mirror of
https://github.com/yacy/yacy_search_server.git
synced 2024-09-19 00:01:41 +02:00
788288eb9e
The default schema uses only some of them and the resting search index has now the following properties: - webgraph size will have about 40 times as much entries as default index - the complete index size will increase and may be about the double size of current amount As testing showed, not much indexing performance is lost. The default index will be smaller (moved fields out of it); thus searching can be faster. The new index will cause that some old parts in YaCy can be removed, i.e. specialized webgraph data and the noload crawler. The new index will make it possible to: - search within link texts of linked but not indexed documents (about 20 times of document index in size!!) - get a very detailed link graph - enhance ranking using a complete link graph To get the full access to the new index, the API to solr has now two access points: one with attribute core=collection1 for the default search index and core=webgraph to the new webgraph search index. This is also avaiable for p2p operation but client access is not yet implemented.
594 lines
32 KiB
Java
594 lines
32 KiB
Java
// Crawler_p.java
|
|
// (C) 2006 by Michael Peter Christen; mc@yacy.net, Frankfurt a. M., Germany
|
|
// first published 18.12.2006 on http://www.anomic.de
|
|
// this file was created using the an implementation from IndexCreate_p.java, published 02.12.2004
|
|
//
|
|
// LICENSE
|
|
//
|
|
// 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
|
|
|
|
import java.io.File;
|
|
import java.io.FileInputStream;
|
|
import java.io.IOException;
|
|
import java.io.Writer;
|
|
import java.net.MalformedURLException;
|
|
import java.util.ArrayList;
|
|
import java.util.Date;
|
|
import java.util.HashMap;
|
|
import java.util.HashSet;
|
|
import java.util.List;
|
|
import java.util.Map;
|
|
import java.util.Properties;
|
|
import java.util.Set;
|
|
import java.util.regex.Pattern;
|
|
import java.util.regex.PatternSyntaxException;
|
|
|
|
import net.yacy.cora.document.ASCII;
|
|
import net.yacy.cora.federate.yacy.CacheStrategy;
|
|
import net.yacy.cora.protocol.RequestHeader;
|
|
import net.yacy.cora.util.SpaceExceededException;
|
|
import net.yacy.crawler.data.CrawlProfile;
|
|
import net.yacy.crawler.data.CrawlQueues;
|
|
import net.yacy.crawler.data.ZURL.FailCategory;
|
|
import net.yacy.crawler.retrieval.Request;
|
|
import net.yacy.crawler.retrieval.SitemapImporter;
|
|
import net.yacy.data.WorkTables;
|
|
import net.yacy.document.Document;
|
|
import net.yacy.document.parser.html.ContentScraper;
|
|
import net.yacy.document.parser.html.TransformerWriter;
|
|
import net.yacy.kelondro.data.meta.DigestURI;
|
|
import net.yacy.kelondro.index.RowHandleSet;
|
|
import net.yacy.kelondro.logging.Log;
|
|
import net.yacy.kelondro.util.FileUtils;
|
|
import net.yacy.peers.NewsPool;
|
|
import net.yacy.repository.Blacklist.BlacklistType;
|
|
import net.yacy.search.Switchboard;
|
|
import net.yacy.search.SwitchboardConstants;
|
|
import net.yacy.search.schema.CollectionSchema;
|
|
import net.yacy.server.serverObjects;
|
|
import net.yacy.server.serverSwitch;
|
|
|
|
public class Crawler_p {
|
|
|
|
// this servlet does NOT create the Crawler servlet page content!
