Classify and Parse Documents using PDF.co and Zapier

Many organizations face the challenge of managing large volumes of data during document processing. However, there are two important processes, namely classifying and parsing, that can simplify workflows and extract valuable insights from the data.

PDF.co and Zapier are two powerful tools that offer a wide range of features designed to automate document processing tasks. These tools can extract data from various sources like PDFs, images, forms, and tables. By utilizing these tools, organizations can convert unstructured data into a structured format that is easily analyzed and processed.

In this guide, we will explore into the process of classifying and parsing documents, exploring how these processes can aid organizations in extracting valuable insights from their data by utilizing the capabilities of PDF.co and Zapier.

1. Create a Zap
2. Add Google Drive App
3. Setup Google Drive Configuration
4. Test Trigger Result
5. Add PDF.co App
6. Setup PDF.co Configuration
7. Document Classifier Result
8. Add Another PDF.co App
9. Configure PDF.co Settings
10. Document Parser Result
11. Add Google Sheets App
12. Setup Google Sheets Configuration
13. Google Sheets Result
14. Parsed Data Value
15. Demo

We will utilize a sample PDF invoice to showcase how automation tools such as PDF.co and Zapier can be employed to parsed data and classify the extracted information from an invoice.

Step 1: Create a Zap

• Let’s start by logging into your Zapier account and clicking on the Create Zap button.

Step 1: Add Google Drive App

• Next, search and select the Google Drive app. You can also use other cloud storage services where you want to get the source file.
• Then, choose the New File in Folder to trigger when a new file is added to a folder.

Step 3: Setup Google Drive Configuration

Let’s set up the Google Drive configuration.

• In the Drive field, select My Google Drive as the drive to be used.
• In the Folder field, enter the specific folder where the source file was stored.

Now that we have set up the trigger, the next step is to test it by retrieving the source file from Google Drive.

Step 4: Test Trigger Result

• Great! The test trigger was successful and retrieved the file from Google Drive. Let’s add another app to classify the invoice information.

Step 5: Add PDF.co App

• In this step, we will add the PDF.co app and choose the Document Classifier option to analyze the text content and classify the invoice information.

Note: To connect your PDF.co account to Zapier add your API key. You can obtain the API key from your PDF.co dashboard or by signing up at this link.

Step 6: Setup PDF.co Configuration

Let’s set up the PDF.co configuration.

• For the Input Document URL field, select the Web Content Link from Google Drive.
• For the Custom Classification Rules field, establish the precise rules for data extraction to automate the workflow for document processing and guarantee precise and efficient handling of documents. You can use the PDF.co Document Classifier features to create custom classification rules.

After setting up the configuration, test the action for document classification and retrieve the corresponding class value.

Step 7: Document Classifier Result

• Awesome! PDF.co has effectively classified the documents and returned their respective class values. We will now add another app to parse data from PDF invoices.

Step 8: Add Another PDF.co App

• In this step, we will add again the PDF.co app and choose the Document Parser option to parse data from the PDF invoice.

Step 9: Configure PDF.co Settings

Let’s set up the PDF.co configuration.

• In the Document URL field, select the Web Content Link from Google Drive.
• For the Template Id field, input the ID of the template you created for the PDF invoice. You can create a temple ID in PDF.co Document Parser Template Editor here. To learn more about Document Parser, please visit here.

Once you’ve finished setting up the PDF.co configuration, run the scenario to extract the parsed data value from the invoice.

Step 10: Document Parser Result

• Excellent! PDF.co has processed our request and returned the parsed data value from the invoice. Let’s proceed to save the parsed data value to Google Sheets.

Step 11: Add Google Sheets App

• In this step, we will add the Google Sheets app and choose the Create Spreadsheet Row option to create a specific row in a spreadsheet.

Step 12: Setup Google Sheets Configuration

Let’s configure the Google Sheets settings.

• In the Drive field, enter My Google Drive from the dropdown menu.
• In the Spreadsheet field, enter the name of the spreadsheet where you wish to add the parsed data.
• In the Worksheet field, specify the name of the worksheet where the parsed data should be added.
• Finally, map the parsed data values to their respective columns in the worksheet.

After setting up the configuration, test the action to save the parsed data to the Google Sheets spreadsheet.

Step 13: Google Sheets Result

• Congratulations on successfully saving the parsed data to your Google Sheets spreadsheet! You can now open Google Sheets to view the output.

Step 14: Parsed Data Value

• Here’s the parsed data that we successfully saved to the Google Sheets spreadsheet.

Step 15: Demo

• Here’s the PDF.co Document Classifier and Parser in action.

In this tutorial, you were guided on the process of utilizing PDF.co and Zapier to classify and parse documents. You gain knowledge on effectively employing PDF.co Document Classifier to categorize or classify documents based on their content. Additionally, you gained insights into utilizing PDF.co Document Parser to automatically extract data fields from PDF documents and images.