首页 > 其他 > 详细

使用Selenium访问出现弹窗

时间:2021-04-20 21:13:32      阅读:27      评论:0      收藏:0      [点我收藏+]

大部分商业网站需要我们登录后才能爬取内容,所以对于爬虫来说,生成cookies给代理使用成为了一个必须要做的事情。今天我们交流下关于使用selenium访问目标网站遇到的一些问题。

因为业务需求我们需要采集小红书的一些数据,程序在挂上代理访问目标网站的时候弹出了验证框。如图所示

技术分享图片

这个问题从来没有遇到过,我以为是的代理的问题,咨询客服才知道这个是因为我的浏览器的驱动和版本的问题,然后更新了新版本就可以解决了。那我们分享下使用chrome driver来进行登录和cookie的生成。

import os
import time
import zipfile

from selenium import webdriver
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.ui import WebDriverWait


class GenCookies(object):
    USER_AGENT = open(‘useragents.txt‘).readlines()
    # 16yun 代理配置
    PROXY_HOST = ‘t.16yun.cn‘  #  proxy or host
    PROXY_PORT = 31111  # port
    PROXY_USER = ‘USERNAME‘  # username
    PROXY_PASS = ‘PASSWORD‘  # password
    
    @classmethod
    def get_chromedriver(cls, use_proxy=False, user_agent=None):
        manifest_json = """
        {
            "version": "1.0.0",
            "manifest_version": 2,
            "name": "Chrome Proxy",
            "permissions": [
                "proxy",
                "tabs",
                "unlimitedStorage",
                "storage",
                "<all_urls>",
                "webRequest",
                "webRequestBlocking"
            ],
            "background": {
                "scripts": ["background.js"]
            },
            "minimum_chrome_version":"22.0.0"
        }
        """

        background_js = """
        var config = {
                mode: "fixed_servers",
                rules: {
                singleProxy: {
                    scheme: "http",
                    host: "%s",
                    port: parseInt(%s)
                },
                bypassList: ["localhost"]
                }
            };

        chrome.proxy.settings.set({value: config, scope: "regular"}, function() {});

        function callbackFn(details) {
            return {
                authCredentials: {
                    username: "%s",
                    password: "%s"
                }
            };
        }

        chrome.webRequest.onAuthRequired.addListener(
                    callbackFn,
                    {urls: ["<all_urls>"]},
                    [‘blocking‘]
        );
        """ % (cls.PROXY_HOST, cls.PROXY_PORT, cls.PROXY_USER, cls.PROXY_PASS)
        path = os.path.dirname(os.path.abspath(__file__))
        chrome_options = webdriver.ChromeOptions()
        if use_proxy:
            pluginfile = ‘proxy_auth_plugin.zip‘

            with zipfile.ZipFile(pluginfile, ‘w‘) as zp:
                zp.writestr("manifest.json", manifest_json)
                zp.writestr("background.js", background_js)
            chrome_options.add_extension(pluginfile)
        if user_agent:
            chrome_options.add_argument(‘--user-agent=%s‘ % user_agent)
        driver = webdriver.Chrome(
            os.path.join(path, ‘chromedriver‘),
            chrome_options=chrome_options)
        return driver

    def __init__(self, username, password):
        self.url = ‘https://passport.weibo.cn/signin/login?entry=mweibo&r=https://m.weibo.cn/‘
        self.browser = self.get_chromedriver(use_proxy=True, user_agent=self.USER_AGENT)
        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 get_cookies(self):
        """
        获取Cookies
        :return:
        """
        return self.browser.get_cookies()

    def main(self):
        """
        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

        cookies = self.get_cookies()
        return {
            ‘status‘: 1,
            ‘content‘: cookies
        }


if __name__ == ‘__main__‘:
    result = GenCookies(
        username=‘180000000‘,
        password=‘16yun‘,
    ).main()
    print(result)




使用Selenium访问出现弹窗

原文:https://www.cnblogs.com/mmz77-aa/p/14681939.html

(0)
(0)
   
举报
评论 一句话评论(0
关于我们 - 联系我们 - 留言反馈 - 联系我们:wmxa8@hotmail.com
© 2014 bubuko.com 版权所有
打开技术之扣,分享程序人生!