当前位置:首页 >> 脚本专栏

python根据京东商品url获取产品价格

京东商品详细的请求处理,是先显示html,然后再ajax请求处理显示价格。
1.可以运行js,并解析之后得到的html
2.模拟js请求,得到价格

# -*- coding: utf-8 -*-
"""
根据京东url地址,获取商品价格
京东请求处理过程,先显示html页面,然后通过ajax get请求获取相应的商品价格
 
1.商品的具体数据在html中的格式,如下(示例)
# product: {
#     skuid: 1310118868,
#     name: '\u9999\u5f71\u77ed\u88d9\u4e24\u4ef6\u5957\u88c5\u5973\u0032\u0030\u0031\u0034\u51ac\u88c5\u65b0\u6b3e\u97e9\u7248\u957f\u8896\u0054\u6064\u4e0a\u8863\u8377\u53f6\u8fb9\u534a\u8eab\u88d9\u6f6e\u0020\u85cf\u9752\u0020\u004d',
#     skuidkey:'7781F505B71CE37A3AFBADA119D3587F',
#     href: 'http://item.jd.com/1310118868.html',
#     src: 'jfs/t385/197/414081450/336886/3070537b/541be890N2995990c.jpg',
#     cat: [1315,1343,1355],
#     brand: 18247,
#     nBrand: 18247,
#     tips: false,
#     type: 2,
#     venderId:38824,
#     shopId:'36786',
#     TJ:'0',
#     specialAttrs:["is7ToReturn-1"],
#     videoPath:'',
#     HM:'0'
#   }
 
2.ajax请求代码如下:
# // 获得数字价格
# var getPriceNum = function(skus, $wrap, perfix, callback) {
#   skus = typeof skus === 'string' """
import urllib
import json
import re
 
 
class JdPrice(object):
  """
  对获取京东商品价格进行简单封装
  """
  def __init__(self, url):
    self.url = url
    self._response = urllib.urlopen(self.url)
    self.html = self._response.read()
 
  def get_product(self):
    """
    获取html中,商品的描述(未对数据进行详细处理,粗略的返回str类型)
    :return:
    """
    product_re = re.compile(r'compatible: true,(.*"""
    通过获取的商品信息,获取商品的skuid
    :return:
    """
    product_info = self.get_product()
    skuid_re = re.compile(r'skuid: (.*"""
    根据商品的skuid信息,请求获得商品price
    :return:
    """
    price = None
    skuid = self.get_product_skuid()
    url = 'http://p.3.cn/prices/mgets"htmlcode">
fromcreepyimportCrawler
fromBeautifulSoupimportBeautifulSoup
importurllib2
importjson

classMyCrawler(Crawler):
defprocess_document(self,doc):
ifdoc.status==200:
print[%d]%s%(doc.status,doc.url)
try:
soup=BeautifulSoup(doc.text.decode(gb18030).encode(utf-8))
exceptExceptionase:
printe
soup=BeautifulSoup(doc.text)
printsoup.find(id="product-intro").div.h1.text
url_id=urllib2.unquote(doc.url).decode(utf8).split(/)[-1].split(.)[0]
f=urllib2.urlopen(http://p.3.cn/prices/get?skuid=J_+url_id,timeout=5)
price=json.loads(f.read())
f.close()
printprice[0][p]
else:
pass

crawler=MyCrawler()
crawler.set_follow_mode(Crawler.F_SAME_HOST)
crawler.set_concurrency_level(16)
crawler.add_url_filter(.(jpg|jpeg|gif|png|js|css|swf)$)
crawler.crawl(http://item.jd.com/982040.html)