I have this sample of my code:
function clickOldShares() {
console.log("Waiting for all shares");
element = document.querySelector("#pagelet_scrolling_pager > div > div > a");
return element;
}
casper.thenOpen("https://www.facebook.com/shares/view?id=" + fb_objectID,function(){
console.log("Open post with object-id");
});
casper.then(function(){
element = this.evaluate(clickOldShares);
});
casper.wait(2000,function() {
console.log('ELEMENT1: ' + element);
element = this.evaluate(clickOldShares);
});
casper.wait(2000,function() {
newelement = this.evaluate(clickOldShares);
console.log('ELEMENT2: ' + newelement);
});
casper.wait(2000,function() {
newelement = this.evaluate(clickOldShares);
console.log('ELEMENT3: ' + newelement);
});
I´m not understanding how can I transform this calls to clickOldShares in a loop using CasperJS because casper.wait is asynchronous. May I have some example of how to do this, please?
The page doesn't load all data in one time. It's necessary to click on the 'Older Shares' button until the data appears. And this can happen many times, depending the amount of data. So, I need to click as often as needed before capturing data.
First thing's first, you can't use clickOldShares for anything as it is now. casper.evaluate() provides access to the DOM, but the passed in function is sandboxed and executed in the page context. All data must be explicitly passed in and out, and this has to be primitive. DOM elements are not primitive and cannot be passed out of the page context (this.evaluate(clickOldShares) will always return null). You will either have to call the click code inside of the page context.
You can wait for an element to appear with waitForSelector. You really don't need to iterate to wait for it.
var selector = "#pagelet_scrolling_pager > div > div > a";
casper.start()
.thenOpen(url)
.waitForSelector(selector, null, null, 15000); // max 15 seconds
.then(function(){
this.capture("screen1.png");
this.click(selector);
})
.then(function(){
this.capture("screen2.png");
})
.run();
The third argument for waitForSelector is the callback for when the timeout is reached, but the element is not found. The fourth argument is a custom timeout. The default timeout is set to 10 seconds.
It seems you need to click on a certain selector until it disappears. You can't use a loop for this, because the functions are asynchronous. You will have to use recursion like this:
var selector = "#pagelet_scrolling_pager > div > div > a";
var i = 0;
function step() {
if (this.exists(selector)) {
this.capture("screen"+(i++)+".png");
this.click(selector);
this.wait(2000, step);
} else {
this.capture("screen_final.png");
}
}
casper.start()
.thenOpen(url)
.then(step)
.then(function(){
// TODO: do something else
})
.run()
Related
Here's the problem. I'm making a callback to the server that receives an MVC partial page. It's been working great, it calls the success function and all that. However, I'm calling a function after which iterates through specific elements:
$(".tool-fields.in div.collapse, .common-fields div.collapse").each(...)
Inside this, I'm checking for a specific attribute (custom one using data-) which is also working great; however; the iterator never finishes. No error messages are given, the program doesn't hold up. It just quits.
Here's the function with the iterator
function HideShow() {
$(".tool-fields.in div.collapse, .common-fields div.collapse").each(function () {
if (IsDataYesNoHide(this)) {
$(this).collapse("show");
}
else
$(this).collapse("hide");
});
alert("test");
}
Here's the function called in that, "IsDataYesNoHide":
function IsDataYesNoHide(element) {
var $element = $(element);
var datayesnohide = $element.attr("data-yes-no-hide");
if (datayesnohide !== undefined) {
var array = datayesnohide.split(";");
var returnAnswer = true;
for (var i in array) {
var answer = array[i].split("=")[1];
returnAnswer = returnAnswer && (answer.toLowerCase() === "true");
}
return returnAnswer;
}
else {
return false;
}
}
This is the way the attribute appears
data-yes-no-hide="pKanban_Val=true;pTwoBoxSystem_Val=true;"
EDIT: Per request, here is the jquery $.post
$.post(path + conPath + '/GrabDetails', $.param({ data: dataArr }, true), function (data) {
ToggleLoader(false); //Page load finished so the spinner should stop
if (data !== "") { //if we got anything back of if there wasn't a ghost record
$container.find(".container").first().append(data); //add the content
var $changes = $("#Changes"); //grab the changes
var $details = $("#details"); //grab the current
SplitPage($container, $details, $changes); //Just CSS changes
MoveApproveReject($changes); //Moves buttons to the left of the screen
MarkAsDifferent($changes, $details) //Adds the data- attribute and colors differences
}
else {
$(".Details .modal-content").removeClass("extra-wide"); //Normal page
$(".Details input[type=radio]").each(function () {
CheckOptionalFields(this);
});
}
HideShow(); //Hide or show fields by business logic
});
For a while, I thought the jquery collapse was breaking, but putting the simple alert('test') showed me what was happening. It just was never finishing.
