Automate Invoice Splitting and Data Extraction Using AI Invoice Parser and Make

This tutorial will show you how to split a PDF with five different invoices into individual files. You'll learn to extract details from each invoice and add them to a Google Spreadsheet using PDF.co API and the Make platform.

Sample PDF Invoice
Sample PDF Invoice

Here are the steps to automate the process using PDF.co and Make:

Step 1: Google Drive Download a File

Let’s use the Google Drive module and select the "Download a file" feature to download the PDF file you need to process.

Google Drive Download a File

Step 2: Setting Up Google Drive

  • Choose the "Select from the list" option to enter a File ID.
  • Select "My Drive" as the Drive to be used.
  • Enter the folder and file name you would like to use.
Setting up Google Drive

Step 3: PDF.co Split a PDF Module

Let's use the PDF.co Split a PDF feature to split the PDF invoice into individual invoices.

PDF.co Split a PDF Module

Step 4: Setup Split a PDF Configuration

  • "Select the 'Upload a file' option to automatically input the downloaded PDF file from Google Drive.
  • Then, choose the 'Split by Page Numbers' feature to split the PDF invoice into individual invoices using a page index.
  • In the Pages field, input the asterisk (*) symbol to split all the PDF pages into individual files.
Setup Split a PDF Configuration

Step 5: Run Scenario to Split Invoices

After setting up, run the scenario to split the PDF invoice into individual invoices.

Run Scenario to Split Invoices

Step 6: Flow Control

Let's use the Iterator tool to loop through each URL invoice one at a time.

Flow Control

Step 7: PDF.co Parse a Document Module

Next let's add the 'PDF.co AI Invoice Parser' module to parse the data from all the individual invoices.

PDF.co Parse a Document Module

Step 8: Setup Parse a Document Module

  • Select the 'Import a file from URL' option to input a file URL.
  • Next, enter the Iterator URL value.
  • Then, select the JSON output as export type.
Setup Parse a Document Module

Step 9: Run Scenario to Parse Data

Now, let’s run the scenario to parse the data from each individual invoice.

Step 10: Add Flow Control

Let's use the Iterator tool to loop through each table item.

Add Flow Control

Step 11: Google Sheets Module

Now that we've parsed the data from all the invoices, let's add the Google Sheets module and select the “Add a Row” feature to map the extracted data to the corresponding fields in Google Sheets.

Google Sheets Module

Step 12: Setup Google Sheets Module

  • Choose the 'Select by path' method.
  • Select 'My Drive' as the drive.
  • Enter the Spreadsheet ID and Sheet name.
  • Map the parsed data values to the respective columns in the Google Sheet.
Setup Google Sheets Module
Setup Google Sheets Module

Step 13: Run Scenario and View Result

Now, run the scenario and open Google Sheets to review the result.

Google Sheets Result
Google Sheets Result

In conclusion, this tutorial has walked you through using the PDF.co API and Make platform to manage your invoice processing workflow. By splitting a PDF with multiple invoices into individual files, extracting essential data, and adding that data to a Google Spreadsheet, you can save time and reduce manual effort.