python 爬虫爬取京东ps4售卖情况

站长资源 2024/11/15 佚名

53 1538 53

相思资源网 Design By www.200059.com

代码

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @File : HtmlParser.py
# @Author: 赵路仓
# @Date : 2020/3/17
# @Desc :
# @Contact : 398333404@qq.com
import json

from lxml import etree
import requests
from bs4 import BeautifulSoup


url="https://search.jd.com/Search"
head={
 'authority': 'search.jd.com',
 'method': 'GET',
 'path': '/s_new.php"开始")
 url = "https://search.jd.com/Search"+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")