summaryrefslogtreecommitdiffstats
path: root/plugins/rssfeed/rsslinkdownloader.cpp
blob: 4c11bb9ddf215b8cf959aab1ceb4355c324f3382 (plain)
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
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
/***************************************************************************
 *   Copyright (C) 2006 by Alan Jones                                      *
 *   [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.          *
 ***************************************************************************/
#include "rsslinkdownloader.h"

#include <klocale.h>
#include <kmimetype.h>
#include <kmessagebox.h>

#include <tqfile.h>

#include "../../libktorrent/torrent/bdecoder.h"
#include "../../libktorrent/torrent/bnode.h"

using namespace bt;

namespace kt
{

	RssLinkDownloader::RssLinkDownloader(CoreInterface* core, TQString link, RssFilter * filter, TQObject * parent) : TQObject (parent)
		{
			//tempFile.setAutoDelete(true);
			m_core = core;
			firstLink = true;
			curFilter = filter;
			if (!KURL(link).isValid())
			{
				// no valid URL, so just display an error message
				KMessageBox::error(0,i18n("Failed to find and download a valid torrent for %1").arg(curLink));
				TQTimer::singleShot(50,this,TQT_SLOT(suicide()));
			}
			else
			{
				//first let's download the link so we can process it to check for the actual torrent
				curLink = curSubLink = link;
				curFile = KIO::storedGet(link,false,false);
				connect(curFile, TQT_SIGNAL(result(KIO::Job*)),this,TQT_SLOT(processLink( KIO::Job* )));
			}
		}
	
	RssLinkDownloader::~RssLinkDownloader()
		{
			
		}
		
	void RssLinkDownloader::processLink(KIO::Job* jobStatus)
		{
		
		if (!jobStatus->error())
			{
			//the file downloaded ok - so let's check if it's a torrent
			KMimeType linkType = *KMimeType::findByContent(curFile->data());
			if (linkType.is("text/html"))
				{
				if (firstLink)
					{
					KURL url = curLink;
					//let's go through the data and populate our sublink array
					TQTextStream html(curFile->data(), IO_ReadOnly);
					
					//go through a line at a time checking for a torrent
					TQString htmlline = html.readLine();
					while (!htmlline.isNull())
						{
						TQRegExp hrefTags = TQString("<A.*HREF.*</A");
						hrefTags.setCaseSensitive(false);
						hrefTags.setMinimal(true);
						
						int matchPos = 0;
						while (htmlline.find(hrefTags, matchPos) >= 0)
							{
							matchPos += hrefTags.matchedLength();
							//we're found an <a href tag - let's check it if contains download
							TQRegExp hrefText = TQString("d(own)?load");
							hrefText.setCaseSensitive(false);
							
							if (!hrefTags.capturedTexts()[0].contains(hrefText))
								{
								//link text doesn't contain dload/download
								continue;
								}
								
							//we're found an <a href tag - now let's the the url out of it
							hrefText = TQString("HREF=\"?([^\">< ]*)[\" ]");
							hrefText.setCaseSensitive(false);
				
							hrefTags.capturedTexts()[0].find(hrefText);
							//lets get the captured
							TQString hrefLink = hrefText.capturedTexts()[1];
								
							if (hrefLink.startsWith("/"))
								{
								hrefLink = url.protocol() + "://" + url.host() + hrefLink;
								} 
							else if (!hrefLink.startsWith("http://", false)) 
								{
								hrefLink = url.url().left(url.url().findRev("/")+1) + hrefLink;
								}
								
							subLinks.append(hrefLink);
							
							}
							
							//run the query again
							htmlline = html.readLine();
						}
						
						
						firstLink = false;
					}
				}
			else
				{
			
				//I know this may check a file which we've already been told is html, but sometimes it lies
				try
					{
						//last ditched brute force attempt to check if it's a torrent file
						BNode* node = 0;
						BDecoder decoder(curFile->data(),false);
						node = decoder.decode();
						BDictNode* dict = dynamic_cast<BDictNode*>(node);
						
						if (dict)
						{
							delete node;
							node = dict = 0;
							
							if (curFilter)
							{
								m_core->loadSilently( curSubLink );
								emit linkDownloaded( curLink, 3);
							}
							else
							{
								m_core->load( curSubLink );
								emit linkDownloaded( curLink, 1);
							}
							
							//delete ourself and finish
							deleteLater();
							return;
						}
						
					
					}
				catch (...)
					{
						//we can just ignore any errors here
					}
				}
				
			}
		//curFile->deleteLater();
		
		//check for the next item
		if (subLinks.isEmpty())
			{
			if (curFilter)
				{
				//we've failed to download a torrent for this match
				curFilter->deleteMatch( curLink );
				}
			else
				{
				//failed to download a selected article from a feed
				KMessageBox::error(0,i18n("Failed to find and download a valid torrent for %1").arg(curLink));
				}
				deleteLater();
			}
		else
			{
			curSubLink = subLinks.first();
			subLinks.pop_front();
			curFile = KIO::storedGet(curSubLink,false,false);
			connect(curFile, TQT_SIGNAL(result(KIO::Job*)),this,TQT_SLOT(processLink( KIO::Job* )));
			}
		}
	
	
	void RssLinkDownloader::suicide()
	{
		deleteLater();
	}

}