selenium爬虫京东商品信息

selenium爬虫京东商品信息

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
import time

try:
    bro = webdriver.Chrome(executable_path='chromedriver_mac64')
    bro.get('https://www.jd.com/')
    bro.implicitly_wait(10)
    bro.maximize_window()
    search_btn = bro.find_element(By.ID, value='key')
    search_btn.send_keys('茅台')
    search_btn.send_keys(Keys.ENTER)
    1.获取到搜索框 输入 茅台 并 按下回车
    time.sleep(2)
    bro.execute_script('scrollTo(0,5000)')
    2.将网页下滑到5000px位置 这样可以加载出更多的商品
    time.sleep(2)
    goods_list = bro.find_elements(By.CLASS_NAME, value='gl-item')
    3.拿到所有的商品标签列表
    for goods in goods_list:
        try:
            img = goods.find_element(By.CSS_SELECTOR, value='.p-img img').get_attribute('src')
            4.获取每一个商品的图片地址，前端有懒加载为加载的我们可以通过其他属性获取
            if not img:
                img = 'https://' + goods.find_element(By.CSS_SELECTOR, value='.p-img img').get_attribute(
                    'data-lazy-img')
            url = goods.find_element(By.CSS_SELECTOR, value='.p-img a').get_attribute('href')
            price = goods.find_element(By.CSS_SELECTOR, value='.p-price i').text
            name = goods.find_element(By.CSS_SELECTOR, value='.p-name em').text   5.获取商品名称，发现在.p-name类属性标签下的 em 标签 内的所有文本信息
            shop = goods.find_element(By.CSS_SELECTOR, value='.p-shop a').text
            
            print('''
            商品名：%s，
            图片地址：%s，
            价格：%s，
            店铺：%s，
            '''%(name,img,price,shop))
        except Exception:
            continue


except Exception as e:
    print(e)