EMAIL PARSER NODE

The Email Parser node allows your workflow to receive incoming emails, extract their contents, and automatically parse PDF attachments into usable text for downstream AI processing.

This is ideal for automating workflows like invoice extraction, document processing, and email-based triggers.

HOW IT WORKS

The Email Parser is triggered via a webhook that receives email data. Each workflow is assigned a unique inbound email address.

When an email is sent to that address:

- The email content is captured

- Attachments are processed

- PDF files are parsed into text

- The result is stored in a variable for use in later steps

SETUP INSTRUCTIONS

1. Copy your unique workflow email address

Format:

wf_[workflow-id]@parse.syncaut.com

2. Go to your email provider (Gmail, Outlook, Zoho, etc.)

3. Create a forwarding rule:

- Condition: incoming invoice emails (or any target emails)

- Action: forward to your workflow email address

4. In your workflow:

- Add the Email Parser node

- Give it a variable name (e.g. invoiceEmail)

5. Connect it to an AI node or next step

6. Save and activate your workflow

Once active, your workflow will automatically run whenever an email is received.

INPUT DATA STRUCTURE

The Email Parser receives structured email data:

{
  from: string

  to: string
  subject: string
  text: string
  html: string
  attachments: [
    {
      filename: string
      contentType: string
      content: string (base64)
    }
  ]
}

PDF PROCESSING

- Only PDF attachments are processed

- Each PDF is converted from base64 → buffer

- Text is extracted using a PDF parser

- Errors are safely handled and logged

Each parsed PDF produces:

{
  filename: string
  text: string
  size: number
}

OUTPUT STRUCTURE

All parsed data is stored under your chosen variable name.

Example (variableName = invoiceEmail):

{

invoiceEmail: {

from: string

to: string

subject: string

body: string

html: string

attachments: [

{

filename: string

text: string

size: number

}

]

pdfText: string

firstPdfText: string

attachmentCount: number

}

}

AVAILABLE OUTPUTS

You can reference these in later nodes:

{{invoiceEmail.pdfText}}

Full combined text from all PDFs

{{invoiceEmail.firstPdfText}}

Text from the first PDF only

{{invoiceEmail.from}}

Sender email address

{{invoiceEmail.subject}}

Email subject line

{{invoiceEmail.body}}

Plain text email body

{{invoiceEmail.attachmentCount}}

Number of PDF attachments

PDF TEXT FORMAT

All PDFs are combined into a single string:

--- file1.pdf ---

[content]

--- file2.pdf ---

[content]

This makes it easy to pass into AI models.

ERROR HANDLING

The node will fail if:

- No variable name is provided

- No email data is present in the trigger

PDF parsing errors:

- Do NOT stop execution

- Are captured per file

- Returned as:

[Failed to parse PDF: error message]

BEST PRACTICES

- Use clear variable names (e.g. invoiceEmail, supportEmail)

- Always connect to an AI node for parsing or extraction

- Filter emails at the inbox level to avoid noise

- Keep PDFs structured for better AI results

COMMON USE CASES

- Invoice processing automation

- Expense tracking from emails

- Contract and document ingestion

- Customer support email parsing

- Logistics and carrier invoice extraction

SUMMARY

The Email Parser node turns incoming emails into structured, AI-ready data by extracting both message content and PDF attachments.

It enables fully automated, email-driven workflows with zero manual input.


Email Parser is still under development