|
|
// this servlet starts a web crawl. The interface for entering the web crawl parameters is in IndexCreate_p.html
|
|
|
|
public static serverObjects respond(final RequestHeader header, final serverObjects post, final serverSwitch env) {
|
|
// return variable that accumulates replacements
|
|
final Switchboard sb = (Switchboard) env;
|
|
// inital values for AJAX Elements (without JavaScript)
|
|
final serverObjects prop = new serverObjects();
|
|
prop.put("rejected", 0);
|
|
prop.put("urlpublictextSize", 0);
|
|
prop.put("webgraphSize", 0);
|
|
prop.put("rwipublictextSize", 0);
|
|
prop.put("list", "0");
|
|
prop.put("loaderSize", 0);
|
|
prop.put("loaderMax", 0);
|
|
prop.put("list-loader", 0);
|
|
prop.put("localCrawlSize", sb.crawlQueues.coreCrawlJobSize());
|
|
prop.put("localCrawlState", "");
|
|
prop.put("limitCrawlSize", sb.crawlQueues.limitCrawlJobSize());
|
|
prop.put("limitCrawlState", "");
|
|
prop.put("remoteCrawlSize", sb.crawlQueues.remoteTriggeredCrawlJobSize());
|
|
prop.put("remoteCrawlState", "");
|
|
prop.put("noloadCrawlSize", sb.crawlQueues.noloadCrawlJobSize());
|
|
prop.put("noloadCrawlState", "");
|
|
prop.put("list-remote", 0);
|
|
prop.put("forwardToCrawlStart", "0");
|
|
|
|
prop.put("info", "0");
|
|
boolean debug = (post != null && post.containsKey("debug"));
|
|
|
|
if (post != null) {
|
|
String c = post.toString();
|
|
if (c.length() < 1000) Log.logInfo("Crawl Start", c);
|
|
}
|
|
|
|
if (post != null && post.containsKey("continue")) {
|
|
// continue queue
|
|
final String queue = post.get("continue", "");
|
|
if ("localcrawler".equals(queue)) {
|
|
sb.continueCrawlJob(SwitchboardConstants.CRAWLJOB_LOCAL_CRAWL);
|
|
} else if ("remotecrawler".equals(queue)) {
|
|
sb.continueCrawlJob(SwitchboardConstants.CRAWLJOB_REMOTE_TRIGGERED_CRAWL);
|
|
}
|
|
}
|
|
|
|
if (post != null && post.containsKey("pause")) {
|
|
// pause queue
|
|
final String queue = post.get("pause", "");
|
|
if ("localcrawler".equals(queue)) {
|
|
sb.pauseCrawlJob(SwitchboardConstants.CRAWLJOB_LOCAL_CRAWL, "user request in Crawler_p from " + header.refererHost());
|
|
} else if ("remotecrawler".equals(queue)) {
|
|
sb.pauseCrawlJob(SwitchboardConstants.CRAWLJOB_REMOTE_TRIGGERED_CRAWL, "user request in Crawler_p from " + header.refererHost());
|
|
}
|
|
}
|
|
|
|
if (post != null && post.containsKey("terminate")) try {
|
|
final String handle = post.get("handle", "");
|
|
// termination of a crawl: shift the crawl from active to passive
|
|
final CrawlProfile p = sb.crawler.getActive(handle.getBytes());
|
|
if (p != null) sb.crawler.putPassive(handle.getBytes(), p);
|
|
// delete all entries from the crawl queue that are deleted here
|
|
sb.crawler.removeActive(handle.getBytes());
|
|
sb.crawlQueues.noticeURL.removeByProfileHandle(handle, 10000);
|
|
} catch (final SpaceExceededException e) {
|
|
Log.logException(e);
|
|
}
|
|
|
|
if (post != null && post.containsKey("crawlingstart")) {
|
|
// init crawl
|
|
if (sb.peers == null) {
|
|
prop.put("info", "3");
|
|
} else {
|
|
|
|
// remove crawlingFileContent before we record the call
|
|
String crawlingFileName = post.get("crawlingFile");
|
|
final File crawlingFile;
|
|
if (crawlingFileName == null || crawlingFileName.isEmpty()) {
|
|
