How to use the Webpage Heading Outline Extractor.
A heading outline should preserve the page's hierarchy and exact labels. Do not infer a heading from visual size alone without noting the difference.
Make the workflow fit your task.
Collect actual heading elements in document order, keeping their level and exact text. Present the hierarchy and flag skipped levels for review without silently renumbering them. State whether hidden sections, dialogs or unloaded content were included.
- What you provide
- Readable article or page.
- What you get
- Navigable heading outline preserving hierarchy.
See the input and the result.
Illustrative input and output · a teaching example, not a live WebAct run
Example input
Page has H1 Reports, H2 Create, H2 Export and H3 CSV.
Completed example
Reports → Create; Reports → Export → CSV.
Load this input into the prompt, then copy it to WebAct to try the task. Your result may differ from the illustration.
Decisions and troubleshooting.
Should large bold text be inserted into the semantic heading outline?
Only if it is a heading element or explicitly identified as a visual heading in a separate finding.
Why is a section missing from the outline although its title is visible?
The title may use ordinary text styling rather than heading markup. Inspect its element and report that distinction.
Try it with your own source.
Replace the example with your material in the task prompt. Keep the requirements you need, then copy the task into WebAct.
Customize and copy the task ↑