Are there specific lengths of time a callback function can be called from a jquery postback? I'm loading everything in modal views which would indicate "oh maybe jquery is included twice", but I've already had that problem for other things and have made sure that it only ever includes once. As in the include is only once in the entire app and the layout is only applied to the main page.
I'm open to any possibilities.
Thanks!
~Brandon
Found the problem. I had a variable that was sometimes being set as undefined cause it to silently crash. I have no idea why there was no error message.
I have an iframe having the id demo and
I have a list of 5 html files (promo1,promo2,promo3,promo4,promo5) which is to be displayed in the iframes, one after the other, repeatedly.
Each html page has a different time intervals for which it should be displayed in the frame
Here is my JavaScript code in which the dict represents each html and the time for which it should be displayed.
the following code causes multiple invocation of demo function at a time
;(function($){
"use strict";
var index=1,
dict={"promo1":70000,"promo2":46500,"promo3":18000,"promo4":93000,"promo5":86000},
var $firstFrame = $("#demo");
$(function (){
function demo(frameId,index){
frameId.attr("src","static/promo" + index + ".html");
frameId.load(function(){
if(index < 5){
a = setTimeout(demo(frameId , index + 1),dict["promo"+index]);
}
else if(index == 5){
var a = setTimeout(demo(frameId , 1),dict["promo"+index]);
}
});
}
demo($firstFrame , 1);
});
}(window.jQuery));
you need to wrap your setTimeout action in a function. When you use setTimeout, you want to pass a function to be called later. Otherwise, you are calling demo immediately and passing the return value.
setTimeout(function() {demo(frameId , 1),dict["promo"+index];});
Im trying to use PhantomJS to scrape the trophy data from http://my.playstation.com/logged-in/trophies/public-trophies/
The page requires you enter a valid username and then click 'go' and the page will load the data. Ive gotten this to work somewhat, but it never loads the trophy data into the div. Im hoping im missing something ajax related thats causing this?
var fullpagehtml = page.evaluate(function()
{
document.getElementById("trophiesId").value = "<<valid user id>>";
//checkPTrophies(); btn click calls this function
$('#btn_publictrophy').click().delay( 6000 );
console.log("\nWaiting for trophy list to load...");
var trophylist = document.getElementById("trophyTrophyList").innerHtml; // all the data i want ends up inside this div
var counter = 0; //delay andset timeout wont work here so this is the best i coukld think of
while (trophylist == null)
{
//presumably the ajax query should kick in on the page and populate this div, but it doesnt.
trophylist = document.getElementById("trophyTrophyList").innerHtml;
counter ++;
if(counter == 1000000)
{
console.log($('#trophyTrophyList').html());
counter = 0;
}
}
return document.all[0].outerHTML;
});
The delay( 6000 ) does absolutely nothing as the documentation says:
The .delay() method is best for delaying between queued jQuery effects. Because it is limited—it doesn't, for example, offer a way to cancel the delay—.delay() is not a replacement for JavaScript's native setTimeout function, which may be more appropriate for certain use cases.
