首页 > 代码库 > amazon爬取亚马逊页面信息

amazon爬取亚马逊页面信息



代码:

# -*- coding: cp936 -*-

import requests

from lxml import etree



ASIN = ‘B00X4WHP5E‘

#ASIN = ‘B017R1YFEG‘

url = ‘https://www.amazon.com/dp/‘+ASIN

r = requests.get(url)

html = r.text


tree = etree.HTML(html)


#获取产品单价

span = tree.xpath("//span[@id=‘priceblock_ourprice‘]/text()")

print "ASIN码:",ASIN

print "单价:",span



#获取产品customer reviews

cus_reviewList = tree.xpath("//div[@id=‘averageCustomerReviews‘]/span/a/span[@id=‘acrCustomerReviewText‘]/text()")

print "Customer Reviews:",cus_reviewList[0]


#获取产品kc


amazon爬取亚马逊页面信息