本文主要是介绍用ipython调试webdriver selenium找元素 不用多次打开浏览器，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！
运行文件，可把相关变量，函数保存在当前，不必多次打开chrome
%run my_script.py
文件内容：
my_script.py
import pymongo,time,os,json,random
from selenium import webdriver
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait
from pyquery import PyQuery as pq
from config import * #数据库、关键词、爬取页数 配置信息
from urllib.parse import quote# browser = webdriver.Chrome()
# browser = webdriver.PhantomJS(service_args=SERVICE_ARGS)chrome_options = webdriver.ChromeOptions()
# chrome_options.add_argument('--headless')
chrome_options.add_argument('user-agent=Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36')
browser = webdriver.Chrome(r'F:\Demo\python\dianshang\chromedriver.exe',chrome_options=chrome_options)
# 读取隐藏webdriver特征的js
with open('./stealth.min.js') as f:js = f.read()
# 在每个页面加载前执行隐藏driver特征的js实现反爬
browser.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {"source": js
})
wait = WebDriverWait(browser, 20)
client = pymongo.MongoClient(MONGO_URL) #读取数据库连接地址
db = client[MONGO_DB] #读取数据库名#浏览器复制到原始cookie文件
original_cookie_path='./cookies/original_cookies.txt'
cookies_path='./cookies/cookies.txt' #转化为json后的cookies
url='https://pinduoduo.com'#把从浏览器复制的原始cookies转为json格式并保存
def original_to_cookies():with open(original_cookie_path) as f:original_cookie=f.read()cookie_list=original_cookie.split(';')# print(cookie)cookies={}for c in cookie_list:k,v=c.split('=',1)cookies[k]=v# print(cookies)with open (cookies_path,'w',encoding='utf-8') as f:f.write(json.dumps(cookies))print('cookie成功转为json格式并保存')# 首次手动登录把cookie保存到文本
def save_cookies(cookies):# 保存cookies到文件，参数来自browser.get_cookies()path = os.getcwd() + '/cookies/'if not os.path.exists(path):os.makedirs(path)with open(path + 'cookies.txt', 'w') as f:cookie = json.dumps(cookies)f.write(cookie)print('cookie登录信息成功保存到文件')def read_add_cookie():#cookie登录:读取文件中的cookie并添加到浏览器中实现自动登录path = os.getcwd() + '/cookies/'if os.path.exists(path):# 读取添加cookiewith open('./cookies/cookies.txt','r',encoding='utf-8') as f:cookies=json.loads(f.read())browser.get(url) #刷新使cookie生效browser.delete_all_cookies()for cookie in cookies:browser.add_cookie(cookie)browser.refresh() # 添加cookie后要刷新才能生效print('cookies登录信息成功添加到浏览器')else:print('没有cookie文件！请进行初始手动登录！')def is_Login():# 是否登录：查找登录窗口的元素列表(注意是elements)login=browser.find_elements(By.XPATH,'//*[@id="mf-mms-goods-container"]/div/div/div[1]/span')if len(login)==1: #存在证明登录成功，返回真return Trueelif len(login)==0:return Falsedef login():if not is_Login(): print('cookie登录中，请稍等……')read_add_cookie()time.sleep(5)# 如果没有登录则循环等待5秒while not is_Login():print('cookie登录失败，请手动进行登录')time.sleep(5)# 结束循环表示登录成功，把cookies保存到文件print('手动登录成功！')cookies=browser.get_cookies()save_cookies(cookies) #保存登录成功的cookie以便下次登录else:print('已经登录，即将开始数据采集')
这篇关于用ipython调试webdriver selenium找元素 不用多次打开浏览器的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！
