day05 selenium爬虫基础

迷南。 2021-10-26 22:50 388阅读 0赞

from selenium import webdriver
    # 导入键盘Keys
    from selenium.webdriver.common.keys import Keys
    import time
    
    driver = webdriver.Chrome()
    
    # 检测代码块
    try:
        # 隐式等待，等待标签加载
        driver.implicitly_wait(10)
    
        # 往京东主页发送请求
        driver.get('https://www.jd.com/')
    
        # 通过id查找input输入框
        input_tag = driver.find_element_by_id('key')
    
        # send_keys为当前标签传值
        input_tag.send_keys('中华字典')
    
        # 按键盘的回车键
        input_tag.send_keys(Keys.ENTER)
    
        time.sleep(3)
    
        '''
        爬取京东商品信息:
            公仔
                名称
                url
                价格
                评价
        '''
        # element 找一个
        # elements 找多个
        # 查找所有的商品列表
        good_list = driver.find_elements_by_class_name('gl-item')
        # print(good_list)
    
        # 循环遍历每一个商品
        for good in good_list:
            # 通过属性选择器查找商品详情页url
            # url
            good_url = good.find_element_by_css_selector('.p-img a').get_attribute('href')
            print(good_url)
    
            # 名称
            good_name = good.find_element_by_css_selector('.p-name em').text
            print(good_name)
    
            # 价格
            good_price = good.find_element_by_class_name('p-price').text
            print(good_price)
    
            # 评价数
            good_commit = good.find_element_by_class_name('p-commit').text
            print(good_commit)
    
    
            str1 = f'''
            url: {good_url}
            名称: {good_name}
            价格: {good_price}
            评价: {good_commit}
            \n
            '''
            # 把商品信息写入文本中
            with open('jd.txt', 'a', encoding='utf-8') as f:
                f.write(str1)
    
    
        time.sleep(10)
    
    # 捕获异常
    except Exception as e:
        print(e)
    
    # 最后都会把驱动浏览器关闭掉
    finally:
        driver.close()

转载于:https://www.cnblogs.com/wangziyu/p/11104579.html