{ "openapi": "3.0.1", "info": { "title": "HTML to JSON Smart Parser", "description": "Convert HTML to structured JSON using AI! Uses OpenAI to extract and structure data from HTML into clean JSON format. Perfect for developers and data analysts who need to transform HTML into structured data without manual parsing.", "version": "1.0", "x-build-id": "x1MSvE0Uu7jr5wcHn" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/parseforge~html-to-json-smart-parser/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-parseforge-html-to-json-smart-parser", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/parseforge~html-to-json-smart-parser/runs": { "post": { "operationId": "runs-sync-parseforge-html-to-json-smart-parser", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/parseforge~html-to-json-smart-parser/run-sync": { "post": { "operationId": "run-sync-parseforge-html-to-json-smart-parser", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "url": { "title": "URL (Fetch HTML)", "type": "array", "description": "URL(s) to fetch HTML content from. This will make a simple HTTP GET request to fetch the HTML. You can provide multiple URLs. Leave empty if pasting HTML or uploading files.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "htmlContent": { "title": "HTML Content (Paste)", "type": "string", "description": "Paste your HTML content here to convert to JSON, if not provided, the AI will automatically extract all important fields it identifies." }, "htmlFileUrl": { "title": "HTML File URL (Upload)", "type": "array", "description": "Upload HTML file(s) and paste their URL(s) here. You can provide multiple file URLs. Leave empty if using URLs or pasting HTML content. You can upload files using the file upload button in Apify Console." }, "openAIApiKey": { "title": "OpenAI API Key", "type": "string", "description": "Your OpenAI API key (if not provided it would return an error). You can get one from https://platform.openai.com/api-keys. If not provided, the actor will log an error and skip processing." }, "model": { "title": "OpenAI Model", "enum": [ "gpt-5", "gpt-4o", "gpt-4o-mini", "gpt-4-turbo", "gpt-3.5-turbo" ], "type": "string", "description": "The OpenAI model to use for conversion. Options: gpt-5, gpt-4o, gpt-4o-mini, gpt-4-turbo, gpt-3.5-turbo", "default": "gpt-4o-mini" }, "fieldsToExtract": { "title": "Fields to Extract (Optional)", "type": "string", "description": "Specify which fields you want extracted from the HTML (e.g., ['title', 'price', 'description', 'images', 'specifications']). You can provide multiple field names. If not provided, the AI will automatically extract all important fields it identifies." }, "systemPrompt": { "title": "System Prompt (Optional)", "type": "string", "description": "Optional custom system prompt to guide the AI extraction. If not provided, a smart default prompt will be used that extracts meaningful information." } } }, "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 } } } } } } } } } }