* <ul>
 * <li>Web crawling - crawls web sites and web content</li>
 * <li>File system crawling - crawls file systems and documents</li>
 * <li>Data store crawling - crawls databases and other data sources</li>
 * <li>Combined crawling - runs multiple crawling types simultaneously</li>
 * </ul>
 *
 * <p>Command line usage:
 * <pre>
 * java org.codelibs.fess.exec.Crawler [options...]

                .status(ApiResult.Status.OK)
                .result());
    }

    /**
     * Retrieves a specific crawling info log by ID.
     *
     * @param id the ID of the crawling info log to retrieve
     * @return JSON response containing the crawling info log data
     */
    // GET /api/admin/crawlinginfo/log/{id}
    @Execute
    public JsonResponse<ApiResult> get$log(final String id) {

 * Each enum constant represents a specific event or state in the crawler's execution.
 */
public enum LogType {
    /** Indicates the start of a crawling process. */
    START_CRAWLING,
    /** Indicates the cleanup phase of crawling. */
    CLEANUP_CRAWLING,
    /** Indicates an unsupported URL was encountered when crawling started. */
    UNSUPPORTED_URL_AT_CRAWLING_STARTED,

/**
 * Form class for crawling configuration wizard in the admin interface.
 * Contains validation constraints for creating new crawling configurations.
 */
public class CrawlingConfigForm {

    /**
     * Creates a new form instance.
     */
    public CrawlingConfigForm() {
        // Default constructor
    }

    /**
     * Name of the crawling configuration.
     */
    @Required

import com.google.common.cache.Cache;
import com.google.common.cache.CacheBuilder;

import jakarta.annotation.PostConstruct;

/**
 * Helper class for managing crawling configurations.
 * Provides functionality to store, retrieve, and manage different types of crawling configurations
 * including web, file, and data configurations. Supports caching and session-based configuration management.
 */
public class CrawlingConfigHelper {

Podrías querer probar sus cursos:

* <a href="https://training.talkpython.fm/fastapi-courses" class="external-link" target="_blank">Talk Python Training</a>

    /**
     * The namespace identifier for the crawling session.
     * Used to organize and identify crawling activities in the system.
     * Defaults to the system crawling info name.
     */
    protected String namespace = Constants.CRAWLING_INFO_SYSTEM_NAME;

    /**
     * Array of web crawling configuration IDs to process.

            }
        }
    }

    /**
     * Delays the crawling process before processing a URL.
     */
    protected abstract void delayBeforeProcessing();

    /**
     * Delays the crawling process after processing a URL.
     */
    protected abstract void delayAfterProcessing();

    /**
     * Delays the crawling process when there are no URLs in the queue.
     */

 *   <li>Handling exceptions that may occur during the crawling process.</li>
 * </ol>
 *
 * <p>
 * The thread also manages the active thread count using {@code crawlerContext.activeThreadCountLock}
 * and provides methods for logging messages using {@link LogHelper}.
 * </p>
 *
 * <p>
 * The crawling process continues until the crawler status is {@link CrawlerStatus#DONE} or the

    @CustomSize(maxKey = "form.admin.max.input.size")
    public String paths;

    /** The paths to include during crawling (pattern-based). */
    @CustomSize(maxKey = "form.admin.max.input.size")
    public String includedPaths;

    /** The paths to exclude during crawling (pattern-based). */
    @CustomSize(maxKey = "form.admin.max.input.size")
    public String excludedPaths;