Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 6 of 6 for addExcludes (0.21 sec)

  1. fess-crawler/src/test/java/org/codelibs/fess/crawler/filter/UrlFilterTest.java

         */
        public void test_addExclude_multiplePatterns() {
            String sessionId = "test-session-006";
            urlFilter.init(sessionId);
    
            urlFilter.addExclude(".*\\.(css|js)$");
            urlFilter.addExclude(".*\\/admin\\/.*");
            urlFilter.addExclude(".*#.*");
    
            assertTrue(urlFilter.match("https://example.com/page.html"));
            assertFalse(urlFilter.match("https://example.com/style.css"));
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Wed Sep 03 14:42:53 UTC 2025
    - 19K bytes
    - Viewed (0)
  2. README.md

    ```java
    // Include patterns
    crawler.urlFilter.addInclude("https://example.com/.*");
    crawler.urlFilter.addInclude(".*\\.pdf$");
    
    // Exclude patterns  
    crawler.urlFilter.addExclude(".*\\.js$");
    crawler.urlFilter.addExclude(".*login.*");
    ```
    
    ## Supported Protocols and Formats
    
    ### Protocols
    - **HTTP/HTTPS**: Full web crawling support with cookies, authentication, redirects
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Aug 31 05:32:52 UTC 2025
    - 15.3K bytes
    - Viewed (0)
  3. fess-crawler/src/main/java/org/codelibs/fess/crawler/Crawler.java

         * @param regexp The regular expression for the exclude filter.
         */
        public void addExcludeFilter(final String regexp) {
            if (StringUtil.isNotBlank(regexp)) {
                urlFilter.addExclude(regexp);
            }
        }
    
        /**
         * Stops the crawling process.
         * Sets the crawler status to DONE and interrupts all crawler threads.
         */
        public void stop() {
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 14K bytes
    - Viewed (0)
  4. fess-crawler-lasta/src/test/java/org/codelibs/fess/crawler/CrawlerTest.java

            crawler.crawlerContext.setMaxAccessCount(maxCount);
            crawler.crawlerContext.setNumOfThread(numOfThread);
            crawler.urlFilter.addInclude(url + ".*");
            crawler.urlFilter.addExclude(url + "/dir1/.*");
            final String sessionId = crawler.execute();
            assertEquals(maxCount, dataService.getCount(sessionId));
            dataService.delete(sessionId);
        }
    
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Sep 06 04:15:37 UTC 2025
    - 12.8K bytes
    - Viewed (0)
  5. fess-crawler/src/test/java/org/codelibs/fess/crawler/CrawlerTest.java

            crawler.crawlerContext.setMaxAccessCount(maxCount);
            crawler.crawlerContext.setNumOfThread(numOfThread);
            crawler.urlFilter.addInclude(url + ".*");
            crawler.urlFilter.addExclude(url + "/dir1/.*");
            final String sessionId = crawler.execute();
            assertEquals(maxCount, dataService.getCount(sessionId));
            dataService.delete(sessionId);
        }
    
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Sep 06 04:15:37 UTC 2025
    - 19.1K bytes
    - Viewed (0)
  6. fess-crawler/src/test/java/org/codelibs/fess/crawler/CrawlerContextTest.java

            @Override
            public void init(String sessionId) {
            }
    
            @Override
            public void addInclude(String urlPattern) {
            }
    
            @Override
            public void addExclude(String urlPattern) {
            }
    
            @Override
            public boolean match(String url) {
                return true;
            }
    
            @Override
            public void processUrl(String url) {
            }
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Sep 06 04:15:37 UTC 2025
    - 25.6K bytes
    - Viewed (0)
Back to top