extract
Read-onlyIdempotent
Read repeated webpage structures like product cards or search results and return each as a structured record using CSS selectors.
Instructions
Read repeated non-tabular structures — product cards, list items, search results — as one record per item: item_selector matches the repeating block, fields map output names to selectors relative to it. Read-only, deterministic, parsed server-side from the main-document HTML.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| fields | Yes | field name → {selector, attr} | |
| format | No | lines is compact; json keeps one object per record | lines |
| tab_id | No | Target tab; omitted = last tab navigated in this session, else the active one | |
| save_to | No | Absolute path: write the records as JSON there and return the path instead of the content | |
| max_items | No | Cap on records returned, in document order | |
| max_length | No | Max output chars | |
| item_selector | Yes | CSS selector matching each item |