runoob crawler for html

runoob.js

var cheerio = require('cheerio');
var request = require('sync-request');
var fs = require('fs');
var process = require('process');

var url = process.argv[2];
if(!url)
{
	console.log('请指定页面。');
	process.exit(0);
}

var ofile = fs.openSync('out.html', 'w');

var html = request('GET', url).getBody().toString();

var toc = getToc(html);
for(var i in toc) {
	var url = toc[i];
	console.log('page: ' + url);
	html = request('GET', url).getBody().toString();
	var content = getContent(html);
	fs.writeSync(ofile, content, null, 'utf-8');
    fs.writeSync(ofile, '\n<!--split-->\n', null, 'utf-8');
}

fs.closeSync(ofile);
console.log('Done..');


function getToc(html)  {
	
	var $ = cheerio.load(html);
	
	var $list = $('#leftcolumn').find('a');
	var res = [];
	for(var i = 0; i < $list.length; i++)
	{
		var url = $list.eq(i).attr('href');
		res.push('http://www.runoob.com/' + url);
	}
	return res;
}


function getContent(html) {
	var $ = cheerio.load(html);
	var content = $('#content').html();
	return content;
}