代码
#!/usr/bin/env python# -*- coding: utf-8 -*-# @File : HtmlParser.py# @Author: 赵路仓# @Date : 2020/3/17# @Desc :# @Contact : 398333404@qq.comimport jsonfrom lxml import etreeimport requestsfrom bs4 import BeautifulSoupurl="https://search.jd.com/Search?keyword=ps4&enc=utf-8&wq=ps4&pvid=cf0158c8664442799c1146a461478c9c"head={ 'authority': 'search.jd.com', 'method': 'GET', 'path': '/s_new.php?keyword=%E6%89%8B%E6%9C%BA&enc=utf-8&qrst=1&rt=1&stop=1&vt=2&wq=%E6%89%8B%E6%9C%BA&cid2=653&cid3=655&page=4&s=84&scrolling=y&log_id=1529828108.22071&tpl=3_M&show_items=7651927,7367120,7056868,7419252,6001239,5934182,4554969,3893501,7421462,6577495,26480543553,7345757,4483120,6176077,6932795,7336429,5963066,5283387,25722468892,7425622,4768461', 'scheme': 'https', 'referer': 'https://search.jd.com/Search?keyword=%E6%89%8B%E6%9C%BA&enc=utf-8&qrst=1&rt=1&stop=1&vt=2&wq=%E6%89%8B%E6%9C%BA&cid2=653&cid3=655&page=3&s=58&click=0', 'user-agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36', 'x-requested-with': 'XMLHttpRequest',}def page(page): print("开始") url = "https://search.jd.com/Search?keyword=ps4&enc=utf-8&qrst=1&rt=1&stop=1&vt=1&wq=ps4&page="+page+"&s=181&click=0" r=requests.get(url,timeout=3,headers=head) r.encoding=r.apparent_encoding # print(r.text) b=BeautifulSoup(r.text,"html.parser") #print(b.prettify()) _element = etree.HTML(r.text) datas = _element.xpath('//li[contains(@class,"gl-item")]') print(datas) for data in datas: p_price = data.xpath('div/div[@class="p-price"]/strong/i/text()') p_comment = data.xpath('div/div[5]/strong/a/text()') p_name = data.xpath('div/div[@class="p-name p-name-type-2"]/a/em/text()') p_href = data.xpath('div/div[@class="p-name p-name-type-2"]/a/@href') comment=' '.join(p_comment) name = ' '.join(p_name) price = ' '.join(p_price) href = ' '.join(p_href) print(name,price,p_comment,href)if __name__=="__main__": page("5")
爬取结果
以上就是python 爬虫爬取某东ps4售卖情况的详细内容,更多关于python 爬虫的资料请关注其它相关文章!