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
|
//QuickCrawlLink_p.java
//-----------------------
//part of the AnomicHTTPD caching proxy
//(C) by Michael Peter Christen; mc@yacy.net
//first published on http://www.anomic.de
//Frankfurt, Germany, 2004
//
//This file was contributed by Martin Thelian
//$LastChangedDate$
//$LastChangedBy$
//$LastChangedRevision$
//
//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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
//You must compile this file with
//javac -classpath .:../classes IndexCreate_p.java
//if the shell's current path is HTROOT
import java.net.MalformedURLException;
import java.util.Date;
import net.yacy.cora.document.encoding.UTF8;
import net.yacy.cora.document.id.DigestURL;
import net.yacy.cora.federate.yacy.CacheStrategy;
import net.yacy.cora.protocol.ClientIdentification;
import net.yacy.cora.protocol.Domains;
import net.yacy.cora.protocol.HeaderFramework;
import net.yacy.cora.protocol.RequestHeader;
import net.yacy.crawler.data.CrawlProfile;
import net.yacy.crawler.retrieval.Request;
import net.yacy.search.Switchboard;
import net.yacy.search.SwitchboardConstants;
import net.yacy.search.index.Segment;
import net.yacy.server.serverObjects;
import net.yacy.server.serverSwitch;
public class QuickCrawlLink_p {
/**
* Example Javascript to call this servlet:
* <code>javascript:w = window.open('http://user:pwd@localhost:8090/QuickCrawlLink_p.html?indexText=on&indexMedia=on&crawlingQ=on&xdstopw=on&title=' + escape(document.title) + '&url=' + location.href,'_blank','height=150,width=500,resizable=yes,scrollbar=no,directory=no,menubar=no,location=no'); w.focus();</code>
* @param header the complete HTTP header of the request
* @param post any arguments for this servlet, the request carried with (GET as well as POST)
* @param env the serverSwitch object holding all runtime-data
* @return the rewrite-properties for the template
*/
public static serverObjects respond(final RequestHeader header, final serverObjects post, final serverSwitch env) {
final serverObjects prop = new serverObjects();
final Switchboard sb = (Switchboard) env;
int port;
// get the http host header
if (header.containsKey(HeaderFramework.HOST)) {
port = header.getServerPort();
} else {
port = sb.getConfigInt(SwitchboardConstants.SERVER_PORT, 8090);
}
prop.put("mode_host", Domains.LOCALHOST);
prop.put("mode_port", port);
if (post == null) {
// send back usage example
prop.put("mode", "0");
return prop;
}
// get the URL
String crawlingStart = post.get("url",null);
if (crawlingStart != null) {
prop.put("mode", "1");
crawlingStart = UTF8.decodeURL(crawlingStart);
// get segment
Segment indexSegment = sb.index;
// get the browser title
String title = post.get("title", null);
if(title != null) {
/* Decode eventual special(non ASCII) characters in title */
title = UTF8.decodeURL(title);
}
// get other parameters if set
final String crawlingMustMatch = post.get("mustmatch", CrawlProfile.MATCH_ALL_STRING);
final String crawlingMustNotMatch = post.get("mustnotmatch", CrawlProfile.MATCH_NEVER_STRING);
final int CrawlingDepth = post.getInt("crawlingDepth", 0);
final boolean crawlingQ = post.get("crawlingQ", "").equals("on");
final boolean followFrames = post.get("followFrames", "").equals("on");
final boolean obeyHtmlRobotsNoindex = post.get("obeyHtmlRobotsNoindex", "").equals("on");
final boolean obeyHtmlRobotsNofollow = post.get("obeyHtmlRobotsNofollow", "").equals("on");
final boolean indexText = post.get("indexText", "off").equals("on");
final boolean indexMedia = post.get("indexMedia", "off").equals("on");
final boolean storeHTCache = post.get("storeHTCache", "").equals("on");
final boolean remoteIndexing = post.get("crawlOrder", "").equals("on");
final String collection = post.get("collection", "user");
prop.put("mode_url", (crawlingStart == null) ? "unknown" : crawlingStart);
prop.putHTML("mode_title", (title == null) ? "unknown" : title);
crawlingStart = crawlingStart.trim();
try {crawlingStart = new DigestURL(crawlingStart).toNormalform(true);} catch (final MalformedURLException e1) {}
// check if url is proper
DigestURL crawlingStartURL = null;
try {
crawlingStartURL = new DigestURL(crawlingStart);
} catch (final MalformedURLException e) {
prop.put("mode_status", "1");
prop.put("mode_code", "1");
return prop;
}
final byte[] urlhash = crawlingStartURL.hash();
indexSegment.fulltext().remove(urlhash);
sb.crawlQueues.noticeURL.removeByURLHash(urlhash);
int timezoneOffset = post.getInt("timezoneOffset", 0);
// create crawling profile
CrawlProfile pe = null;
try {
pe = new CrawlProfile(
(crawlingStartURL.getHost() == null) ? crawlingStartURL.toNormalform(true) : crawlingStartURL.getHost(),
crawlingMustMatch, //crawlerUrlMustMatch
crawlingMustNotMatch, //crawlerUrlMustNotMatch
CrawlProfile.MATCH_ALL_STRING, //crawlerIpMustMatch
CrawlProfile.MATCH_NEVER_STRING, //crawlerIpMustNotMatch
CrawlProfile.MATCH_NEVER_STRING, //crawlerCountryMustMatch
CrawlProfile.MATCH_NEVER_STRING, //crawlerNoDepthLimitMatch
CrawlProfile.MATCH_ALL_STRING, //indexUrlMustMatch
CrawlProfile.MATCH_NEVER_STRING, //indexUrlMustNotMatch
CrawlProfile.MATCH_ALL_STRING, //indexContentMustMatch
CrawlProfile.MATCH_NEVER_STRING, //indexContentMustNotMatch
CrawlingDepth,
true,
CrawlProfile.getRecrawlDate(60 * 24 * 30), // recrawlIfOlder (minutes); here: one month
-1, // domMaxPages, if negative: no count restriction
crawlingQ, followFrames,
obeyHtmlRobotsNoindex, obeyHtmlRobotsNofollow,
indexText, indexMedia,
storeHTCache, remoteIndexing,
-1, false, true, CrawlProfile.MATCH_NEVER_STRING,
CacheStrategy.IFFRESH,
collection,
ClientIdentification.yacyIntranetCrawlerAgentName,
null, null,
timezoneOffset);
sb.crawler.putActive(pe.handle().getBytes(), pe);
} catch (final Exception e) {
// mist
prop.put("mode_status", "2");//Error with url
prop.put("mode_code", "2");
prop.putHTML("mode_status_error", e.getMessage());
return prop;
}
// stack URL
String reasonString = null;
reasonString = sb.crawlStacker.stackCrawl(new Request(
sb.peers.mySeed().hash.getBytes(),
crawlingStartURL,
null,
(title==null)?"CRAWLING-ROOT":title,
new Date(),
pe.handle(),
0,
pe.timezoneOffset()
));
// validate rejection reason
if (reasonString == null) {
prop.put("mode_status", "0");//start msg
prop.put("mode_code", "0");
} else {
prop.put("mode_status", "3");//start msg
prop.put("mode_code","3");
prop.putHTML("mode_status_error", reasonString);
}
}
return prop;
}
}
|
