view FeedUpdater.py @ 9:fd4c8bfa62d6

FeedUpdater throws an exception if the URL could not be retrieved successfully. Includes unit tests.
author Dirk Olmes <dirk@xanthippe.ping.de>
date Tue, 27 Apr 2010 10:22:35 +0200
parents 215c34f61e95
children 01a86b178e60
line wrap: on
line source


from datetime import datetime
from Feed import Feed
from FeedEntry import FeedEntry
import feedparser

STATUS_OK = 200

def updateAllFeeds(session):
    allFeeds = session.query(Feed)
    for feed in allFeeds:
        FeedUpdater(session, feed).update()
        session.commit()

class FeedUpdater(object):
    def __init__(self, session, feed):
        self.session = session
        self.feed = feed
        
    def update(self):
        result = self.getFeed()
        for entry in result.entries:
            self.processEntry(entry)

    def getFeed(self):
        result = feedparser.parse(self.feed.rss_url)
        if result["status"] is not STATUS_OK:
            raise FeedUpdateException()
        return result

    def processEntry(self, entry):
        feedEntry = FeedEntry.findById(entry.id, self.session)
        if feedEntry is None:
            self.createFeedEntry(entry)
            
    def createFeedEntry(self, entry):
        new = FeedEntry()
        new.id = entry.id
        new.link = entry.link
        new.title = entry.title
        new.updated = datetime(*entry.updated_parsed[:6])
        new.summary = entry.summary
        new.feed = self.feed
        self.session.add(new)

class FeedUpdateException(Exception):
    pass