> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Parsera

> Parsera provides AI-powered web extraction, content parsing, and reusable scraper agents through its developer API.

![Parsera logo](https://mintcdn.com/composio-preview/gqjBKmmJCINafaiK/images/toolkits/parsera.svg?fit=max\&auto=format\&n=gqjBKmmJCINafaiK\&q=85\&s=dac2b2a474a6f9f67b93b06a65af9256)

* **Category:** ai web scraping
* **Auth:** API\_KEY
* **Composio-managed OAuth available?** N/A
* **Tools:** 15
* **Triggers:** 0
* **Slug:** `PARSERA`
* **Version:** 20261101\_00

## Tools

> [accordion] Create Scraper
>
> **Slug:** `PARSERA_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.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Agent
>
> **Slug:** `PARSERA_DELETE_AGENT`
>
> Delete an existing legacy Parsera agent by name.
>
> #### Input Parameters
>
> **name** `string` *required*
>
> Name of the agent to be removed. This should match the name used when the agent was created.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Scraper
>
> **Slug:** `PARSERA_DELETE_SCRAPER`
>
> Delete an existing scraper by ID using Parsera's legacy scraper deletion endpoint.
>
> #### Input Parameters
>
> **scraper\_id** `string` *required*
>
> Scraper ID returned by PARSERA\_CREATE\_SCRAPER. Only scrapers created by that tool can be deleted.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Extract Data from Webpage
>
> **Slug:** `PARSERA_EXTRACT_DATA`
>
> 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.
>
> #### Input Parameters
>
> **url** `string` *required*
>
> The webpage URL to extract data from.
>
> **mode** `string ("standard" | "precision")`
>
> Extraction mode. 'standard' mode performs efficient extraction. 'precision' mode minimizes page reduction to detect data hidden in HTML tags but uses more credits.
>
> **prompt** `string`
>
> Additional scraping instructions to guide the extraction process.
>
> **cookies** `array`
>
> Authentication or session cookies for extraction. Each cookie should be a dictionary with cookie properties.
>
> **attributes** `object` *required*
>
> 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.
>
> **proxy\_country** `string`
>
> Case-sensitive Parsera proxy-country identifier. Call PARSERA\_LIST\_PROXY\_COUNTRIES to retrieve supported values.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Extract Markdown
>
> **Slug:** `PARSERA_EXTRACT_MARKDOWN`
>
> Extract markdown from exactly one uploaded file or webpage URL.
>
> #### Input Parameters
>
> **url** `string`
>
> URL of the page to extract markdown from. Provide exactly one of file or url.
>
> **file** `object`
>
> File to upload for markdown extraction. Provide exactly one of file or url.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Scraper Run Status
>
> **Slug:** `PARSERA_GET_SCRAPER_RUN_STATUS`
>
> Return the current state and available results for a scraper run by run ID, including a synchronous run continued asynchronously.
>
> #### Input Parameters
>
> **run\_id** `string` *required*
>
> Run ID returned by PARSERA\_RUN\_SCRAPER\_ASYNC.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Health Check
>
> **Slug:** `PARSERA_HEALTH_CHECK`
>
> Check Parsera's readiness endpoint and report healthy when it returns HTTP 200 with valid JSON.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Agents
>
> **Slug:** `PARSERA_LIST_AGENTS`
>
> List the authenticated user's agents from Parsera's legacy agent service.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List LLM Specifications
>
> **Slug:** `PARSERA_LIST_LLM_SPECS`
>
> List the LLM models Parsera supports, including their capabilities and pricing metadata.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Proxy Countries
>
> **Slug:** `PARSERA_LIST_PROXY_COUNTRIES`
>
> List the case-sensitive proxy-country identifiers accepted by Parsera scraping tools.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Scrapers
>
> **Slug:** `PARSERA_LIST_SCRAPERS`
>
> List scraper IDs and names for the authenticated account, including extractor and agentic scrapers.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Parse Content
>
> **Slug:** `PARSERA_PARSE_CONTENT`
>
> Extract structured data from supplied HTML or text without fetching a webpage.
>
> #### Input Parameters
>
> **mode** `string ("standard" | "precision" | "code")`
>
> Extraction mode selection. 'standard' for regular extraction, 'precision' for enhanced data discovery in HTML, 'code' for code extraction.
>
> **prompt** `string`
>
> Additional instructions or context for the extraction process.
>
> **content** `string` *required*
>
> Raw HTML or plain text content to parse and extract data from.
>
> **max\_pages** `integer`
>
> Maximum number of pages to parse when pagination is enabled.
>
> **attributes** `string` *required*
>
> 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\_pagination** `boolean`
>
> Enable multi-page parsing. When enabled, the parser will attempt to extract data across multiple pages.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Run Legacy Agent
>
> **Slug:** `PARSERA_RUN_LEGACY_AGENT`
>
> Run a custom or pre-built agent from Parsera's legacy agent service against one webpage and return structured records. Prefix pre-built agent names with public/.
>
> #### Input Parameters
>
> **url** `string` *required*
>
> The webpage URL where data extraction will occur.
>
> **name** `string` *required*
>
> Identifier for the agent/scraper to use. For pre-built agents, prefix with 'public/' (e.g., 'public/hackernews', 'public/crunchbase').
>
> **cookies** `array`
>
> Authentication or session cookies for the request. Each cookie should be a dictionary with 'name' and 'value' fields.
>
> **proxy\_country** `string`
>
> Geographic location for proxy routing (e.g., 'UnitedStates', 'UnitedKingdom'). Default: 'UnitedStates'.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Run Scraper Asynchronously
>
> **Slug:** `PARSERA_RUN_SCRAPER_ASYNC`
>
> Queue an existing extractor or agentic scraper and return a run ID immediately for later status checks. Use PARSERA\_LIST\_SCRAPERS to find a template ID and PARSERA\_GET\_SCRAPER\_RUN\_STATUS to retrieve results.
>
> #### Input Parameters
>
> **url** `string`
>
> Optional target URL or URLs. Extractor scrapers accept up to 100 URLs; agentic scrapers accept one.
>
> **cookies** `array`
>
> Optional browser cookie objects for extractor scrapers. Each object is passed to Parsera unchanged.
>
> **max\_pages** `integer`
>
> Optional maximum number of target-site pages to scrape. This controls extraction and is not REST API pagination.
>
> **parameters** `object`
>
> Optional values for an agentic scraper's parameters\_schema.
>
> **template\_id** `string` *required*
>
> ID of the existing extractor or agentic scraper to run; obtain it from PARSERA\_LIST\_SCRAPERS.
>
> **callback\_url** `string`
>
> Optional HTTPS URL Parsera should notify when the run finishes.
>
> **proxy\_country** `string`
>
> Optional case-sensitive Parsera proxy-country identifier. It is ignored for agentic scrapers.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Run Scraper Synchronously
>
> **Slug:** `PARSERA_RUN_SCRAPER_SYNC`
>
> Run an existing Parsera template or legacy scraper synchronously. Returns extracted records when complete, or a run ID to poll when Parsera continues a long request asynchronously. Use PARSERA\_RUN\_SCRAPER\_ASYNC to queue work immediately.
>
> #### Input Parameters
>
> **url** `string`
>
> 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.
>
> **cookies** `array`
>
> Browser cookies to include with the request. Useful for authenticated sessions or maintaining state.
>
> **template\_id** `string` *required*
>
> 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.
>
> **proxy\_country** `string`
>
> Case-sensitive Parsera proxy-country identifier. Call PARSERA\_LIST\_PROXY\_COUNTRIES to retrieve supported values.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not
