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’ ? [skus]: skus;
# $wrap = $wrap || $(‘body’);
# perfix = perfix || ‘j-p-‘;
# $.ajax({
# url: ‘http://p.3.cn/prices/mgets?skuids=j_’ + skus.join(‘,j_’) + ‘&type=1’,
# datatype: ‘jsonp’,
# success: function (r) {
# if (!r && !r.length) {
# return false;
# }
# for (var i = 0; i < r.length; i++) {
# var sku = r[i].id.replace('j_', '');
# var price = parsefloat(r[i].p, 10);
#
# if (price > 0) {
# $wrap.find(‘.’+ perfix + sku).html(‘￥’ + r[i].p + ”);
# } else {
# $wrap.find(‘.’+ perfix + sku).html(‘暂无报价’);
# }
#
# if ( typeof callback === ‘function’ ) {
# callback(sku, price, r);
# }
# }
# }
# });
# };
“””
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,(.*?)};’, re.s)
product_info = re.findall(product_re, self.html)[0]
return product_info
def get_product_skuid(self):
“””
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: (.*?),’)
skuid = re.findall(skuid_re, product_info)[0]
return skuid
def get_product_name(self):
pass
def get_product_price(self):
“””
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?skuids=j_’ + skuid + ‘&type=1’
price_json = json.load(urllib.urlopen(url))[0]
if price_json[‘p’]:
price = price_json[‘p’]
return price
# 测试代码
if __name__ == ‘__main__’:
url = ‘http://item.jd.com/1310118868.html’
url = ‘http://item.jd.com/1044773.html’
jp = jdprice(url)
print jp.get_product_price()
# htm.decode(‘gb2312’, ‘ignore’).encode(‘utf-8’)
# f = open(‘jjs.html’, ‘w’)
# f.write(htm)
# f.close()
再给大家分享一个京东价格的爬虫：
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().p.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)