PDF Parse icon

PDF Parse

Parse PDF files and extract text content with enhanced AI-friendly formatting

Actions2

Parse PDF

AI-generated

Overview

The node "PDF Parse" is designed to process PDF files by either extracting their text content or converting PDF pages into images. It supports two main operations:

  • Parse PDF: Extracts text from a PDF file with various formatting options to suit different use cases, including AI-friendly raw text extraction or visually structured layouts.
  • Convert to Image: Converts one or more pages of a PDF into image files (PNG or JPEG), allowing customization of resolution, size, and aspect ratio.

This node is useful in scenarios such as:

  • Automating data extraction from invoices, reports, or contracts stored as PDFs.
  • Preparing textual content for further processing like natural language analysis or indexing.
  • Generating preview images or thumbnails of PDF documents for display purposes.

Practical examples:

  • Extracting all text from a multi-page PDF invoice and storing it in a workflow variable for downstream processing.
  • Converting the first three pages of a PDF report into PNG images to embed in an email.

Properties

Name Meaning
Operation Choose between "Parse PDF" (extract text) or "Convert to Image" (convert pages to images).
PDF Source Select the source of the PDF file: "Binary Data" (from a binary property in the input item) or "URL" (download PDF from a web address).
Binary Property (Shown if source is Binary Data) Name of the binary property containing the PDF file.
URL (Shown if source is URL) The URL of the PDF file to parse.
Output Property Name The name of the property where the extracted content or image info will be stored in the output JSON.
Additional Options Collection of optional settings depending on the operation:
- Max Pages Maximum number of pages to parse or convert (0 means all pages).
- Page Range Start Starting page number (1-based) for parsing or conversion.
- Page Range End Ending page number (0 means last page).
- Text Formatting (For parsing) Style of text formatting applied to extracted content. Options: Raw, Smart Layout, Minimal Cleanup, Visual Layout, Structured, Compact.
- Include Metadata (For parsing) Whether to include PDF metadata (like author, creation date) in the output.
- Split by Pages (For parsing) Whether to split the output text by pages, returning an array of page texts instead of a single string.
- Version (For parsing) PDF.js library version used internally for parsing.
- Image Format (For conversion) Output image format: PNG (supports transparency) or JPEG (smaller file size).
- DPI (Resolution) (For conversion) Dots per inch setting controlling image quality and size (range 72–600).
- Width (For conversion) Desired image width in pixels; 0 means auto-calculated based on DPI.
- Height (For conversion) Desired image height in pixels; 0 means auto-calculated based on DPI.
- Preserve Aspect Ratio (For conversion) Whether to maintain the original aspect ratio when resizing images.

Output

  • For Parse PDF operation:

    • The output JSON contains the extracted text under the specified output property name.
    • If "Split by Pages" is enabled, the output is an array of strings, each representing one page's text.
    • Optionally includes PDF metadata if enabled.
    • Additional statistics such as total number of pages, text length, and word count are included.
    • The binary data remains unchanged from the input.

  • For Convert to Image operation:

    • The output JSON contains an array of objects under the specified output property name.
    • Each object represents one converted page with details: page number, width, height, file size, image format, and the name of the binary property holding the image.
    • The binary data contains base64-encoded image files keyed by generated binary property names (e.g., image_page_1).
    • Images are provided in the chosen format (PNG or JPEG).

Dependencies

  • Requires the following npm packages bundled with the node:
    • A PDF parsing library for text extraction.
    • A PDF-to-image conversion library relying on GraphicsMagick and Ghostscript system dependencies.
  • For URL source, requires network access to fetch PDF files.
  • When converting PDFs to images, the environment must have GraphicsMagick and Ghostscript installed:
    • On Docker/Ubuntu: apt-get install -y graphicsmagick ghostscript
    • On Alpine Linux: apk add graphicsmagick ghostscript

Troubleshooting

  • Common issues:

    • Invalid or empty PDF file input.
    • Incorrect binary property name or missing binary data.
    • Invalid or unreachable URL when using URL source.
    • Missing system dependencies (GraphicsMagick, Ghostscript) for image conversion.
    • Unsupported or corrupted PDF files.

  • Error messages and resolutions:

    • "URL is required when source is set to URL": Provide a valid URL.
    • "Invalid URL format": Check URL syntax.
    • "Failed to fetch PDF from URL": Verify network connectivity and URL accessibility.
    • "File does not appear to be a valid PDF": Confirm the input file is a proper PDF.
    • Errors mentioning missing GraphicsMagick or Ghostscript: Install these tools in your n8n environment as described above.
    • Conversion errors related to system delegates indicate missing or misconfigured system dependencies.

Links and References

Discussion