update-planet

   1 #!/usr/bin/python
   2 #
   3 # update-planet
   4 #
   5 # Downloads feeds from the URLs specified and generates the XHTML files.
   6 #
   7 # (c) 2004, Davyd Madeley <[email protected]>
   8 #
   9
  10 import sys, codecs
  11 import XMLParse2 as XMLParse, XMLWriter, CacheHandler
  12
  13 # step 1: read in the config and check each object from cache
  14 cache   = CacheHandler.CacheHandler()
  15 feeds   = []
  16
  17 for feed in open('feedlist').readlines():
  18         if feed.strip()[0] != '#':
  19                 storage         = feed.strip().split('\t')
  20                 name, feed      = storage[0], storage[-1]
  21                 try:
  22                         feeds.append((name, feed, cache.getBlog(name, feed)))
  23                 except:
  24                         sys.stderr.write('DEBUG: update-planet: something went wrong retrieving feed\n')
  25
  26 # step 2: process each feed
  27 blogs   = []
  28 for feed in feeds:
  29         # XMLParse2 takes two paramaters, a URL and a CacheObject
  30         blog    = XMLParse.XMLParse(feed[1], feed[2]).parse()
  31         if blog:
  32                 blog.blogTitle  = feed[0]
  33                 blog.feedURL    = feed[1]
  34                 blogs.append(blog)
  35                 # write the cache back down to disk
  36                 cache.storeBlog(blog)
  37         else:
  38                 pass
  39
  40 # step 3: write feed to disk
  41 try:
  42         codecs.open('planet.html', 'wb', 'utf-8').write(XMLWriter.XMLWriter(XMLWriter.XHTMLWriter, blogs).write())
  43 except:
  44         sys.stderr.write('DEBUG: update-planet: could not write planet.html, aborting\n')