{ "openapi": "3.0.1", "info": { "title": "Bluesky Scraper - Fast & Monitoring Friendly", "description": "Scrapes Bluesky posts, author feeds, search results, and reply threads via Bluesky's public AppView API. No login, API key, or app password required. Clean dedup keys and ISO timestamps make it ready for scheduled, diffable monitoring.", "version": "1.0", "x-build-id": "4HRua2uOyIczctmPj" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/iwc~bluesky-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-iwc-bluesky-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/iwc~bluesky-scraper/runs": { "post": { "operationId": "runs-sync-iwc-bluesky-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/iwc~bluesky-scraper/run-sync": { "post": { "operationId": "run-sync-iwc-bluesky-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "searchQueries": { "title": "Search queries", "type": "array", "description": "Keyword searches (app.bsky.feed.searchPosts). If Authors are also provided, each query is searched scoped to each author; otherwise it searches all of Bluesky.", "items": { "type": "string" } }, "authors": { "title": "Authors", "type": "array", "description": "Bluesky handles or DIDs whose post feed to scrape (app.bsky.feed.getAuthorFeed), e.g. \"bsky.app\" or \"did:plc:z72i7hdynmk6r22z27h6tvur\".", "items": { "type": "string" } }, "startUrls": { "title": "Start URLs", "type": "array", "description": "Direct bsky.app URLs to start from — a profile (https://bsky.app/profile/{handle}) or a single post (https://bsky.app/profile/{handle}/post/{rkey}).", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "sort": { "title": "Sort", "enum": [ "latest", "top" ], "type": "string", "description": "Sort order for search results. \"latest\" is the recommended default for monitoring/alerting use cases since it surfaces the freshest posts first. Only applies to Search queries (author feeds are always returned newest-first by Bluesky).", "default": "latest" }, "maxItems": { "title": "Max items (posts)", "minimum": 1, "type": "integer", "description": "Hard cap on the number of posts scraped in this run. This is the main billing guardrail — the run stops once it's reached.", "default": 100 }, "includeReplies": { "title": "Include replies", "type": "boolean", "description": "Master switch for reply scraping. When off, no reply-thread requests are made and no reply-scraped events are charged, regardless of Scrape type.", "default": false }, "maxRepliesPerPost": { "title": "Max replies per post", "minimum": 0, "type": "integer", "description": "Cap on replies scraped per post (only used when Include replies is on). Defaults to 50 to keep billing predictable. Set to 0 to remove the cap and scrape every reply in the thread — note that popular posts can have thousands of replies (and reply charges).", "default": 50 }, "scrapeType": { "title": "Scrape type", "enum": [ "posts", "replies", "both" ], "type": "string", "description": "What to push to the output dataset: post records only, reply records only, or both. Replies are only fetched at all if \"Include replies\" is also on.", "default": "posts" }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy is ON by default (plain datacenter group) and is required: Bluesky blocks the searchPosts endpoint from cloud/datacenter egress IPs (403) unless requests go through a proxy. Author feeds and post threads work either way. Residential proxy is not needed.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }