Turn any url into clean data
prompt
to the endpoint. The llm chooses the structure of the data.
jsonOptions
object accepts the following parameters:
schema
: The schema to use for the extraction.systemPrompt
: The system prompt to use for the extraction.prompt
: The prompt to use for the extraction without a schema.wait
action before/after executing other actions to give enough time for the page to load.
location
object in your request body with the following properties:
country
: ISO 3166-1 alpha-2 country code (e.g., ‘US’, ‘AU’, ‘DE’, ‘JP’). Defaults to ‘US’.languages
: An array of preferred languages and locales for the request in order of priority. Defaults to the language of the specified location./crawl
endpoint works. It submits a batch scrape job and returns a job ID to check the status of the batch scrape.
The sdk provides 2 methods, synchronous and asynchronous. The synchronous method will return the results of the batch scrape job, while the asynchronous method will return a job ID that you can use to check the status of the batch scrape.
/batch/scrape/{id}
endpoint. This endpoint is meant to be used while the job is still running or right after it has completed as batch scrape jobs expire after 24 hours.
/scrape
endpoint to apply intelligent navigation before scraping the final content.
Activating FIRE-1 is straightforward. Simply include an agent
object in your scrape or extract API request:
prompt
field is required for scrape requests, instructing FIRE-1 precisely how to interact with the webpage.