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
|
# Miro - an RSS based video player application
# Copyright (C) 2005-2008 Participatory Culture Foundation
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
#
# In addition, as a special exception, the copyright holders give
# permission to link the code of portions of this program with the OpenSSL
# library.
#
# You must obey the GNU General Public License in all respects for all of
# the code used other than OpenSSL. If you modify file(s) with this
# exception, you may extend this exception to your version of the file(s),
# but you are not obligated to do so. If you do not wish to do so, delete
# this exception statement from your version. If you delete this exception
# statement from all source files in the program, then also delete it here.
import re
# =============================================================================
# Purify a feed item data (usually its description) from ads. Returns the data
# untouched if no ad were found.
def purify(data):
return _process(data, 'purify', data)
# Scrape ads from a feed item data (usually its description). Returns an empty
# string if no ad were found.
def scrape(data):
return _process(data, 'scrape', '')
# =============================================================================
def _process(data, fkey, default):
if data is None:
return ''
processed = None
for funcs in FUNCS:
process = funcs[fkey]
processed = process(data)
if processed is not None:
break
if processed is None:
processed = default
return processed
# =============================================================================
FEEDBURNER_AD_PATTERN = re.compile("""
<p> # <p>
<a\shref="http://feeds\.feedburner\.com/~a/[^"]*"> # <a href="...">
<img\ssrc="http://feeds\.feedburner\.com/~a/[^"]*"\sborder="0"> # <img src="..." border="0">
</img> # </img>
</a> # </a>
</p> # </p>
""", re.VERBOSE)
def _tryPurifyingFeedBurner(data):
if FEEDBURNER_AD_PATTERN.search(data):
return FEEDBURNER_AD_PATTERN.sub('', data)
return None
def _tryScrapingFeedBurner(data):
match = FEEDBURNER_AD_PATTERN.search(data)
if match is not None:
return match.group(0)
return None
# =============================================================================
FUNCS = [
{'purify': _tryPurifyingFeedBurner, 'scrape': _tryScrapingFeedBurner}
]
|
