Question

我有一个幻像js脚本，它检查每个重定向并通过page.onNavigationRequested回调方法在控制台中显示它。

但是当我想要捕获从page.onNavigationRequested回调方法返回的所有URL并将它们推送到数组并最终显示脚本末尾的所有URL时，它只显示第一个重定向URL。

请您查看脚本和建议。

var page = require('webpage').create();
var sys = require('system');
var fs = require('fs');
var response = {};
var arrayOfResponses = [];
var pageUrl = 'http://example.com/r1.php';

phantom.onError = function (msg, trace) {
    phantom.exit(1);
};

function forceExit(){
   phantom.exit(0);
}

page.onNavigationRequested = function(url, type, willNavigate, main) {
    arrayOfResponses.push(url) ;
}

response.content = arrayOfResponses;

page.open(pageUrl, function(status) {
    if ( status !== 'success' ) {
        phantom.exit( 1 );
    } else {
        phantom.exit( 0 );
    }
}, 100);

setTimeout(forceExit,2000);

console.log(JSON.stringify(response));

并提前感谢你。

Answer 1

您的脚本存在两个问题：

在第一个网址打开后，你太早地退出PhantomJS。它没有时间关注重定向。

您从上到下编写脚本，就像程序流是线性/同步一样，而在javascript中它不是 - onNavigationRequested可以多次调用。

< / LI>

因此，考虑到这一点，让我们重写脚本以收集所有重定向，并在2秒内没有进行新的重定向时退出。

var page = require('webpage').create();
var response = {};
var arrayOfResponses = [];
var pageUrl = 'http://admin.weeqo.com/redirect/r1.php';
var exitTimeout;

// This will be called if no redirects are requested in 2 seconds
function forceExit(){
    // Just for fun we'll note the final URL
    var curURL = page.evaluate(function(){ 
        return document.location.href 
    });
    console.log("Final URL is " + curURL);

    // Prepare and output the report:
    response.content = arrayOfResponses;
    console.log("List of all requested URLs: " + JSON.stringify(response));

    // Now we can exit safely
    phantom.exit(0);
}

// This is called before each redirect
page.onNavigationRequested = function(url, type, willNavigate, main) {

    // Clear timeout so that script is not shut down
    // because we have a new redirect
    if(exitTimeout) {
        clearTimeout(exitTimeout);
    }
    arrayOfResponses.push(url);
    console.log("Navigation requested: " + url);

    // Create timeout that will shut down the script
    // in two seconds unless cancelled
    exitTimeout = setTimeout(forceExit, 2000);
}

// open the first page
page.open(pageUrl, function(status) {

    // We only care for errors because
    // who knows how many time will pass before 
    // we hit the last redirect
    if ( status !== 'success' ) {
        phantom.exit( 1 );
    }
});

PhantomJS将所有onNavigationRequested回调推送到数组

1 个答案: