Invoice to Excel: Invoice & Receipt OCR with AI

Invoices and receipts → structured data. Amounts, dates, vendors, line items, tax details. Clean JSON, zero manual entry.

Ask a research question and name your fields. The agent searches the web, reads the top pages and returns every item it finds as JSON in your schema, with source URL and a per-field confidence label. Callable as a tool via the Apify MCP server.

Scrape Shopify stores (public products.json) and eBay search results into one clean schema: one row per variant with price, compare-at price, currency, SKU, stock, images and URL. Blocked or empty targets are reported with a reason and never billed.

Personio Job Scraper: Company Job Listings to JSON

enezli/personio-scraper

Job scraper for company career pages on Personio: paste a company board and get every open job listing as clean, de-duplicated JSON with title, department, location and apply URL. Use it for job boards, hiring signals and recruiting research. No login, no API key.

Invoice & Receipt OCR to JSON

ratio_tech/invoice-ocr-scraper

Extract structured data from invoice and receipt PDFs or images — vendor, invoice number, dates, line items, subtotal, tax, total, and currency. On-box OCR (Tesseract + Poppler), no external API. Ideal for accounting automation and document data pipelines.

Extract structured data from receipts and invoices: PDF, JPG, PNG in; clean JSON and ledger-ready CSV out. Date, supplier, tax/GST, ABN, totals with confidence scores. OCR for scans and photos. Batch URLs. LLM/RAG-ready output. $0.01 per document.

Uptime and incident monitor for any Cachet status page: get components, current status and incidents as clean JSON. Track vendor outages, feed alerts or dashboards, and keep an incident history. No login, API and MCP ready.

Pdf to json

shahabuddin38/pdf-to-json

Convert PDF files into structured JSON with optional OCR, table extraction, key-value detection, and metadata parsing. Ideal for invoices, receipts, contracts, statements, forms, and document automation workflows. Supports digital and scanned PDFs for API-ready data extraction.

AI Invoice Parser - Extract Receipt & Bill Data

ntriqpro/invoice-extraction-mcp

Read invoices, receipts and bills automatically and get structured data back: vendor, line items, totals, tax, dates and currency. Accepts PDF and image files, returns clean JSON, and runs as an MCP server so an AI agent can call it directly.

Parse Word, PowerPoint, Excel and PDF documents into clean Markdown and structured JSON: tables extracted cell-by-cell, document metadata, and RAG-ready chunks with heading paths. Built-in OCR for scans and images.