crawlingFile = null;
|
|
} else {
|
|
if (crawlingFileName.startsWith("file://")) crawlingFileName = crawlingFileName.substring(7);
|
|
crawlingFile = new File(crawlingFileName);
|
|
}
|
|
if (crawlingFile != null && crawlingFile.exists()) {
|
|
post.remove("crawlingFile$file");
|
|
}
|
|
|
|
// prepare some filter that are adjusted in case that this is wanted
|
|
boolean storeHTCache = "on".equals(post.get("storeHTCache", "off"));
|
|
String newcrawlingMustMatch = post.get("mustmatch", CrawlProfile.MATCH_ALL_STRING);
|
|
String newcrawlingMustNotMatch = post.get("mustnotmatch", CrawlProfile.MATCH_NEVER_STRING);
|
|
if (newcrawlingMustMatch.length() < 2) newcrawlingMustMatch = CrawlProfile.MATCH_ALL_STRING; // avoid that all urls are filtered out if bad value was submitted
|
|
final boolean fullDomain = "domain".equals(post.get("range", "wide")); // special property in simple crawl start
|
|
final boolean subPath = "subpath".equals(post.get("range", "wide")); // special property in simple crawl start
|
|
|
|
final boolean restrictedcrawl = fullDomain || subPath || !CrawlProfile.MATCH_ALL_STRING.equals(newcrawlingMustMatch);
|
|
final boolean deleteage = restrictedcrawl && "age".equals(post.get("deleteold","off"));
|
|
Date deleteageDate = null;
|
|
if (deleteage) {
|
|
long t = timeParser(true, post.getInt("deleteIfOlderNumber", -1), post.get("deleteIfOlderUnit","year")); // year, month, day, hour
|
|
if (t > 0) deleteageDate = new Date(t);
|
|
}
|
|
final boolean deleteold = (deleteage && deleteageDate != null) || (restrictedcrawl && post.getBoolean("deleteold"));
|
|
|
|
String crawlingStart0 = post.get("crawlingURL","").trim(); // the crawljob start url
|
|
String[] rootURLs0 = crawlingStart0.indexOf('\n') > 0 || crawlingStart0.indexOf('\r') > 0 ? crawlingStart0.split("[\\r\\n]+") : crawlingStart0.split(Pattern.quote("|"));
|
|
Set<DigestURI> rootURLs = new HashSet<DigestURI>();
|
|
String crawlName = "";
|
|
if (crawlingFile == null) for (String crawlingStart: rootURLs0) {
|
|
if (crawlingStart == null || crawlingStart.length() == 0) continue;
|
|
// add the prefix http:// if necessary
|
|
int pos = crawlingStart.indexOf("://",0);
|
|
if (pos == -1) {
|
|
if (crawlingStart.startsWith("www")) crawlingStart = "http://" + crawlingStart;
|
|
if (crawlingStart.startsWith("ftp")) crawlingStart = "ftp://" + crawlingStart;
|
|
}
|
|
try {
|
|
DigestURI crawlingStartURL = new DigestURI(crawlingStart);
|
|
rootURLs.add(crawlingStartURL);
|
|
crawlName += crawlingStartURL.getHost() + ',';
|
|
if (crawlingStartURL != null && (crawlingStartURL.isFile() || crawlingStartURL.isSMB())) storeHTCache = false;
|
|
|
|
} catch (MalformedURLException e) {
|
|
Log.logException(e);
|
|
}
|
|
} else {
|
|
crawlName = crawlingFile.getName();
|
|
}
|
|
if (crawlName.length() > 256) {
|
|
int p = crawlName.lastIndexOf(',');
|
|
if (p >= 8) crawlName = crawlName.substring(0, p);
|
|
}
|
|
if (crawlName.endsWith(",")) crawlName = crawlName.substring(0, crawlName.length() - 1);
|
|
|
|
|
|
// set the crawl filter
|
|
String ipMustMatch = post.get("ipMustmatch", CrawlProfile.MATCH_ALL_STRING);
|
|
final String ipMustNotMatch = post.get("ipMustnotmatch", CrawlProfile.MATCH_NEVER_STRING);
|
|
