Convert PDF tables to Excel and CSV
Extract tables from any PDF, scanned or digital, into clean spreadsheets. Merged cells, nested headers, and multi-page tables handled automatically.
Using Claude Code, Cursor, or other coding agents?
Prefer a native integration? Add the Reducto MCP server and your agent can parse documents inline, no SDK code required.
# Authenticate once
uvx mcp-server-reducto --login
# Add to Claude Code
claude mcp add reducto -- uvx mcp-server-reductoConvert a PDF to Excel in minutes
From sign-up to clean, spreadsheet-ready tables. No OCR to configure, no infrastructure to manage.
Get your API key
Sign up at studio.reducto.ai and create an API key. Set it as an environment variable.
export REDUCTO_API_KEY="your_api_key_here"Install the SDK
pip install reductoExtract tables from your PDF
Pass a file or URL to /parse and set the table output format to CSV. Reducto rebuilds every table, including merged cells and multi-page spans.
from reducto import Reducto
client = Reducto()
result = client.parse.run(
input="https://cdn.reducto.ai/samples/fidelity-example.pdf",
formatting={"table_output_format": "csv"},
)
# Every table comes back as CSV, ready for Excel
for chunk in result.result.chunks:
for block in chunk.blocks:
if block.type == "Table":
print(block.content)Save it to Excel or CSV
Because each table block is already CSV, you can write it straight to a .csv file and open it in Excel. HTML, JSON, and Markdown are available too.
with open("tables.csv", "w", newline="") as f:
for chunk in result.result.chunks:
for block in chunk.blocks:
if block.type == "Table":
f.write(block.content + "\n\n")PDF to Excel questions
Turn your PDFs into spreadsheets
Drop a PDF in Studio, or hit the API with a single call. No setup, no credit card.
