Bluesky Scraper
Pricing
Pay per usage
Scrape Bluesky posts, profiles, feeds. 10+ runs, monitor trends on decentralized net. JSON/CSV. No API key. Custom scraper in 48h, $100 pilot. Email: spinov001@gmail.com • Tips: t.me/scraping_ai
Pricing
Pay per usage
Rating
0.0
(0)
Developer
Alex
Actor stats
0
Bookmarked
2
Total users
1
Monthly active users
3 days ago
Last modified
Categories
Share
{ "name": "bluesky-scraper", "version": "1.0.0", "main": "src/main.js", "scripts": { "start": "node src/main.js" }, "keywords": [], "author": "", "license": "ISC", "description": "", "dependencies": { "apify": "^3.7.0", "crawlee": "^3.16.0" }, "type": "module"}FROM apify/actor-node:22
COPY package*.json ./RUN npm --quiet set progress=false \ && npm install --omit=dev --omit=optional
COPY . ./{ "actorSpecification": 1, "name": "bluesky-scraper", "title": "Bluesky Scraper — Profiles, Posts & Hashtags", "description": "Need Bluesky data? Extract profiles and posts from the 41M+ user platform. Full engagement metrics — likes, reposts, replies, quotes, hashtags. AT Protocol API, no login for profiles. Automatic pagination for 1000+ posts. Search posts by keyword with App Password.", "version": "1.0", "seoTitle": "Bluesky scraper API — extract posts and profiles", "seoDescription": "Extract Bluesky profiles, posts & hashtags via AT Protocol. No login needed for profiles. Get engagement metrics, 1000+ posts per run. Free tier available.", "input": "./input_schema.json", "dockerfile": "./Dockerfile"}{ "title": "Bluesky Scraper Input", "type": "object", "schemaVersion": 1, "properties": { "handles": { "title": "Bluesky Handles", "type": "array", "description": "Bluesky handles to scrape (e.g., 'jay.bsky.team', 'bsky.app'). Works without login.", "editor": "stringList", "default": [] }, "searchQueries": { "title": "Search Queries", "type": "array", "description": "Search Bluesky for posts containing these keywords. Requires Bluesky credentials below.", "editor": "stringList", "default": [] }, "maxPostsPerSource": { "title": "Max Posts Per Source", "type": "integer", "description": "Maximum number of posts to extract per handle or search query", "default": 100, "minimum": 1, "maximum": 1000 }, "blueskyHandle": { "title": "Bluesky Handle (for search)", "type": "string", "description": "Your Bluesky handle for authenticated search (e.g., 'yourname.bsky.social'). Only needed for search queries.", "editor": "textfield", "default": "" }, "blueskyPassword": { "title": "Bluesky App Password (for search)", "type": "string", "description": "Your Bluesky App Password for authenticated search. Create one at Settings > App Passwords. Only needed for search queries.", "editor": "textfield", "isSecret": true }, "includeLikes": { "title": "Include Liked Posts", "type": "boolean", "description": "Whether to also scrape posts liked by the specified handles", "default": false }, "includeReposts": { "title": "Include Reposts", "type": "boolean", "description": "Whether to include reposted content in the results", "default": false } }}1import { Actor } from 'apify';2
3await Actor.init();4
5const input = await Actor.getInput() ?? {};6
7const {8 handles = [],9 searchQueries = [],10 maxPostsPerSource = 100,11 includeLikes = false,12 includeReposts = false,13 blueskyHandle = '',14 blueskyPassword = '',15} = input;16
17// Bluesky uses AT Protocol with public API18const BLUESKY_API = 'https://public.api.bsky.app';19const BLUESKY_AUTH_API = 'https://bsky.social';20let authToken = null;21
22async function fetchJson(url, useAuth = false) {23 const headers = {};24 if (useAuth && authToken) {25 headers['Authorization'] = `Bearer ${authToken}`;26 }27 const response = await fetch(url, { headers });28 if (!response.ok) throw new Error(`HTTP ${response.status}: ${url}`);29 return response.json();30}31
