Convert PDF to CSV
Pull tables out of a PDF for CSV. Today you get each table as a Markdown table, or as JSON rows you can write to CSV.
Your Markdown or JSON shows up here.
3 free pages a day, no sign-up.
CSV download is coming soon. For now you get each table as a Markdown table, or as JSON rows you can save as CSV.
How it works
- Step 1Upload your PDF
- Step 2We detect each table
- Step 3Copy the table, or take the JSON rows
Why use this PDF to CSV converter
The JSON output already has tables as rows of cells, which is CSV minus the commas.
Tables in scanned or photographed PDFs are read with OCR.
Send many PDFs through the API and write the rows straight into your own CSV files or database.
What people use it for
- Loading tables from PDF reports into a database or pandas
- Getting transaction lists out of PDF exports
- Preparing PDF data for import into accounting or CRM tools
- Collecting tables from many PDFs into one dataset via the API
Models that do this well
The free tool picks one for you. With the API you choose, and can set fallbacks so a failed page is retried on the next model.
mistral/mistral-ocr6 credits / page2Azure Document IntelligenceAzure layout model with tables, selection marks and prebuilt invoice and ID readers.azure/document-intelligence15 credits / page3Amazon TextractAWS OCR with form key-value pairs, tables and per-word confidence scores.aws/textract6 credits / page4Reducto ParseHigh-accuracy parsing for complex financial and legal documents, with citations.reducto/parse20 credits / pageDo it with the API
Converting more than a few files? The same conversion is one request. Pick any model, or let auto choose.
curl https://api.ocrrouter.ai/v1/ocr \
-H "Authorization: Bearer $OCRROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "auto",
"file_url": "https://example.com/invoice.pdf",
"format": "markdown"
}'