Best Way To Parse Google Custom Search Engine Results

I need to parse through the results of google custom search engine. My first issue is that it is all in javascript. below page loads the results to be parsed, which opens in a js p

Solution 1:

for anyone still looking. Alter the code below to fit your needs. You put your procedure into method(s) and run that in function check(). Anything inside the function will be looped until it has looped the array.

*Known issue: * capserjs runs faster than google js. The result is duplicate links. I haven't been able to tell casperjs to wait for google js popup to close first.

var casper = require("casper").create({
    verbose: true
});
url = casper.cli.get(0)
// The base links arrayvar links = [
    url
];

// If we don't set a limit, it could go on forevervar upTo = ~~casper.cli.get(0) || 10;

var currentLink = 0;

// Get the links, and add them to the links array// (It could be done all in one step, but it is intentionally splitted)functionaddLinks(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://'functionsearchLinks() {
    var filter, map;
    filter = Array.prototype.filter;
    map = Array.prototype.map;
    return map.call(filter.call(document.querySelectorAll("a"), function(a) {
        return (/^http:\/\/.*/i).test(a.getAttribute("href"));
    }), function(a) {
        return a.getAttribute("href");
    });
}

// Just opens the page and prints the titlefunctionstart(link) {
    this.start(link, function() {
        this.echo('Page title: ' + this.getTitle());
    });
}

// As long as it has a next link, and is under the maximum limit, will keep runningfunctioncheck() {
    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);

src: http://code.ohloh.net/file?fid=VzTcq4GkQhozuKWkprFfBghgXy4&cid=ZDmcCGgIq6k&s=&fp=513476&mp&projSelected=true#L0