Replacing Yahoo! Pipes with Python

html5gamesde.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import os
import sys
import datetime
import htmllib
import urllib
import PyRSS2Gen
from BeautifulSoup import BeautifulSoup

def get(url):
  return urllib.urlopen(url).read()

def unescape(s):
  p = htmllib.HTMLParser(None)
  p.save_bgn()
  p.feed(s)
  return p.save_end()

# Don't print if not on a tty.
if not sys.stdout.isatty():
  from StringIO import StringIO
  sys.stdout = StringIO()

# Grab original feed.
FEED_URL = 'http://feeds2.feedburner.com/html5games-de?format=xml'
print 'Fetching', FEED_URL
feed = BeautifulSoup(get(FEED_URL))

# Iterate over latest N items.
items = []
for item in feed.findAll('item')[0:5]:
  href = item.contents[2] # <link> is broken on feedburner
  print 'Fetching', href
  page = BeautifulSoup(get(href))
  img = page.find('img',
      **{'class': 'attachment-single-post-thumbnail wp-post-image'})
  print 'Image:', img
  items.append(PyRSS2Gen.RSSItem(
      title=item.find('title').string,
      link=href,
      description='<a href="%s">%s</a><br/>%s' % (
        href, img, item.find('description').string\
            .replace('&lt;', '<').replace('&gt;', '>')),
      guid=PyRSS2Gen.Guid(href),
      pubDate=None,
      ))

rss = PyRSS2Gen.RSS2(
    title='html5games.de with images',
    link='http://www.html5games.de/',
    description='Fast täglich gibt es neue kostenlose Online Spiel in HTML5.',
    lastBuildDate=datetime.datetime.utcnow(),
    items=items)

# foo.py -> foo.rss
filename = os.path.basename(sys.argv[0]).replace('.py', '.rss')
path = os.path.join(os.path.dirname(sys.argv[0]), filename)
print 'Writing', path
rss.write_xml(open(path, 'w'), encoding='utf-8')