Can you provide examples of parsing HTML?

Question

How do you parse HTML with a variety of languages and parsing libraries?

---

When answering:

Individual comments will be linked to in answers to questions

Answer 1

Using phantomjs, save this file as extract-links.js:

var page = new WebPage(),
    url = 'http://www.udacity.com';

page.open(url, function (status) {
    if (status !== 'success') {
        console.log('Unable to access network');
    } else {
        var results = page.evaluate(function() {
            var list = document.querySelectorAll('a'), links = [], i;
            for (i = 0; i < list.length; i++) {
                links.push(list[i].href);
            }
            return links;
        });
        console.log(results.join('\n'));
    }
    phantom.exit();
});

run:

$ ../path/to/bin/phantomjs extract-links.js