python 爬取派米比价详情页

目标网站
在这里插入图片描述
在这里插入图片描述
找到请求地址,发现没有加密,直接请求,用xpath提取数据
在这里插入图片描述
完整代码:

import requests
from lxml import etree

url = 'http://www.mypricemix.com/wap/goods_detail/fc73a3511f8911e98985525400a3d313.html'
resp = requests.get(url)

# print(resp.text)

eroot = etree.HTML(resp.text)
goods_name = eroot.xpath('/html/body/header/h1/text()')
print('商品名称:',goods_name)

pictures_ele = eroot.xpath('/html/body/div[2]/div[2]/div/div')
for picture_ele in pictures_ele:
    pic_src = picture_ele.xpath('./a/img/@src')
    print('图片url:',pic_src)

goods_num = eroot.xpath('/html/body/div[3]/table/tbody/tr[1]/td[1]/span[2]/text()')
print('货号',goods_num)

detail = eroot.xpath('/html/body/div[3]/table/tbody/tr[2]/td/span/text()')
print('细节特征',detail)

print('以下折合人民币价格均按照今日最新汇率计算')
update_time = eroot.xpath('/html/body/div[4]/span[2]/text()')
print(update_time)

prices_ele = eroot.xpath('/html/body/div[4]/div')
for price_ele in prices_ele:
    url = price_ele.xpath('./ul/a/@href')
    # 欧洲不一样,另外写个规则
    if not url:
        url = price_ele.xpath('./ul/li/@data-url')
        countries_ele = price_ele.xpath('./ul/li')
        for country in countries_ele:
            country_name = country.xpath('./text()')
            print('国家:',country_name)
    else:
        country = price_ele.xpath('./ul/a/li/text()')
        print('国家:',country)
    print('官网链接:',url)
    local_price = price_ele.xpath('./div[1]/span/text()')
    print('官方售价:',local_price)
    rmb_price = price_ele.xpath('./div[2]/span/text()')
    print('折合人民币:', rmb_price)
    print('*'*100)

猜你喜欢

转载自blog.csdn.net/weixin_43751840/article/details/88782001