final DOMParser parser = getDomParser();
        try (final Reader reader = new StringReader(content)) {
            parser.parse(new InputSource(reader));
        } catch (final Exception e) {
            logger.warn("Failed to parse the content.", e);
            return new ExtractData(extractString(content));
        }

        final Document document = parser.getDocument();
        try {

import jakarta.annotation.Resource;

/**
 * A response processor implementation that handles sitemaps.
 * It parses the response body as a SitemapSet, extracts URLs from the sitemaps,
 * and adds them as child URLs to be crawled.
 *
 * <p>
 * This class uses a {@link SitemapsHelper} to parse the sitemap XML or text.
 * It then iterates through the sitemaps in the SitemapSet, extracts the URL

                parser.setProperty(XMLConstants.ACCESS_EXTERNAL_SCHEMA, StringUtil.EMPTY);
            } catch (final Exception e) {
                if (logger.isDebugEnabled()) {
                    logger.debug("Failed to set a property.", e);
                }
            }
            // parse a content
            parser.parse(is, handler);

            return handler.getDataMap();
        } catch (final Exception e) {

            } catch (final CrawlingAccessException e) {
                throw e;
            } catch (final Exception e) {
                if (logger.isDebugEnabled()) {
                    logger.debug("Failed a sitemap check: {}", responseData, e);
                }
            }
        }

        return false;
    }

        mimeType = contentType;
    }

    /**
     * Gets the URL of the crawled resource.
     *
     * @return the URL
     */
    public String getUrl() {
        return url;
    }

    /**
     * Sets the URL of the crawled resource.
     *
     * @param url the URL to set
     */
    public void setUrl(final String url) {
        this.url = url;

import org.apache.tika.metadata.Message;
import org.apache.tika.metadata.TIFF;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.metadata.TikaMimeKeys;

/**
 * Represents extracted data from a crawled resource, including content and metadata.
 */
public class ExtractData
        implements TikaCoreProperties, CreativeCommons, Geographic, HttpHeaders, Message, ClimateForcast, TIFF, TikaMimeKeys, Serializable {

            crawlerClientFactory.addClient(regex, client);
        } catch (final Exception e) {
            if (logger.isDebugEnabled()) {
                logger.debug("Failed to create {}.", componentName, e);
            } else {
                logger.info("{} is not available.", componentName);
            }
        }
    }

    /**

                    consumer.accept(response, httpEntity);
                } catch (final Exception e) {
                    request.abort();
                    logger.warn("Failed to authenticate on " + scheme, e);
                } finally {
                    EntityUtils.consumeQuietly(httpEntity);
                }
            });
        });

                        }
                    }
                }
            } catch (final IOException e) {
                logger.warn("Failed to parse annotation.", e);
            }
        }
    }

    /**
     * Extracts text from an embedded file using the appropriate extractor.
     * @param filename the filename of the embedded file

import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;

/**
 * <p>
 * FileTransformer stores the content of a crawled resource as a file on the file system.
 * It extends HtmlTransformer and provides functionality to:
 * </p>
 * <ul>
 *     <li>Specify a base directory for storing files.</li>