Parsio icon

Parsio

Extract structured data from emails, PDFs, images, and other documents

Actions4

Document → Import Text/HTML (Async)

AI-generated

Summary

Import HTML or plain text content asynchronously into a specified Parsio mailbox, creating a document and returning its document ID for later retrieval of parsed results.

Inputs

  • Mailbox (required) — Select the Parsio mailbox where the document will be imported.
  • HTML/Text Content (required) — Provide the HTML or plain text content to parse, either by direct input or referencing previous node data via expression.
  • Filename — Optionally specify a custom filename for the document including file extension (e.g., "page.html"). Defaults to "document.html" if not provided.
  • Additional Metadata (Optional) — Optional JSON object to include extra context or external IDs with the document, such as {"orderId":"12345","customerId":"abc"}.

Output shape

a single record

The operation returns the document ID representing the uploaded and queued document for parsing. The actual extracted data is not returned immediately but can be retrieved later using this document ID.

Examples

Example 1: Uploading HTML content for asynchronous parsing

Specify the mailbox and provide HTML content along with an optional filename and metadata. The node returns the document ID immediately after uploading.

Links

Discussion