2020-04-26

标题自动爬取京东商城物品价格名称链接评论

导入库

from selenium import webdriver
#from selenium.webdriver import ActionChains
#from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys #键盘按键操作库
#import time

获取页面自动搜索

def spider(url,keyword):
Driver = webdriver.Chrome()
Driver.get(url)
Driver.implicitly_wait(3) #确保节点全部加载
try:
input_tag = Driver.find_element_by_id(‘key’) #定位搜索栏
input_tag.send_keys(keyword) # 模拟键盘输入
input_tag.send_keys(Keys.ENTER) #模拟回车键
#time.sleep(5)
get_goods(Driver) #czsp
finally:
Driver.close()

获取数据并打印

def get_goods(Driver):
try:
goods = Driver.find_elements_by_class_name(‘gl-i-wrap’)
for good in goods:
detail_url=good.find element_by_tag_name(‘a’).get_attrib ute(‘href’)
p_name=good.find_element_by_css_selector(’.p-name em’).text.replace(’\n’,’ ‘)
p_price = good.find_element_by_css_selector(’.p-price i’).text
p_commit = good.find_element_by_css_selector(’.p-name a’).text
msg = ‘’’ 名称:%s 链接:%s 价格:%s 评论:%s ‘’’%(p_name,detail_url,p_price,p_commit)
print(msg)
button = Driver.find_element_by_link_text(‘下一页’)
button.click()
get_goods(Driver)
except:
pass

执行

if name == ‘main’ :
spider(‘https://www.jd.com/’,keyword = ‘口罩’)

备注

第一次弄不知道怎么排版，这个程序非常简单，运行结果大家自己去验证吧