How to for loop in casperjs

问题

I am trying to click a 'next' button N number of times and grab the page source each time. I understand that I can run an arbitrary function on the remote website, so instead of click() I just use the remote function nextPage() How do I run the following, an arbitrary number of times:

var casper = require('casper').create();

casper.start('http://www.example.com', function() {

    this.echo(this.getHTML());
    this.echo('-------------------------');

    var numTimes = 4, count = 2;

    casper.repeat(numTimes, function() {
        this.thenEvaluate(function() {
            nextPage(++count);
        });

        this.then(function() {
            this.echo(this.getHTML());
            this.echo('-------------------------');
        });
    });

});

'i' here is an index I tried to use in a javascript for loop.

So tl;dr: I want lick 'next', print pages source, click 'next', print page source, click 'next'... continue that N number of times.

回答1:

First, you can pass a value to the remote page context (i.e. to thenEvaluate function like this:

    this.thenEvaluate(function(remoteCount) {
        nextPage(remoteCount);
    }, ++count);

However, Casper#repeat might not be a good function to use here as the loop would NOT wait for each page load and then capture the content.

You may rather devise a event based chaining.

The work-flow of the code would be:

Have a global variable (or at-least a variable accessible to the functions mentioned below) to store the count and the limit.
listen to the load.finished event and grab the HTML here and then call the next page.

A simplified code can be:

var casper = require('casper').create();

var limit = 5, count = 1;

casper.on('load.finished', function (status) {
    if (status !== 'success') {
        this.echo ("Failed to load page.");
    }
    else {
        this.echo(this.getHTML());
        this.echo('-------------------------');
    }



    if(++count > limit) {
        this.echo ("Finished!");

    }
    else {
        this.evaluate(function(remoteCount) {
            nextPage(remoteCount);
            // [Edit the line below was added later]
            console.log(remoteCount);
            return remoteCount;
        }, count);

    }

});

casper.start('http://www.example.com').run();

NOTE: If you pages with high load of JS processes etc. you may also want to add a wait before calling the nextPage :

this.wait( 
   1000, // in ms
   function () {
        this.evaluate(function(remoteCount) {
            nextPage(remoteCount);
        }, count);
   }
);

[EDIT ADDED] The following event listeners will help you debug.

// help is tracing page's console.log 
casper.on('remote.message', function(msg) { 
    console.log('[Remote Page] ' + msg); 
}); 

// Print out all the error messages from the web page 
casper.on("page.error", function(msg, trace) { 
    casper.echo("[Remote Page Error] " + msg, "ERROR"); 
    casper.echo("[Remote Error trace] " + JSON.stringify(trace, undefined, 4)); 
});

回答2:

You could try using Casper#repeat

This should do, for the most part, what you want:

var numTimes = 10, count = 1;

casper.repeat(numTimes, function() {
    this.thenEvaluate(function(count) {
        nextPage(count);
    }, ++count);

    this.then(function() {
        this.echo(this.getHTML());
        this.echo('-------------------------');
    });
});

回答3:

var global_page_links = [];

casper.then(function(){
    for(var i=1; i<=5; i++){    
        // you just add all your links to array, and use it in casper.each()
        global_page_links.push(YOUR_LINK);
    }

    this.each(global_page_links, function(self, link) {
        if (link){
            self.thenOpen(link, function() {
                console.log("OPENED: "+this.getCurrentUrl());
                // do here what you need, evaluate() etc.
            });
        }
    });
});

This is answer to question, how to use for() in casperjs to launch several links

来源：https://stackoverflow.com/questions/18835159/how-to-for-loop-in-casperjs

标签

javascript

phantomjs

casperjs