Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 2 of 2 for WildcardBot (0.04 sec)

  1. fess-crawler/src/test/java/org/codelibs/fess/crawler/helper/RobotsTxtHelperTest.java

            assertFalse(robotsTxt.allows("/admin/private/", "WildcardBot"));
            assertFalse(robotsTxt.allows("/users/private/data.txt", "WildcardBot"));
            assertTrue(robotsTxt.allows("/private/", "WildcardBot")); // no parent directory
    
            // Allow: /public/*.html - should allow HTML files in public directory
            assertTrue(robotsTxt.allows("/public/index.html", "WildcardBot"));
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Mon Nov 24 03:59:47 UTC 2025
    - 20.6K bytes
    - Viewed (0)
  2. fess-crawler/src/test/resources/org/codelibs/fess/crawler/helper/robots_wildcard.txt

    # Test robots.txt for wildcard (*) and end-of-path ($) support
    # Based on RFC 9309 specification
    
    # Test wildcard patterns
    User-agent: WildcardBot
    Disallow: /*.pdf$
    Disallow: /admin/*.php
    Disallow: /*/private/
    Allow: /public/*.html
    
    # Test end-of-path ($) patterns
    User-agent: EndPathBot
    Disallow: /fish$
    Disallow: /temp$
    Allow: /fishing
    
    # Test complex patterns
    User-agent: ComplexBot
    Disallow: /
    Allow: /$
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Thu Nov 13 14:03:41 UTC 2025
    - 910 bytes
    - Viewed (0)
Back to top