{ "openapi": "3.0.1", "info": { "title": "Bluesky Scraper - Search, Profiles & Posts", "description": "Scrape Bluesky data: keyword post search, author feeds, profiles, followers, and follows. Filter by date, language, author, domain, hashtag, and engagement. Export JSON, CSV, Excel.", "version": "1.0", "x-build-id": "j3KpwSaBQfwsRqFrb" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/parsebird~bluesky-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-parsebird-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/parsebird~bluesky-scraper/runs": { "post": { "operationId": "runs-sync-parsebird-bluesky-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/parsebird~bluesky-scraper/run-sync": { "post": { "operationId": "run-sync-parsebird-bluesky-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "actionToPerform" ], "properties": { "actionToPerform": { "title": "Action", "enum": [ "searchPosts", "getAuthorFeed", "getFollowers", "getFollows", "getProfile" ], "type": "string", "description": "Selects what to collect.", "default": "searchPosts" }, "queries": { "title": "Queries", "type": "array", "description": "One or more input values to process. Use keywords for Search posts, and Bluesky handles for user-focused actions (Get author feed, Get followers, Get follows, Get profile).", "items": { "type": "string" }, "default": [ "bluesky" ] }, "startUrls": { "title": "Start URLs", "type": "array", "description": "One or more Bluesky URLs to scrape directly. Supports search pages, post pages, profile pages, followers pages, and follows/following pages. Can be combined with Queries.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL", "description": "A Bluesky search, post, profile, followers, or follows page URL." } } }, "default": [] }, "maxItems": { "title": "Max Items", "minimum": 1, "type": "integer", "description": "Maximum number of primary records to collect across all queries. Leave empty to collect as many matching records as are available." }, "sortOrder": { "title": "Sort Order", "enum": [ "latest", "top" ], "type": "string", "description": "Sort order for Search posts. This field applies only to keyword-based post search.", "default": "latest" }, "dateFrom": { "title": "Date From", "type": "string", "description": "Optional posting date lower bound (YYYY-MM-DD, UTC). Adds a since: search operator and is also applied locally to post-like records.", "default": "" }, "dateTo": { "title": "Date To", "type": "string", "description": "Optional posting date upper bound (YYYY-MM-DD, UTC). Applied locally to post-like records after fetching.", "default": "" }, "language": { "title": "Language", "type": "string", "description": "Optional language code (e.g. en, fr, ja). For post search, the actor appends lang: to each query.", "default": "" }, "fromAuthor": { "title": "From Author", "type": "string", "description": "Optional Bluesky handle or DID. For post search, the actor appends from: to each query.", "default": "" }, "mentionsAuthor": { "title": "Mentions Author", "type": "string", "description": "Optional Bluesky handle or DID. For post search, the actor appends mentions: to each query.", "default": "" }, "hashtags": { "title": "Hashtags", "type": "array", "description": "Optional hashtags to append to post search queries. Values can be entered with or without #.", "default": [], "items": { "type": "string" } }, "domain": { "title": "Domain", "type": "string", "description": "Optional linked domain filter. For post search, the actor appends domain:.", "default": "" }, "exactUrl": { "title": "Exact URL", "type": "string", "description": "Optional exact shared URL to append to post search queries.", "default": "" }, "minLikes": { "title": "Min Likes", "minimum": 0, "type": "integer", "description": "Optional local engagement filter applied after Bluesky returns post-like records." }, "minReposts": { "title": "Min Reposts", "minimum": 0, "type": "integer", "description": "Optional local engagement filter applied after Bluesky returns post-like records." }, "minReplies": { "title": "Min Replies", "minimum": 0, "type": "integer", "description": "Optional local engagement filter applied after Bluesky returns post-like records." }, "includeReplies": { "title": "Include Replies", "type": "boolean", "description": "When off, skips saved post records that are replies to another post. This does not enable or disable thread reply scraping (see Scrape Comments below).", "default": true }, "includeReposts": { "title": "Include Reposts", "type": "boolean", "description": "When off, skips feed/search records returned because they were reposted by another account.", "default": true }, "scrapeComments": { "title": "Scrape Comments", "type": "boolean", "description": "When enabled, the actor also collects replies for each post in Search posts and Get author feed runs, as separate comment records.", "default": false }, "maxComments": { "title": "Max Comments", "minimum": 1, "type": "integer", "description": "Maximum number of replies to collect per source post when Scrape Comments is enabled.", "default": 50000 }, "sentiment_analysis": { "title": "Sentiment Analysis", "type": "boolean", "description": "Adds sentiment_score and sentiment_label to supported post and comment records, using a lightweight lexicon-based heuristic (not a trained ML model).", "default": false }, "content_analysis": { "title": "Content Analysis", "type": "boolean", "description": "Adds content-category fields to supported post records for topic-oriented grouping and filtering, using a lightweight keyword-based heuristic (not a trained ML model).", "default": false }, "proxy": { "title": "Proxy Configuration", "type": "object", "description": "Optional proxy override. Bluesky's public API is reachable directly, so proxy is disabled by default.", "default": { "useApifyProxy": 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 } } } } } } } } } }