To wait you have to do this outside of the page context (busy waiting doesn't work in JavaScript because it is single threaded):
page.evaluate(function() {
document.getElementById("trophiesId").value = "<<valid user id>>";
//checkPTrophies(); btn click calls this function
$('#btn_publictrophy').click();
});
console.log("\nWaiting for trophy list to load...");
setTimeout(function(){
var fullpagehtml = page.evaluate(function() {
var trophylist = document.getElementById("trophyTrophyList").innerHTML;
return trophylist;
});
}, 20000);
You also might want to use waitFor to wait until #trophyTrophyList is populated instead of using setTimeout:
waitFor(function(){
return page.evaluate(function(){
var e = document.getElementById("trophyTrophyList");
return e && e.innerHTML;
});
}, function(){
// TODO: get trophies
});
This won't get you far, because just because #trophyTrophyList is loaded, doesn't mean that the descendent elements are already in the DOM. You have to find some selector which signalizes that the page is sufficiently loaded for example by waiting until a .trophy-image exists in the page. It works for me with a 20 second timeout of the waitFor function.
waitFor(function(){
return page.evaluate(function(){
var e = document.querySelector("#trophyTrophyList .trophy-image");
return e;
});
}, function(){
setTimeout(function(){
var trophiesDiv = page.evaluate(function(){
return document.getElementById("trophyTrophyList").innerHTML;
});
console.log(trophiesDiv);
}, 1000); // wait a little longer
}, 20000);
Don't forget that you need page.evaluate to actually access the DOM. Btw, it is innerHTML not innerHtml.
Trying to automate some testing for some analytics tracking code, and I'm running into issues when I try passing links into the each() method.
I copied a lot of this from stackoverflow - how to follow all links in casperjs, but I don't need return the href of the link; I need to return the link itself (so I can click it). I keep getting this error: each() only works with arrays. Am I not returning an array?
UPDATE:
For each anchor tag that has .myClass, click it, then return requested parameters from casper.options.onResourceReceived e.g. event category, event action, etc. I may or may not have to cancel the navigation the happens after the click; I simply only need to review the request, and do not need the follow page to load.
Testing steps:
click link that has .myClass
look at request parameters
cancel the click to prevent it from going to the next page.
I'm new to javascript and casper.js, so I apologize if I'm misinterpreting.
ANOTHER UPDATE:
I've updated the code to instead return an array of classes. There are a few sketchy bits of code in this though (see comments inline).
However, I'm now having issues canceling the navigation after the click. .Clear() canceled all js. Anyway to prevent default action happening after click? Like e.preventDefault();?
var casper = require('casper').create({
verbose: true,
logLevel: 'debug'
});
casper.options.onResourceReceived = function(arg1, response) {
if (response.url.indexOf('t=event') > -1) {
var query = decodeURI(response.url);
var data = query.split('&');
var result = {};
for (var i = 0; i < data.length; i++) {
var item = data[i].split('=');
result[item[0]] = item[1];
}
console.log('EVENT CATEGORY = ' + result.ec + '\n' +
'EVENT ACTION = ' + result.ea + '\n' +
'EVENT LABEL = ' + decodeURIComponent(result.el) + '\n' +
'REQUEST STATUS = ' + response.status
);
}
};
var links;
//var myClass = '.myClass';
casper.start('http://www.leupold.com', function getLinks() {
links = this.evaluate(function() {
var links = document.querySelectorAll('.myClass');
// having issues when I attempted to pass in myClass var.
links = Array.prototype.map.call(links, function(link) {
// seems like a sketchy way to get a class. what happens if there are multiple classes?
return link.getAttribute('class');
});
return links;
});
});
casper.waitForSelector('.myClass', function() {
this.echo('selector is here');
//this.echo(this.getCurrentUrl());
//this.echo(JSON.stringify(links));
this.each(links, function(self, link) {
self.echo('this is a class : ' + link);
// again this is horrible
self.click('.' + link);
});
});
casper.run(function() {
this.exit();
});
There are two problems that you're dealing with.
1. Select elements based on class
Usually a class is used multiple times. So when you first select elements based on this class, you will get elements that have that class, but it is not guaranteed that this will be unique. See for example this selection of element that you may select by .myClass:
myClass
myClass myClass2
myClass myClass3
myClass
myClass myClass3
When you later iterate over those class names, you've got a problem, because 4 and 5 can never be clicked using casper.click("." + links[i].replace(" ", ".")) (you need to additionally replace spaces with dots). casper.click only clicks the first occurrence of the specific selector. That is why I used createXPathFromElement taken from stijn de ryck to find the unique XPath expression for every element inside the page context.
You can then click the correct element via the unique XPath like this
casper.click(x(xpathFromPageContext[i]));
2. Cancelling navigation
This may depend on what your page actually is.