if (ipMustMatch.length() < 2) ipMustMatch = CrawlProfile.MATCH_ALL_STRING;
|
|
final String countryMustMatch = post.getBoolean("countryMustMatchSwitch") ? post.get("countryMustMatchList", "") : "";
|
|
sb.setConfig("crawlingIPMustMatch", ipMustMatch);
|
|
sb.setConfig("crawlingIPMustNotMatch", ipMustNotMatch);
|
|
if (countryMustMatch.length() > 0) sb.setConfig("crawlingCountryMustMatch", countryMustMatch);
|
|
|
|
String crawlerNoDepthLimitMatch = post.get("crawlingDepthExtension", CrawlProfile.MATCH_NEVER_STRING);
|
|
final String indexUrlMustMatch = post.get("indexmustmatch", CrawlProfile.MATCH_ALL_STRING);
|
|
final String indexUrlMustNotMatch = post.get("indexmustnotmatch", CrawlProfile.MATCH_NEVER_STRING);
|
|
|
|
final boolean crawlOrder = post.get("crawlOrder", "off").equals("on");
|
|
env.setConfig("crawlOrder", crawlOrder);
|
|
|
|
if (crawlOrder) crawlerNoDepthLimitMatch = CrawlProfile.MATCH_NEVER_STRING; // without limitation the crawl order does not work
|
|
|
|
int newcrawlingdepth = post.getInt("crawlingDepth", 8);
|
|
env.setConfig("crawlingDepth", Integer.toString(newcrawlingdepth));
|
|
if ((crawlOrder) && (newcrawlingdepth > 8)) newcrawlingdepth = 8;
|
|
|
|
boolean directDocByURL = "on".equals(post.get("directDocByURL", "off")); // catch also all linked media documents without loading them
|
|
env.setConfig("crawlingDirectDocByURL", directDocByURL);
|
|
|
|
final String collection = post.get("collection", "user");
|
|
env.setConfig("collection", collection);
|
|
|
|
// recrawl
|
|
final String recrawl = post.get("recrawl", "nodoubles"); // nodoubles, reload, scheduler
|
|
long crawlingIfOlder = 0;
|
|
if ("reload".equals(recrawl)) {
|
|
crawlingIfOlder = timeParser(true, post.getInt("reloadIfOlderNumber", -1), post.get("reloadIfOlderUnit","year")); // year, month, day, hour
|
|
}
|
|
env.setConfig("crawlingIfOlder", crawlingIfOlder);
|
|
|
|
// store this call as api call
|
|
sb.tables.recordAPICall(post, "Crawler_p.html", WorkTables.TABLE_API_TYPE_CRAWLER, "crawl start for " + ((rootURLs.size() == 0) ? post.get("crawlingFile", "") : rootURLs.iterator().next().toNormalform(true)));
|
|
|
|
final boolean crawlingDomMaxCheck = "on".equals(post.get("crawlingDomMaxCheck", "off"));
|
|
final int crawlingDomMaxPages = (crawlingDomMaxCheck) ? post.getInt("crawlingDomMaxPages", -1) : -1;
|
|
env.setConfig("crawlingDomMaxPages", Integer.toString(crawlingDomMaxPages));
|
|
|
|
boolean crawlingQ = "on".equals(post.get("crawlingQ", "off"));
|
|
env.setConfig("crawlingQ", crawlingQ);
|
|
|
|
final boolean indexText = "on".equals(post.get("indexText", "off"));
|
|
env.setConfig("indexText", indexText);
|
|
|
|
final boolean indexMedia = "on".equals(post.get("indexMedia", "off"));
|
|
env.setConfig("indexMedia", indexMedia);
|
|
|
|
env.setConfig("storeHTCache", storeHTCache);
|
|
|
|
CacheStrategy cachePolicy = CacheStrategy.parse(post.get("cachePolicy", "iffresh"));
|
|
if (cachePolicy == null) cachePolicy = CacheStrategy.IFFRESH;
|
|
|
|
String crawlingMode = post.get("crawlingMode","url");
|
|
|
|
if ("file".equals(crawlingMode) && post.containsKey("crawlingFile")) {
|
|
newcrawlingMustNotMatch = CrawlProfile.MATCH_NEVER_STRING;
|
|
directDocByURL = false;
|
|
}
|
|
|
|
if ("sitemap".equals(crawlingMode)) {
|
|
