Created
June 21, 2018 18:02
-
-
Save klebinhopk/f87635620c0cd80cbe37ba06628c4cf8 to your computer and use it in GitHub Desktop.
Google news scraper
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| const request = require('request'); | |
| const cheerio = require('cheerio'); | |
| var searchTerm = 'tech'; | |
| var searchUrl = 'https://www.google.com/search?q=' + searchTerm + '&tbm=nws'; | |
| var savedData = []; | |
| request(searchUrl, function(err, response, html) { | |
| // First we'll check to make sure no errors occurred when making the request | |
| if (err) { | |
| return res.status(500).send(err); | |
| } | |
| var $ = cheerio.load(html); | |
| // For each outer div with class g, parse the desired data | |
| $('div.g').each(function(i, element) { | |
| var title = $(this).find('.r').text(); | |
| var link = $(this).find('.r').find('a').attr('href').replace('/url?q=', '').split('&')[0]; | |
| var text = $(this).find('.st').text(); | |
| var img = $(this).find('img.th').attr('src'); | |
| savedData.push({ | |
| title: title, | |
| link: link, | |
| text: text, | |
| img: img | |
| }); | |
| }); | |
| console.log(JSON.stringify(savedData)); | |
| }); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment