Created
February 18, 2011 16:12
-
-
Save phpnode/833888 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
var nodeio = require('node.io'); | |
var methods = { | |
input: false, | |
run: function(row) { | |
var self = this; | |
row = "elance.com http://investing.businessweek.com/research/stocks/snapshot/snapshot.asp?capId=101648 1248 517895"; | |
var input = row.split("\t"); | |
try { | |
this.getHtml(input[1], function(err, $) { | |
if (err) { | |
self.emit(input.join("\t") + "\t" + err); | |
return; | |
} | |
var titles = [], scores = [], output = []; | |
try { | |
//Select all titles on the page | |
$('a').each(function(a) { | |
if (a.attribs === undefined || a.attribs.href === undefined) { | |
return; | |
} | |
url = a.attribs.href.toLowerCase(); | |
if (url.indexOf("//" + input[0].toLowerCase()) != -1 || url.indexOf("//www." + input[0].toLowerCase()) != -1) { | |
titles.push(a.fulltext); | |
} | |
}); | |
self.emit(input.join("\t") + "\tOK\t" + titles.join(" ").replace("\t"," ").replace("\n"," ").replace("\r"," ").trim()); | |
} | |
catch (e) { | |
self.emit(input.join("\t") + "\t" + e); | |
return; | |
} | |
}); | |
} | |
catch (e) { | |
self.emit(input.join("\t") + "\t" + e); | |
return; | |
} | |
} | |
} | |
exports.job = new nodeio.Job({timeout:10, max: 1, retries: 1}, methods); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment