-"""
- Objects to represent bookmarks.html structure
+"""Objects to represent bookmarks.html structure
+
+This file is a part of Bookmarks database and Internet robot.
- Written by Oleg Broytman. Copyright (C) 2000-2010 PhiloSoft Design.
"""
-import os, cgi
-BKMK_FORMAT = os.environ.get("BKMK_FORMAT", "MOZILLA")
+__author__ = "Oleg Broytman <phd@phdru.name>"
+__copyright__ = "Copyright (C) 2000-2012 PhiloSoft Design"
+__license__ = "GNU GPL"
+
+__all__ = ['Folder', 'Bookmark', 'Ruler', 'Walker', 'Writer', 'Robot',
+ 'InverseLinker', 'Linear', 'make_linear', 'make_tree', 'break_tree',
+ 'quote_title', 'unquote_title',
+]
+
+import os, urllib
+
+BKMK_FORMAT = os.environ.get("BKMK_FORMAT", "MOZILLA")
class Folder(list):
isFolder = 1
isBookmark = 1
def __init__(self, href, add_date, last_visit=None, last_modified=None,
- keyword=None, comment='', icon=None, charset=None):
+ keyword=None, comment='', icon_href=None, icon=None,
+ charset=None, parser_charset=None):
+ protocol, request = urllib.splittype(href)
+ user, password, port = None, None, None
+ host, path = urllib.splithost(request)
+ if host:
+ user, host = urllib.splituser(host)
+ if user:
+ user, password = urllib.splitpasswd(user)
+ host, port = urllib.splitport(host)
+ if port: port = int(port)
+
+ if protocol == 'place':
+ href = protocol + ":"
+ else:
+ href = protocol + "://"
+ if user:
+ href += urllib.quote(user)
+ if password:
+ href += ':' + urllib.quote(password)
+ href += '@'
+ if host:
+ href += host.decode(parser_charset or 'utf-8').encode('idna')
+ if port:
+ href += ':%d' % port
+ if path:
+ href += path
+
self.href = href
self.add_date = add_date
self.last_visit = last_visit
self.last_modified = last_modified
self.keyword = keyword
self.comment = comment
+ self.icon_href = icon_href
self.icon = icon
self.charset = charset
class Robot:
- def __init__(self, tempfname, log):
- self.tempfname = tempfname
+ def __init__(self, log):
self.log = log
def stop(self):
def unquote_title(title):
if BKMK_FORMAT == "MOZILLA":
from HTMLParser import HTMLParser
- title = HTMLParser().unescape(title.replace("&", '&'))
- title = title.replace("'", "'")
+ title = HTMLParser().unescape(title.replace("&", '&').decode('utf-8'))
+ title = title.encode('utf-8').replace("'", "'")
return title