Note: I use the casper.test property which is the Tester module. You get access to it by invoking casper like this: casperjs test script.js.
Note: There is also the casper.waitForResource function. Have a look at it.
2.1 Web 1.0
When a click means a new page will be loaded, you may add an event handler to the page.resource.requested event. You can then abort() the request without resetting the page back to the startURL.
var resourceAborted = false;
casper.on('page.resource.requested', function(requestData, request){
if (requestData.url.match(/someURLMatching/)) {
// you can also check requestData.headers which is an array of objects:
// [{name: "header name", value: "some value"}]
casper.test.pass("resource passed");
} else {
casper.test.fail("resource failed");
}
if (requestData.url != startURL) {
request.abort();
}
resourceAborted = true;
});
and in the test flow:
casper.each(links, function(self, link){
self.thenClick(x(link));
self.waitFor(function check(){
return resourceAborted;
});
self.then(function(){
resourceAborted = false; // reset state
});
});
2.2 Single page application
There may be so many event handlers attached, that it is quite hard to prevent them all. An easier way (at least for me) is to
get all the unique element paths,
iterate over the list and do every time the following:
Open the original page again (basically a reset for every link)
do the click on the current XPath
This is basically what I do in this answer.
Since single page apps don't load pages. The navigation.requested and page.resource.requested will not be triggered. You need the resource.requested event if you want to check some API call:
var clickPassed = -1;
casper.on('resource.requested', function(requestData, request){
if (requestData.url.match(/someURLMatching/)) {
// you can also check requestData.headers which is an array of objects:
// [{name: "header name", value: "some value"}]
clickPassed = true;
} else {
clickPassed = false;
}
});
and in the test flow:
casper.each(links, function(self, link){
self.thenOpen(startURL);
self.thenClick(x(link));
self.waitFor(function check(){
return clickPassed !== -1;
}, function then(){
casper.test.assert(clickPassed);
clickPassed = -1;
}, function onTimeout(){
casper.test.fail("Resource timeout");
});
});
i have a simple question, there is a function with parameter emp_id that opens up a form for a chat with different attributes, i want it to be refreshed automatically each 10 sec, now it works a bit wrongly, since there is a parameter emp_id that is can be changed, and once i change it, the chat with messages and form are refreshed double time or triple times :) depend on how many times u change the emp_id, i hope i was clear )) anyway here is the javascript function:
function load_chat(emp_id) {
var url = "#request.self#?fuseaction=objects2.popup_list_chatform"
url = url + "&employee_id=" + emp_id;
document.getElementById('form_div').style.display = 'block'; AjaxPageLoad(url,'form_div',1,'Yükleniyor');
setInterval( function() {
load_chat(emp_id);
},10000);
}
there a list of names, once i click on one of them, this form is opened by this function, but if i click another user, i mean if i change the emp_id, it refreshes, the previous and present form. how do i change it so that it will refresh only the last emp_id, but not all of id's which i've changed
thank you all for the help, i really appreciate it!
This would nicely encapsulate what you're doing. The timer id (tid) is kept inside the closure, so when you call load_chat it will stop the interval if there was one running.
Once the new url is set up, it will start the interval timer again.
var ChatModule = (function() {
var tid,
url;
function refresh()
{
AjaxPageLoad(url, 'form_div', 1, 'Yükleniyor');
}
return {
load_chat: function(emp_id) {
if (tid) {
clearInterval(tid);
}
// setup url
url = "#request.self#?fuseaction=objects2.popup_list_chatform"
url = url + "&employee_id=" + emp_id;
document.getElementById('form_div').style.display = 'block';
// load ajax
refresh();
// set timer
tid = setInterval(refresh, 10000);
}
}
}());
ChatModule.load_chat(123);
Use setTimeout instead. Each time your function is executed, it will set up the next execution (you could also make it conditional):
function load_chat(emp_id) {
... // do something
if (condition_still_met)
setTimeout(function() {
load_chat(emp_id); // with same id
}, 10000);
}
load_chat("x"); // to start
Or you will have to use setInterval outside the load_chat function. You can clear the interval when necessary.
function get_chat_loader(emp_id) {
return function() {
... // do something
};
}
var id = setInterval(get_chat_loader("x"), 10000); // start
// then, somewhen later:
clearInterval(id);