newcrawlingMustMatch = CrawlProfile.MATCH_ALL_STRING;
|
|
newcrawlingMustNotMatch = CrawlProfile.MATCH_NEVER_STRING;
|
|
newcrawlingdepth = 0;
|
|
directDocByURL = false;
|
|
crawlingQ = true;
|
|
}
|
|
|
|
if ("sitelist".equals(crawlingMode)) {
|
|
newcrawlingMustNotMatch = CrawlProfile.MATCH_NEVER_STRING;
|
|
Set<DigestURI> newRootURLs = new HashSet<DigestURI>();
|
|
for (DigestURI sitelistURL: rootURLs) {
|
|
// download document
|
|
Document scraper;
|
|
try {
|
|
scraper = sb.loader.loadDocument(sitelistURL, CacheStrategy.IFFRESH, BlacklistType.CRAWLER, CrawlQueues.queuedMinLoadDelay);
|
|
// get links and generate filter
|
|
for (DigestURI u: scraper.getAnchors().keySet()) {
|
|
newRootURLs.add(u);
|
|
}
|
|
} catch (IOException e) {
|
|
Log.logException(e);
|
|
}
|
|
}
|
|
rootURLs = newRootURLs;
|
|
crawlingMode = "url";
|
|
if ((fullDomain || subPath) && newcrawlingdepth > 0) newcrawlingMustMatch = CrawlProfile.MATCH_ALL_STRING; // to prevent that there is a restriction on the original urls
|
|
}
|
|
|
|
// compute mustmatch filter according to rootURLs
|
|
if ((fullDomain || subPath) && newcrawlingdepth > 0) {
|
|
String siteFilter = ".*";
|
|
if (fullDomain) {
|
|
siteFilter = CrawlProfile.siteFilter(rootURLs);
|
|
if (deleteold) {
|
|
for (DigestURI u: rootURLs) {
|
|
sb.index.fulltext().deleteDomainHashpart(u.hosthash(), deleteageDate, rootURLs.size() > 1);
|
|
}
|
|
}
|
|
} else if (subPath) {
|
|
siteFilter = CrawlProfile.subpathFilter(rootURLs);
|
|
if (deleteold) {
|
|
for (DigestURI u: rootURLs) {
|
|
String basepath = u.toNormalform(true);
|
|
if (!basepath.endsWith("/")) {int p = basepath.lastIndexOf("/"); if (p > 0) basepath = basepath.substring(0, p + 1);}
|
|
int count = sb.index.fulltext().remove(basepath, deleteageDate, rootURLs.size() > 1);
|
|
if (count > 0) Log.logInfo("Crawler_p", "deleted " + count + " documents for host " + u.getHost());
|
|
}
|
|
}
|
|
}
|
|
if (CrawlProfile.MATCH_ALL_STRING.equals(newcrawlingMustMatch)) {
|
|
newcrawlingMustMatch = siteFilter;
|
|
} else if (!CrawlProfile.MATCH_ALL_STRING.equals(siteFilter)) {
|
|
// combine both
|
|
newcrawlingMustMatch = "(" + newcrawlingMustMatch + ")|(" + siteFilter + ")";
|
|
}
|
|
}
|
|
|
|
// check if the crawl filter works correctly
|
|
try {
|
|
Pattern mmp = Pattern.compile(newcrawlingMustMatch);
|
|
for (DigestURI u: rootURLs) {
|
|
assert mmp.matcher(u.toNormalform(true)).matches() : "pattern " + mmp.toString() + " does not match url " + u.toNormalform(true);
|
|
}
|
|
} catch (final PatternSyntaxException e) {
|
|
prop.put("info", "4"); // crawlfilter does not match url
|
|
prop.putHTML("info_newcrawlingfilter", newcrawlingMustMatch);
|
|
prop.putHTML("info_error", e.getMessage());
|
|
}
|
|
try {
|
|
Pattern.compile(newcrawlingMustNotMatch);
|
|
} catch (final PatternSyntaxException e) {
|
|
prop.put("info", "4"); // crawlfilter does not match url
|
|
prop.putHTML("info_newcrawlingfilter", newcrawlingMustNotMatch);
|
|
prop.putHTML("info_error", e.getMessage());
|
|
}
|
|
|
|
// prepare a new crawling profile
|
|
final CrawlProfile profile = new CrawlProfile(
|
|
crawlName,
|
|
newcrawlingMustMatch,
|
|
newcrawlingMustNotMatch,
|
|
ipMustMatch,
|
|
ipMustNotMatch,
|
|
countryMustMatch,
|
|
crawlerNoDepthLimitMatch,
