javascript - 在 phantomjs 中使用策略模式

Question

我正在尝试在我的爬虫中实现策略模式，我认为使用不同的策略来爬行不同的网站会很巧妙。因此，我希望 page.evaluate 中的内容根据当前运行的网站而有所不同。 page.evaluate 中的注释代码可以工作，但是有没有办法可以将其提取到函数中？我尝试运行 this.findJobs() 但没有成功。

"use strict";

var Crawler = function() {
    this.page = require('webpage').create();
    this.website = "";
    this.jobs_list = [];

};

Crawler.prototype.setStrategy = function(company) {
    this.website = company;
};

Crawler.prototype.findJobData = function() {
    return this.website.findJobData();
};

Crawler.prototype.collectJobData = function() {
    var page = require('webpage').create();
    page.onConsoleMessage = function(msg) { console.log(msg) };

    page.open('URL', function (status) {
        page.includeJs("https://ajax.googleapis.com/ajax/libs/jquery/3.1.0/jquery.min.js", function() {
            var temp_jobs = page.evaluate(this.findJobs());

                /*
                var jobs = [];
                var job;
                    $('ul.job-list').each(function(){
                    $(this).find('li').each(function(){
                        var job_link = $(this).find('a');
                        var url = "URL" + job_link.attr("href");
                        var location = $(this).find('span').text();

                        job = {title: job_link.text(), url: url, location: location, description: ""}
                        jobs.push(job);
                        console.log(job.title, job.url, job.location);
                    })
                });
                return jobs;*/
            console.log(temp_jobs[0].title)

            phantom.exit(0);
        });
    });

};

var strategy_a = function() {

    this.findJobs = function() {
            var jobs = [];
            var job;
            $('ul.job-list').each(function(){
                $(this).find('li').each(function(){
                    var job_link = $(this).find('a');
                    var url = "URL" + job_link.attr("href");
                    var location = $(this).find('span').text();

                    job = {title : job_link.text(), url : url, location : location, description : ""};
                    jobs.push(job);
                    console.log(job.title, job.url, job.location);
                })
            });
            return jobs;
    };
};


var strategy_a = new strategy_a();
var crawler = new Crawler();

crawler.setStrategy(strategy_a);
crawler.collectJobData();

Answer 1

您有两个问题:

• 您打算使用page.evaluate(this.findJobs);而不是page.evaluate(this.findJobs());和

• this page.includeJs里面回调不是对 Crawler 的引用实例。

这应该有效:

Crawler.prototype.collectJobData = function() {
    var page = this.page;
    var self = this;
    page.onConsoleMessage = function(msg) { console.log(msg) };

    page.open('URL', function (status) {
        page.includeJs("https://ajax.googleapis.com/ajax/libs/jquery/3.1.0/jquery.min.js", function() {
            var temp_jobs = page.evaluate(self.website.findJobs);
            console.log(temp_jobs[0].title)

            phantom.exit(0);
        });
    });
};

请注意，您生成了多个页面但没有使用所有页面，因此我删除了第二个 require('webpage').create() .