Tutorials
Practical, real-world guides for developers — essential workflows broken down into clear steps, with ready-to-use code you can drop into your project.
Get PDF Form Field Names and Values in Python
Python form libraries hand you raw PDF objects to decode. Send the form URL to the Apdf API instead and get every field as JSON — name, value in a Python-friendly shape, options, required flag and the question printed next to it — then turn a folder of filled rental applications into a CSV that flags missing answers.
8 min read
Convert Word to PDF in Python — Without Microsoft Word on Your Server
docx2pdf needs Microsoft Word, and an office suite on the server needs babysitting. Send the .docx URL to the Apdf API instead and download the PDF — one script for a single document, and a webhook receiver that converts a whole batch of client reports without polling.
6 min read
Turn Scanned Invoices into Structured Data with an Agent
OCR reads tabular scans in scrambled order — the wall every regex parser dies against, and exactly where the agent shines: it reassembles vendor, number, date and line items from the mess, cross-checks the sums against each stated total, and flags mismatches for human eyes instead of your books.
3 min read
Search a PDF From Your Editor
The integration spec is a PDF and your questions arrive mid-function. With the editor connected over MCP, 'what's the retry policy?' comes back with the exact line and page — and a regex search turns 'list every error code' into one call with three cited matches.
3 min read
Watermark Draft PDFs via Claude Before Sharing
The draft that leaks is the one you didn't stamp. Conversationally it's one message: the agent designs the translucent DRAFT — CONFIDENTIAL stamp itself with the PDF generator, overlays it across every page, renders a page to prove it looks right — and mints one named copy per reviewer.
3 min read
Password-Protect PDFs in an Agent Workflow
Encryption as a step the agent runs, not a desktop-tool detour: lock a client statement with owner and user passwords, have the agent probe the result to prove the lock held (encrypted: true, everything else hidden), and unlock the archive copy in the same conversation.
4 min read
Extract PDF Content into Markdown Notes with an Agent
Stop pasting PDFs into chat windows: the agent pulls clean, page-numbered text over MCP and writes the vault-ready note itself — front matter, the headline stat with its page citation, and a section map. Weeks later, search-pdf-content retrieves the exact quote without re-reading anything.
4 min read
Split Bulk PDF Statements by Asking Claude
The accounting export is one PDF with every client's statement stacked inside. Describe the structure — 'three pages per client' — and the agent translates it into a page-range expression, splits the batch into per-client files, and reads them back to verify nothing leaked between clients.
4 min read
Compress a Folder of PDFs with Claude Code
Batch compression without the batch script: hand Claude Code a folder of hosted PDFs and the agent loops the compress tool over every file, polls the jobs, and reports honestly — a 74 MB board pack collapses 94%, a lean text file shaves 4%, and an optimized scan keeps its original.
3 min read
OCR Scanned PDFs by Asking Claude
That folder of scans — old leases, signed contracts, photographed paperwork — becomes searchable conversationally: Claude checks the text layer, runs the OCR job through the Apdf MCP tools, and answers questions from the recovered text with page-level receipts.
4 min read
How to Generate PDFs from Claude
Describe the document, get the PDF: Claude drafts the HTML layout and renders it through the Apdf MCP tools — invoices, reports and one-pagers straight from the conversation, with page format, margins and headers steered in plain English. Revisions are just more chat.
3 min read