run_scraper
Run Scraper
Run a previously created reusable scraper on one or more URLs. Returns structured data extracted according to the scraper's configured attributes. Use this after creating a scraper with the **Create Scraper** tool.
run_scraper
Run a previously created reusable scraper on one or more URLs. Returns structured data extracted according to the scraper's configured attributes. Use this after creating a scraper with the **Create Scraper** tool.
create_scraper
Create a new reusable scraper and generate its extraction code in one step. Provide a sample URL (or raw content) and the attributes to extract. The scraper can then be run on multiple URLs with the **Run Scraper** tool. Ideal for scenarios where the same type of data needs to be extracted from many pages with a similar structure.
extract_markdown
Convert any web page into markdown format by providing its URL. Returns the full page content as clean markdown text. Supports proxy configuration for geo-restricted pages and cookies for authenticated pages.
extract_data
Extract structured data from any web page using AI. Provide a URL and describe the data you want using either a natural-language prompt or a list of named attributes with descriptions. Supports **precision mode** for extracting data hidden in HTML tags and **proxy configuration** for geo-restricted pages.
parse_content
Extract structured data from raw HTML or text content you already have, without fetching from a URL. Provide the content directly along with a prompt or attributes describing the data to extract. Useful when you have pre-fetched HTML or text and want AI-powered data extraction from it.
list_scrapers
List all reusable scrapers in your Parsera account. Returns the ID and name of each scraper.
delete_scraper
Delete a reusable scraper from your Parsera account by its ID. Only scrapers created via the API can be deleted; legacy scrapers cannot be removed this way.
Extract structured data from web pages using AI-powered natural-language descriptions. Scrape any URL by specifying desired attributes with names, descriptions, and types. Parse raw HTML or text content directly. Convert web pages to markdown. Create reusable scrapers that can be run across multiple URLs at once. Generate deterministic Python scraping code for faster, cost-effective extraction. Supports proxy configuration for geo-specific access, precision mode for hidden HTML data, and custom cookies for authenticated pages.
Common questions about connecting Parsera to AI agents with Metorial.