Reading SDF Chatter

gistfile1.py

import urllib2
import re
from xml.dom.minidom import parseString

class GUIDS:

    guids = []

    def __init__(self):
        f = open("/meta/i/irl/.chatterguids")
        c = f.read().replace("\n", "")
        f.close()

        self.guids = c.split(";")


class Statuses:

    items = []

    def getText(self, nodelist):
        rc = []
        for node in nodelist:
            if node.nodeType == node.TEXT_NODE:
                rc.append(node.data)
        xtxt = ''.join(rc)
        return re.sub("<[^>]+>", "", xtxt)

    def __init__(self, user):
        url = urllib2.urlopen("https://wm.sdf.org/status/api/statuses/user_timeline/" + user + ".rss")
        rss = url.read()
        url.close()
        dom = parseString(rss)

        for item in dom.getElementsByTagName("item"):
            i = {}
            i["pubDate"] = self.getText(item.getElementsByTagName("pubDate")[0].childNodes)
            i["guid"] = self.getText(item.getElementsByTagName("guid")[0].childNodes)
            i["description"] = self.getText(item.getElementsByTagName("description")[0].childNodes)
            self.items.append(i)

    def getNewItems(self):

        g = GUIDS().guids
        n = []

        for i in self.items:
            if i["guid"] not in g:
                n.append(i)

        return n