Search Options

Results per page
Sort
Preferred Languages
Advance

Results 71 - 80 of 104 for url (0.08 sec)

  1. fess-crawler/src/main/java/org/codelibs/fess/crawler/Crawler.java

        }
    
        /**
         * Adds a URL to the crawling queue.
         * @param url The URL to add.
         */
        public void addUrl(final String url) {
            try {
                urlQueueService.add(crawlerContext.sessionId, url);
            } catch (final Exception e) {
                logger.warn("Failed to add url: " + url, e);
            }
            urlFilter.processUrl(url);
        }
    
        /**
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 14K bytes
    - Viewed (0)
  2. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/ApiExtractor.java

                    }
                }
            }
            return data;
        }
    
        /**
         * Sets the URL of the API endpoint.
         * @param url The URL to set.
         */
        public void setUrl(final String url) {
            this.url = url;
        }
    
        /**
         * Sets the connection timeout.
         * @param connectionTimeout The connection timeout in milliseconds.
         */
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 12.2K bytes
    - Viewed (0)
  3. fess-crawler/src/main/java/org/codelibs/fess/crawler/client/AbstractCrawlerClient.java

         * @param url The URL to request.
         * @return The ResponseData.
         */
        protected ResponseData doHead(final String url) {
            throw new CrawlerSystemException("HEAD method is not supported.");
        }
    
        /**
         * Performs a POST request.
         * @param url The URL to request.
         * @return The ResponseData.
         */
        protected ResponseData doPost(final String url) {
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Sep 06 04:15:37 UTC 2025
    - 9.7K bytes
    - Viewed (10)
  4. fess-crawler-lasta/src/main/resources/crawler/rule.xml

    		<property name="responseProcessor">
    			<component
    				class="org.codelibs.fess.crawler.processor.impl.SitemapsResponseProcessor">
    			</component>
    		</property>
    		<postConstruct name="addRule">
    			<arg>"url"</arg>
    			<arg>".*sitemap.*"</arg>
    		</postConstruct>
    	</component>
    
    	<component name="fileRule" class="org.codelibs.fess.crawler.rule.impl.RegexRule">
    		<property name="ruleId">"fileRule"</property>
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Oct 11 02:16:55 UTC 2015
    - 1.5K bytes
    - Viewed (0)
  5. fess-crawler/src/main/java/org/codelibs/fess/crawler/entity/Sitemap.java

     * It extends the Serializable interface to allow sitemap objects to be serialized.
     */
    public interface Sitemap extends Serializable {
    
        /**
         * Retrieves the location (URL) of the sitemap.
         *
         * @return the location of the sitemap as a String.
         */
        String getLoc();
    
        /**
         * Retrieves the last modification date of the sitemap.
         *
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Mar 15 06:52:00 UTC 2025
    - 1.2K bytes
    - Viewed (0)
  6. fess-crawler/src/test/resources/extractor/test.xml

    <?xml version="1.0" encoding="UTF-8"?>
    <address xmlns:hoge="http://www.example.com/hoge">
    	<item sex="male" custid="A12345">
    		<name>鈴木太郎</name>
    		<access kind="email"></access>
    		<access kind="url">http://www.taro.com/</access>
    		<image file="taro.png" />
    	</item>
    	<item sex="male" custid="B23456">
    		<name>佐藤二朗</name>
    		<access kind="email">******@****.***</access>
    		<image file="jiro.png" />
    	</item>
    	<item sex="female" custid="C34567">
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Oct 11 02:16:55 UTC 2015
    - 582 bytes
    - Viewed (0)
  7. fess-crawler/src/main/java/org/codelibs/fess/crawler/client/smb1/SmbClient.java

         *
         * @see org.codelibs.fess.crawler.client.CrawlerClient#doHead(java.lang.String)
         */
        @Override
        public ResponseData doHead(final String url) {
            try {
                final ResponseData responseData = processRequest(url, false);
                responseData.setMethod(Constants.HEAD_METHOD);
                return responseData;
            } catch (final ChildUrlsException e) {
                return null;
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Sep 18 09:30:45 UTC 2025
    - 23K bytes
    - Viewed (0)
  8. fess-crawler/src/main/java/org/codelibs/fess/crawler/util/CrawlingParameterUtil.java

            return URL_QUEUE_THREAD_LOCAL.get();
        }
    
        /**
         * Sets the URL queue for the current thread. If the provided URL queue is null,
         * the URL queue for the current thread is removed.
         *
         * @param urlQueue the URL queue to be set for the current thread, or null to remove the URL queue
         */
        public static void setUrlQueue(final UrlQueue<?> urlQueue) {
            if (urlQueue == null) {
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Mar 15 06:52:00 UTC 2025
    - 6.4K bytes
    - Viewed (0)
  9. fess-crawler/src/main/java/org/codelibs/fess/crawler/entity/SitemapFile.java

     * This class encapsulates the essential attributes of a Sitemap entry, allowing for efficient management
     * and processing of Sitemap data.
     * </p>
     *
     * <p>
     * The {@code loc} attribute specifies the URL of the Sitemap, while the {@code lastmod} attribute
     * indicates the last time the Sitemap file was modified.  The {@code lastmod} attribute is used by crawlers
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 4.4K bytes
    - Viewed (1)
  10. fess-crawler/src/main/java/org/codelibs/fess/crawler/rule/impl/SitemapsRule.java

    /**
     * SitemapsRule is a rule implementation that extends RegexRule to determine if a given response data
     * represents a valid sitemap. It uses a SitemapsHelper to validate the response body as an InputStream.
     * The rule checks if the URL matches the defined regex pattern and then validates the content as a sitemap.
     * If any exception occurs during the sitemap validation, it logs the error and returns false.
     *
     */
    public class SitemapsRule extends RegexRule {
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 2.6K bytes
    - Viewed (0)
Back to top