import time from selenium import webdriver keyword = input('请输入你要搜索的关键字:') brow = webdriver.Firefox() brow.get('http://www.jd.com') search_form = brow.find_element_by_id('key') search_form.send_keys(keyword) search_button = brow.find_element_by_class_name('button') search_button.click() time.sleep(2) file_handle = open('%s.txt'%keyword,mode='w',encoding='utf-8') for x in range(1,6): print('正在爬取第%s页数据,请稍等'%x) for x in range(1,11,2): time.sleep(1) j = x / 10 js = 'document.documentElement.scrollTop = document.documentElement.scrollHeight * %f' % j brow.execute_script(js) shops = brow.find_elements_by_class_name('gl-item') for shop in shops: file_handle.write(shop.text) next_li = brow.find_element_by_class_name('pn-next') next_li.click() brow.quit()
Python的网络爬虫小系统——爬取京东商城商品信息
最新推荐文章于 2024-07-08 14:10:21 发布