由于 CasperJS 的结构化方式/控制流程与 PhantomJS 相比,这样的任务并不容易。
1。拉取方式(文件轮询)
假设有一个辅助程序(类型 1)处理显示验证码、接收输入并使用验证码输入写入文本文件。 CasperJS 可以处理的只是将 CAPTCHA 屏幕截图写入磁盘并等待带有“已解析”文本的文件。
var fs = require("fs"),
captchaFile = "cfile.png",
parsedFile = "pfile.txt";
casper.waitForCaptcha = function(captchaFile, parsedFile){
casper.then(function(){
this.captureSelector(captchaFile, "someSelectorOfTheCaptcha");
});
casper.waitFor(function check(){
return fs.exists(parsedFile);
}, function then(){
// do something on time
// check if correct...
if (!correct) {
fs.remove(captchaFile);
fs.remove(parsedFile);
this.waitForCaptcha(captchaFile, parsedFile);
// Problem: the secondary process needs to sense that a new CAPTCHA is presented
}
}, function onTimeout(){
// do something when failed
}, 60000); // 1min should suffice as a timeout
return this;
};
casper.start(url).waitForCaptcha(captchaFile, parsedFile).run();
此代码假定您想在验证码错误时重试,但如果故意在没有解码文件的情况下经过一分钟,则不会。这是一个通过轮询文件是否已经存在的拉取过程。
2。推送方法
在辅助程序(类型 2)通过使用PhantomJS webserver module 向 CasperJS 进程发送请求的情况下,推送过程也是可能的。因为会有两个并发的控制流,所以CasperJS部分需要等待很长时间,但是一旦收到带有解码字的请求,就可以用unwait打破等待。
var server = require('webserver').create(),
fs = require("fs"),
captchaFile = "cfile.png";
function neverendingWait(){
this.wait(5000, neverendingWait);
}
casper.checkCaptcha = function(captchaFile, phantomPort, secondaryPort){
// here the CAPTCHA is saved to disk but it can also be set directly if captured through casper.captureBase64
this.captureSelector(captchaFile, "someSelectorOfTheCaptcha");
// send request to the secondary program from the page context
this.evaluate(function(file){
__utils__.sendAJAX("http://localhost:"+secondaryPort+"/", "POST", {file: file}, true);
}, captchaFile);
// start the server to receive solved CAPTCHAs
server.listen(phantomPort, {
'keepAlive': true
}, function (request, response) {
console.log('Request received at ' + new Date());
if (request.post) { // is there a response?
this.then(function(){
// check if it is correct by reading request.post ...
if (!correct){
response.statusCode = 404;
response.headers = {
'Cache': 'no-cache',
'Content-Type': 'text/plain;charset=utf-8'
};
response.close();
server.close();
this.checkCaptcha(captchaFile, phantomPort, secondaryPort);
} else {
response.statusCode = 200;
response.headers = {
'Cache': 'no-cache',
'Content-Type': 'text/plain;charset=utf-8'
};
response.close();
server.close();
this.unwait(); // abort the neverendingWait
}
});
} else {
response.statusCode = 404;
response.headers = {
'Cache': 'no-cache',
'Content-Type': 'text/plain;charset=utf-8'
};
response.close();
server.close();
this.checkCaptcha(captchaFile, phantomPort, secondaryPort);
}
});
return this;
};
casper.start(url).then(function(){
this.checkCaptcha(captchaFile, 8080, 8081);
}).then(neverendingWait).then(function(){
// Do something here when the captcha is successful
}).run();