespool.tester import *
# 产生器类,如扩展其他站点,请在此配置
GENERATOR_MAP = {
'weibo': 'WeiboCookiesGenerator'
}
# 测试类,如扩展其他站点,请在此配置
TESTER_MAP = {
'weibo': 'WeiboValidTester'
}
TEST_URL_MAP = {
'weibo': 'https://m.weibo.cn/'
}
# 产生器和验证器循环周期
CYCLE = 120
# 产生器开关,模拟登录添加Cookies
GENERATOR_PROCESS = True
# 验证器开关,循环检测数据库中Cookies是否可用,不可用删除
VALID_PROCESS = True
# API接口服务
API_PROCESS = True
class Scheduler(object): @staticmethod def valid_cookie(cycle=CYCLE): while True: print('Cookies检测进程开始运行') try: for website, cls in TESTER_MAP.items(): tester = eval(cls + '(website="' + website + '")') tester.run() print('Cookies检测完成') del tester time.sleep(cycle) except Exception as e: print(e.args) @staticmethod def generate_cookie(cycle=CYCLE): while True: print('Cookies生成进程开始运行') try: for website, cls in GENERATOR_MAP.items(): generator = eval(cls + '(website="' + website + '")') generator.run() print('Cookies生成完成') generator.close() time.sleep(cycle) except Exception as e: print(e.args) @staticmethod def api(): print('API接口开始运行') app.run(host=API_HOST, port=API_PORT) def run(self): if API_PROCESS: api_process = Process(target=Scheduler.api) api_process.start() if GENERATOR_PROCESS: generate_process = Process(target=Scheduler.generate_cookie) generate_process.start() if VALID_PROCESS: valid_process = Process(target=Scheduler.valid_cookie) valid_process.start()
api接口
import json from flask import Flask, g from cookiespool.db import *
# API地址和端口
API_HOST = '127.0.0.1'
API_PORT = 5000
__all__ = ['app'] app = Flask(__name__) @app.route('/') def index(): return '<h2>Welcome to Cookie Pool System</h2>' def get_conn(): """ 获取 :return: """ for website in GENERATOR_MAP: print(website) if not hasattr(g, website): setattr(g, website + '_cookies', eval('RedisClient' + '("cookies", "' + website + '")')) setattr(g, website + '_accounts', eval('RedisClient' + '("accounts", "' + website + '")')) return g @app.route('/<website>/random') def random(website): """ 获取随机的Cookie, 访问地址如 /weibo/random :return: 随机Cookie """ g = get_conn() cookies = getattr(g, website + '_cookies').random() return cookies @app.route('/<website>/add/<username>/<password>') def add(website, username, password): """ 添加用户, 访问地址如 /weibo/add/user/password :param website: 站点 :param username: 用户名 :param password: 密码 :return: """ g = get_conn() print(username, password) getattr(g, website + '_accounts').set(username, password) return json.dumps({'status': '1'}) @app.route('/<website>/count') def count(website): """ 获取Cookies总数 """ g = get_conn() count = getattr(g, website + '_cookies').count() return json.dumps({'status': '1', 'count': count}) if __name__ == '__main__': app.run(host='0.0.0.0')
运行效果如下