{ "openapi": "3.0.1", "info": { "title": "AI Web Scraper – JSON Schema Data Extractor", "description": "AI web scraper: give URLs and your own JSON Schema or a ready-made preset (product, job, event, article); get one schema-valid JSON object per page. Claude reads page text and JSON-LD, every answer is validated and retried with the errors, and invalid output is free. Uses your own Anthropic API key.", "version": "1.0", "x-build-id": "6zDbCti8jic6rXsoy" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/brisaworks~schema-json-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-brisaworks-schema-json-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/brisaworks~schema-json-extractor/runs": { "post": { "operationId": "runs-sync-brisaworks-schema-json-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/brisaworks~schema-json-extractor/run-sync": { "post": { "operationId": "run-sync-brisaworks-schema-json-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Pages to extract from. Each page is fetched once (no crawling). The example is a page of Books to Scrape, a demo shop built for scraping practice.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "preset": { "title": "Preset schema", "enum": [ "product", "job", "event", "article" ], "type": "string", "description": "A ready-made schema for a common page type, used when the JSON Schema field below is empty. Product: name, brand, SKU, price, currency, stock, rating, reviews. Job: title, company, location, remote, salary range, date posted, skills. Event: name, dates, venue, city, country, online, price. Article: headline, authors, dates, publisher, summary, key points. Your own JSON Schema always wins over a preset." }, "jsonSchema": { "title": "JSON Schema", "type": "object", "description": "Your own JSON Schema (draft 2020-12 / draft-07) for the record you want per page. Leave empty to use the preset above; when both are set, this schema wins. Every result is validated against it; add a \"description\" to each field to guide the model." }, "anthropicApiKey": { "title": "Anthropic API key", "type": "string", "description": "Your Anthropic API key (console.anthropic.com). Claude usage is billed to your Anthropic account. Without a key the run returns free page previews only." }, "model": { "title": "Claude model", "type": "string", "description": "Model ID. claude-haiku-5-5 is fast and cheap; use claude-sonnet-5-5 for hard pages.", "default": "claude-haiku-5-5" }, "instructions": { "title": "Extra instructions", "type": "string", "description": "Optional guidance, e.g. \"prices in EUR as numbers\" or \"only the main product, not related items\"." }, "maxPageChars": { "title": "Max page characters sent", "minimum": 1000, "maximum": 400000, "type": "integer", "description": "Longer pages are cut to this many characters of text (the output's truncated flag tells you).", "default": 60000 }, "maxRetriesOnInvalid": { "title": "Retries when output fails validation", "minimum": 0, "maximum": 3, "type": "integer", "description": "How many times the model is shown the validation errors and asked to fix its JSON.", "default": 1 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip pages the site's robots.txt disallows.", "default": true }, "includePageText": { "title": "Include page text", "type": "boolean", "description": "Also return the page text that was sent to the model.", "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }