Skip to main content
The Read Content from Doc node extracts content from Google Docs documents, including text, headings, lists, and tables. Supports both plain text and Markdown export formats. This is an AI-powered node that can understand natural language instructions.

​
When to Use It

  • Extract content from existing documents for analysis
  • Import document content into workflows
  • Convert documents to structured data formats
  • Analyze document content with AI tools
  • Migrate content between platforms
  • Create summaries from existing documents

​
Inputs

FieldTypeRequiredDescription
DocumentTextYesGoogle Docs document URL or ID
Export as MarkdownToggleNoConvert content to Markdown format (default: false)

​
Document Input Options

URL Format: 
https://docs.google.com/document/d/1BxiMVs0XRA5nFMdKvBdBZjgmUUqptlbs74OgvE2upms/edit
Document ID Format: 
1BxiMVs0XRA5nFMdKvBdBZjgmUUqptlbs74OgvE2upms

​
Export Format Options

FormatDescriptionWhen to Use
Plain TextRaw text content with basic structureSimple text extraction, AI analysis
MarkdownFormatted text with headers, lists, links, tablesStructured content, web publishing, documentation

​
Output

Returns the extracted document content: Plain Text Export: 
{
  "document_id": "1BxiMVs0XRA5nFMdKvBdBZjgmUUqptlbs74OgvE2upms",
  "document_title": "Project Status Report",
  "content": "Project Status Report\n\nExecutive Summary\nThis quarter we achieved...",
  "content_length": 1247,
  "export_format": "plain_text",
  "elements_found": {
    "headings": 5,
    "paragraphs": 12,
    "lists": 3,
    "tables": 1
  }
}
Markdown Export: 
{
  "document_id": "1BxiMVs0XRA5nFMdKvBdBZjgmUUqptlbs74OgvE2upms",
  "document_title": "Project Status Report",
  "content": "# Project Status Report\n\n## Executive Summary\n\nThis quarter we achieved:\n\n- Revenue target exceeded by 15%\n- Customer satisfaction at 92%\n\n| Metric | Q3 | Q4 |\n|--------|----|----|...",
  "content_length": 1543,
  "export_format": "markdown",
  "elements_found": {
    "headings": 5,
    "paragraphs": 12,
    "lists": 3,
    "tables": 1
  }
}

​
Output Fields:

FieldDescription
document_idUnique Google Docs document ID
document_titleTitle of the document
contentExtracted text content (plain text or Markdown)
content_lengthNumber of characters in the content
export_formatFormat of the exported content
elements_foundCount of different document elements

​
Credit Cost

  • Cost per run: 1 credit

​
Supported Elements

​
Plain Text Export

  • Text content: All paragraph text
  • Headings: Converted to text with line breaks
  • Lists: Bullet points and numbered lists
  • Tables: Tab-separated values
  • Links: Link text only (URLs stripped)

​
Markdown Export

  • Headings: # H1, ## H2, ### H3, etc.
  • Lists: - Bullet points and 1. Numbered lists
  • Tables: Markdown table format with | separators
  • Links: [Link text](URL) format
  • Bold/Italic: **bold** and *italic* formatting
  • Line breaks: Proper Markdown spacing
Note: Images are ignored in both export formats.

​
Common Workflows

Content Analysis: 
[Read Content from Doc] → [AI Analyze Data] → [Generate Summary] → [Create Report]
Document Migration: 
[Read Content: Markdown] → [Process Content] → [Create New Doc] → [Append Formatted Text]
Content Extraction: 
[Read Content from Doc] → [Extract Key Information] → [Write to Sheets] → [Generate Dashboard]
Document Processing: 
[Read Content] → [Split by Sections] → [Process Each Section] → [Combine Results]

​
Tips

Format Selection:
  • Use Plain Text for simple content extraction and AI analysis
  • Use Markdown for preserving formatting and structure
  • Markdown is better for content that will be republished or reformatted
Content Processing:
  • Large documents may have significant content - consider processing in chunks
  • Check content_length to understand document size before processing
  • Use elements_found to understand document structure
  • Combine with text processing nodes for content analysis
Performance Considerations:
  • Large documents take longer to process
  • Markdown export requires more processing than plain text
  • Cache results if you need to read the same document multiple times
⌘I