{ "openapi": "3.0.1", "info": { "title": "Bluesky Jetstream Scraper", "description": "Bluesky Social Feed Scraper collects posts from Bluesky's Jetstream API. Filter by hashtags, usernames, or languages to gather targeted data. Includes media attachments, user profiles, and reply context. Perfect for social research, trend analysis, and content monitoring on the platform.", "version": "0.0", "x-build-id": "Xu8sMzu1SvkSeMlMU" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/skyscraping~bluesky-jetstream-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-skyscraping-bluesky-jetstream-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/skyscraping~bluesky-jetstream-scraper/runs": { "post": { "operationId": "runs-sync-skyscraping-bluesky-jetstream-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/skyscraping~bluesky-jetstream-scraper/run-sync": { "post": { "operationId": "run-sync-skyscraping-bluesky-jetstream-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "timeLimit" ], "properties": { "hashtags": { "title": "Hashtags", "type": "array", "description": "List of hashtags to filter posts (without the # symbol)", "items": { "type": "string" } }, "usernames": { "title": "Usernames", "type": "array", "description": "List of Bluesky usernames to filter posts (will be resolved to DIDs for efficient filtering)", "items": { "type": "string" } }, "languages": { "title": "Languages", "uniqueItems": true, "type": "array", "description": "Select languages to filter posts (multiple selection allowed)", "items": { "type": "string", "enum": [ "en", "ar", "cs", "zh", "da", "nl", "fi", "fr", "de", "el", "he", "hi", "hu", "id", "it", "ja", "ko", "no", "pl", "pt", "ru", "es", "sv", "th", "tr", "uk", "vi" ], "enumTitles": [ "English", "Arabic", "Czech", "Chinese", "Danish", "Dutch", "Finnish", "French", "German", "Greek", "Hebrew", "Hindi", "Hungarian", "Indonesian", "Italian", "Japanese", "Korean", "Norwegian", "Polish", "Portuguese", "Russian", "Spanish", "Swedish", "Thai", "Turkish", "Ukrainian", "Vietnamese" ] } }, "wantedCollections": { "title": "Wanted Collections", "uniqueItems": true, "type": "array", "description": "Specific collections to filter from Jetstream (defaults to feed posts)", "items": { "type": "string", "enum": [ "app.bsky.feed.post", "app.bsky.feed.like", "app.bsky.feed.repost", "app.bsky.graph.follow", "app.bsky.graph.block", "app.bsky.actor.profile" ], "enumTitles": [ "Posts", "Likes", "Reposts", "Follows", "Blocks", "Profiles" ] }, "default": [ "app.bsky.feed.post" ] }, "region": { "title": "Jetstream Region", "enum": [ "us-east", "us-west" ], "type": "string", "description": "Region for the Jetstream server", "default": "us-east" }, "instance": { "title": "Jetstream Instance", "minimum": 1, "maximum": 2, "type": "integer", "description": "Instance number for the Jetstream server (1 or 2)", "default": 2 }, "includeMedia": { "title": "Include Media Links", "type": "boolean", "description": "Whether to include URLs for media attachments", "default": true }, "includeImages": { "title": "Include Image Links", "type": "boolean", "description": "Whether to include URLs for images in the output", "default": true }, "detectLanguage": { "title": "Auto-detect Language", "type": "boolean", "description": "Automatically detect language for posts that don't specify one", "default": true }, "enrichUserProfiles": { "title": "Enrich User Profiles", "type": "boolean", "description": "Fetch additional user profile information for authors", "default": true }, "includeReplies": { "title": "Include Replies", "type": "boolean", "description": "Include reply information in collected posts", "default": true }, "maxPosts": { "title": "Maximum Posts", "minimum": 0, "type": "integer", "description": "Maximum number of posts to collect (0 for unlimited)", "default": 500 }, "timeLimit": { "title": "Time Limit (minutes)", "minimum": 1, "maximum": 180, "type": "integer", "description": "Maximum time to run the scraper in minutes", "default": 60 }, "autoReconnect": { "title": "Auto Reconnect", "type": "boolean", "description": "Automatically reconnect if connection is lost", "default": true }, "maxRetries": { "title": "Max Reconnection Attempts", "minimum": 1, "maximum": 10, "type": "integer", "description": "Maximum number of times to attempt reconnection", "default": 5 }, "saveCheckpoints": { "title": "Save Checkpoints", "type": "boolean", "description": "Periodically save data to prevent loss on errors", "default": true }, "proxy": { "title": "Proxy Configuration", "type": "object", "description": "Proxy settings for the scraper", "default": { "useApifyProxy": true } }, "debugMode": { "title": "Debug Mode", "type": "boolean", "description": "Enable detailed logging for troubleshooting", "default": false }, "verboseDebug": { "title": "Verbose Debug", "type": "boolean", "description": "Enable extremely detailed logging for message format diagnostics (warning: generates large logs)", "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 } } } } } } } } } }