python抓取京东价格分析京东商品价格走势

from creepy import crawler
from beautifulsoup import beautifulsoup
import urllib2
import json

class mycrawler(crawler):
    def process_document(self, doc):
        if doc.status == 200:
            print '[%d] %s' % (doc.status, doc.url)
            try:
                soup = beautifulsoup(doc.text.decode('gb18030').encode('utf-8'))
            except exception as e:
                print e
                soup = beautifulsoup(doc.text)
            print soup.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()
            print price[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')