Question

我尝试使用以下步骤模拟Google用户查询搜索。

打开谷歌搜索索引页面并发送搜索查询
通过css选择器解析链接文本
并点击目标，否则请点击下一页

我可以看到引擎点击目标链接，但不幸的是，如果我尝试从第77行的页面中提取链接，78确实无效。知道我做错了什么吗？

var casper = require("casper").create({
    waitTimeout: 1000,
    pageSettings: {
        userAgent: "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.8; rv:23.0) Gecko/20130404 Firefox/23.0",
        loadImages: false, // The WebPage instance used by Casper will
        loadPlugins: false,
        verbose: true,
        logLevel: "debug"
    }

});
var x = require('casper').selectXPath;
casper.options.waitTimeout = 10000;
var currentPage = 1;
var links = [];


function getLinks() {
    var links = document.querySelectorAll("h3.r a");
    return Array.prototype.map.call(links, function(e) {
        try {
            return (/url\?q=(.*)&sa=U/).exec(e.getAttribute("href"))[1];
        } catch (err) {
            return e.getAttribute("href");
        }
    });
}


var terminate = function() {
    this.echo("that's all, folks.").exit();
};

casper.on("http.status.200", function(resource) {
    this.echo(resource.url + " is OK", "INFO");
});

casper.on("http.status.301", function(resource) {
    this.echo(resource.url + " is permanently redirected", "PARAMETER");
});

casper.on("http.status.302", function(resource) {
    this.echo(resource.url + " is temporarily redirected", "PARAMETER");
});

casper.on("http.status.404", function(resource) {
    this.echo(resource.url + " is not found", "COMMENT");
});

casper.on("http.status.500", function(resource) {
    this.echo(resource.url + " is in error", "ERROR");
});

var processCustomerPage = function() {
    this.echo(this.getCurrentUrl());
};


var processPage = function() {
    var url;

    this.wait(10000, function() {
        if (currentPage >= 5 || !this.exists("#pnnext")) {
            return terminate.call(casper);
        }

        currentPage++;
        this.echo("requesting next page: " + currentPage);
        url = this.getCurrentUrl();


        this.wait(3000, function() {
            this.waitForSelector(x("//a[normalize-space(text())='testing - Phantom/Caperjs User input - Stack Overflow']"), function() {
                this.click(x("//a[normalize-space(text())='testing - Phantom/Caperjs User input - Stack Overflow']"));
                this.echo(this.getCurrentUrl());

                                                links = this.evaluate(getLinks);
                        this.echo(this.getCurrentUrl());
                        this.echo(' [+] ' + links.join("\n - "));

                this.reload(function() {
                    this.echo(this.getCurrentUrl());
                });

                this.echo("loaded again");
                this.echo(this.getTitle());
                return terminate.call(casper);

            });


            return terminate.call(casper);
        });

        this.echo(this.getCurrentUrl());

        this.thenClick("#pnnext").then(function() {

            this.waitFor(function() {
                return url !== this.getCurrentUrl();
            }, processPage, terminate);
        });
    });
};

casper.start("http://google.de/", function() {
    this.fill('form[action="/search"]', {
        q: 'casperjs'
    }, true);
});

casper.waitForSelector('#pnnext', processPage, terminate);

casper.run();

如何点击谷歌搜索链接并关注网址

0 个答案: