🛫 Vistara Invoice Data Extraction API

This project is a Flask-based REST API that extracts structured data from Vistara Airlines PDF invoices. It processes invoices to retrieve key financial and supplier details, then stores the output in a structured CSV format.

---

📌 Features

• Accepts Vistara Airlines invoice PDFs via a POST request.
• Extracts fields such as invoice number, GST details, company name/address, tax amounts, and more.
• Converts the extracted information into a structured format and saves it as output.csv.
• Designed specifically for Vistara Airlines invoices only.

---

🚀 Technologies Used

• Python 3
• Flask
• pdfplumber
• Pandas
• Regular Expressions (re)

---

📂 API Endpoint

POST /validate

Headers:

• Content-Type: multipart/form-data

Form Data:

• airline: (Required) Must be Vistara
• file: (Required) PDF file of the Vistara invoice

Response (on success):

{
  "message": "Data extracted successfully",
  "output_csv": "output.csv"
}

Response (on failure):

• Airline name is missing
• This API only for Vistara
• No file part
• Only read pdf files
• No selected file

---

📄 Extracted Fields

The API extracts and stores the following fields:

• Invoice Number and Date
• GSTIN and Place of Supply
• Company and Site Name
• Supplier Address and GST Details
• Invoice Amounts (CGST, SGST, IGST)
• Net Taxable Value
• Description of Services
• SAC Code
• And more...

---

🧪 How to Run Locally

1. Clone the repository:

   git clone https://github.com/yourusername/vistara-invoice-api.git
   cd vistara-invoice-api

2. Install dependencies:

   pip install flask pdfplumber pandas

3. Run the Flask app:

   python app.py

4. Test using Postman or CURL: Example using curl:

   curl -X POST http://127.0.0.1:5000/validate \
        -F "airline=Vistara" \
        -F "file=@/path/to/invoice.pdf"

---

🛑 Limitations

• Currently supports only Vistara Airlines invoice format.
• Extracts data based on regex patterns, which may break for inconsistent layouts.
• Saves output to a static output.csv file (can be improved with unique naming or DB storage).

---

✅ Future Enhancements

• Add support for multiple airline formats.
• Improve PDF parsing robustness using layout-aware models.
• Return extracted data as JSON along with CSV.
• Integrate database for better data management and history tracking.

---

👨‍💻 Author

Gautam Raj
AI Engineer | Python Developer | Backend Engineer
LinkedIn | GitHub

---