Python实战项目之模拟浏览器访问京东网站并输入关键字自动搜索
1、下载安装PyCharm
下载网址:http://www.jetbrains.com/pycharm/
2、下载chromedriver
下载网址:http://chromedriver.storage.googleapis.com/index.html
3、在PyCharm环境安装selenium库
4、创建项目,输入如下代码,大功告成!!
# encoding:utf-8
from selenium import webdriver
# import os
from time import sleep
# 模拟浏览器访问京东并搜索关键字
def jingdong():
chrome_path = r'E:\chromedriver_win32/chromedriver.exe'
# os.environ['webdriver.chrome.driver'] = chrome_path#设置系统环境变量
# 打开谷歌浏览器
driver = webdriver.Chrome(chrome_path)
# 打开一个网址#driver.quit() #退出浏览器
driver.fullscreen_window()
driver.get('https://www.jd.com/')
print('Before search================')
# 打印当前页面title
title = driver.title
print(title)
# 打印当前页面URL
now_url = driver.current_url
print(now_url)
driver.find_element_by_id("key").send_keys("衣服")
driver.find_element_by_class_name("button").click()
sleep(1)
print('After search================')
# 再次打印当前页面title
title = driver.title
print(title)
# 打印当前页面URL
now_url = driver.current_url
print(now_url)
# # 获取结果数目
# user = driver.find_element_by_class_name('nums').text
# print(user)
# #关闭所有窗口
# driver.fullscreen_window()
sleep(5)
driver.quit()
def main():
jingdong()
if __name__ == '__main__':
main()
20190125代码功能添加:提取衣服页面中的商店名字、商品链接、商品价格
from selenium import webdriver
from lxml import etree
import time
KeyWord="衣服"
JDHTTP="https:"
def Jingdong_spider():
webdriver_path=r"D:\python-tools\chromedriver_win32\chromedriver.exe"
drivers=webdriver.Chrome(webdriver_path)
drivers.get("https://www.jd.com/")
time.sleep(5)
drivers.find_element_by_id("key").send_keys(KeyWord)
time.sleep(5)
drivers.find_element_by_class_name("button").click()
time.sleep(10)
html=etree.HTML(drivers.page_source)
shoplis=html.xpath("//li[@class='gl-item']")
for shopli in shoplis:
#获取商店名字
shopname=shopli.xpath(".//span[@class='J_im_icon']/a/@title")
print(shopname[0])
#获取商品链接
shoplink=shopli.xpath(".//div[@class='p-img']/a/@href")
print("http:"+shoplink[0])
#获取商品价格
shopprice=shopli.xpath(".//div[@class='p-price']//i")
print("¥"+shopprice[0].text)