js抓取list中item的html,Nodejs HTML抓取与内容提取

来代码实在了：

var Crawler = require("crawler");

var c = new Crawler({

maxConnections : 1,

rateLimit:2000,

callback : function (error, res, done) {

if(error){

console.error(error);

}else{

var $ = res.$;

var index = 0;

var querystring = require('querystring')

var url = require('url')

var item = $('div.left-container').find('div.design-goods-list-item-contianer').each(function($this){

var a = $(this).find('.design-goods-image-container').children('a').attr('href');

var img = $(this).find('.design-goods-image-container').children('a').children('img').attr('src')

var title =$(this).find('.design-goods-image-container').children('a').children('img').attr('title')

var price = $(this).find('.design-goods-price-and-collect-container').children('div.design-goods-price').text()

//var ref = a.attr('href')

//var img = a.children('img').attr('src')

var argstr = url.parse('http://gz.17zwd.com'+a).query

var arg = querystring.parse(argstr);

console.log('GID='+arg.GID)

console.log(a)

console.log(img)

console.log(title)

console.log(price)

console.log('------------')

console.log()

});

}

done();

}

});

c.queue({

uri:"http://gz.17zwd.com/sks.htm?pstart=80&pend=89&ax=&zdid=42&mid=-1&fid=-1&cateid=50010850&color=&size=&so=2017+春&page=2",

});