throw new CrawlingAccessException("[" + e.status() + "] Failed to insert " + id, e);
            }
            throw new OpenSearchAccessException("[" + e.status() + "] Failed to insert " + id, e);
        } catch (final Exception e) {
            throw new OpenSearchAccessException("Failed to insert " + id, e);
        }
    }

    /**

});

// Add sitemap URL
crawler.addUrl("https://example.com/sitemap.xml");
```

## Data Access and Storage

### Accessing Crawled Data

```java
// Get data service
DataService dataService = container.getComponent("dataService");

// Iterate through crawled data
dataService.iterate(sessionId, accessResult -> {
    System.out.println("URL: " + accessResult.getUrl());

            throw new CrawlerSystemException("officeManager is null.");
        }
        try {
            officeManager.start();
        } catch (final OfficeException e) {
            throw new CrawlerSystemException("Failed to start officeManager.", e);
        }
        if (logger.isDebugEnabled()) {
            logger.debug(officeManager.getClass().getSimpleName() + " is started.");
        }
    }

    /**

            // gz
            bis.reset();
            return isValid(new GZIPInputStream(bis), false);
        } catch (final Exception e) {
            if (logger.isDebugEnabled()) {
                logger.debug("Failed to validate a file.", e);
            }
        }
        return false;
    }

    /**
     * Generates SitemapSet instance.
     *
     * This method does not close the input stream.
     *

/**
 * {@link ChildUrlsException} is thrown when child URLs are found during crawling.
 * It extends {@link CrawlerSystemException} and holds a set of {@link RequestData}
 * representing the child URLs that caused the exception.
 *
 */
public class ChildUrlsException extends CrawlerSystemException {

    private static final long serialVersionUID = 1L;

    /**
     * The list of child URLs.
     */

        assertNotNull(originalStackTrace);
        assertTrue(originalStackTrace.length > 0);

        // Fill in stack trace again
        Throwable filled = exception.fillInStackTrace();
        assertSame(exception, filled);

        StackTraceElement[] newStackTrace = exception.getStackTrace();
        assertNotNull(newStackTrace);
        assertTrue(newStackTrace.length > 0);
    }

    /**

    /** The property name for maximum cached content size. */
    public static final String MAX_CACHED_CONTENT_SIZE = "maxCachedContentSize";

    /** The crawler container. */
    @Resource
    protected CrawlerContainer crawlerContainer;

    /** The initialization parameter map. */
    protected Map<String, Object> initParamMap;

    /** The maximum cached content size in bytes. Default is 1MB. */

                                .collect(Collectors.toList());
                    } catch (final Exception e) {
                        logger.warn("Failed to parse passwords for " + url, e);
                        list = Collections.emptyList();
                    }
                    configPasswordMap.put(value, list);
                }

     * This method is used to clean up failed connections.
     *
     * @param client The FTP client to disconnect
     */
    protected void disconnectInternalClient(final FTPClient client) {
        try {
            client.disconnect();
        } catch (final IOException e) {
            logger.warn("Failed to close FTPClient", e);
        }
    }

    /**

 */
package org.codelibs.fess.crawler.exception;

/**
 * Exception thrown during the extraction process in the crawler.
 * This exception indicates a failure or error that occurred while extracting content from a crawled resource.
 * It extends {@link org.codelibs.fess.crawler.exception.CrawlerSystemException} and provides constructors
 * to handle different scenarios such as wrapping another exception or providing a specific error message.
 */