复制代码 代码如下:
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')

风云阁资源网 Design By www.bgabc.com
广告合作:本站广告合作请联系QQ:858582 申请时备注:广告合作(否则不回)
免责声明:本站资源来自互联网收集,仅供用于学习和交流,请遵循相关法律法规,本站一切资源不代表本站立场,如有侵权、后门、不妥请联系本站删除!
风云阁资源网 Design By www.bgabc.com