Parsera is a lightweight Python library for scraping websites using large language models (LLMs).
Tools
Create Scraper
Tool to create a new empty scraper for your account. Returns a scraper_id that can be used with the generate endpoint to generate scraping code.
Delete Scraper
Tool to delete an existing scraper by its ID. Use when you need to remove a scraper that was created through the /v1/scrapers/new endpoint.
Extract Data From Webpage
Tool to perform LLM-powered data extraction from a live webpage URL with specified attributes. Use when you need to extract structured data from web pages based on field descriptions.
Extract Data From Url (array Attributes)
Tool to extract data from a URL using LLM-powered data extraction with array-based attributes. Use for one-time data extraction from unstructured data requiring specific field definitions.
Extract Markdown
Tool to extract markdown content from a file or URL.
Extract Markdown V2
Tool to extract markdown content from a URL. Converts the webpage content to markdown format. Use when you need to get a clean markdown representation of a webpage.