Search Options

Results per page
Sort
Preferred Languages
Advance

Results 21 - 30 of 35 for fess_crawler (0.34 sec)

  1. fess-crawler-lasta/src/main/resources/crawler/sitemaps.xml

    <?xml version="1.0" encoding="UTF-8"?>
    <!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
    	"http://dbflute.org/meta/lastadi10.dtd">
    <components namespace="fessCrawler">
    	<include path="crawler/container.xml" />
    
    	<component name="sitemapsHelper" class="org.codelibs.fess.crawler.helper.SitemapsHelper"
    		instance="singleton">
    	</component>
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sun Oct 11 02:16:55 UTC 2015
    - 365 bytes
    - Viewed (0)
  2. src/main/resources/crawler_opensearch+crawlerThread.xml

    <?xml version="1.0" encoding="UTF-8"?>
    <!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN" 
    	"http://dbflute.org/meta/lastadi10.dtd">
    <components namespace="fessCrawler">
    	<!-- Crawler Thread -->
    	<component name="crawlerThread" class="org.codelibs.fess.crawler.FessCrawlerThread" instance="prototype" >
    	</component>
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Thu Oct 30 05:29:49 UTC 2025
    - 342 bytes
    - Viewed (0)
  3. fess-crawler-lasta/src/main/resources/crawler/urlconverter.xml

    <?xml version="1.0" encoding="UTF-8"?>
    <!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
    	"http://dbflute.org/meta/lastadi10.dtd">
    <components namespace="fessCrawler">
    	<include path="crawler/container.xml" />
    
    	<!-- Converts child links to normalize it. -->
    	<component name="urlConvertHelper" class="org.codelibs.fess.crawler.helper.UrlConvertHelper">
    	</component>
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sun Oct 11 02:16:55 UTC 2015
    - 394 bytes
    - Viewed (0)
  4. fess-crawler-lasta/src/main/resources/crawler/robotstxt.xml

    <?xml version="1.0" encoding="UTF-8"?>
    <!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
    	"http://dbflute.org/meta/lastadi10.dtd">
    <components namespace="fessCrawler">
    	<include path="crawler/container.xml" />
    
    	<component name="robotsTxtHelper" class="org.codelibs.fess.crawler.helper.RobotsTxtHelper"
    		instance="prototype">
    	</component>
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sun Oct 11 02:16:55 UTC 2015
    - 367 bytes
    - Viewed (0)
  5. src/main/resources/crawler/extractor+tikaExtractor.xml

    <?xml version="1.0" encoding="UTF-8"?>
    <!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
    	"http://dbflute.org/meta/lastadi10.dtd">
    <components namespace="fessCrawler">
    	<include path="crawler/container.xml" />
    	<component name="tikaExtractor"
    		class="org.codelibs.fess.crawler.extractor.impl.TikaExtractor">
    		<property name="maxCompressionRatio">2</property>
    		<property name="maxUncompressionSize">10000000</property>
    	</component>
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Sun Aug 25 12:46:12 UTC 2019
    - 461 bytes
    - Viewed (0)
  6. src/main/resources/crawler/contentlength.xml

    <?xml version="1.0" encoding="UTF-8"?>
    <!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
    	"http://dbflute.org/meta/lastadi10.dtd">
    <components namespace="fessCrawler">
    	<include path="crawler/container.xml" />
    
    	<component name="contentLengthHelper"
    		class="org.codelibs.fess.crawler.helper.ContentLengthHelper" instance="singleton">
    		<property name="defaultMaxLength">10485760</property><!-- 10M -->
    		<postConstruct name="addMaxLength">
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Sun Oct 11 06:51:14 UTC 2015
    - 561 bytes
    - Viewed (0)
  7. fess-crawler/src/test/resources/org/codelibs/fess/crawler/helper/robots.txt

    User-agent: FessCrawler
    Disallow:           # allows all 
    
    User-agent: BruteBot
    Disallow: /
    Allow: /foo/bar/
    Crawl-delay: 1314000
    
    # welcome!
    User-agent: Googlebot
    Crawl-delay: 1
    
    User-agent: *
    Disallow: /private/
    Disallow: /help        # disallows /help.html, /help/index.html, etc.
    Allow: /help/faq.html
    Crawl-delay: 3
    
    User-agent: Crawler
    Disallow: /aaa
    
    User-agent: Crawler/1.0
    Disallow: /bbb
    
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sun Oct 11 02:16:55 UTC 2015
    - 566 bytes
    - Viewed (0)
  8. fess-crawler/src/test/java/org/codelibs/fess/crawler/helper/RobotsTxtHelperTest.java

            try {
                robotsTxt = robotsTxtHelper.parse(in);
            } finally {
                CloseableUtil.closeQuietly(in);
            }
    
            for (String userAgent : new String[] { "FessCrawler", "FessCrawler/1.0", "Mozilla FessCrawler" }) {
                assertTrue(robotsTxt.allows("/aaa", userAgent));
                assertTrue(robotsTxt.allows("/private/", userAgent));
                assertTrue(robotsTxt.allows("/private/index.html", userAgent));
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Mon Nov 24 03:59:47 UTC 2025
    - 20.6K bytes
    - Viewed (0)
  9. src/main/resources/crawler/transformer.xml

    <?xml version="1.0" encoding="UTF-8"?>
    <!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
    	"http://dbflute.org/meta/lastadi10.dtd">
    <components namespace="fessCrawler">
    	<include path="crawler/transformer_basic.xml"/>
    
    	<component name="fessXpathTransformer" class="org.codelibs.fess.crawler.transformer.FessXpathTransformer" instance="singleton">
    		<property name="name">"fessXpathTransformer"</property>
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Fri Dec 20 13:14:54 UTC 2024
    - 1.7K bytes
    - Viewed (0)
  10. src/main/resources/crawler/rule.xml

    <?xml version="1.0" encoding="UTF-8"?>
    <!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
    	"http://dbflute.org/meta/lastadi10.dtd">
    <components namespace="fessCrawler">
    	<include path="crawler/container.xml" />
    	<include path="crawler/transformer.xml" />
    
    	<component name="ruleManager" class="org.codelibs.fess.crawler.rule.impl.RuleManagerImpl" instance="prototype">
    		<postConstruct name="addRule">
    			<arg>sitemapsRule</arg>
    		</postConstruct>
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Thu Jun 04 08:42:49 UTC 2020
    - 4.6K bytes
    - Viewed (0)
Back to top