{ "openapi": "3.0.1", "info": { "title": "ChatGPT Conversation Scraper", "description": "Extract complete conversations from ChatGPT shared links with smart Pay-Per-Event pricing. Get full dialogues, code blocks, and metadata - perfect for training datasets, conversation analysis, and knowledge management.", "version": "2.0", "x-build-id": "0LQTDDTVWFpD0hmgl" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/straightforward_understanding~chatgpt-conversation-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-straightforward_understanding-chatgpt-conversation-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/straightforward_understanding~chatgpt-conversation-scraper/runs": { "post": { "operationId": "runs-sync-straightforward_understanding-chatgpt-conversation-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/straightforward_understanding~chatgpt-conversation-scraper/run-sync": { "post": { "operationId": "run-sync-straightforward_understanding-chatgpt-conversation-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "startUrls" ], "properties": { "startUrls": { "title": "ChatGPT Shared URLs", "type": "array", "description": "List of ChatGPT shared conversation URLs to scrape. URLs should be in format: https://chatgpt.com/share/xxx", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy settings for the scraper to avoid being blocked. Recommended to use residential proxies for ChatGPT.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } }, "maxRequestsPerCrawl": { "title": "Max requests per crawl", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of conversations to scrape in a single run", "default": 100 }, "headless": { "title": "Headless mode", "type": "boolean", "description": "Run browser in headless mode (recommended for production). Set to false only for debugging.", "default": true }, "includeMetadata": { "title": "Include metadata", "type": "boolean", "description": "Include additional metadata like page information and extraction details", "default": true }, "includeHtmlContent": { "title": "Include HTML content", "type": "boolean", "description": "Store original HTML content of messages (additional charge applies: +$0.02 per conversation)", "default": false }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 5, "type": "integer", "description": "Maximum number of pages to process simultaneously (recommended: 1 for stability)", "default": 1 }, "maxScrollAttempts": { "title": "Max scroll attempts", "minimum": 5, "maximum": 200, "type": "integer", "description": "Maximum number of scroll attempts to load all conversation content. Increase for very long conversations.", "default": 50 }, "debugMode": { "title": "Debug mode", "type": "boolean", "description": "Enable detailed debugging information to help diagnose extraction issues", "default": false }, "navigationTimeout": { "title": "Navigation timeout (ms)", "minimum": 10000, "maximum": 60000, "type": "integer", "description": "Maximum time to wait for page navigation (milliseconds)", "default": 30000 }, "waitForContentTimeout": { "title": "Content wait timeout (ms)", "minimum": 5000, "maximum": 120000, "type": "integer", "description": "Maximum time to wait for conversation content to appear (milliseconds)", "default": 30000 }, "requestHandlerTimeoutSecs": { "title": "Request handler timeout (seconds)", "minimum": 120, "maximum": 1800, "type": "integer", "description": "Maximum time for processing a single conversation. Increase for very long conversations (100+ messages). Default 600s (10 min) handles most extremely long conversations.", "default": 600 }, "enableCostTracking": { "title": "Enable cost tracking", "type": "boolean", "description": "Track and report pricing information in results and generate cost report", "default": true }, "outputFormat": { "title": "Message content format", "enum": [ "markdown", "text", "html" ], "type": "string", "description": "Format for message content extraction. 'markdown' preserves ChatGPT's formatting (headings, lists, code blocks, bold/italic). 'text' preserves newlines but strips formatting. 'html' keeps raw HTML.", "default": "markdown" } } }, "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 } } } } } } } } } }