🕷️️ Job Radar • SCRAPING

upwork.com 🟠 2026-05-18

🔹 AI Invoice Extractor for Email Monitoring and Google Sheets Export
👤 Client: 🇵🇰 Pakistan Member since 2026-05-17
💰 Price: $50.00 Fixedprice
🚩 Problem: Automate the process of extracting invoice and receipt data from emails to reduce manual entry into spreadsheets.
📦 Existing: [Not specified]

Specifications:

[Target] Gmail API integration for inbox monitoring and attachment detection
[Method] Python script with OAuth authentication
[UI/UX] N/A (CLI or simple web interface for testing)
[Stack] Python, PyMuPDF, Tesseract OCR, Claude/OpenAI, Google Sheets API
[Security] Secure OAuth credentials management, data validation checks
[Format] JSON structured output for Google Sheets

Workflow:

Set up Gmail API with read-only scope and OAuth authentication.
Develop a Python script to monitor the inbox and detect attachments of invoices/receipts.
Implement PDF text extraction using PyMuPDF for native PDF documents.
Integrate Tesseract OCR for extracting data from scanned documents and image-based receipts.
Use Claude or OpenAI API for structured JSON extraction of key invoice details: vendor name, invoice number, date, due date, line items, subtotal, tax, total, currency, payment terms.
Implement validation logic to cross-check the extracted data and flag discrepancies.
Export validated data into a Google Sheet with one row per invoice, highlighting flagged rows.
Test the system against provided sample documents.