{ "openapi": "3.0.1", "info": { "title": "Intelligent Website Scrapper", "description": "An intelligent website scraper that uses LangChain and LLM to extract and process content based on high-level goals like summarization, product extraction, service extraction, and FAQ extraction.", "version": "0.0", "x-build-id": "onUgMbcMlPNqyE1y7" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/happitap~intelligent-website-scrapper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-happitap-intelligent-website-scrapper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/happitap~intelligent-website-scrapper/runs": { "post": { "operationId": "runs-sync-happitap-intelligent-website-scrapper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/happitap~intelligent-website-scrapper/run-sync": { "post": { "operationId": "run-sync-happitap-intelligent-website-scrapper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "startUrls" ], "properties": { "startUrls": { "title": "Start URLs", "type": "array", "description": "List of web pages where the scraper will begin. Each entry must be an object with a 'url' property containing a valid HTTP/HTTPS URL. The scraper will visit these pages first and optionally follow internal links based on your configuration. Example: [{ \"url\": \"https://example.com\" }, { \"url\": \"https://example.com/products\" }]. This field is required and must contain at least one URL.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "taskType": { "title": "Task Type", "enum": [ "summarize", "extractProducts", "extractServices", "extractFAQs" ], "type": "string", "description": "Specifies how the AI should process the scraped content. Choose 'summarize' to get a concise summary of each page's main content. Select 'extractProducts' to identify and extract product names, descriptions, and pricing information. Use 'extractServices' to find service offerings and their details. Pick 'extractFAQs' to extract question-and-answer pairs from help pages. The AI uses OpenAI's language model to intelligently parse and structure the content according to your selected task. Default is 'summarize'.", "default": "summarize" }, "maxDepth": { "title": "Maximum Crawl Depth", "minimum": 0, "maximum": 5, "type": "integer", "description": "Controls how many levels deep the scraper will follow links from your start URLs. Set to 0 to scrape only the start URLs without following any links. Set to 1 to scrape start URLs plus all pages directly linked from them. Set to 2 to go two levels deep, and so on. Higher values will scrape more pages but take longer and consume more resources. Maximum allowed value is 5. This setting only applies when 'Follow Internal Links' is enabled. Default is 1.", "default": 1 }, "followInternalLinks": { "title": "Follow Internal Links", "type": "boolean", "description": "Enable this to automatically discover and scrape additional pages within the same website. When enabled, the scraper will find links on each page that point to the same domain and add them to the crawl queue (up to 5 links per page, respecting the maxDepth setting). This is useful for comprehensive site scraping, such as extracting all products from an e-commerce site or all articles from a blog. Disable this if you only want to scrape the exact URLs you specified in Start URLs. Default is false.", "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 } } } } } } } } } }