Extraction Nodes
Use extraction nodes to capture page content and transform it into structured inputs for AI, conditions, spreadsheets, and integrations.
Node List
| Node | Required Parameters | Main Output |
|---|---|---|
| Get HTML from page | Web page | Html |
| Get element from page | Selector | Element |
| Extract text from HTML | Html, Selector | Extracted text |
| Extract text from Element | Element, Selector | Extracted text |
| Extract Number from Text | Text | Extracted Number |
Input / Output Example
- Input chain:
Get HTML from page -> Extract text from HTML -> Extract Number from Text - Output example:
"$1,249.00"from text extraction ->1249from number extraction.
Common Errors
- Selector not found in current page state.
- HTML/Element output not passed correctly to the next extraction node.
- Number extraction against non-numeric text format.
Retry Tips
- Precede extraction with
Wait for Elementto avoid extracting before content appears. - Use narrower selectors for the exact content block you need.
- Normalize noisy text before numeric extraction where possible.
When you plan to send extracted content to AI nodes, use extraction nodes to isolate only the relevant section first. This improves output quality and consistency.
title: Extraction Nodes description: Reference for Xenbox extraction nodes used to read HTML, elements, text, and numeric values.
Extraction Nodes
Use extraction nodes to capture page content and transform it into structured inputs for AI, conditions, spreadsheets, and integrations.
Node List
| Node | Required Parameters | Main Output |
|---|---|---|
| Get HTML from page | Web page | Html |
| Get element from page | Selector | Element |
| Extract text from HTML | Html, Selector | Extracted text |
| Extract text from Element | Element, Selector | Extracted text |
| Extract Number from Text | Text | Extracted Number |
Input / Output Example
- Input chain:
Get HTML from page -> Extract text from HTML -> Extract Number from Text - Output example:
"$1,249.00"from text extraction ->1249from number extraction.
Common Errors
- Selector not found in current page state.
- HTML/Element output not passed correctly to the next extraction node.
- Number extraction against non-numeric text format.
Retry Tips
- Precede extraction with
Wait for Elementto avoid extracting before content appears. - Use narrower selectors for the exact content block you need.
- Normalize noisy text before numeric extraction where possible.
When you plan to send extracted content to AI nodes, use extraction nodes to isolate only the relevant section first. This improves output quality and consistency.
Last updated on