如何查找具有特定文件扩展名的网页中的所有链接？

Question

Is it possible to find a href in a website that has a certain file extension. for example it would print http://www.test.com/something.mp3 http://www.test.com/somelinktoamuscifile.mp3 http://www.test.com/music.mp3 .

It would show all of links, with a file extension of .mp3 for example.

would you do var extension = ".mp3"

var checker = url + extension

if(url == checker){console.log(url);}

Answer 1

So you want to extract all links that contain a certain string from any given url? Maybe this script will help you:

var request = require('request');
var cheerio = require('cheerio');

var url = "http://www.stackoverflow.com";
var toFind = "delete"  //use file extension or whatever you want to find

request(url, function(err, resp, body) {
    if (err) throw err;
    var $ = cheerio.load(body);

    $('a').each(function (i, element) {
        var a = $(this);
        //console.log(a.attr('href'));

        var href = a.attr('href');
        if (href && href.indexOf(toFind) != -1) {
            console.log(href);
        }
    })
})

Output:
$ node scraping.js 
http://ux.stackexchange.com/questions/49991/should-yes-delete-it-be-red-or-green

Just change the content of url and toFind . There is a good tutorial on web scraping here and here . Of course this can be done in a lot of different programming languages. I merely used javascript because you tagged it that way.

Answer 2

Here is a native javascript solution that works in current browsers (IE8+, Chrome, Firefox) without jQuery.

function getLinksWithExtension(extension) {
    var links = document.querySelectorAll('a[href$="' + extension + '"]'),
        i;

    for (i=0; i<links.length; i++){
        console.log(links[i]);
    }
}

Answer 3

I think it goes like this:

var mp3_extension = '.mp3';
var url_string = url.split('.');
var url_extension = url_string[url_string.length-1];

if(url_extension === mp3_extension){

    //go go go!!!     

}