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
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
|
/*
This file is part of Akregator.
Copyright (C) 2004 Teemu Rytilahti <[email protected]>
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 Street, Fifth Floor, Boston, MA 02110-1301, USA.
As a special exception, permission is given to link this program
with any edition of TQt, and distribute the resulting executable,
without including the source code for TQt in the source distribution.
*/
#include <tqregexp.h>
#include <tqstring.h>
#include <tqstringlist.h>
#include <tqvaluelist.h>
#include <kcharsets.h>
#include <kurl.h>
#include "feeddetector.h"
using namespace RSS;
FeedDetectorEntryList FeedDetector::extractFromLinkTags(const TQString& s)
{
//reduce all sequences of spaces, newlines etc. to one space:
TQString str = s.simplifyWhiteSpace();
// extracts <link> tags
TQRegExp reLinkTag("<[\\s]?LINK[^>]*REL[\\s]?=[\\s]?\\\"[\\s]?(ALTERNATE|SERVICE\\.FEED)[\\s]?\\\"[^>]*>", false);
// extracts the URL (href="url")
TQRegExp reHref("HREF[\\s]?=[\\s]?\\\"([^\\\"]*)\\\"", false);
// extracts type attribute
TQRegExp reType("TYPE[\\s]?=[\\s]?\\\"([^\\\"]*)\\\"", false);
// extracts the title (title="title")
TQRegExp reTitle("TITLE[\\s]?=[\\s]?\\\"([^\\\"]*)\\\"", false);
int pos = 0;
int matchpos = 0;
// get all <link> tags
TQStringList linkTags;
//int strlength = str.length();
while ( matchpos != -1 )
{
matchpos = reLinkTag.search(str, pos);
if (matchpos != -1)
{
linkTags.append( str.mid(matchpos, reLinkTag.matchedLength()) );
pos = matchpos + reLinkTag.matchedLength();
}
}
FeedDetectorEntryList list;
for ( TQStringList::Iterator it = linkTags.begin(); it != linkTags.end(); ++it )
{
TQString type;
int pos = reType.search(*it, 0);
if (pos != -1)
type = TQString(reType.cap(1)).lower();
// we accept only type attributes indicating a feed
if ( type != "application/rss+xml" && type != "application/rdf+xml"
&& type != "application/atom+xml" && type != "text/xml" )
continue;
TQString title;
pos = reTitle.search(*it, 0);
if (pos != -1)
title = reTitle.cap(1);
title = KCharsets::resolveEntities(title);
TQString url;
pos = reHref.search(*it, 0);
if (pos != -1)
url = reHref.cap(1);
url = KCharsets::resolveEntities(url);
// if feed has no title, use the url as preliminary title (until feed is parsed)
if ( title.isEmpty() )
title = url;
if ( !url.isEmpty() )
list.append(FeedDetectorEntry(url, title) );
}
return list;
}
TQStringList FeedDetector::extractBruteForce(const TQString& s)
{
TQString str = s.simplifyWhiteSpace();
TQRegExp reAhrefTag("<[\\s]?A[^>]?HREF=[\\s]?\\\"[^\\\"]*\\\"[^>]*>", false);
// extracts the URL (href="url")
TQRegExp reHref("HREF[\\s]?=[\\s]?\\\"([^\\\"]*)\\\"", false);
TQRegExp rssrdfxml(".*(RSS|RDF|XML)", false);
int pos = 0;
int matchpos = 0;
// get all <a href> tags and capture url
TQStringList list;
//int strlength = str.length();
while ( matchpos != -1 )
{
matchpos = reAhrefTag.search(str, pos);
if ( matchpos != -1 )
{
TQString ahref = str.mid(matchpos, reAhrefTag.matchedLength());
int hrefpos = reHref.search(ahref, 0);
if ( hrefpos != -1 )
{
TQString url = reHref.cap(1);
url = KCharsets::resolveEntities(url);
if ( rssrdfxml.exactMatch(url) )
list.append(url);
}
pos = matchpos + reAhrefTag.matchedLength();
}
}
return list;
}
TQString FeedDetector::fixRelativeURL(const TQString &s, const KURL &baseurl)
{
TQString s2=s;
KURL u;
if (KURL::isRelativeURL(s2))
{
if (s2.startsWith("//"))
{
s2=s2.prepend(baseurl.protocol()+":");
u=s2;
}
else if (s2.startsWith("/"))
{
KURL b2(baseurl);
b2.setPath(TQString()); // delete path and query, so that only protocol://host remains
b2.setQuery(TQString());
u = KURL(b2, s2.remove(0,1)); // remove leading "/"
}
else
{
u = KURL(baseurl, s2);
}
}
else
u=s2;
u.cleanPath();
//kdDebug() << "AKREGATOR_PLUGIN_FIXURL: " << "url=" << s << " baseurl=" << baseurl.url() << " fixed=" << u.url() <<
//endl;
return u.url();
}
|
