{ "openapi": "3.0.1", "info": { "title": "Text-to-JSON Structured Extractor", "description": "A versatile Apify actor that converts unstructured text and HTML into clean, structured JSON. Supports four extraction modes with auto-detection, URL fetching, and batch processing.", "version": "0.0", "x-build-id": "fcyoMLqXn8etf93Dd" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/moving_beacon-owner1~my-actor-68/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-moving_beacon-owner1-my-actor-68", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/moving_beacon-owner1~my-actor-68/runs": { "post": { "operationId": "runs-sync-moving_beacon-owner1-my-actor-68", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/moving_beacon-owner1~my-actor-68/run-sync": { "post": { "operationId": "run-sync-moving_beacon-owner1-my-actor-68", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "extractionMode", "inputType" ], "properties": { "extractionMode": { "title": "Extraction Mode", "enum": [ "resume", "ecommerce", "blog_seo", "chat_log", "auto" ], "type": "string", "description": "Which extractor to use for processing the input.", "default": "auto" }, "inputType": { "title": "Input Type", "enum": [ "raw_text", "urls", "key_value_store" ], "type": "string", "description": "How the source content is provided.", "default": "raw_text" }, "rawInput": { "title": "Raw Text / HTML Input", "type": "string", "description": "Paste your resume text, e-commerce HTML, blog HTML, or chat log directly here. Used when Input Type is 'Raw Text / HTML'.", "default": "John Doe\njohndoe@email.com | (555) 123-4567\nlinkedin.com/in/johndoe | github.com/johndoe\nNew York, NY\n\nSummary\nFull-stack developer with 5+ years of experience in building web applications using Python, JavaScript, and cloud technologies.\n\nExperience\n\nSenior Developer at Acme Corp\nNew York, NY — March 2021 – Present\n• Architected microservices platform handling 2M+ daily requests\n• Led team of 4 engineers on payment integration project\n• Reduced API latency by 40% through caching strategy\n\nSoftware Developer at StartupIO\nBoston, MA — June 2018 – February 2021\n• Built React dashboard used by 500+ enterprise clients\n• Implemented CI/CD pipelines with GitHub Actions and Docker\n• Designed PostgreSQL schema supporting multi-tenant SaaS\n\nEducation\n\nMIT\nBachelor of Science in Computer Science\nSeptember 2014 – June 2018\nGPA: 3.75/4.0\n\nSkills\nLanguages: Python, JavaScript, TypeScript, SQL, Go\nFrameworks: React, Django, FastAPI, Express.js\nCloud: AWS (EC2, Lambda, S3, RDS), Docker, Kubernetes\nDatabases: PostgreSQL, MongoDB, Redis\n\nCertifications\n- AWS Solutions Architect Associate\n- Certified Kubernetes Administrator\n\nLanguages\n- English (Native)\n- French (Conversational)" }, "urls": { "title": "URLs to Fetch", "type": "array", "description": "List of URLs to fetch and extract data from. Used when Input Type is 'Fetch from URLs'.", "items": { "type": "string" }, "default": [] }, "kvStoreKeys": { "title": "Key-Value Store Keys", "type": "array", "description": "Keys to read from the default Key-Value Store. Used when Input Type is 'Read from Key-Value Store'.", "items": { "type": "string" }, "default": [] }, "chatLogFormat": { "title": "Chat Log Format Hint", "enum": [ "auto", "whatsapp", "slack", "discord", "irc", "generic", "simple" ], "type": "string", "description": "Helps the chat log extractor parse correctly. Use 'auto' to let the extractor detect the format automatically.", "default": "auto" }, "outputFormat": { "title": "Output Format", "enum": [ "full", "compact", "flat" ], "type": "string", "description": "How to structure the output dataset records.", "default": "full" }, "includeSourceText": { "title": "Include Source Text in Output", "type": "boolean", "description": "Whether to include the original input text/HTML in each output record.", "default": false }, "maxConcurrency": { "title": "Max Concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Maximum number of URLs to fetch concurrently (only for URL mode).", "default": 5 }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Proxy settings for fetching URLs. Leave empty to use direct connection.", "default": { "useApifyProxy": true } }, "requestTimeoutSecs": { "title": "Request Timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Timeout in seconds when fetching URLs.", "default": 30 } } }, "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 } } } } } } } } } }