You can access the Website Content Crawler for AI and RAG programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.

Python

JavaScript

CLI

OpenAPI

HTTP

MCP

{
  "openapi": "3.0.1",
  "info": {
    "version": "0.0",
    "x-build-id": "uu8Xq3Gr5urf6XGUl"
  },
  "servers": [
    {
      "url": "https://api.apify.com/v2"
    }
  ],
  "paths": {
    "/acts/tropical_quince~website-content-crawler-rag/run-sync-get-dataset-items": {
      "post": {
        "operationId": "run-sync-get-dataset-items-tropical_quince-website-content-crawler-rag",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    },
    "/acts/tropical_quince~website-content-crawler-rag/runs": {
      "post": {
        "operationId": "runs-sync-tropical_quince-website-content-crawler-rag",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor and returns information about the initiated run in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/runsResponseSchema"
                }
              }
            }
          }
        }
      }
    },
    "/acts/tropical_quince~website-content-crawler-rag/run-sync": {
      "post": {
        "operationId": "run-sync-tropical_quince-website-content-crawler-rag",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    }
  },
  "components": {
    "schemas": {
      "inputSchema": {
        "type": "object",
        "properties": {
          "startUrls": {
            "title": "Start URLs",
            "type": "array",
            "description": "List of URLs to start crawling from. The crawler will follow links on these pages.",
            "items": {
              "type": "string"
            },
            "default": [
              "https://docs.apify.com"
            ]
          },
          "maxPages": {
            "title": "Max Pages",
            "minimum": 1,
            "maximum": 10000,
            "type": "integer",
            "description": "Maximum number of pages to crawl. Set lower for focused extraction or higher for full site coverage.",
            "default": 100
          },
          "outputFormat": {
            "title": "Output Format",
            "enum": [
              "markdown",
              "text"
            ],
            "type": "string",
            "description": "Format for extracted content. Markdown preserves structure, plain text strips all formatting.",
            "default": "markdown"
          },
          "chunkSize": {
            "title": "Chunk Size (characters)",
            "minimum": 100,
            "maximum": 10000,
            "type": "integer",
            "description": "Size of content chunks in characters. Smaller chunks work better for embedding models, larger for context windows.",
            "default": 1000
          },
          "includeLinks": {
            "title": "Include Links in Output",
            "type": "boolean",
            "description": "Whether to preserve hyperlinks in the extracted content.",
            "default": true
          },
          "stripNavigation": {
            "title": "Strip Navigation & Footers",
            "type": "boolean",
            "description": "Remove navigation menus, headers, footers, and sidebars from extracted content.",
            "default": true
          },
          "useResidentialProxy": {
            "title": "Use Residential Proxy",
            "type": "boolean",
            "description": "Enable residential proxy for sites that block datacenter IPs.",
            "default": false
          }
        }
      },
      "runsResponseSchema": {
        "type": "object",
        "properties": {
          "data": {
            "type": "object",
            "properties": {
              "id": {
                "type": "string"
              },
              "actId": {
                "type": "string"
              },
              "userId": {
                "type": "string"
              },
              "startedAt": {
                "type": "string",
                "format": "date-time",
                "example": "2025-01-08T00:00:00.000Z"
              },
              "finishedAt": {
                "type": "string",
                "format": "date-time",
                "example": "2025-01-08T00:00:00.000Z"
              },
              "status": {
                "type": "string",
                "example": "READY"
              },
              "meta": {
                "type": "object",
                "properties": {
                  "origin": {
                    "type": "string",
                    "example": "API"
                  },
                  "userAgent": {
                    "type": "string"
                  }
                }
              },
              "stats": {
                "type": "object",
                "properties": {
                  "inputBodyLen": {
                    "type": "integer",
                    "example": 2000
                  },
                  "rebootCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "restartCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "resurrectCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "computeUnits": {
                    "type": "integer",
                    "example": 0
                  }
                }
              },
              "options": {
                "type": "object",
                "properties": {
                  "build": {
                    "type": "string",
                    "example": "latest"
                  },
                  "timeoutSecs": {
                    "type": "integer",
                    "example": 300
                  },
                  "memoryMbytes": {
                    "type": "integer",
                    "example": 1024
                  },
                  "diskMbytes": {
                    "type": "integer",
                    "example": 2048
                  }
                }
              },
              "buildId": {
                "type": "string"
              },
              "defaultKeyValueStoreId": {
                "type": "string"
              },
              "defaultDatasetId": {
                "type": "string"
              },
              "defaultRequestQueueId": {
                "type": "string"
              },
              "buildNumber": {
                "type": "string",
                "example": "1.0.0"
              },
              "containerUrl": {
                "type": "string"
              },
              "usage": {
                "type": "object",
                "properties": {
                  "ACTOR_COMPUTE_UNITS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_WRITES": {
                    "type": "integer",
                    "example": 1
                  },
                  "KEY_VALUE_STORE_LISTS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_INTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_SERPS": {
                    "type": "integer",
                    "example": 0
                  }
                }
              },
              "usageTotalUsd": {
                "type": "number",
                "example": 0.00005
              },
              "usageUsd": {
                "type": "object",
                "properties": {
                  "ACTOR_COMPUTE_UNITS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_WRITES": {
                    "type": "number",
                    "example": 0.00005
                  },
                  "KEY_VALUE_STORE_LISTS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_INTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_SERPS": {
                    "type": "integer",
                    "example": 0
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}

