Data Extraction Category
Get HTML from Page
Retrieves the entire HTML of the page.
This output can be passed to Prepare Content for AI.
Best practice: Always connect this task to Prepare Content for AI to reduce AI token costs.
Prepare Content for AI
Processes HTML into optimized formats.
Outputs include:
- Clean markdown
- Reduced content for AI
- Automation interaction map (all selectors on the page)
Extract Text from HTML
Extracts text content from HTML.
Requires a selector.
Get Element from Page
Retrieves a specific element including its HTML.
Requires a selector.
Extract Number from Text (Deprecated)
Extracts a single number from text.
Note: This is deprecated. AI-based extraction is recommended.
Extract Data with AI
Uses AI to extract structured data from raw input.
Supports:
- Text
- HTML
- Markdown
Outputs clean, structured data.
Modify Data with AI
Similar to Extract Data with AI, but operates on already clean data and modifies it.
Last updated on