- XML documents
- JSON and structured data

#### Media Files
- Audio formats (MP3, WAV, FLAC)
- Video formats (MP4, AVI, MOV)
- Metadata extraction from media files

## Architecture

### Multi-Module Structure

```
fess-crawler-parent/
├── fess-crawler/              # Core crawler framework
│   ├── client/               # Protocol clients (HTTP, FTP, SMB, etc.)
│   ├── extractor/           # Content extractors

				"application/vnd.japannet-setstore-wakeup",
				"application/vnd.japannet-verification",
				"application/vnd.japannet-verification-wakeup",
				"application/vnd.jcp.javame.midlet-rms",
				"application/vnd.jisp",
				"application/vnd.joost.joda-archive",
				"application/vnd.kahootz",
				"application/vnd.kde.karbon",
				"application/vnd.kde.kchart",
				"application/vnd.kde.kformula",

        this.connectionCheckInterval = connectionCheckInterval;
    }

    /**
     * Sets the idle connection timeout in milliseconds.
     *
     * @param idleConnectionTimeout The idle connection timeout
     */
    public void setIdleConnectionTimeout(final long idleConnectionTimeout) {
        this.idleConnectionTimeout = idleConnectionTimeout;
    }

/*! jQuery v2.1.1 | (c) 2005, 2014 jQuery Foundation, Inc. | jquery.org/license */

  <mime-type type="application/vnd.japannet-verification"/>
  <mime-type type="application/vnd.japannet-verification-wakeup"/>
  <mime-type type="application/vnd.jcp.javame.midlet-rms">
    <glob pattern="*.rms"/>
  </mime-type>
  <mime-type type="application/vnd.jisp">
    <glob pattern="*.jisp"/>
  </mime-type>
  <mime-type type="application/vnd.joost.joda-archive">