Last active
June 9, 2016 15:10
Example of using icrawler to scrape data from Ferra.ru
This file contains 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
| var icrawler = require('icrawler'); | |
| var fs = require('fs'); | |
| var URL = 'http://www.ferra.ru/ru/techlife/news/'; | |
| var opts = { | |
| errorsFirst: true, | |
| concurrency: 10, | |
| saveOnFinish: false, | |
| saveOnCount: 500, | |
| asyncParse: true, | |
| file: './data.json', | |
| }; | |
| icrawler(URL, opts, function(url, $, _, res){ | |
| if ($('div.b-option-nav').length < 1) { | |
| return _.cb(true); | |
| } | |
| if($('.b_infopost').contents().eq(2).text().trim().slice(0, -1) === 'Алексей Козлов'){ | |
| _.save({ | |
| title: $('h1').text(), | |
| date: $('.b_infopost>.date').text(), | |
| href: url, | |
| size: $('.newsbody').text().length | |
| }); | |
| _.step(); | |
| } | |
| $('.b_rewiev p>a').each(function() { | |
| _.push($(this).attr('href')); | |
| }); | |
| $('.bpr_next>a').slice(0,1).each(function() { | |
| _.push($(this).attr('href')); | |
| }); | |
| _.cb(); | |
| }, function(result){ | |
| fs.writeFileSync('./data.json', JSON.stringify(result, null, 4)) | |
| console.log('Results saved'); | |
| }); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment