src/lib/OPMLImport.py

   1 """ OPMLImport.py
   2 """
   3
   4 __copyright__ = "Copyright (c) 2002-2005 Free Software Foundation, Inc."
   5 __license__ = """
   6 Straw is free software; you can redistribute it and/or modify it under the
   7 terms of the GNU General Public License as published by the Free Software
   8 Foundation; either version 2 of the License, or (at your option) any later
   9 version.
  10
  11 Straw is distributed in the hope that it will be useful, but WITHOUT ANY
  12 WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR
  13 A PARTICULAR PURPOSE. See the GNU General Public License for more details.
  14
  15 You should have received a copy of the GNU General Public License along with
  16 this program; if not, write to the Free Software Foundation, Inc., 59 Temple
  17 Place - Suite 330, Boston, MA 02111-1307, USA. """
  18
  19
  20 import OPML
  21 import feeds
  22
  23 class BlogListEntry(object):
  24     __slots__ = ('text', 'url')
  25
  26 def _find_entries(outline):
  27     entries = []
  28     for c in outline.children:
  29         entries += _find_entries(c)
  30     type = outline.get('type', '')
  31     text = outline.get('text', '')
  32     e = None
  33     if type == 'link':
  34         url = outline.get('url', '')
  35         if url != '':
  36             e = BlogListEntry()
  37             e.text = text
  38             e.url = url
  39     else:
  40         xmlurl = outline.get('xmlUrl', '')
  41         e = BlogListEntry()
  42         e.text = text
  43         if text == '':
  44             title = outline.get('title', '')
  45             if title == '':
  46                 e = None
  47             e.text = title
  48         if e != None:
  49             if xmlurl != '':
  50                 # there's something in xmlurl. There's a good chance that's
  51                 # our feed's URL
  52                 e.url = xmlurl
  53             else:
  54                 htmlurl = outline.get('htmlUrl', '')
  55                 if htmlurl != '':
  56                     # there's something in htmlurl, and xmlurl is empty. This
  57                     # might be our feed's URL.
  58                     e.url = htmlurl
  59                 else:
  60                     # nothing else to try.
  61                     e = None
  62     if e is not None:
  63         entries[0:0] = [e]
  64     return entries
  65
  66 def find_entries(outlines):
  67     entries = []
  68     for o in outlines:
  69         entries += _find_entries(o)
  70     return entries
  71
  72 def read(stream):
  73     try:
  74         o = OPML.parse(stream)
  75     except ValueError:
  76         return None
  77     entries = find_entries(o.outlines)
  78     ret = list()
  79     edict = dict()
  80     # avoid duplicates.
  81     for e in entries:
  82         ek = (e.text, e.url)
  83         edict[ek] = edict.get(ek, 0) + 1
  84         if edict[ek] < 2:
  85             ret.append(e)
  86     return ret
  87
  88 def import_opml(filename,category=None):
  89     feedlist = feeds.get_instance()
  90     fstream = open (filename)
  91     opml = read(fstream)
  92     if not opml:
  93         return
  94     feeds = [feed.access_info[0] for feed in feedlist]
  95     newitems = [feeds.Feed.create_new_feed(b.text, b.url) for b in opml if b.url not in feeds]
  96     feedlist.extend(category, newitems)
  97     return