selenium自动化测试豆瓣电影近期热门榜，和保存至Excel

废话少说，直接上代码。

这是成果:

以下是全部代码:

from selenium import webdriver  # webdriver 的驱动程序
from selenium.webdriver.common.by import By # 提取数据
from selenium.webdriver import ChromeOptions    # chromeOptions 是一个配置 chrome 启动是属性的类。通过这个类，我们可以为chrome配置参数
from selenium.webdriver.support.wait import WebDriverWait   # 显示等待
from selenium.webdriver.support import expected_conditions as EC
import time # 导入time
import csv  # 导入csv
import os.path  # 创建文件夹
import requests # 请求网页数据
import re   # 正则匹配 文字匹配


driver = webdriver.Chrome()

WAIT = WebDriverWait(driver, 10)      # 等待



def get_serch(url):
    try:
       # 发送请求
       driver.get(url=url)
       time.sleep(1)
       WAIT.until(EC.presence_of_element_located((By.LINK_TEXT,'分类'))).click()
       time.sleep(1)
       return WAIT
    except:
        print("erro")


def get_data(WAIT):
    all_list = []
    n = 15   # 设置点击加载更多的次数
    for page in range(n):
        WAIT.until(EC.presence_of_element_located((By.LINK_TEXT,'加载更多'))).click()
        print(f'==============================正在点击第{page}页的数据内容==============================')
        time.sleep(5)
    # 找到所有的a标签
    all_data = WAIT.until(EC.presence_of_all_elements_located((By.XPATH,'//*[@id="app"]/div/div[1]/div[3]/a')))
    for i in all_data:  # 找到所有的a标签循环并点击
        i.click()
        # 浏览器切换对象
        driver.switch_to.window(driver.window_handles[-1])
        # 提取想要的信息
        title = WAIT.until(EC.presence_of_element_located((By.XPATH,'//*[@id="content"]/h1/span[1]'))).text
        images = WAIT.until(EC.presence_of_element_located((By.XPATH,'//*[@class="subject clearfix"]/div[1]/a/img'))).get_attribute('src')
        ditail = WAIT.until(EC.presence_of_element_located((By.XPATH,'//div[@class="related-info"]/div/span'))).text
        aoter = WAIT.until(EC.presence_of_element_located((By.XPATH,'//*[@class="subject clearfix"]/div[2]/span[1]'))).get_attribute('textContent') # 取文本
        score = WAIT.until(EC.presence_of_element_located((By.XPATH,'//*[@class="subjectwrap clearfix"]/div[2]/div[1]/div[2]/strong'))).text
        evaluate = WAIT.until(EC.presence_of_element_located((By.XPATH,'//*[@class="subjectwrap clearfix"]/div[2]/div[1]/div[2]/div/div/a/span'))).get_attribute('textContent')
        item = {
            '标题': title,
            '图片': images,
            '简介': ditail,
            '作者': aoter,
            '评分': score,
            '评价': evaluate
        }
        all_list.append(item)
        print(item)
        save_Images(images,title)

        driver.close()
        driver.switch_to.window(driver.window_handles[0])
    return all_list



def save_csv(all_list):
    # 表头
    headers = ['标题','图片','简介','作者','评分','评价']
    # 打开文件
    with open('豆瓣电影.csv','a+',encoding='utf-8',newline='')as f:
        f_csv = csv.DictWriter(f,headers)
        f_csv.writeheader()
        f_csv.writerows(all_list)



def save_Images(images,title):
    if not os.path.exists('豆瓣图片'):  # 创建文件夹
        os.mkdir('豆瓣图片')
    images_data = requests.get(url=images).content
    big = '[?/\|:"*]'     # 剔除特殊字符保存图片
    li = re.sub(big,"",title)
    with open('豆瓣图片\\' + li + '.jpg',mode='wb')as f:
        f.write(images_data)
        print("保存图片===>",title)



def main():
    url = 'https://movie.douban.com/'
    WAIT = get_serch(url)
    all_list = get_data(WAIT)
    save_csv(all_list)



if __name__ == '__main__':
    main()