{ "openapi": "3.0.1", "info": { "title": "Telegram Scraper + AI Analysis — Posts, Sentiment, MCP-Ready", "description": "Scrape any public Telegram channel and enrich each post with Gemini AI — sentiment, topics, summaries, translation, entities, and image descriptions. Built-in content moderation. MCP-ready for Claude Desktop and AI agents.", "version": "0.0", "x-build-id": "7lsjVtCzrLT5Y7MvB" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ml_boost~tg-apify-actor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ml_boost-tg-apify-actor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ml_boost~tg-apify-actor/runs": { "post": { "operationId": "runs-sync-ml_boost-tg-apify-actor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ml_boost~tg-apify-actor/run-sync": { "post": { "operationId": "run-sync-ml_boost-tg-apify-actor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "channels" ], "properties": { "channels": { "title": "Channels", "type": "array", "description": "One or more public Telegram channel identifiers. Accepts plain usernames (`durov`), @-prefixed (`@durov`), or t.me URLs (`https://t.me/durov`). Private channels, users and bots are not supported.", "items": { "type": "string" } }, "maxMessagesPerChannel": { "title": "Max messages per channel", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Maximum number of messages to scrape per channel. Iterates from newest to oldest. Hard-capped at 5,000 regardless of this value. Use a smaller number (50-200) for fast exploratory queries.", "default": 200 }, "outputFormat": { "title": "Output format", "enum": [ "json", "markdown", "both" ], "type": "string", "description": "`json` returns one structured record per message with all fields (recommended for programmatic consumers and AI agents). `markdown` returns a compact YAML-frontmatter + body string ideal for RAG pipelines. `both` includes both.", "default": "json" }, "includeChannelInfo": { "title": "Include channel info record", "type": "boolean", "description": "When true, emits one extra record per channel containing channel-level metadata (title, description, subscribers, photos/videos/links counts, verified, avatar). The record has `recordType: \"channel_info\"`.", "default": true }, "incrementalMode": { "title": "Incremental mode", "type": "boolean", "description": "When true, only fetches messages newer than the highest message ID scraped in a previous run of this actor. The cursor is stored per channel in the actor's key-value store. Use this for scheduled monitoring (combine with Apify Schedules).", "default": false }, "enrichSentiment": { "title": "AI: Sentiment analysis", "type": "boolean", "description": "Classify each post as positive / neutral / negative with confidence score and one-line rationale. Adds a `sentiment: {label, score, rationale}` field. Token-metered ($3 per 1M input, $15 per 1M output).", "default": false }, "enrichTopics": { "title": "AI: Topic tags", "type": "boolean", "description": "Assign 1-5 topic tags from this controlled vocabulary: politics, tech, finance, crypto, ai, sports, entertainment, science, business, lifestyle, news, other. Adds a `topics: [string]` field.", "default": false }, "enrichSummary": { "title": "AI: One-line summary", "type": "boolean", "description": "Produce a single-sentence summary of each post. Adds a `summary: string` field. Useful for digests, briefings, and timeline views where the full text is too long.", "default": false }, "enrichTranslation": { "title": "AI: Translation", "type": "boolean", "description": "Translate each post's text into the language specified by `translationTarget`. Adds a `translation: string` field. URLs, hashtags and @mentions are preserved verbatim.", "default": false }, "translationTarget": { "title": "Translation target language", "type": "string", "description": "ISO-639-1 language code for translations (e.g. `en`, `es`, `de`, `fr`, `ru`, `zh`, `ja`, `pt`). Only used when `enrichTranslation` is true.", "default": "en" }, "enrichEntities": { "title": "AI: Named entity extraction", "type": "boolean", "description": "Extract named entities mentioned in each post. Adds an `entities: {companies, people, places, tokens}` field, where `tokens` are crypto tickers like BTC, ETH, SOL.", "default": false }, "enrichImageDescriptions": { "title": "AI: Image descriptions (vision)", "type": "boolean", "description": "Generate 1-2 sentence descriptions for each image attached to a post, using Gemini multimodal. Adds `imageDescriptions: [{url, description, contains_text}]`. Capped at 4 images per post and 6 MB per image. Vision tokens (~1,000+ per image) cost more than text — enable only when you actually need visual content extracted.", "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 } } }, "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 } } } } } } } } } }