我一直在尝试登录Marktplaats.nl (CraigsList-like webpage in Netherlands)使用 CasperJS。但是,我坚持接受 cookie 政策。
这是我到目前为止的脚本:
var casper = require('casper').create({
verbose: true,
logLevel: 'debug',
pageSettings: {
loadImages: false,
loadPlugins: false,
userAgent: 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.157 Safari/537.36'
}
});
var x = require('casper').selectXPath;
casper.start('https://www.marktplaats.nl', function() {
this.echo(this.getTitle()); //Prints "Marktplaats Cookiewall"
//POINT1
//Here I just check and log if the "Agree" button exists.
if (casper.exists(x("//input[contains(@value, 'Cookies accepteren')]"))) {
casper.echo("Agree button found");
}
else
{
casper.echo("Agree button not found");
}
});
casper.then(function() {
if(this.getTitle().indexOf("Cookiewall") !== -1)
{
//POINT2
//If we are on the cookiewall page, click on agree.
casper.echo("Clicking on agree");
casper.click(x("//input[contains(@value, 'Cookies accepteren')]"));
}
});
casper.thenOpen('https://www.marktplaats.nl', function() {
//POINT3
//Reloaded page
this.echo('Second Page: ' + this.getTitle());
});
casper.run();
首先尝试导航到主页(在代码中标记为 POINT1),但被重定向到 Cookiewall 页面,该页面希望我接受 cookie 策略。在浏览器中截取的屏幕截图,未连接到 CasperJS。
在 POINT2,我的脚本点击“Cookies Accepteren” - 记录为:
[debug] [phantom] Mouse event 'mousedown' on selector: xpath selector: //input[contains(@value, 'Cookies accepteren')]
[debug] [phantom] Mouse event 'mouseup' on selector: xpath selector: //input[contains(@value, 'Cookies accepteren')]
[debug] [phantom] Mouse event 'click' on selector: xpath selector: //input[contains(@value, 'Cookies accepteren')]
我是 CasperJS 新手,但这对我来说看起来不错。
最后,在 POINT3,我重新加载主页,但再次重定向到 Cookiewall 页面 - casper 记录 Cookiewall 标题并记录重定向 评论后更新:我按照 Artjom 的评论注册了 resource.error、page.error、remote.message 和 casper.page.onResourceTimeout。已出现 2 个资源错误。我相应地编辑了此日志:
[info] [phantom] Step anonymous 3/5: done in 2018ms.
[debug] [phantom] opening url: https://www.marktplaats.nl/, HTTP GET
ResourceError: {
"errorCode": 5,
"errorString": "Operation canceled",
"id": 7,
"status": null,
"statusText": null,
"url": "http://s3.amazonaws.com/ki.js/56612/b7M.js"
}
[debug] [phantom] Navigation requested: url=https://www.marktplaats.nl/, type=Other, willNavigate=true, isMainFrame=true
[debug] [phantom] Navigation requested: url=http://www.marktplaats.nl/, type=Other, willNavigate=true, isMainFrame=true
[debug] [phantom] Navigation requested: url=http://www.marktplaats.nl/cookiewall
/?target=http%3A%2F%2Fwww.marktplaats.nl%2F, type=Other, willNavigate=true, isMa
inFrame=true
[debug] [phantom] url changed to "http://www.marktplaats.nl/cookiewall/?target=http%3A%2F%2Fwww.marktplaats.nl%2F"
[debug] [phantom] Successfully injected Casper client-side utilities
[info] [phantom] Step anonymous 5/5 http://www.marktplaats.nl/cookiewall/?target
=http://www.marktplaats.nl/ (HTTP 200)
Second Page: ? Marktplaats - Cookiewall
[info] [phantom] Step anonymous 5/5: done in 2224ms.
[info] [phantom] Done 5 steps in 2243ms
[debug] [phantom] Navigation requested: url=about:blank, type=Other, willNavigate=true, isMainFrame=true
ResourceError: {
"errorCode": 5,
"errorString": "Operation canceled",
"id": 11,
"status": null,
"statusText": null,
"url": "http://s3.amazonaws.com/ki.js/56612/b7M.js"
}
[debug] [phantom] url changed to "about:blank"
我似乎无法进入主页。
最佳答案
你需要做两件事:
- 加载图像,因为当图像未加载时,按钮似乎没有尺寸。
- 点击后稍等一下。 CasperJS 似乎没有意识到正在发生页面加载。
完整脚本:
var casper = require('casper').create({
//verbose: true,
//logLevel: 'debug',
pageSettings: {
loadImages: true,
loadPlugins: false,
userAgent: 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.157 Safari/537.36'
}
});
var x = require('casper').selectXPath;
var acceptBtn = x("//input[contains(@value, 'Cookies accepteren')]");
casper.start('http://www.marktplaats.nl', function() {
this.echo(this.getTitle());
})
.waitForSelector(acceptBtn)
.thenClick(acceptBtn)
.wait(100)
.then(function(){
this.echo(this.getTitle());
})
.run();
关于javascript - 使用 CasperJS 接受 cookie 策略,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/39183064/