Created
June 12, 2011 10:20
-
-
Save fb55/1021408 to your computer and use it in GitHub Desktop.
A simple (not feature complete) feedparser for node.js. Requires sax.js
This file contains hidden or 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
/* | |
Simple feedparser | |
Based upon: | |
- https://raw.github.com/drudge/node-easyrss | |
*/ | |
var sax = require('./libs/sax'); | |
module.exports.streamParser = function(){ | |
var articles = this.articles = []; | |
var feed = this.feed = { | |
title: "", | |
link: "", | |
parseError: false, | |
articles: this.articles | |
}; | |
var parser = sax.parser(false, { | |
trim : true, | |
normalize: true, | |
lowercasetags : true | |
}); | |
parser.onerror = function(e){ | |
this.feed.parseError = e || true; | |
}; | |
var writeCache, closed; | |
this.evaluate = function(data){ | |
if(!closed){ | |
parser.write(data).close(); | |
closed = true; | |
} | |
else | |
this.write(data); | |
}; | |
this.write = function(data){ | |
writeCache += data; | |
}; | |
this.end = parser.onend = function(){ | |
closed = false; | |
if(writeCache) | |
this.evaluate(writeCache); | |
writeCache = ""; | |
}; | |
var itemCount = 0, | |
inItem = false, | |
charCache = ""; | |
parser.onopentag = function(tag){ | |
if(tag.name === "item" || tag.name === "entry"){ | |
inItem = true; | |
articles[itemCount] = {}; | |
} | |
}; | |
parser.onclosetag = function(tagName){ | |
if(inItem) | |
switch(tagName){ | |
case "pubdate": | |
articles[itemCount]["pubdate"] = new Date(charCache); break; | |
case "content": case "content:encoded": | |
articles[itemCount]["content"] = charCache; break; | |
case "dc:creator": case "author": | |
articles[itemCount]["author"] = charCache; break; | |
case "description": case "summary": | |
case "link": case "title": | |
case "comments": | |
case "guid": | |
articles[itemCount][tagName] = charCache; break; | |
case "item": case "entry": | |
inItem = false; itemCount++; break; | |
default: console.log(tagName); | |
} | |
else | |
//get feed info | |
switch(tagName){ | |
case "title": | |
feed.title = charCache; break; | |
case "link": | |
feed.link = charCache; break; | |
} | |
charCache = ""; | |
}; | |
parser.ontext = parser.oncdata = function(text){ | |
if(charCache === "") | |
charCache = text; | |
else | |
charCache += " " + text; | |
}; | |
return this; | |
}; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment