# Text Extraction Worker

*/Agents/Text_Extraction_Worker*

## Neighborhood

### Composed into

- [Gorgond](/Startups/Gorgond) — composes · Startups
- [Fbrb](/Startups/Fbrb) — composes · Startups

### What it does

- [Extract Text From PDF Batches](/Tasks/Extract_Text_From_PDF_Batches) — performs · Tasks
- [Run OCR On Scanned Pages](/Tasks/Run_OCR_On_Scanned_Pages) — performs · Tasks
- [Strip Boilerplate From HTML](/Tasks/Strip_Boilerplate_From_HTML) — performs · Tasks

### Realizes

- [Archive Digitization Backfill](/Services/Archive_Digitization_Backfill) — realizes · Services
- [Document Text Extraction Service](/Services/Document_Text_Extraction_Service) — realizes · Services

### Uses tool

- [Queue Based Batch Processing](/Action/Queue_Based_Batch_Processing) — uses tool · Action
- [Apache Tika](/Products/Apache_Tika) — uses tool · Products
- [PDF Text Layer Parsers](/Products/PDF_Text_Layer_Parsers) — uses tool · Products
- [Tesseract OCR](/Products/Tesseract_OCR) — uses tool · Products