Created
January 18, 2016 07:35
-
-
Save dskyyy/991666915cbb0ba2302a to your computer and use it in GitHub Desktop.
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
| var utils = require('utils'); | |
| var casper = require('casper').create({ | |
| pageSettings: { | |
| loadImages: false, | |
| loadPlugins: false, | |
| userAgent: 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:40.0) Gecko/20100101 Firefox/40.1' | |
| } | |
| }); | |
| // | |
| // casper.options.onResourceRequested = function(C, requestData, request) { | |
| // utils.dump(requestData.headers); | |
| // }; | |
| // casper.options.onResourceReceived = function(C, response) { | |
| // utils.dump(response.headers); | |
| // }; | |
| var dailyNewsUrl = 'https://news.yandex.ru/yandsearch?rpt=nnews2&catnews={cid}&grhow=clutop&rel=tm&p={page}&within=7'; | |
| var cid = casper.cli.get('cid') || null; | |
| var dueUrl = casper.cli.get('due-url') || null; | |
| var subjects = []; | |
| var proxyList = [ | |
| '185.67.247.1:1080', | |
| '78.31.21.174:1080', | |
| '77.87.113.113:15398', | |
| '176.28.43.210:1080', | |
| '94.41.225.232:1080', | |
| '91.156.185.219:10200' | |
| ]; | |
| var parseSubjectLinks = function() { | |
| var subjectSelector = document.querySelectorAll('.story-item__title > a'); | |
| return Array.prototype.map.call(subjectSelector, function(e) { | |
| return e.getAttribute('href'); | |
| }); | |
| }; | |
| var countButtons = function() { | |
| return document.querySelectorAll('.pager__group > a').length; | |
| }; | |
| function fromRange(min, max) { | |
| return Math.round(Math.random() * (max - min)) + min; | |
| } | |
| var parsePages = function(obj) { | |
| var page = -1; | |
| var loop = function() { | |
| page++; | |
| obj.handler(loop, page); | |
| }; | |
| loop(); | |
| }; | |
| casper.start(); | |
| casper.then(function() { | |
| parsePages({ | |
| handler: function(loop, page) { | |
| var delay = fromRange(1500, 3000); | |
| casper.wait(delay, function() { | |
| var url = dailyNewsUrl.replace(/\{cid}/g, cid).replace(/\{page}/g, page); | |
| this.thenOpen(url, function(response) { | |
| //utils.dump(this.getPageContent()); | |
| // this.echo(url); | |
| // this.echo(utils.dump(response)); | |
| var btnCount = this.evaluate(countButtons); | |
| if (btnCount === 0) { | |
| this.exit(); | |
| } | |
| this.waitFor(function() { | |
| return btnCount !== 6; | |
| }, | |
| function success() { | |
| this.echo(this.evaluate(parseSubjectLinks).join('\n')); | |
| }, | |
| function fail() { | |
| this.exit(); | |
| } | |
| ); | |
| }); | |
| loop(); | |
| }); | |
| } | |
| }); | |
| }); | |
| casper.run(); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment