page.content support about node-phantom

[ehartford]

What other methods? I would like to know please.

[ehartford]

+1 by the way.

[DavidLeoni]

You just need to evaluate document.documentElement.innerHTML inside the opened page, like I do here after a timeout, to take into account presence of Javascript inside the page that could modified it on load:

var phantom=require('node-phantom');    
var waitTime = 5000;

phantom.create(function(err,ph) {    
    return ph.createPage(function(err,page) {
    /* to show browser console.log

        page.onConsoleMessage = function(msg) {
        console.log(msg);
    }; */
        var pstr = "http://www.google.com";
        console.log("browsing to ", pstr);
        return page.open(pstr, function(err,status) {
            console.log("opened site? ", status);
            if ( status === "success" ) {
                setTimeout(function(){                   
                    var p = page.evaluate(function () {
                        return document.documentElement.innerHTML;                    
                    }, function(err,result){
                        if (err) {
                            console.log("Error!");
                        } else {
                                console.log("*****   The html is:   *****");                                
                                console.log(result);                              
                        }                        
                        ph.exit();
                    });                                               

                }, waitTime)                   
            };
        });
    });                        
});

[alexscheelmeyer]

You can get to page.content through the page.get function

page.get('content',function(err,content){
  //content will now be 'page.content'
});

[JeStasG]

in code:

page.get('content',function(err,content){
  //content will now be 'page.content'
});

page content consist in variable err

PS: Sorry fo my english:(

[raeesaa]

@alexscheelmeyer We are getting content in err object of page.get('content', function(err, content){}) function and content object is undefined. Has the callback method signature changed since this answer was posted?

Thanks,
Raeesaa

[tholu]

@raeesaa
This should work:

page.get('content',function(content){
  //content will now be in var 'content'
});