Skip to main content
If instructions is null then the whole page will be scraped. Otherwise, only the data that matches the instructions will be scraped. Instructions should be given as natural language, e.g. ‘Extract the title and the price of the product’. Example: 
session.execute(type="scrape", instructions="Extract product title and price")
session.execute(type="scrape", only_main_content=True)
session.execute(type="scrape")  # Scrape entire page
session.execute(type="scrape", only_images=True)  # Scrape only images
session.execute(type="scrape", response_format={"type": "object", "properties": {...}})  # With JSON schema

​
Fields

​
type
Literal['scrape']
default:"scrape"
​
category
str
default:"Special Browser Actions"
​
description
str
​
instructions
UnionType[str, None]
​
only_main_content
bool
default:"True"
Whether to only scrape the main content of the page. If True, navbars, footers, etc. are excluded.
​
selector
UnionType[str, None]
Playwright selector to scope the scrape to. Only content inside this selector will be scraped.
​
only_images
bool
default:"False"
Whether to only scrape images from the page. If True, the page content is excluded.
​
scrape_links
bool
default:"True"
Whether to scrape links from the page. Links are scraped by default.
​
scrape_images
bool
default:"False"
Whether to scrape images from the page.
​
ignored_tags
UnionType[list[str], None]
HTML tags to ignore from the page.
​
response_format
UnionType[Dict[str, Any], None]
JSON schema dict for structured output. Agent can provide a schema to extract structured data.

​
Module

notte_core.actions.actions