数据用

https://segmentfault.com/a/1190000008745531

var cheerio = require('cheerio');
var http = require('http');
var iconv = require('iconv-lite');
//https://segmentfault.com/a/1190000008745531
//var url = 'http://www.ygdy8.net/html/gndy/dyzz/index.html';
var url = "http://nj.rent.house365.com/district_i1/dl_x1.html";
http.get(url, function(sres) {
    var chunks = [];
    sres.on('data', function(chunk) {
        chunks.push(chunk);
    });
    // chunks里面存储着网页的 html 内容,将它zhuan ma传给 cheerio.load 之后
    // 就可以得到一个实现了 jQuery 接口的变量,将它命名为 `$`
    // 剩下就都是 jQuery 的内容了
    sres.on('end', function() {
        var titles = [];
        //由于咱们发现此网页的编码格式为gb2312,所以需要对其进行转码,否则乱码
        //依据:“<meta http-equiv="Content-Type" content="text/html; charset=gb2312">”
        var html = iconv.decode(Buffer.concat(chunks), 'gb2312');
        var $ = cheerio.load(html, {decodeEntities: false});
        $('.info .name a').each(function (idx, element) {
            var $element = $(element);
            console.log($element.attr("href"),$element.text());
            titles.push({
                title: $element.text()
            })
        })
        //console.log(titles);
    });
});

  

原文地址:https://www.cnblogs.com/cnchengv/p/8605728.html