Ai Powered Scraper
Pricing
$10.00 / 1,000 results
Go to Apify Store
Ai Powered Scraper
AI Powered Scraper using LangChain and OpenAI.
0.0 (0)
Pricing
$10.00 / 1,000 results
1
1
1
Last modified
3 days ago
Pricing
$10.00 / 1,000 results
AI Powered Scraper using LangChain and OpenAI.
0.0 (0)
Pricing
$10.00 / 1,000 results
1
1
1
Last modified
3 days ago
You can access the Ai Powered Scraper programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.0", "x-build-id": "71GZXJSJVTUTigmU1" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/devwithbobby~ai-powered-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-devwithbobby-ai-powered-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/devwithbobby~ai-powered-scraper/runs": { "post": { "operationId": "runs-sync-devwithbobby-ai-powered-scraper", "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/devwithbobby~ai-powered-scraper/run-sync": { "post": { "operationId": "run-sync-devwithbobby-ai-powered-scraper", "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": "One or more URLs of pages where the crawler will start. Note that the Actor will additionally only crawl sub-pages of these URLs. For example, for start URL `https://www.example.com/blog`, it will crawl pages like `https://example.com/blog/article-1`, but will skip `https://example.com/docs/something-else`.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxCrawlPages": { "title": "Max pages", "minimum": 0, "type": "integer", "description": "The maximum number pages to crawl. It includes the start URLs, pagination pages, pages with no content, etc. The crawler will automatically finish after reaching this number. This setting is useful to prevent accidental crawler runaway.", "default": 9999999 }, "openAIApiKey": { "title": "OpenAI API key", "type": "string", "description": "Enter your [OpenAI](https://openai.com/) account and an API key. This is needed for vectorizing the data and also to be able to prompt the OpenAI model." }, "query": { "title": "Query", "type": "string", "description": "The query you want to ask the model about the crawled data." }, "forceRecrawl": { "title": "Re-crawl the data", "type": "boolean", "description": "If enabled, the data will be re-crawled even if cached vector index is available.", "default": false }, "loadUrlsFromSitemaps": { "title": "Load URLs from Sitemaps", "type": "boolean", "description": "If enabled, the scraper will automatically find and load URLs from sitemap.xml files.", "default": false }, "respectRobotsTxt": { "title": "Respect robots.txt file", "type": "boolean", "description": "If enabled, the scraper will respect the robots.txt file and avoid crawling disallowed pages.", "default": true }, "crawlerType": { "title": "Crawler type", "enum": [ "adaptive", "cheerio", "playwright", "jsdom" ], "type": "string", "description": "Select the crawler type based on your needs", "default": "adaptive" }, "userAgent": { "title": "User Agent", "type": "string", "description": "Custom User-Agent string to use for requests", "default": "Mozilla/5.0 (compatible; AI-Powered-Scraper/1.0)" }, "requestDelay": { "title": "Request delay (ms)", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Delay between requests in milliseconds to avoid overwhelming the server", "default": 1000 }, "maxRequestRetries": { "title": "Max request retries", "minimum": 0, "maximum": 10, "type": "integer", "description": "Maximum number of times to retry failed requests", "default": 3 } } }, "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 } } } } } } } } }}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 Ai Powered Scraper from the options below:
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: