解析多个网站页面并计算总项目数

时间:2015-02-07 04:51:00

标签: javascript casperjs

我的脚本只是收集页面上的报告数量,然后转到下一页并执行相同的操作。目标是获得跨多个页面的报告总数。

已更新

var casper = require('casper').create({
    clientScripts: ["./lib/jquery-2.1.3.min.js"],
    // verbose: true,
    logLevel: "debug"
});

casper.on('remote.message', function(msg) {
    this.echo('LOG: ' + msg);
});

casper.on('page.error', function (msg, trace) {
    this.echo( 'Error: ' + msg, 'ERROR' );
});

var reportCount, newReportCount, reportPages;

casper.start("reports.html", function() {

    reportPages = this.evaluate(function() {
        return $('#table2 tbody tr td').children('a').length -1;
  });

  //first page of reports
  reportCount = this.evaluate(function() {
      return $('#table1 tbody').first().children('tr').length;
  });

  this.echo('initial count: ' + reportCount);
  this.echo('pages: ' + reportPages);

  //check if more than 1 page and add report count
  if (reportPages > 1) {
    newReportCount = this.thenOpen('reports2.html', function(){
        var newCount = this.evaluate(function(count) {
            add = count + $('#table1 tbody').first().children('tr').length;
            // console.log('new count inside: ' + add);
            return add;
        }, reportCount);
        console.log(newCount); //this shows correct new value 32
    });
    console.log(newReportCount); //this shows [object Casper]

    neoReportCount = this.thenOpen('reports3.html', function(count){
        console.log(newReportCount); //this shows [object Casper]
        //do the same count
    }, newReportCount);
  }

casper.run();

这是控制台中的输出

Pages: 3
First count: 15
[object Casper], currently at file:///**/reports.html
32
[object Casper], currently at file:///**/reports3.html

1 个答案:

答案 0 :(得分:0)

是的,有可能,但您使用casper.thenOpenAndEvaluate(),其中包含then字样。这意味着此函数是异步的,它返回casper对象以启用构建器/承诺模式。所以你不能从这样的函数返回任何东西。由于它是异步的,因此将在当前步骤结束后执行,即在console.log(newCount);之后执行。

您需要拆分该功能,例如:

//check if more than 1 page and add report count
if (reportPages > 1) {
  var newCount;
  this.thenOpen('reports2.html', function(count){
    newCount = this.evaluate(function(count){
      add = count + $('#table1 tbody').first().children('tr').length;
      console.log('new count inside: ' + add);
      return add;
    }, reportCount);
    console.log(newCount);
  }).thenOpen('reports3.html', function(count){
    newCount += this.evaluate(function(count){
      add = count + $('#table1 tbody').first().children('tr').length;
      console.log('new count inside: ' + add);
      return add;
    }, reportCount);
    console.log(newCount);
  }).then(function(){
    console.log(newCount);
  });
}

好像你想要遍历多个页面。这通常是递归完成的,因为CasperJS是异步的,您事先并不知道需要打开多少页面。我建议你看看这个问题的一些例子:CasperJS loop or iterate through multiple web pages?