NAiOS IconNAiOS Logo
Contacto
Volver al catálogo

Scrapegraph Ai

scrapegraph_ai

ScrapeGraphAI is an AI-powered web scraping API that enables developers to extract structured data from any website using natural language prompts. Website https://scrapegraphai.com

AI Web ScrapingDeveloper ToolsWeb del proveedor
Acciones
10
Triggers
0
Autenticación
—
OAuth gestionado
No
Información técnica: el detalle de parámetros, schemas y triggers de esta página está pensado para equipos de integración. Si solo necesitas saber si tu herramienta favorita está disponible, basta con ver la lista de acciones.

Acciones disponibles (10)

Cada acción es una operación que el agente puede ejecutar contra este conector. Haz clic en una acción para ver sus parámetros.

Get CreditsSCRAPEGRAPH_AI_GET_CREDITSAcción

Retrieve remaining and used credits for your scrapegraphai account.

Parámetros de entrada

Sin parámetros.

Parámetros de salida

  • dataobjectObligatorio

    Data from the action execution

  • errorstring

    Error if any occurred during the execution of the action

  • successfulbooleanObligatorio

    Whether or not the action execution was successful or not

Convert Webpage to MarkdownSCRAPEGRAPH_AI_MARKDOWNIFYAcción

Tool to convert a specified webpage into clean, formatted markdown.

Parámetros de entrada

  • waitboolean

    If true, wait for job completion and return full results instead of request_id.

  • website_urlstringObligatorio

    The URL of the webpage to convert to Markdown.

Parámetros de salida

  • dataobjectObligatorio

    Data from the action execution

  • errorstring

    Error if any occurred during the execution of the action

  • successfulbooleanObligatorio

    Whether or not the action execution was successful or not

Markdownify StatusSCRAPEGRAPH_AI_MARKDOWNIFY_STATUSAcción

Check status and results of webpage-to-markdown conversion jobs.

Parámetros de entrada

  • request_idstringObligatorio

    The unique identifier of the Markdownify request

Parámetros de salida

  • dataobjectObligatorio

    Data from the action execution

  • errorstring

    Error if any occurred during the execution of the action

  • successfulbooleanObligatorio

    Whether or not the action execution was successful or not

Search ScraperSCRAPEGRAPH_AI_SEARCH_SCRAPERAcción

Perform ai-powered web searches with structured, parsed results.

Parámetros de entrada

  • parseboolean

    If true, parses individual result pages for additional content.

  • querystringObligatorio

    The search query to execute.

  • languagestring

    ISO 639-1 language code for the search (e.g., 'en').

  • num_resultsinteger

    Maximum number of search results to return. Must be ≥ 1.

Parámetros de salida

  • dataobjectObligatorio

    Data from the action execution

  • errorstring

    Error if any occurred during the execution of the action

  • successfulbooleanObligatorio

    Whether or not the action execution was successful or not

Check SearchScraper StatusSCRAPEGRAPH_AI_SEARCH_SCRAPER_STATUSAcción

Check the status and results of an asynchronous searchscraper job.

Parámetros de entrada

  • request_idstringObligatorio

    The unique identifier of the SearchScraper request

Parámetros de salida

  • dataobjectObligatorio

    Data from the action execution

  • errorstring

    Error if any occurred during the execution of the action

  • successfulbooleanObligatorio

    Whether or not the action execution was successful or not

Start Smart CrawlerSCRAPEGRAPH_AI_SMART_CRAWLER_STARTAcción

Start ai-powered web crawling with structured data extraction across multiple pages.

Parámetros de entrada

  • urlstringObligatorio

    Starting URL for the crawl.

  • waitboolean

    If true, wait for job completion and return full results instead of task_id.

  • depthinteger

    How many link levels to follow from the start URL; default is 1.

  • rulesobject

    Custom crawl rules, e.g., include/exclude URL patterns.

  • promptstringObligatorio

    Instructions for what data to extract during the crawl.

  • headersobject

    Custom HTTP headers to include in crawl requests.

  • sitemapboolean

    Whether to use sitemap.xml for discovery; default is false.

  • max_pagesinteger

    Maximum number of pages to crawl; default is 20.

  • website_htmlstring

    Raw HTML content to seed the crawl; overrides `url` if provided (max 2 MB).

  • output_schemaobject

    Optional Pydantic or Zod schema for structured output.

  • number_of_scrollsinteger

    Number of infinite scroll actions per page.

Parámetros de salida

  • dataobjectObligatorio

    Data from the action execution

  • errorstring

    Error if any occurred during the execution of the action

  • successfulbooleanObligatorio

    Whether or not the action execution was successful or not

SmartCrawler StatusSCRAPEGRAPH_AI_SMART_CRAWLER_STATUSAcción

Check status and results of smartcrawler web crawling jobs.

Parámetros de entrada

  • task_idstringObligatorio

    The unique identifier of the SmartCrawler task

Parámetros de salida

  • dataobjectObligatorio

    Data from the action execution

  • errorstring

    Error if any occurred during the execution of the action

  • successfulbooleanObligatorio

    Whether or not the action execution was successful or not

Start Smart ScraperSCRAPEGRAPH_AI_SMART_SCRAPER_STARTAcción

Start ai-powered web scraping with natural language extraction prompts.

Parámetros de entrada

  • waitboolean

    If true, wait for job completion and return full results instead of request_id.

  • headersobject

    Additional HTTP headers to include in the scraping request.

  • user_promptstringObligatorio

    Natural language description of the information to extract.

  • website_urlstring

    URL of the webpage to scrape. Required if `website_html` is not provided.

  • website_htmlstring

    Raw HTML content of the webpage. Required if `website_url` is not provided.

  • output_schemaobject

    Optional JSON Schema to structure the output.

Parámetros de salida

  • dataobjectObligatorio

    Data from the action execution

  • errorstring

    Error if any occurred during the execution of the action

  • successfulbooleanObligatorio

    Whether or not the action execution was successful or not

SmartScraper StatusSCRAPEGRAPH_AI_SMART_SCRAPER_STATUSAcción

Check status and results of smartscraper web scraping jobs.

Parámetros de entrada

  • request_idstringObligatorio

    The unique identifier of the SmartScraper request

Parámetros de salida

  • dataobjectObligatorio

    Data from the action execution

  • errorstring

    Error if any occurred during the execution of the action

  • successfulbooleanObligatorio

    Whether or not the action execution was successful or not

Submit FeedbackSCRAPEGRAPH_AI_SUBMIT_FEEDBACKAcción

Submit feedback and ratings for completed scrapegraphai requests.

Parámetros de entrada

  • ratingintegerObligatorio

    Star rating from 0 (lowest) to 5 (highest)

  • request_idstringObligatorio

    UUID of the request/session this feedback is for

  • feedback_textstring

    Optional comments about the request

Parámetros de salida

  • dataobjectObligatorio

    Data from the action execution

  • errorstring

    Error if any occurred during the execution of the action

  • successfulbooleanObligatorio

    Whether or not the action execution was successful or not