Pagination Extraction
paginateExtract data from multiple pages in one call. Handles click, scroll, and URL pagination with auto-detection of next buttons. Returns content and metadata from each page.
Instructions
Extract data across multiple pages in a single call. Handles click-next, infinite scroll, and URL-pattern pagination. Auto-detects 'next' buttons when nextSelector='auto'. Returns extracted content from each page plus metadata. Replaces 3-4 tool calls per page with one invocation. Cap: 50 pages, 100K total chars.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| sessionId | Yes | Session ID. | |
| extractType | No | What to extract from each page. | text |
| extractTarget | No | CSS selector to scope extraction to a specific container. | |
| extractJs | No | JavaScript expression for extractType='js'. | |
| nextSelector | No | CSS selector for the next button, or 'auto' to detect automatically. | auto |
| paginationType | No | Pagination strategy: click (next button), scroll (infinite scroll), url (URL pattern). | click |
| urlPattern | No | URL pattern with {page} placeholder for paginationType='url'. | |
| maxPages | No | Maximum pages to extract. Default: 10. | |
| delayMs | No | Delay between pages in ms. Default: 1000. | |
| maxCharsPerPage | No | Max characters per page extraction. Default: 5000. | |
| stopWhen | No | Stop condition. Default: auto (all heuristics). | auto |