Website Content Crawler for AI and RAG - Markdown OpenAPI definition

OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.

OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.

By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.

You can download the OpenAPI definitions for Website Content Crawler for AI and RAG from the options below:

OpenAPI.json

If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.

You can also check out our other API clients:

Website Content Crawler for AI and RAG API in Python

Website Content Crawler for AI and RAG API in JavaScript

Website Content Crawler for AI and RAG API through CLI

Website Content Crawler for AI and RAG API

Rag Architect

ai_solutionist/rag-architect

Transform any website into vector-store-ready knowledge chunks for Pinecone, Weaviate, LangChain, LlamaIndex, Supabase, n8n & more. AI-generated Q&A pairs, smart chunking, PII scrubbing. Build hallucination-free RAG chatbots in minutes.

Jason Pellerin

Quick Website Content Scraper ( Extract Text for RAG & LLMs )

automateitplease/ai-web-content-scraper-extract-text-for-rag-llms

Extract clean text from any website for AI/LLM applications. Supports both static and JavaScript-rendered sites (React, Vue, Angular). Perfect for RAG systems, chatbot training, and content analysis.

AutomateItPlease Workflow And Automaton Ops

Website Content Crawler

apify/website-content-crawler

Crawl websites and extract text content to feed AI models, LLM applications, vector databases, or RAG pipelines. The Actor supports rich formatting using Markdown, cleans the HTML, downloads files, and integrates well with 🦜🔗 LangChain, LlamaIndex, and the wider LLM ecosystem.

Apify

102K

4.5

(167)

Rag Content Chunker

labrat011/rag-content-chunker

Turn raw text, Markdown, or Apify datasets into token-perfect RAG chunks with deterministic IDs, source metadata, and a billing-ready summary—ready for embeddings or vector DBs without extra glue code.

Mick

Rag Vector Store Writer

labrat011/rag-vector-store-writer

Apify Actor that writes embedding vectors to Pinecone or Qdrant vector databases. Chains directly with RAG Embedding Generator output or accepts raw vectors with metadata. Handles batching, retries, collection creation, metadata mapping, and ID generation. Bring your own vector DB API key.

Mick

Rag Embedding Generator

labrat011/rag-embedding-generator

Generate vector embeddings from text or chunked datasets using OpenAI or Cohere. Chains with RAG Content Chunker for end-to-end RAG pipelines. Outputs raw vectors ready for any vector database.

Mick

Website Content Crawler Pro

datascoutapi/website-content-crawler-pro

Crawl websites and extract clean, structured content in Markdown, JSON, or plain text for AI models, LLMs, vector DBs, or RAG pipelines. Fast, reliable, and stealthy, with bulk processing, advanced metadata extraction, and seamless integration with LangChain, LlamaIndex, and AI workflows.

halam

428

3.4

(3)

Website Content Crawler

alizarin_refrigerator-owner/website-crawler

Crawl websites for SEO audits. Extracts HTML, title, meta tags, headings, links, & text content from pages. Automatic sitemap detection & parsing Extracts metadata (title, description, OG tags) Heading structure (H1, H2, H3) Internal & external link analysis Image extraction w/alt text Word count

John Rippy

Website Content Crawler

jasondev/website-content-crawler

A powerful web crawler that extracts text content from websites, optimized for AI models, Large Language Models (LLMs), vector databases, and Retrieval-Augmented Generation (RAG) pipelines.

Jason Giang

AI Website Content Localizer & Scraper

eunit/ai-website-content-localizer-scraper

Scrape any website and instantly translate the content into 83+ languages using Lingo.dev AI. Build multilingual datasets, localize competitor data, and power global RAG pipelines with clean, context-aware translations. The ultimate tool for shipping global apps fast!