我正试图从这个网站http://www.basketball-reference.com/teams/GSW/2016_games.html抓取所有特殊链接(boxscore-links),然后逐个访问它们,从每个访问过的链接中抓取一些信息。首先,我想抓取所有链接,逐一访问它们并获得网站标题。问题是它总是打印相同的标题和相同的当前URL(初始URL),即使它显然必须是一个新的。在我看来,这个' -keyword存在问题...... (不要看链接的限制,我从casperjs的github上的示例中获取代码,然后我把它留给控制台不要超载。) 这是我的代码:
var casper = require("casper").create({
verbose: true
});
// The base links array
var links = [ "http://www.basketball-reference.com/teams/GSW/2016_games.html" ];
// If we don't set a limit, it could go on forever
var upTo = ~~casper.cli.get(0) || 10;
var currentLink = 0;
// Get the links, and add them to the links array
function addLinks(link) {
this.then(function() {
var found = this.evaluate(searchLinks);
this.echo(found.length + " links found on " + link);
links = links.concat(found);
});
}
// Fetch all <a> elements from the page and return
// the ones which contains a href starting with 'http://'
function searchLinks() {
var links = document.querySelectorAll('#teams_games td:nth-child(5) a');
return Array.prototype.map.call(links, function(e) {
return e.getAttribute('href');
});
}
// Just opens the page and prints the title
function start(link) {
this.start(link, function() {
this.wait(5000, function() {
this.echo('Page title: ' + this.getTitle());
this.echo('Current url: ' + this.getCurrentUrl());
});
});
}
// As long as it has a next link, and is under the maximum limit, will keep running
function check() {
if (links[currentLink] && currentLink < upTo) {
this.echo('--- Link ' + currentLink + ' ---');
start.call(this, links[currentLink]);
addLinks.call(this, links[currentLink]);
currentLink++;
this.run(check);
} else {
this.echo("All done.");
this.exit();
}
}
casper.start().then(function() {
this.echo("Starting");
});
casper.run(check);
答案 0 :(得分:1)
考虑一系列网址,您可以迭代它们,连续访问每个网址,如下所示:
casper.each(urls, function(self, url) {
self.thenOpen(url, function(){
this.echo('Opening: ' + url);
// Do Whatever
});
});
显然,这不会在页面上找到链接,但这是查看一组已知网址的好方法。