|
|
indexUrlMustMatch,
|
|
indexUrlMustNotMatch,
|
|
newcrawlingdepth,
|
|
directDocByURL,
|
|
crawlingIfOlder,
|
|
crawlingDomMaxPages,
|
|
crawlingQ,
|
|
indexText,
|
|
indexMedia,
|
|
storeHTCache,
|
|
crawlOrder,
|
|
cachePolicy,
|
|
collection);
|
|
byte[] handle = ASCII.getBytes(profile.handle());
|
|
|
|
// before we fire up a new crawl, we make sure that another crawl with the same name is not running
|
|
sb.crawler.removeActive(handle);
|
|
sb.crawler.removePassive(handle);
|
|
try {sb.crawlQueues.noticeURL.removeByProfileHandle(profile.handle(), 10000);} catch (SpaceExceededException e1) {}
|
|
|
|
// delete all error urls for that domain
|
|
List<byte[]> hosthashes = new ArrayList<byte[]>();
|
|
for (DigestURI u: rootURLs) {
|
|
hosthashes.add(ASCII.getBytes(u.hosthash()));
|
|
}
|
|
sb.crawlQueues.errorURL.removeHost(hosthashes, true);
|
|
for (byte[] hosthash: hosthashes) {
|
|
try {
|
|
sb.index.fulltext().getDefaultConnector().deleteByQuery(CollectionSchema.host_id_s.getSolrFieldName() + ":\"" + ASCII.String(hosthash) + "\" AND " + CollectionSchema.failreason_t.getSolrFieldName() + ":[* TO *]");
|
|
} catch (IOException e) {Log.logException(e);}
|
|
}
|
|
sb.index.fulltext().commit(true);
|
|
|
|
// start the crawl
|
|
if ("url".equals(crawlingMode)) {
|
|
if (rootURLs.size() == 0) {
|
|
prop.put("info", "5"); //Crawling failed
|
|
prop.putHTML("info_crawlingURL", "(no url given)");
|
|
prop.putHTML("info_reasonString", "you must submit at least one crawl url");
|
|
} else {
|
|
|
|
// stack requests
|
|
sb.crawler.putActive(handle, profile);
|
|
final Set<DigestURI> successurls = new HashSet<DigestURI>();
|
|
final Map<DigestURI,String> failurls = new HashMap<DigestURI, String>();
|
|
sb.stackURLs(rootURLs, profile, successurls, failurls);
|
|
|
|
if (failurls.size() == 0) {
|
|
// liftoff!
|
|
prop.put("info", "8");
|
|
prop.putHTML("info_crawlingURL", post.get("crawlingURL"));
|
|
|
|
// generate a YaCyNews if the global flag was set
|
|
if (!sb.isRobinsonMode() && crawlOrder) {
|
|
final Map<String, String> m = new HashMap<String, String>(profile); // must be cloned
|
|
m.remove("specificDepth");
|
|
m.remove("indexText");
|
|
m.remove("indexMedia");
|
|
m.remove("remoteIndexing");
|
|
m.remove("xsstopw");
|
|
m.remove("xpstopw");
|
|
m.remove("xdstopw");
|
|
m.remove("storeTXCache");
|
|
m.remove("storeHTCache");
|
|
m.remove("generalFilter");
|
|
m.remove("specificFilter");
|
|
m.put("intention", post.get("intention", "").replace(',', '/'));
|
|
sb.peers.newsPool.publishMyNews(sb.peers.mySeed(), NewsPool.CATEGORY_CRAWL_START, m);
|
|
}
|
|
} else {
|
|
StringBuilder fr = new StringBuilder();
|
|
for (Map.Entry<DigestURI, String> failure: failurls.entrySet()) {
|
|
sb.crawlQueues.errorURL.push(
|
|
new Request(
|
|
sb.peers.mySeed().hash.getBytes(),
|
|
failure.getKey(),
|
|
null,
|
|
"",
|
|
new Date(),
|
|
profile.handle(),
|
|
0,
|
|
0,
|
|
0,
|
|
0),
|
|
sb.peers.mySeed().hash.getBytes(),
|
|
new Date(),
|
|
1,
|
|
FailCategory.FINAL_LOAD_CONTEXT,
|
|
failure.getValue(), -1);
|
|
fr.append(failure.getValue()).append('/');
|
|
}
|
|
|
|
prop.put("info", "5"); //Crawling failed
|
|
prop.putHTML("info_crawlingURL", (post.get("crawlingURL")));
|
|
