{ "openapi": "3.0.1", "info": { "title": "Web Scraper For Llms", "description": "Stealth web scraping engine built for LLMs. Converts any web page to clean markdown or HTML", "version": "0.1", "x-build-id": "rLxN7cRc12ooaT29F" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/abotapi~web-scraper-for-llms/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-abotapi-web-scraper-for-llms", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/abotapi~web-scraper-for-llms/runs": { "post": { "operationId": "runs-sync-abotapi-web-scraper-for-llms", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/abotapi~web-scraper-for-llms/run-sync": { "post": { "operationId": "run-sync-abotapi-web-scraper-for-llms", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "urls" ], "properties": { "urls": { "title": "URLs", "type": "array", "description": "URLs to scrape. When crawl is enabled, each URL is used as a seed to discover linked pages.", "items": { "type": "string" } }, "crawl": { "title": "Enable Crawl Mode (follow links and scrape discovered pages)", "type": "boolean", "description": "When enabled, the scraper will follow links from each URL to discover and scrape additional pages. Use Crawl Depth and Max Pages below to control how far it goes.", "default": false }, "crawlDepth": { "title": "Crawl Depth", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many link hops from the starting URL. Ignored when crawl is off.", "default": 1 }, "crawlMaxPages": { "title": "Max Pages to Discover", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum pages to discover per seed URL. Ignored when crawl is off.", "default": 20 }, "formats": { "title": "Output Formats", "type": "array", "description": "Which content formats to extract.", "items": { "type": "string", "enum": [ "markdown", "html" ] }, "default": [ "markdown" ] }, "concurrency": { "title": "Concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Number of URLs to process in parallel.", "default": 3 }, "maxRetries": { "title": "Max Retries", "minimum": 0, "maximum": 10, "type": "integer", "description": "Maximum retry attempts for failed URLs. Ignored when crawl is on.", "default": 2 }, "timeoutMs": { "title": "Timeout (ms)", "minimum": 5000, "maximum": 120000, "type": "integer", "description": "Request timeout per URL in milliseconds.", "default": 30000 }, "onlyMainContent": { "title": "Only Main Content", "type": "boolean", "description": "Extract only main content, removing nav/header/footer/sidebar. Ignored when crawl is on.", "default": true }, "removeAds": { "title": "Remove Ads", "type": "boolean", "description": "Remove ads and tracking elements.", "default": true }, "removeBase64Images": { "title": "Remove Base64 Images", "type": "boolean", "description": "Remove base64-encoded images to reduce output size.", "default": true }, "includeTags": { "title": "Include Tags", "type": "array", "description": "CSS selectors for elements to include. If set, only matching elements are kept. Ignored when crawl is on.", "items": { "type": "string" } }, "excludeTags": { "title": "Exclude Tags", "type": "array", "description": "CSS selectors for elements to exclude from output. Ignored when crawl is on.", "items": { "type": "string" } }, "includePatterns": { "title": "Include URL Patterns", "type": "array", "description": "Regex patterns for URL filtering. In crawl mode, controls which discovered links to follow.", "items": { "type": "string" } }, "excludePatterns": { "title": "Exclude URL Patterns", "type": "array", "description": "Regex patterns for URL filtering. In crawl mode, controls which discovered links to skip.", "items": { "type": "string" } }, "waitForSelector": { "title": "Wait For Selector", "type": "string", "description": "CSS selector to wait for before considering page loaded. Ignored when crawl is on." }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Apify proxy configuration." } } }, "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 } } } } } } } } } }