NagentArtefacts
Dev & Technology
Enterprise and White Glove
Company
Parsera connects to a Nagent workspace with an API key. Once it is connected, agents can call 13 Parsera actions, such as "Create Scraper", "Get LLM Specifications" and "Get Proxy Countries". Nothing is enabled on connect: each action is allowed one at a time, and an action with side effects runs or waits for a person according to the agent's level.
Every operation an agent can call against Parsera, with input parameters and output schema.
PARSERA_CREATE_SCRAPERTool 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.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PARSERA_DELETE_SCRAPERTool 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.
Input parameters
Unique identifier of the scraper to delete. Only scrapers created through the /v1/scrapers/new endpoint can be deleted.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PARSERA_EXTRACT_DATATool 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.
Input parameters
The webpage URL to extract data from.
Extraction mode. 'standard' mode performs efficient extraction. 'precision' mode minimizes page reduction to detect data hidden in HTML tags but uses more credits.
Additional scraping instructions to guide the extraction process.
Authentication or session cookies for extraction. Each cookie should be a dictionary with cookie properties.
Map of field names and descriptions to extract. Supports two formats: 1) Simple format: {'field_name': 'description'}, 2) Typed format: {'field_name': {'description': '...', 'type': 'string\\ | integer\\ | number\\ | bool\\ | list\\ | object\\ | any'}}. NOTE: You cannot mix both formats in a single request - use either all simple strings or all typed objects.
Geographic location for proxy routing. Recommended to set as pages may be unavailable from certain locations. Use GET /v1/proxy-countries to retrieve supported countries.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PARSERA_EXTRACT_MARKDOWNTool to extract markdown content from a file or URL.
Input parameters
URL of the page to extract markdown from.
File to upload for markdown extraction.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PARSERA_GET_LLM_SPECSTool to retrieve standardized LLM capabilities and pricing specifications. Use to get up-to-date information about models from various providers.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PARSERA_GET_PROXY_COUNTRIESTool to retrieve the list of available proxy countries for web scraping requests. Use when you need to know which countries are supported for proxy-based scraping.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PARSERA_HEALTH_CHECKTool to verify API availability and operational status. Use to check if the Parsera service is accessible before making other API calls.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PARSERA_LIST_AGENTSTool to retrieve all available agents for the authenticated user. Use when you need to list agents that can be used for scraping tasks.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PARSERA_LIST_SCRAPERSTool to list all templates and old scrapers for the authenticated user. Use when you need to retrieve available scraper configurations.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PARSERA_PARSE_CONTENT2Tool to extract structured data from raw HTML or text content using AI with advanced options. Use when you have content already loaded and need to extract specific fields with pagination or different extraction modes.
Input parameters
Extraction mode selection. 'standard' for regular extraction, 'precision' for enhanced data discovery in HTML, 'code' for code extraction.
Additional instructions or context for the extraction process.
Raw HTML or plain text content to parse and extract data from.
Maximum number of pages to parse when pagination is enabled.
Field mapping defining what data to extract. Can be formatted as: (1) Object with name-description pairs: {'title': 'News title'}, (2) Object with detailed schema: {'title': {'description': 'Article title', 'type': 'string'}}, or (3) Array of Attribute objects with name, description, and type fields. Supported types: string, integer, number, bool, list, object, any, image. Default type: any.
Enable multi-page parsing. When enabled, the parser will attempt to extract data across multiple pages.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PARSERA_REMOVE_AGENTTool to delete an existing agent by name. Use when you need to remove a previously created agent from the Parsera platform.
Input parameters
Name of the agent to be removed. This should match the name used when the agent was created.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PARSERA_RUN_SCRAPER_TEMPLATETool to run a scraper template on a specified URL with optional proxy and cookies. Use when you need to execute a pre-defined scraper template to extract structured data from web pages.
Input parameters
Target URL(s) for extraction. Can be a single URL string, an array of URL strings, or null. When multiple URLs are provided, the scraper will process each URL independently.
Browser cookies to include with the request. Useful for authenticated sessions or maintaining state.
Identifier for the template or scraper to execute. Template IDs prefixed with 'scraper:' route to the legacy scrapers API, while others execute as template extractions.
Country code for proxy routing during requests. Use to route requests through a proxy server in a specific country. See GET /v1/proxy-countries for available country codes.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
PARSERA_SCRAPE_WITH_AGENTTool to run a previously generated scraper agent on a specific URL to extract structured data. Use when you need to apply an existing scraper to a webpage.
Input parameters
The webpage URL where data extraction will occur.
Identifier for the agent/scraper to use. For pre-built agents, prefix with 'public/' (e.g., 'public/hackernews', 'public/crunchbase').
Authentication or session cookies for the request. Each cookie should be a dictionary with 'name' and 'value' fields.
Geographic location for proxy routing (e.g., 'UnitedStates', 'UnitedKingdom'). Default: 'UnitedStates'.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
Agents can call 13 Parsera actions on Nagent, including "Create Scraper", "Get LLM Specifications" and "Get Proxy Countries". Create Scraper: Create a new empty scraper for your account. Each action is listed on this page with its input parameters and its output.
Parsera connects with an API key, under your workspace's own connection. Nothing is enabled on connect: each action is allowed one at a time and can be scoped to the agents that need it.
It returns data, error and successful.