prop.putHTML("info_reasonString", fr.toString());
|
|
}
|
|
if (successurls.size() > 0) sb.continueCrawlJob(SwitchboardConstants.CRAWLJOB_LOCAL_CRAWL);
|
|
}
|
|
} else if ("sitemap".equals(crawlingMode)) {
|
|
final String sitemapURLStr = post.get("sitemapURL","");
|
|
try {
|
|
final DigestURI sitemapURL = new DigestURI(sitemapURLStr);
|
|
sb.crawler.putActive(handle, profile);
|
|
final SitemapImporter importer = new SitemapImporter(sb, sitemapURL, profile);
|
|
importer.start();
|
|
sb.continueCrawlJob(SwitchboardConstants.CRAWLJOB_LOCAL_CRAWL);
|
|
} catch (final Exception e) {
|
|
// mist
|
|
prop.put("info", "6");//Error with url
|
|
prop.putHTML("info_crawlingStart", sitemapURLStr);
|
|
prop.putHTML("info_error", e.getMessage());
|
|
Log.logException(e);
|
|
}
|
|
} else if ("file".equals(crawlingMode)) {
|
|
if (post.containsKey("crawlingFile")) {
|
|
final String crawlingFileContent = post.get("crawlingFile$file", "");
|
|
try {
|
|
// check if the crawl filter works correctly
|
|
Pattern.compile(newcrawlingMustMatch);
|
|
final ContentScraper scraper = new ContentScraper(new DigestURI(crawlingFile), 10000000);
|
|
final Writer writer = new TransformerWriter(null, null, scraper, null, false);
|
|
if (crawlingFile != null && crawlingFile.exists()) {
|
|
FileUtils.copy(new FileInputStream(crawlingFile), writer);
|
|
} else {
|
|
FileUtils.copy(crawlingFileContent, writer);
|
|
}
|
|
writer.close();
|
|
|
|
// get links and generate filter
|
|
final Map<DigestURI, Properties> hyperlinks = scraper.getAnchors();
|
|
if (newcrawlingdepth > 0) {
|
|
if (fullDomain) {
|
|
newcrawlingMustMatch = CrawlProfile.siteFilter(hyperlinks.keySet());
|
|
} else if (subPath) {
|
|
newcrawlingMustMatch = CrawlProfile.subpathFilter(hyperlinks.keySet());
|
|
}
|
|
}
|
|
|
|
sb.crawler.putActive(handle, profile);
|
|
sb.crawlStacker.enqueueEntriesAsynchronous(sb.peers.mySeed().hash.getBytes(), profile.handle(), hyperlinks);
|
|
} catch (final PatternSyntaxException e) {
|
|
prop.put("info", "4"); // crawlfilter does not match url
|
|
prop.putHTML("info_newcrawlingfilter", newcrawlingMustMatch);
|
|
prop.putHTML("info_error", e.getMessage());
|
|
} catch (final Exception e) {
|
|
// mist
|
|
prop.put("info", "7"); // Error with file
|
|
prop.putHTML("info_crawlingStart", crawlingFileName);
|
|
prop.putHTML("info_error", e.getMessage());
|
|
Log.logException(e);
|
|
}
|
|
sb.continueCrawlJob(SwitchboardConstants.CRAWLJOB_LOCAL_CRAWL);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
if (post != null && post.containsKey("crawlingPerformance")) {
|
|
setPerformance(sb, post);
|
|
}
|
|
|
|
// performance settings
|
|
final long LCbusySleep = env.getConfigLong(SwitchboardConstants.CRAWLJOB_LOCAL_CRAWL_BUSYSLEEP, 1000L);
|
|
final int LCppm = (int) (60000L / Math.max(1,LCbusySleep));
|
|
prop.put("crawlingSpeedMaxChecked", (LCppm >= 30000) ? "1" : "0");
|
|
prop.put("crawlingSpeedCustChecked", ((LCppm > 10) && (LCppm < 30000)) ? "1" : "0");
|
|
prop.put("crawlingSpeedMinChecked", (LCppm <= 10) ? "1" : "0");
|
|
prop.put("customPPMdefault", Integer.toString(LCppm));
|
|
|
|
// generate crawl profile table
|
|
int count = 0;
|
|
boolean dark = true;
|
|
final int domlistlength = (post == null) ? 160 : post.getInt("domlistlength", 160);
