ScraperCodeGenerator
Pricing
Pay per usage
Go to Store
ScraperCodeGenerator
An intelligent web scraping tool that automatically generates custom scraping code for any website.
0.0 (0)
Pricing
Pay per usage
0
Total users
1
Monthly users
1
Last modified
a day ago
You can access the ScraperCodeGenerator 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": "1.1", "x-build-id": "bF9DDedBOF6H3shA4" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ohlava~scrapercodegenerator/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ohlava-scrapercodegenerator", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ohlava~scrapercodegenerator/runs": { "post": { "operationId": "runs-sync-ohlava-scrapercodegenerator", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ohlava~scrapercodegenerator/run-sync": { "post": { "operationId": "run-sync-ohlava-scrapercodegenerator", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "targetUrl", "userGoal", "claudeApiKey" ], "properties": { "targetUrl": { "title": "Target URL", "type": "string", "description": "The URL of the website you want to scrape" }, "userGoal": { "title": "Scraping Goal", "type": "string", "description": "Describe what data you want to extract from the website" }, "claudeApiKey": { "title": "Claude API Key", "type": "string", "description": "Your Anthropic Claude API key for AI-powered code generation" }, "maxRetries": { "title": "Max Retries", "minimum": 1, "maximum": 10, "type": "integer", "description": "Maximum number of retry attempts for scraping", "default": 3 }, "timeout": { "title": "Timeout (seconds)", "minimum": 10, "maximum": 300, "type": "integer", "description": "Timeout for each scraping attempt in seconds", "default": 60 }, "testScript": { "title": "Test Generated Script", "type": "boolean", "description": "Whether to test the generated scraping script before saving it", "default": true }, "claudeModel": { "title": "Claude Model", "enum": [ "claude-sonnet-4-20250514", "claude-opus-4-20250514", "claude-3-7-sonnet-20250219", "claude-3-5-sonnet-20241022", "claude-3-5-haiku-20241022", "claude-3-sonnet-20240229", "claude-3-haiku-20240307" ], "type": "string", "description": "Choose which Claude model to use for AI analysis", "default": "claude-sonnet-4-20250514" }, "htmlPruningEnabled": { "title": "Enable HTML Pruning", "type": "boolean", "description": "Enable HTML content processing before analysis", "default": true }, "htmlMaxListItems": { "title": "Max List Items", "minimum": 1, "maximum": 20, "type": "integer", "description": "Maximum number of items to keep in lists when pruning HTML", "default": 3 }, "htmlMaxTextLength": { "title": "Max Text Length", "minimum": 50, "maximum": 2000, "type": "integer", "description": "Maximum length of text content to keep when pruning HTML", "default": 200 }, "htmlPruneBeforeEvaluation": { "title": "Prune Before Evaluation", "type": "boolean", "description": "Apply HTML pruning before quality evaluation", "default": true }, "htmlPrunePercentage": { "title": "Prune Percentage", "minimum": 0, "maximum": 100, "type": "integer", "description": "Percentage of HTML content to prune (0-100)", "default": 80 }, "actors": { "title": "Scraping Actors Configuration", "type": "array", "description": "Select and configure which Apify actors to use for scraping" }, "concurrentActors": { "title": "Concurrent Actors", "type": "boolean", "description": "Run multiple actors simultaneously for faster results", "default": true }, "forActor": { "title": "Generate for Apify Actor", "type": "boolean", "description": "Choose the output format for the generated script", "default": true } } }, "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 } } } } } } } } }}ScraperCodeGenerator 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 ScraperCodeGenerator 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:
![Linkedin Profile Posts Scraper [NO COOKIES] avatar](https://images.apifyusercontent.com/s_O_fFD0AYINXh8_JVN3CD3Ofg4QN-ZCDgVnobPoBp8/rs:fill:76:76/cb:1/aHR0cHM6Ly9hcGlmeS1pbWFnZS11cGxvYWRzLXByb2QuczMudXMtZWFzdC0xLmFtYXpvbmF3cy5jb20vdFhKaEQ5SFNvdTY4N2NEUTQtYWN0b3ItTFFRSVhOOU90aGY4ZjdSNW4tS1loTXZ4SVB0Vy1saW5rZWRpbl9jb2xvcmVkXzIuanBn.webp){kind=avatar}
