PDF tools by Workato - Extract text from PDF action
The Extract text from PDF action extracts raw, unstructured text from digital (machine-readable) PDF documents and returns the content page by page. Supported source PDFs include those created from Word, Excel, PowerPoint, web pages, or system-generated reports.
This action is commonly used to ingest PDF content into knowledge bases for AI agents or to prepare text for AI summarization.
Scanned PDFs and structured extraction aren't supported
This action returns raw text only. It doesn't support scanned or image-based PDFs and doesn't extract data into a defined schema. To extract structured data, or to process scanned documents, use IDP by Workato instead.
Input
| Input field | Description |
|---|---|
| Source PDF | Provide the file content of the PDF to extract text from. The maximum size is 100 MB. |
| Page range | Specify the pages to extract text from. For example, 1-3,5-5,7-10. Defaults to all pages if not specified. |
Output
| Output field | Description |
|---|---|
| Pages | A list of pages with extracted text. Each item in the list contains the following fields. |
| Page number (Pages) | The page number in the source PDF, for example, 1. |
| Content (Pages) | The extracted text content from the page. |
| List size (Pages) | The total number of pages in the Pages list. |
| List index (Pages) | The position of the current page in the Pages list. |
Last updated: