Create a Parser
Learn how to create a Parser in PerfectParser — upload a sample, review automatically detected fields and values, then save.
A Parser is your custom data extractor. You set up one Parser per document layout or use case — for example, one for supplier invoices and another for delivery notes. Once configured, you can process many documents through the same Parser.

Step 1: Open the create page
- Sign in to your PerfectParser dashboard.
- Click Parsers in the left-hand sidebar.
- Click New Parser in the top-right corner.
Step 2: Upload a sample document
Drop one representative file on Create Extraction Parser, or click Choose file.
- Accepted formats: PDF, PNG, JPG, JPEG (max 50MB)
- Best results: a real document with typical content (not a blank template)
- A sample is required before you can save the parser
PerfectParser suggests a parser name from the file name. You can edit the name and an optional description while detection runs.
Step 3: Wait for automatic field detection
As soon as the sample finishes uploading, PerfectParser reads the document, detects fields, and extracts sample values.
Uses page credits — the estimate is shown on the sample panel (about 1 credit per page).
Change the file if this sample is the wrong layout. Detection runs again on the new file.
Step 4: Review fields and values
The right panel has two tabs:
- Results — sample values next to the document preview. Correct a value inline, or click Re-run extraction after you change the schema (uses credits again).
- Schema — the field list. Rename a field, change its type, edit its instructions, remove it, or click Add field.
Compare the detected list with a setup guide for your document type when you want a recommended set of fields.
For field types, see Configure Fields — especially Field types explained.
Step 5: Save the parser
- Confirm the schema has at least one field.
- Click Save parser.
- You land on that parser’s Results tab, with the sample extraction in batch history.
To change fields later, open the parser Fields tab. To process more files, open Run Extraction and choose How are your files organized? (One document per file vs One document per page).
File organization is configured when you run extractions, not during parser creation. See Bulk Extraction for multi-page and batch scenarios.
Related guides
- Configure Fields — Field types and how to refine instructions
- Parser setup guides — Recommended fields per document type
- Bulk Extraction — Process documents and choose extraction mode