Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 2 of 2 for processRobotsTxt (0.18 sec)

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

                urlFilter.init(sessionId);
                crawlerContext.setUrlFilter(urlFilter);
                CrawlingParameterUtil.setCrawlerContext(crawlerContext);
                httpClient.init();
                httpClient.processRobotsTxt(url);
                assertEquals(1, crawlerContext.getRobotsTxtUrlSet().size());
                assertTrue(crawlerContext.getRobotsTxtUrlSet().contains("http://localhost:7070/robots.txt"));
    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/client/http/HcHttpClient.java

            if (StringUtil.isNotBlank(name) && value != null) {
                httpClientPropertyMap.put(name, value);
            }
        }
    
        protected void processRobotsTxt(final String url) {
            if (StringUtil.isBlank(url)) {
                throw new CrawlerSystemException("url is null or empty.");
            }
    
            if (robotsTxtHelper == null || !robotsTxtHelper.isEnabled()) {
    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