|
|
CrawlProfile profile;
|
|
// put active crawls into list
|
|
String hosts = "";
|
|
for (final byte[] h: sb.crawler.getActive()) {
|
|
profile = sb.crawler.getActive(h);
|
|
if (CrawlProfile.ignoreNames.contains(profile.name())) continue;
|
|
profile.putProfileEntry("crawlProfilesShow_list_", prop, true, dark, count, domlistlength);
|
|
prop.put("crawlProfilesShow_list_" + count + "_debug", debug ? 1 : 0);
|
|
if (debug) {
|
|
RowHandleSet urlhashes = sb.crawler.getURLHashes(h);
|
|
prop.put("crawlProfilesShow_list_" + count + "_debug_count", urlhashes == null ? "unknown" : Integer.toString(urlhashes.size()));
|
|
}
|
|
if (profile.urlMustMatchPattern() == CrawlProfile.MATCH_ALL_PATTERN) {
|
|
hosts = hosts + "," + profile.name();
|
|
}
|
|
dark = !dark;
|
|
count++;
|
|
}
|
|
prop.put("crawlProfilesShow_debug", debug ? 1 : 0);
|
|
prop.put("crawlProfilesShow_list", count);
|
|
prop.put("crawlProfilesShow_count", count);
|
|
prop.put("crawlProfilesShow", count == 0 ? 0 : 1);
|
|
|
|
if (count > 0) {
|
|
// collect the host names for 'wide' crawls which can be visualized
|
|
boolean showLinkstructure = hosts.length() > 0;
|
|
/*
|
|
// check if there is actually something to see
|
|
if (showLinkstructure) {
|
|
showLinkstructure = false;
|
|
for (String host: hosts.substring(1).split(",")) {
|
|
String hash = null;
|
|
try {hash = ASCII.String((new DigestURI("http://" + host)).hash(), 6, 6);} catch (final MalformedURLException e) {Log.logException(e);}
|
|
if (hash != null && sb.webStructure.referencesCount(hash) > 0) {showLinkstructure = true; break;}
|
|
}
|
|
}
|
|
*/
|
|
if (showLinkstructure) {
|
|
prop.put("crawlProfilesShow_linkstructure", 1);
|
|
prop.put("crawlProfilesShow_linkstructure_hosts", hosts.substring(1));
|
|
} else {
|
|
prop.put("crawlProfilesShow_linkstructure", 0);
|
|
}
|
|
}
|
|
|
|
// return rewrite properties
|
|
return prop;
|
|
}
|
|
|
|
private static long timeParser(final boolean recrawlIfOlderCheck, final int number, final String unit) {
|
|
if (!recrawlIfOlderCheck) return 0L;
|
|
if ("year".equals(unit)) return System.currentTimeMillis() - number * 1000L * 60L * 60L * 24L * 365L;
|
|
if ("month".equals(unit)) return System.currentTimeMillis() - number * 1000L * 60L * 60L * 24L * 30L;
|
|
if ("day".equals(unit)) return System.currentTimeMillis() - number * 1000L * 60L * 60L * 24L;
|
|
if ("hour".equals(unit)) return System.currentTimeMillis() - number * 1000L * 60L * 60L;
|
|
if ("minute".equals(unit)) return System.currentTimeMillis() - number * 1000L * 60L;
|
|
return 0L;
|
|
}
|
|
|
|
private static void setPerformance(final Switchboard sb, final serverObjects post) {
|
|
final String crawlingPerformance = post.get("crawlingPerformance", "custom");
|
|
final long LCbusySleep = sb.getConfigLong(SwitchboardConstants.CRAWLJOB_LOCAL_CRAWL_BUSYSLEEP, 1000L);
|
|
int wantedPPM = (LCbusySleep == 0) ? 30000 : (int) (60000L / LCbusySleep);
|
|
try {
|
|
wantedPPM = post.getInt("customPPM", wantedPPM);
|
|
} catch (final NumberFormatException e) {}
|
|
if ("minimum".equals(crawlingPerformance.toLowerCase())) wantedPPM = 10;
|
|
if ("maximum".equals(crawlingPerformance.toLowerCase())) wantedPPM = 30000;
|
|
sb.setPerformance(wantedPPM);
|
|
}
|
|
|
|
}
|