脚本专栏 发布日期:2025/11/2 浏览次数:1
#!/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")
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!