XMLParse2.py

   1 #
   2 # XMLParse2.py
   3 #
   4 # Parse arbitrary XML news streams into an object type
   5 # understandable by Planet UCC.
   6 # Now uses feedparser to parse 9 different types of RSS _and_ Atom
   7 #
   8 # (c) 2004, Davyd Madeley <[email protected]>
   9 #
  10
  11 import sys, time
  12 import CacheHandler
  13 sys.path.insert(0, 'extra')
  14 import feedparser
  15
  16 feedparser.USER_AGENT = "PlanetUCC/1.0b +http://planet.ucc.asn.au/ %s" % feedparser.USER_AGENT
  17
  18 class Blog:
  19         def __init__(self):
  20                 self.blogName   = None
  21                 self.blogTitle  = None
  22                 self.blogURL    = None
  23                 self.feedURL    = None
  24                 self.imageURL   = None
  25                 self.imageLink  = None
  26                 self.items      = []
  27                 self.cache      = None
  28
  29 class BlogItem:
  30         def __init__(self):
  31                 self.itemTitle  = None
  32                 self.itemDate   = None
  33                 self.itemURL    = None
  34                 self.contents   = None
  35
  36 class XMLParse:
  37         def __init__(self, URL, blogObject):
  38                 self.feedURL    = URL
  39                 self.blogObject = blogObject
  40
  41         def parse(self):
  42                 "Return a single Blog object"
  43                 item            = Blog()
  44                 if self.blogObject and self.blogObject.cache:
  45                         sys.stdout.write('Downloading feed %s...' % self.feedURL)
  46                         try:
  47                                 data    = feedparser.parse(self.feedURL, self.blogObject.cache.etag, self.blogObject.cache.date)
  48                                 sys.stdout.write('done.\n')
  49                         except:
  50                                 sys.stdout.write('failed.\n')
  51                                 return None
  52                         # check to see what we got returned
  53                         if data['items'] == [] and data['channel'] == {}:
  54                                 sys.stdout.write('Feed %s is upto date.\n' % self.feedURL)
  55                                 return self.blogObject
  56                 else:
  57                         sys.stdout.write('Downloading feed from %s (no cache)...' % self.feedURL)
  58                         try:
  59                                 data    = feedparser.parse(self.feedURL)
  60                                 sys.stdout.write('done.\n')
  61                         except:
  62                                 sys.stdout.write('failed.\n')
  63                                 return None
  64                 # create caching data
  65                 try:
  66                         cache           = CacheHandler.CacheObject()
  67                         try:
  68                                 cache.etag      = data['etag']
  69                         except:
  70                                 cache.etag      = None
  71                         try:
  72                                 cache.date      = data['modified']
  73                         except:
  74                                 cache.date      = None
  75                         item.cache      = cache
  76                 except:
  77                         sys.stderr.write('DEBUG: XMLParse2: cache item generation failed\n')
  78                         item.cache      = None
  79                 # parse the return of data into a blog
  80                 if data['channel'].has_key('title'):
  81                         item.blogTitle  = data['channel']['title']
  82                 else:
  83                         item.blogTitle  = '(Unknown)'
  84                 if data['channel'].has_key('link'):
  85                         item.blogURL    = data['channel']['link']
  86                 else:
  87                         item.blogURL    = self.feedURL
  88                 for entry in data['items']:
  89                         blogItem                = BlogItem()
  90                         if entry.has_key('title'):
  91                                 blogItem.itemTitle      = entry['title']
  92                         else:
  93                                 blogItem.itemTitle      = '(Untitled)'
  94                         if entry.has_key('link'):
  95                                 blogItem.itemURL        = entry['link']
  96                         else:
  97                                 blogItem.itemURL        = item.blogURL
  98                         if entry.has_key('date_parsed'):
  99                                 blogItem.itemDate       = time.mktime(entry['date_parsed']) + 28800
 100                         else:
 101                                 blogItem.itemDate       = 0
 102                         if entry.has_key('description'):
 103                                 blogItem.contents       = entry['description']
 104                         else:
 105                                 blogItem.contents       = '(entry could not be retrieved)'
 106                         item.items.append(blogItem)
 107                 return item