python根據(jù)京東商品url獲取產(chǎn)品價(jià)格

更新時(shí)間：2015年08月09日 17:38:30 投稿：hebedich

閑著沒事嘗試抓一下京東的數(shù)據(jù)，需要使用到的庫有：BeautifulSoup，urllib2，在Python2下測(cè)試通過

京東商品詳細(xì)的請(qǐng)求處理，是先顯示html，然后再ajax請(qǐng)求處理顯示價(jià)格。
1.可以運(yùn)行js，并解析之后得到的html
2.模擬js請(qǐng)求，得到價(jià)格

# -*- coding: utf-8 -*-
"""
根據(jù)京東url地址，獲取商品價(jià)格
京東請(qǐng)求處理過程，先顯示html頁面，然后通過ajax get請(qǐng)求獲取相應(yīng)的商品價(jià)格
 
1.商品的具體數(shù)據(jù)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請(qǐng)求代碼如下：
# // 獲得數(shù)字價(jià)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('暫無報(bào)價(jià)');
#         }
#
#         if ( typeof callback === 'function' ) {
#           callback(sku, price, r);
#         }
#       }
#     }
#   });
# };
"""
import urllib
import json
import re
 
 
class JdPrice(object):
  """
  對(duì)獲取京東商品價(jià)格進(jìn)行簡單封裝
  """
  def __init__(self, url):
    self.url = url
    self._response = urllib.urlopen(self.url)
    self.html = self._response.read()
 
  def get_product(self):
    """
    獲取html中，商品的描述(未對(duì)數(shù)據(jù)進(jìn)行詳細(xì)處理，粗略的返回str類型)
    :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):
    """
    通過獲取的商品信息，獲取商品的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):
    """
    根據(jù)商品的skuid信息，請(qǐng)求獲得商品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
 
 
# 測(cè)試代碼
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()

再給大家分享一個(gè)京東價(jià)格的爬蟲：

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)

您可能感興趣的文章: