Parsera is a lightweight Python library for scraping websites using large language models (LLMs).
Parsera is a lightweight Python library for scraping websites using large language models (LLMs). On Nagent, Parsera is exposed as a fully-configurable ai web scraping integration that any agent can call — 13 actions, and API key authentication. No code is required to wire Parsera into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use Parsera to automate the kinds of tasks ai web scraping teams previously handled manually. Concrete examples — each one is a single agent step in Nagent — include:
Every action and trigger is paired with a structured input/output schema (visible in the sections below), so when you wire Parsera into Helix — our agentic agent builder — the editor knows exactly what each step expects and produces. Configure once, deploy anywhere across your Nagent agents.
Every operation an agent can call against Parsera, with input parameters and output schema. Drop these into any step of an agent built in Helix.
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
No publicly available marketplace agent is found using this tool yet. There are 94 agents privately built on Nagent that already use Parsera.
Build on Nagent
Connect Parsera to any Nagent agent in minutes — no API key management, no boilerplate. Just configure and deploy.
The five questions agent builders ask before adopting a new integration.
Open the External Integrations panel inside Nagent (app.nagent.ai/externalIntegration), find Parsera, and click "Connect Now." You'll authenticate with an API key — Nagent handles credential storage and refresh automatically. Once connected, Parsera is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once Parsera is connected, you configure its 13 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop Parsera steps into any workflow visually. Pick an action (e.g., one of those listed above), fill in the inputs (Helix knows the required vs. optional schema for each parameter), and connect it to upstream/downstream steps. Triggers run as the entry point of an agent, so when a Parsera event fires, the agent kicks off automatically.
Every Parsera action and trigger ships with a fully-typed schema — input parameters with name, type, required flag, and description, plus the output payload shape. The schemas are documented in the sections above. Helix uses these schemas to validate your configuration at build time and to type-check the data flowing between steps.
Yes. While Parsera ships with 13 pre-built ai web scraping actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching Parsera together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build Parsera-based workflows tailored to your business.