使用casperjs

时间:2016-12-10 20:33:41

标签: javascript iframe casperjs

我有以下代码:

var casper = require("casper").create({
        //  verbose: true,
        //    logLevel: "debug",
        webSecurityEnabled : false
    });
var links = [];
function get_links(obj) {
    return obj.evaluate(function () {
        var i,
            l = document.querySelectorAll("a"),
            l2 = [];
        for (i = 0; i < l.length; i++) {
            l2[i] = l[i].href;
        }
        return l2
    });
}
function unique(arr) {
    var obj = {};
    for (var i = 0; i < arr.length; i++) {
        if (/http(.*)?/.test(arr[i])) {
            var str = arr[i];
            obj[str] = true;
        }
    }
    return Object.keys(obj);
}

function getLinksFromIframes(callback) {
    this.echo("Here we come: " + this.getCurrentUrl() + "\n");
    function to_frame(obj) {
        var iframes = to_evaluate(obj);
        iframes.forEach(function (index) {
            this.withFrame(index, function () {
                this.echo("We are here: " + this.getCurrentUrl());
                var l = unique(get_links(this));
                var i;
                for (i = 0; i < l.length; i++) {
                    console.log(l[i]);
                    links.push(l[i])
                }
                links = unique(links);
                console.log("");
                to_frame(this)
            });
        }, obj);
    }
    function to_evaluate(obj) {
        return obj.evaluate(function () {
            var iframes = [];
            [].forEach.call(document.querySelectorAll("iframe"), function (iframe, i) {
                iframes.push(i);
            });
            return iframes;
        })
    }
    to_frame(this);
    this.then(function () {
        callback.call(this);
    });
}

casper.start("http://domu-test-2/node/1", function () {
    getLinksFromIframes.call(this, function () {
        console.log("Done!\n");
        var i;
        for (i = 0; i < links.length; i++) {
            console.log(links[i]);
        }
    });
}).then(function () {}).run();

现在的问题是:

如果我想通过第一级iframe获取链接,我应该如何重构getLinksFromIframes()函数。目前,他们共享全球&#39;变量links。我认为links肯定是链接列表列表并在withFrame函数中初始化新列表,然后将这个新引用传递给子iframe。那么我应该如何通过它并“回溯”#39;嵌套iframe中的所有链接?

1 个答案:

答案 0 :(得分:1)

如果我弄错了,你想要从你那里选择哪个iframe获取链接,并且只能从那个iframe中获取。如果是这种情况,那么您可以简单地使用switchToChildFrame切换到所需的iframe,然后通过调用get_links(obj)来获取链接。

我的例子有3页。在iframe中加载index.html的{​​{1}}和iframe1.html内部有另一个加载iframe1.html的iframe。每个文件里面都有3个链接:

<强>的index.html

iframe2.html

<强> iframe1.html

<a href="link1/from/index">Link 1 from index</a>
<a href="link2/from/index">Link 2 from index</a>
<a href="link3/from/index">Link 3 from index</a>

<iframe src="iframe1.html"></iframe>

<强> iframe2.html

<a href="link1/from/iframe1">Link 1 from iframe 1</a>
<a href="link2/from/iframe1">Link 2 from iframe 1</a>
<a href="link3/from/iframe1">Link 3 from iframe 1</a>

<iframe src="iframe2.html"></iframe>

并且重构的<a href="link1/from/iframe2">Link 1 from iframe 2</a> <a href="link2/from/iframe2">Link 2 from iframe 2</a> <a href="link3/from/iframe2">Link 3 from iframe 2</a> 函数将是这样的:

getLinksFromIframes

<强>结果

如果您同时评论function getLinksFromIframes(callback) { this.echo("Here we come: " + this.getCurrentUrl() + "\n"); function to_frame(obj) { obj.echo("We are here: " + obj.getCurrentUrl()); var l = unique(get_links(obj)); var i; for (i = 0; i < l.length; i++) { console.log(l[i]); links.push(l[i]) } links = unique(links); console.log(""); } function to_evaluate(obj) { return obj.evaluate(function () { var iframes = []; [].forEach.call(document.querySelectorAll("iframe"), function (iframe, i) { iframes.push(i); }); return iframes; }) } // Leave both switchToChildFrame as comments to get the "index.html" links this.page.switchToChildFrame(0); // Uncomment to get the links of "iframe1.html" //this.page.switchToChildFrame(0); // Uncomment to get the links of "iframe2.html" to_frame(this); this.then(function () { callback.call(this); }); } ,则会获得switchToChildFrame的链接:

index.html

如果您取消注释第一个casperjs caspers-read-iframes.js Here we come: http://pjs.lytrax.net/node/1/ We are here: http://pjs.lytrax.net/node/1/ http://pjs.lytrax.net/node/1/link1/from/index http://pjs.lytrax.net/node/1/link2/from/index http://pjs.lytrax.net/node/1/link3/from/index Done! http://pjs.lytrax.net/node/1/link1/from/index http://pjs.lytrax.net/node/1/link2/from/index http://pjs.lytrax.net/node/1/link3/from/index ,您将获得第一级switchToChildFrame的链接:

iframe1.html

如果您取消注释第一个和第二个casperjs caspers-read-iframes.js Here we come: http://pjs.lytrax.net/node/1/ We are here: http://pjs.lytrax.net/node/1/iframe1.html http://pjs.lytrax.net/node/1/link1/from/iframe1 http://pjs.lytrax.net/node/1/link2/from/iframe1 http://pjs.lytrax.net/node/1/link3/from/iframe1 Done! http://pjs.lytrax.net/node/1/link1/from/iframe1 http://pjs.lytrax.net/node/1/link2/from/iframe1 http://pjs.lytrax.net/node/1/link3/from/iframe1 ,您将获得第二级switchToChildFrame的链接:

iframe2.html