crawler.crawlerContext.setDefaultIntervalTime(1000); // 1 second
```

### URL Filtering

```java
// Include patterns
crawler.urlFilter.addInclude("https://example.com/.*");
crawler.urlFilter.addInclude(".*\\.pdf$");

// Exclude patterns  
crawler.urlFilter.addExclude(".*\\.js$");
crawler.urlFilter.addExclude(".*login.*");
```

## Supported Protocols and Formats

### Protocols

        final String tempPath = "/tmp/source.pdf";
        final String outputPath = "/tmp/thumbnail.jpg";

        final String expandedCommand = testCommand.replace("${url}", tempPath).replace("${outputFile}", outputPath);

        assertEquals("convert /tmp/source.pdf -resize 100x100 /tmp/thumbnail.jpg", expandedCommand);

    }

    @Test
    @DisplayName("Test decode with valid single entry")
    void testDecodeValidSingleEntry() throws SMBProtocolDecodingException {
        String fileName = "document.pdf";
        int action = FileNotifyInformation.FILE_ACTION_MODIFIED;
        byte[] buffer = createValidNotificationBuffer(fileName, action);

        int bytesRead = notifyInfo.decode(buffer, 0, buffer.length);

						<option value="html" <c:if test="${as.filetype.contains('html')}">selected</c:if>><la:message
								key="labels.advance_search_filetype_html"
							/></option>
						<option value="pdf" <c:if test="${as.filetype.contains('pdf')}">selected</c:if>><la:message
								key="labels.advance_search_filetype_pdf"
							/></option>
						<option value="word" <c:if test="${as.filetype.contains('word')}">selected</c:if>><la:message

						<option value="html" <c:if test="${as.filetype.contains('html')}">selected</c:if>><la:message
								key="labels.advance_search_filetype_html"
							/></option>
						<option value="pdf" <c:if test="${as.filetype.contains('pdf')}">selected</c:if>><la:message
								key="labels.advance_search_filetype_pdf"
							/></option>
						<option value="word" <c:if test="${as.filetype.contains('word')}">selected</c:if>><la:message

        exception = new SmbOperationException(SmbOperationException.ErrorCode.FILE_EXISTS, "document.pdf already exists");
        assertTrue(exception.getMessage().contains("FILE_EXISTS"));
        assertTrue(exception.getMessage().contains("File already exists"));
        assertTrue(exception.getMessage().contains("document.pdf already exists"));

        // Without custom message

   * href="ftp://www.3gpp.org/tsg_sa/TSG_SA/TSGS_23/Docs/PDF/SP-040065.pdf#page=10">3GPP TS
   * 26.244</a>.
   *
   * @since 20.0
   */
  public static final MediaType THREE_GPP_VIDEO = createConstant(VIDEO_TYPE, "3gpp");

  /**
   * The 3G2 multimedia container format. For more information, see <a
   * href="http://www.3gpp2.org/Public_html/specs/C.S0050-B_v1.0_070521.pdf#page=16">3GPP2
   * C.S0050-B</a>.
   *

        when(locator.getCanonicalURL()).thenReturn("smb://server/share/");

        // Mock directory listing
        SmbFile file1 = mock(SmbFile.class);
        when(file1.getName()).thenReturn("document.pdf");
        when(file1.isDirectory()).thenReturn(false);
        when(file1.length()).thenReturn(2048L);
        when(file1.lastModified()).thenReturn(System.currentTimeMillis());

      }
      assertSip(msg, EXPECTED[i]);
    }
  }

  // This test data comes from "SipHash: a fast short-input PRF", "Appendix A: Test values".
  // It can be downloaded here: https://131002.net/siphash/siphash.pdf
  public void test15ByteStringFromSipHashPaper() {
    byte[] message =
        new byte[] {
          0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e
        };

                    TikaExtractor tikaExtractor = container.getComponent("tikaExtractor");
                    factory.addExtractor("application/pdf", tikaExtractor);
                });
        emlExtractor = container.getComponent("emlExtractor");
    }

    public void test_getText() throws IOException {