CODEWITHSUNDEEP
javascriptnode.jsmongodb
Rodney Wilson
Rodney Wilson

Reputation: 369

Web Scraping Using Nodejs

I have created a simple web scraper that pulls in the article titles and URL from this website: http://espn.go.com/college-football/. However, the scraper only returns 46-50 articles, instead of all the articles from the site. I've tried changing the CSS selector that cheerio uses, but nothing changes with regards to the number of articles it scrapes. Here is the code I'm using:

var fs = require('fs');
var request = require('request');
var cheerio = require('cheerio');
var mongo = require('mongoskin');
var db = mongo.db("mongodb://localhost:27017/test", { native_parser: true });


url = 'http://espn.go.com/college-football/';

function Headline(title, link) {
    this.Title = title;
    this.link = link;
}

request(url, function (error, response, html) {
    if (!error) {
        var $ = cheerio.load(html);

        var result = [];

        // Grab the articles titles/url
        $('.text-container h1 a.realStory', '#news-feed-content').each(function (i, elem) {
            console.log($(elem).text(), elem.attribs.href);
            var articleObject = new Headline($(elem).text(), elem.attribs.href);
            result.push(articleObject);
        });
    }

    fs.writeFile('espn_articles.json', JSON.stringify(result, null, 4), function (err) {

        console.log('File successfully written! - Check your project directory for the output.json file');

    })

    db.collection('articles').insert(result, function (error, record) {
        if (error) throw error;
        console.log("data saved");
    });
});

Upvotes: 0

Views: 696

Answers (2)

rchipka
rchipka

Reputation: 66

Here's an example using Osmosis.

osmosis('http://espn.go.com/college-football/')
    .find('#news-feed-content .text-container')
    .set({
        author:   '.author',
        category: '.category-link',
        title:    '.realStory',
        link:     '.realStory@href',
        blurb:    'p'
    })
    .follow('.realStory@href')
    .set({
        date:    '.article-meta @data-date',
        images:  [ 'picture @srcset' ],
        content: '.article-body'
    })
    .data(function (article) {
        /*
        { author: '...',
          category: '...',
          title: 'Harbaugh, Michigan reel in Florida OL Herbert',
          link: '...',
          blurb: 'Jim Harbaugh and Michigan have landed another recruit from SEC country in Kai-Leon Herbert of Florida.',
          date: '2016-07-06T17:25:09Z',
          images: [ '...', '...' ],
          content: '...'
        }
        */

        db.collection('articles').insert(article, function (error, record) {
            // ...
        });
    })
    .log(console.log)
    .error(console.log)
    .debug(console.log);

Upvotes: 2

Revln9
Revln9

Reputation: 847

when you take a look at the page with the chrome dev tools you'll see that it makes an api call everytime it renders more posts . here's the url : http://cdn.espn.go.com/core/now?render=true&partial=nowfeed&xhr=1&sport=ncf&offset=0&device=desktop&userab=8

I assume that the offset params is used for pagination.

Keep in mind that scraping is "illegal" in certain cases so better to ask for permission first

hope it helps !

Upvotes: 2

Related Questions