gpt4 book ai didi

javascript - 从 Playstation 官方网站抓取奖杯数据

转载 作者:行者123 更新时间:2023-12-02 16:32:09 25 4
gpt4 key购买 nike

我正在尝试使用 PhantomJS 从 http://my.playstation.com/logged-in/trophies/public-trophies/ 中抓取奖杯数据

该页面要求您输入有效的用户名,然后单击“开始”,页面将加载数据。我已经让它在某种程度上起作用了,但它从未将奖杯数据加载到 div 中。我希望我错过了一些与ajax相关的东西导致了这个?

  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;

});

最佳答案

delay( 6000 ) 绝对不会像 documentation 那样做任何事情。说:

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.

要等待,您必须在页面上下文之外执行此操作(忙等待在 JavaScript 中不起作用,因为它是单线程的):

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);

您可能还想使用waitFor等待填充#tropyTrophyList,而不是使用setTimeout:

waitFor(function(){
return page.evaluate(function(){
var e = document.getElementById("trophyTrophyList");
return e && e.innerHTML;
});
}, function(){
// TODO: get trophies
});

这不会让您走得太远,因为加载 #tropyTrophyList 并不意味着后代元素已经在 DOM 中。您必须找到一些选择器来表明页面已充分加载,例如通过等待页面中存在 .tropy-image 。它适用于我的 waitFor 函数 20 秒超时。

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);

不要忘记您需要 page.evaluate 才能实际访问 DOM。顺便说一句,它是 innerHTML 而不是 innerHtml

关于javascript - 从 Playstation 官方网站抓取奖杯数据,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/28206062/

25 4 0
Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
广告合作:1813099741@qq.com 6ren.com