+ "|application/rdf\\+xml" //
            + "|application/pdf" //
            + "|application/x-freemind" //
            + "|application/lha" //
            + "|application/x-lha" //
            + "|application/x-lha-compressed" //
            + "|text/xml" //
            + "|text/xml-external-parsed-entity" //
            + "|text/html)";

    // HTML rule pattern from webHtmlRule in rule.xml

			<!-- Supported MIME type -->
			<arg>
  "(application/xml"
+ "|application/xhtml\+xml"
+ "|application/rdf\+xml"
+ "|application/pdf"
+ "|application/x-freemind"
+ "|application/lha"
+ "|application/x-lha"
+ "|application/x-lha-compressed"
+ "|text/xml"
+ "|text/xml-external-parsed-entity"
+ "|text/html)"
			</arg>
		</postConstruct>
	</component>

### Protocols

HTTP/HTTPS, File, FTP/FTPS, SMB/CIFS (SMB1/SMB2+), Storage (MinIO via `storage://`), S3 (`s3://`), GCS (`gcs://`)

### Content Formats

Office (Word, Excel, PowerPoint), PDF, Archives (ZIP, TAR, GZ, LHA), HTML, XML, JSON, Markdown, Media metadata, Images (EXIF/IPTC/XMP), Email (EML)

---

## Architecture

### Module Structure

```
fess-crawler-parent/
├── fess-crawler/              # Core framework

#### PDFs and Images
- PDF documents (text and metadata extraction)
- Images (JPEG, PNG, GIF, TIFF, BMP)
- Image metadata (EXIF, IPTC, XMP)

#### Archives and Compressed Files
- ZIP, TAR, GZ archives
- LHA compression format
- Nested archive extraction

#### Web and Markup
- HTML, XHTML with XPath support
- XML documents
- JSON and structured data

#### Media Files
- Audio formats (MP3, WAV, FLAC)

		<postConstruct name="addExtractor">
			<arg>[
				"application/pdf"
				]</arg>
			<arg>pdfExtractor</arg>
		</postConstruct>
		<postConstruct name="addExtractor">
			<arg>[
				"application/x-lha",
				"application/x-lharc"
				]</arg>
			<arg>lhaExtractor</arg>
		</postConstruct>
		<postConstruct name="addExtractor">
			<arg>[
				"message/rfc822"
				]</arg>
			<arg>emlExtractor</arg>