- Sort Score
- Result 10 results
- Languages All
Results 1 - 6 of 6 for RobotsTxt (0.05 sec)
-
fess-crawler/src/main/java/org/codelibs/fess/crawler/entity/RobotsTxt.java
private final List<String> sitemapList = new ArrayList<>(); /** * Creates a new RobotsTxt instance. */ public RobotsTxt() { // Default constructor } /** * Checks if access to a given path is allowed for a specific user agent according to robots.txt rules. * * @param path The path to check for access permission
Registered: Sun Sep 21 03:50:09 UTC 2025 - Last Modified: Sun Jul 06 02:13:03 UTC 2025 - 10K bytes - Viewed (0) -
fess-crawler-lasta/src/main/resources/crawler/robotstxt.xml
Shinsuke Sugaya <******@****.***> 1444529815 +0900
Registered: Sun Sep 21 03:50:09 UTC 2025 - Last Modified: Sun Oct 11 02:16:55 UTC 2015 - 367 bytes - Viewed (0) -
fess-crawler/src/test/java/org/codelibs/fess/crawler/helper/RobotsTxtHelperTest.java
assertTrue(robotsTxt.allows("/bbb", "Crawler")); assertTrue(robotsTxt.allows("/ccc", "Crawler")); assertTrue(robotsTxt.allows("/ddd", "Crawler")); assertTrue(robotsTxt.allows("/aaa", "Crawler/1.0")); assertFalse(robotsTxt.allows("/bbb", "Crawler/1.0")); assertTrue(robotsTxt.allows("/ccc", "Crawler/1.0")); assertTrue(robotsTxt.allows("/ddd", "Crawler/1.0"));
Registered: Sun Sep 21 03:50:09 UTC 2025 - Last Modified: Sat Mar 15 06:52:00 UTC 2025 - 5.9K bytes - Viewed (0) -
fess-crawler/src/main/java/org/codelibs/fess/crawler/helper/RobotsTxtHelper.java
Registered: Sun Sep 21 03:50:09 UTC 2025 - Last Modified: Sun Jul 06 02:13:03 UTC 2025 - 7.7K bytes - Viewed (0) -
fess-crawler/src/main/java/org/codelibs/fess/crawler/client/http/HcHttpClient.java
} } if (httpEntity != null) { final RobotsTxt robotsTxt = robotsTxtHelper.parse(httpEntity.getContent()); if (robotsTxt != null) { final String[] sitemaps = robotsTxt.getSitemaps(); if (sitemaps.length > 0) { crawlerContext.addSitemaps(sitemaps);
Registered: Sun Sep 21 03:50:09 UTC 2025 - Last Modified: Thu Aug 07 02:55:08 UTC 2025 - 52.2K bytes - Viewed (0) -
fess-crawler-lasta/src/main/resources/crawler/client.xml
<!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/robotstxt.xml" /> <include path="crawler/contentlength.xml" /> <include path="crawler/mimetype.xml" /> <component name="internalHttpClient" class="org.codelibs.fess.crawler.client.http.HcHttpClient" instance="prototype">
Registered: Sun Sep 21 03:50:09 UTC 2025 - Last Modified: Tue Aug 08 12:54:47 UTC 2023 - 2.8K bytes - Viewed (0)