1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
|
# -*- coding: utf-8 -*-
''' Atom (rfc 4287) feed parser, used to read data from atom-over-pubsub transports
and services. Very simple. Actually implements only atom:entry. Implement more features
if you need. '''
# suggestion: rewrite functions that return dates to return standard python time tuples,
# exteneded to contain timezone
import xmpp
import time
class PersonConstruct(xmpp.Node, object):
''' Not used for now, as we don't need authors/contributors in pubsub.com feeds.
They rarely exist there. '''
def __init__(self, node):
''' Create person construct from node. '''
xmpp.Node.__init__(self, node=node)
def get_name(self):
return self.getTagData('name')
name = property(get_name, None, None,
'''Conveys a human-readable name for the person. Should not be None,
although some badly generated atom feeds don't put anything here
(this is non-standard behavior, still pubsub.com sometimes does that.)''')
def get_uri(self):
return self.getTagData('uri')
uri = property(get_uri, None, None,
'''Conveys an IRI associated with the person. Might be None when not set.''')
def get_email(self):
return self.getTagData('email')
email = property(get_email, None, None,
'''Conveys an e-mail address associated with the person. Might be None when
not set.''')
class Entry(xmpp.Node, object):
def __init__(self, node=None):
''' Create new atom entry object. '''
xmpp.Node.__init__(self, 'entry', node=node)
def __repr__(self):
return '<Atom:Entry object of id="%r">' % self.id
class OldEntry(xmpp.Node, object):
''' Parser for feeds from pubsub.com. They use old Atom 0.3 format with
their extensions. '''
def __init__(self, node=None):
''' Create new Atom 0.3 entry object. '''
xmpp.Node.__init__(self, 'entry', node=node)
def __repr__(self):
return '<Atom0.3:Entry object of id="%r">' % self.id
def get_feed_title(self):
''' Returns title of feed, where the entry was created. The result is the feed name
concatenated with source-feed title. '''
if self.parent is not None:
main_feed = self.parent.getTagData('title')
else:
main_feed = None
if self.getTag('feed') is not None:
source_feed = self.getTag('feed').getTagData('title')
else:
source_feed = None
if main_feed is not None and source_feed is not None:
return u'%s: %s' % (main_feed, source_feed)
elif main_feed is not None:
return main_feed
elif source_feed is not None:
return source_feed
else:
return u''
feed_title = property(get_feed_title, None, None,
''' Title of feed. It is built from entry''s original feed title and title of feed
which delivered this entry. ''')
def get_feed_link(self):
''' Get source link '''
try:
return self.getTag('feed').getTags('link',{'rel':'alternate'})[1].getData()
except:
return None
feed_link = property(get_feed_link, None, None,
''' Link to main webpage of the feed. ''')
def get_title(self):
''' Get an entry's title. '''
return self.getTagData('title')
title = property(get_title, None, None,
''' Entry's title. ''')
def get_uri(self):
''' Get the uri the entry points to (entry's first link element with rel='alternate'
or without rel attribute). '''
for element in self.getTags('link'):
if element.attrs.has_key('rel') and element.attrs['rel']<>'alternate': continue
try:
return element.attrs['href']
except AttributeError:
pass
return None
uri = property(get_uri, None, None,
''' URI that is pointed by the entry. ''')
def get_updated(self):
''' Get the time the entry was updated last time. This should be standarized,
but pubsub.com sends it in human-readable format. We won't try to parse it.
(Atom 0.3 uses the word «modified» for that).
If there's no time given in the entry, we try with <published>
and <issued> elements. '''
for name in ('updated', 'modified', 'published', 'issued'):
date = self.getTagData(name)
if date is not None: break
if date is None:
# it is not in the standard format
return time.asctime()
return date
updated = property(get_updated, None, None,
''' Last significant modification time. ''')
feed_tagline = u''
|