Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 3 of 3 for getRobotsTxtUrlSet (0.11 sec)

  1. fess-crawler/src/test/java/org/codelibs/fess/crawler/client/http/HcHttpClientTest.java

                CrawlingParameterUtil.setCrawlerContext(crawlerContext);
                httpClient.init();
                httpClient.processRobotsTxt(url);
                assertEquals(1, crawlerContext.getRobotsTxtUrlSet().size());
                assertTrue(crawlerContext.getRobotsTxtUrlSet().contains("http://localhost:7070/robots.txt"));
                assertFalse(urlFilter.match("http://localhost:7070/admin/"));
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu May 09 09:28:25 UTC 2024
    - 8.8K bytes
    - Viewed (0)
  2. fess-crawler/src/main/java/org/codelibs/fess/crawler/CrawlerContext.java

        }
    
        public void setIntervalController(final IntervalController intervalController) {
            this.intervalController = intervalController;
        }
    
        public Set<String> getRobotsTxtUrlSet() {
            return robotsTxtUrlSet;
        }
    
        public void setRobotsTxtUrlSet(final Set<String> robotsTxtUrlSet) {
            this.robotsTxtUrlSet = robotsTxtUrlSet;
        }
    
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Sat Oct 12 01:40:57 UTC 2024
    - 4.5K bytes
    - Viewed (0)
  3. fess-crawler/src/main/java/org/codelibs/fess/crawler/client/http/HcHttpClient.java

            } else {
                hostUrl = url;
            }
            final String robotTxtUrl = hostUrl + "/robots.txt";
    
            // check url
            if (crawlerContext.getRobotsTxtUrlSet().contains(robotTxtUrl)) {
                if (logger.isDebugEnabled()) {
                    logger.debug("{} is already visited.", robotTxtUrl);
                }
                return;
            }
    
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu May 09 09:29:26 UTC 2024
    - 41K bytes
    - Viewed (0)
Back to top