CODEWITHSUNDEEP
node.jsweb-scrapingweb-crawler
july77
july77

Reputation: 823

I cannot get url from a website using nodejs

I hope to scrape urls from this website by using the code below:

var request = require("request");
cheerio = require("cheerio");
urls = [];

request("http://news.sabay.com.kh/topics/sport", function(err, resp, body){
    if(!err && resp.statusCode ==200){
        var $ = cheerio.load(body);
        $(".article","h4.title").each(function(){
            var url = this.attr("href");
            urls.push(url);
        });
        console.log(urls);
    }
});

but I cannot get the result. When I run I got this

$ node server.js
[]

Upvotes: 0

Views: 98

Answers (1)

KeatsPeeks
KeatsPeeks

Reputation: 19327

First, use a proper CSS selector :

.article h4.title > a

Then, use the proper field :

var url = this.attribs.href

Which gives :

var request = require("request");
cheerio = require("cheerio");
urls = [];

request("http://news.sabay.com.kh/topics/sport", function(err, resp, body){
    if(!err && resp.statusCode ==200){
        var $ = cheerio.load(body);
        $(".article h4.title > a").each(function(){
            var url = this.attribs.href;
            urls.push(url);
        });
        console.log(urls);
    }
});

and outputs :

[ 'http://news.sabay.com.kh/article/546826',
  'http://news.sabay.com.kh/article/546763',
  'http://news.sabay.com.kh/article/546520',
  'http://news.sabay.com.kh/article/546568',
  'http://news.sabay.com.kh/article/546460',
  'http://news.sabay.com.kh/article/546448',
  'http://news.sabay.com.kh/article/545674',
  'http://news.sabay.com.kh/article/546235',
  'http://news.sabay.com.kh/article/545698',
  'http://news.sabay.com.kh/article/546091' ]

Upvotes: 1

Related Questions