Skip to content

PDF to CSV converter

PDF to CSV uses AI Deep Read first, then our table engine converts the model's Markdown table response into delimited text.

  • Converted with AI Deep Read · input deleted within 24 h
  • Free: 5 conversions a day · 5 MB each
  • Higher limits →

From real runs

What you get — and what changes

  • Page title Changed

    The PDF heading became a row under a generic Text column instead of CSV metadata.

  • Paragraph text Changed

    The explanatory sentence was included as a quoted CSV row before the detected table content.

  • Table columns Lost

    The tested CSV did not preserve customer, qty, amount, and note as separate columns after Deep Read materialization.

  • Invoice IDs Kept

    INV-1001, INV-1002, and INV-1003 appeared as rows in the CSV output.

  • Numeric amounts Lost

    The CSV output from the table PDF omitted visible amount values such as 1234.50 and (19.95).

  • Page marker Changed

    A Page column and value 1 were appended, which is useful for traceability but not a source table field.

  • PDF layout Lost

    Column widths, fonts, page breaks, and table rules have no place in plain CSV output.

Sample conversions

Vendor table PDF

Input
One-page PDF with title, paragraph, and a five-column invoice table containing three rows.
Output
CSV began with Text, then title, paragraph, invoice, INV-1001, INV-1002, INV-1003, Page, 1. Most table columns were lost.

Accounting negative row

Input
PDF row INV-1002, Bo Foods, 1, (19.95), credit.
Output
The row identifier appeared, but the tested CSV did not include Bo Foods, 1, -19.95, or credit as separate cells.

A real PDF → CSV run

We converted our PDF sample (91 KB) with AI Deep Read under AI Deep Read on 2026-09-11. It took 13 s and produced a 380 B CSV file, 100% smaller than the input. The engine raised 1 warning, listed below.

Input · sample.pdf · 91 KB

PDF 1.4, 1 page, no text layer, 1 image object

Version
1.4
Pages
1
Images
1
Text layer
no

Output · sample.csv · 380 B

15 data rows × 1 column; header: Content

Rows
15
Columns
1
Header
Content
  • AI Deep Read read 1 page; 1 credit per page

First lines of the output

csv
Content
Feedback Atlas — Q3 activity trail
Prepared for: Board of Directors · 12 Sep 2026
Headline numbers
Metric
ARR
Net revenue retention
Support CSAT
Refunds
Content
What went well
• Enterprise pipeline doubled after the SOC 2 report shipped.
• Support CSAT held at 94% while ticket volume rose 31%.
• Two renewals slipped into October. Owner: VP Sales.
Signed
Signed:

Is your file a scan?

A scanned PDF will not have selectable table text and usually has one image-heavy object per page. AI Deep Read spends vision credits by page, reads the page image, and then asks our table engine to materialize detected pipe tables. Review totals, merged labels, and accounting negatives against the original.

Options and when to change them

vision
Required for this pair; set true when calling the API so Deep Read handles the PDF.

Do it yourself

pdftotext

bash
pdftotext -layout statement.pdf statement.txt

This gives layout text for digital PDFs, but you still need a table parser and it will not OCR image-only pages.

PDF to CSV by API or MCP

The HTTP API and the MCP server run the exact engine this page uses (AI Deep Read); the response carries the same warnings the web converter shows. Check support first with GET /api/v1/pairs?from=pdf&to=csv.

curl
curl -X POST https://filetypeconverters.com/api/v1/convert \
  -H "Authorization: Bearer $FTC_API_KEY" \
  -F "file=@input.pdf" -F "from=pdf" -F "to=csv" \
  -F "deepRead=true" \
  --output output.csv
API reference

When this is the wrong conversion

  • Use /convert/pdf-to-xlsx when you need typed numeric cells and a workbook you can inspect in Excel.
  • Use /convert/pdf-to-json when you need to keep paragraphs and table Markdown rather than flattening directly to CSV.

PDF to CSV questions

Why did PDF to CSV lose columns from my table?

The current route converts Deep Read Markdown through our table engine. In our tested PDF, that path flattened much of the table into a Text column instead of preserving all five columns.

Is PDF to CSV good for accounting imports?

Only after review. The tested output kept invoice IDs but dropped amounts, so it is not safe to import without checking each column against the source.

What does the Page row mean?

Deep Read included page traceability in the structured response. The CSV materializer wrote Page and 1 as rows rather than metadata.

Related conversions