});

// 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());

/**
 * This is an implementation of the HMACT64 keyed hashing algorithm.
 * HMACT64 is defined by Luke Leighton as a modified HMAC-MD5 (RFC 2104)
 * in which the key is truncated at 64 bytes (rather than being hashed
 * via MD5).
 */
public class HMACT64 extends MessageDigest implements Cloneable {

    private static final int BLOCK_LENGTH = 64;

    private static final byte IPAD = (byte) 0x36;

/**
 * This is an implementation of the HMACT64 keyed hashing algorithm.
 * HMACT64 is defined by Luke Leighton as a modified HMAC-MD5 (RFC 2104)
 * in which the key is truncated at 64 bytes (rather than being hashed
 * via MD5).
 */
class HMACT64 extends MessageDigest implements Cloneable {

    private static final int BLOCK_LENGTH = 64;

    private static final byte IPAD = (byte) 0x36;

        .onlyIfCached()
        .noTransform()
        .immutable()
        .build()
    assertThat(cacheControl.toString()).isEqualTo(
      "no-cache, no-store, max-age=1, max-stale=2, min-fresh=3, only-if-cached, " +
        "no-transform, immutable",
    )
    assertThat(cacheControl.noCache).isTrue()
    assertThat(cacheControl.noStore).isTrue()
    assertThat(cacheControl.maxAgeSeconds).isEqualTo(1)

        if (maxStaleSeconds != -1) append("max-stale=").append(maxStaleSeconds).append(", ")
        if (minFreshSeconds != -1) append("min-fresh=").append(minFreshSeconds).append(", ")
        if (onlyIfCached) append("only-if-cached, ")
        if (noTransform) append("no-transform, ")
        if (immutable) append("immutable, ")
        if (isEmpty()) return ""
        deleteRange(length - 2, length)
      }
    headerValue = result
  }

    @Size(max = 200)
    public String name;

    /**
     * The description of the web configuration.
     */
    @Size(max = 1000)
    public String description;

    /**
     * The URLs to be crawled by this web configuration.
     */
    @Required
    @UriType(protocolType = ProtocolType.WEB)
    @CustomSize(maxKey = "form.admin.max.input.size")
    public String urls;

    /**

        SmbPipeInputStream in1 = handle.getInput();
        SmbPipeInputStream in2 = handle.getInput();
        SmbPipeOutputStream out1 = handle.getOutput();
        SmbPipeOutputStream out2 = handle.getOutput();

        // Assert: same instances are returned subsequently
        assertSame(in1, in2, "Input stream should be cached");

  }

  @J2ktIncompatible // https://youtrack.jetbrains.com/issue/KT-58242/ undefined behavior (crash)
  @Override
  public void testContainsKey() {
    try {
      super.testContainsKey();
    } catch (ClassCastException tolerated) {
    }
  }

  @J2ktIncompatible // https://youtrack.jetbrains.com/issue/KT-58242/ undefined behavior (crash)
  @Override
  public void testEntrySetContainsEntryIncompatibleKey() {
    try {

  }

  /**
   * {@inheritDoc}
   *
   * <p>This implementation of {@code getAllPresent} lacks any insight into the internal cache data
   * structure, and is thus forced to return the query keys instead of the cached keys. This is only
   * possible with an unsafe cast which requires {@code keys} to actually be of type {@code K}.
   *
   * @since 11.0
   */
  /*

/**
 * Helper class for managing data crawling operations in Fess.
 * This class coordinates the execution of data store crawling processes,
 * managing multiple concurrent crawling threads and handling the indexing
 * of crawled documents into the search engine.
 *
 * <p>The DataIndexHelper supports:</p>
 * <ul>
 *   <li>Concurrent crawling of multiple data configurations</li>
 *   <li>Thread pool management for crawler execution</li>