Playwright selector to scope the scrape to. Only content inside this selector will be scraped.
scrape_linksboolean
Whether to scrape links from the page. Links are scraped by default.
scrape_imagesboolean
Whether to scrape images from the page. Images are scraped by default.
ignored_tagsstring[] nullable
HTML tags to ignore from the page
only_main_contentboolean
Whether to only scrape the main content of the page. If True, navbars, footers, etc. are excluded.
only_imagesboolean
Whether to only scrape images from the page. If True, the page content is excluded.
{"stackTrail":"components:schemas:ScrapeFromHtmlRequest:properties:response_format:anyOf","oasType":"schema","type":"unknown","title":"Response Format","description":"The response format to use for the scrape. You can use a Pydantic model or a JSON Schema dict (cf. https://docs.pydantic.dev/latest/concepts/json_schema/#generating-json-schema.)","nullable":true}
instructionsstring
User description as to what needs to be scraped
use_link_placeholdersboolean
Whether to use link/image placeholders to reduce the number of tokens in the prompt and hallucinations. However this is an experimental feature and might not work as expected.