32async function authenticate() {33 if (!blueskyHandle || !blueskyPassword) return false;34 try {35 const response = await fetch(`${BLUESKY_AUTH_API}/xrpc/com.atproto.server.createSession`, {36 method: 'POST',37 headers: { 'Content-Type': 'application/json' },38 body: JSON.stringify({39 identifier: blueskyHandle,40 password: blueskyPassword,41 }),42 });43 if (!response.ok) {44 console.error(`Authentication failed: ${response.status}`);45 return false;46 }47 const data = await response.json();48 authToken = data.accessJwt;49 console.log(`Authenticated as ${data.handle}`);50 return true;51 } catch (e) {52 console.error(`Authentication error: ${e.message}`);53 return false;54 }55}56
57async function resolveHandle(handle) {58 const cleanHandle = handle.replace('@', '').replace('bsky.app/', '');59 const data = await fetchJson(`${BLUESKY_API}/xrpc/com.atproto.identity.resolveHandle?handle=${cleanHandle}`);60 return data.did;61}62
63async function getProfile(did) {64 const data = await fetchJson(`${BLUESKY_API}/xrpc/app.bsky.actor.getProfile?actor=${did}`);65 return {66 did: data.did,67 handle: data.handle,68 displayName: data.displayName,69 description: data.description,70 avatar: data.avatar,71 banner: data.banner,72 followersCount: data.followersCount,73 followsCount: data.followsCount,74 postsCount: data.postsCount,75 createdAt: data.createdAt,76 };77}78
79async function getAuthorFeed(did, limit = 50, cursor = null) {80 let url = `${BLUESKY_API}/xrpc/app.bsky.feed.getAuthorFeed?actor=${did}&limit=${Math.min(limit, 100)}`;81 if (cursor) url += `&cursor=${cursor}`;82 return fetchJson(url);83}84
85async function searchPosts(query, limit = 50, cursor = null) {86 // Search requires authentication87 const baseUrl = authToken ? BLUESKY_AUTH_API : BLUESKY_API;88 let url = `${baseUrl}/xrpc/app.bsky.feed.searchPosts?q=${encodeURIComponent(query)}&limit=${Math.min(limit, 100)}`;89 if (cursor) url += `&cursor=${cursor}`;90 return fetchJson(url, true);91}92
93function extractPostData(feedItem) {94 const post = feedItem.post || feedItem;95 const record = post.record || {};96
97 return {98 uri: post.uri,99 cid: post.cid,100 author: {101 did: post.author?.did,102 handle: post.author?.handle,103 displayName: post.author?.displayName,104 },105 text: record.text || '',106 createdAt: record.createdAt,107 likeCount: post.likeCount || 0,108 repostCount: post.repostCount || 0,109 replyCount: post.replyCount || 0,110 quoteCount: post.quoteCount || 0,111 hasImages: record.embed?.$type === 'app.bsky.embed.images',112 hasVideo: record.embed?.$type === 'app.bsky.embed.video',113 hasLink: record.embed?.$type === 'app.bsky.embed.external',114 externalLink: record.embed?.external?.uri || null,115 externalTitle: record.embed?.external?.title || null,116 labels: post.labels?.map(l => l.val) || [],117 languages: record.langs || [],118 hashtags: (record.text || '').match(/#\w+/g) || [],119 mentions: record.facets?.filter(f => f.features?.some(feat => feat.$type === 'app.bsky.richtext.facet#mention')).map(f => f.features[0]?.did) || [],120 isReply: !!record.reply,121 parentUri: record.reply?.parent?.uri || null,122 indexedAt: post.indexedAt,123 };124}125
126try {127 // Authenticate if credentials provided (needed for search)128 if (blueskyHandle && blueskyPassword) {129 await authenticate();130 }131
132 // Scrape by handles133 for (const handle of handles) {134 console.log(`\nProcessing handle: ${handle}`);135 try {136 const did = await resolveHandle(handle);137 const profile = await getProfile(did);138
139 await Actor.pushData({140 _type: 'PROFILE',141 ...profile,142 scrapedAt: new Date().toISOString(),143 });144
145 let collected = 0;146 let cursor = null;147
148 while (collected < maxPostsPerSource) {149 const remaining = maxPostsPerSource - collected;150 const feed = await getAuthorFeed(did, remaining, cursor);151 const items = feed.feed || [];152
153 if (items.length === 0) break;154
155 for (const item of items) {156 const postData = extractPostData(item);157 postData._type = 'POST';158 postData.source = `profile:${handle}`;159 postData.scrapedAt = new Date().toISOString();160 await Actor.pushData(postData);161 collected++;162 }163
164 cursor = feed.cursor;165 if (!cursor) break;166 }167
168 console.log(`Collected ${collected} posts from ${handle}`);169 } catch (e) {170 console.error(`Error processing ${handle}: ${e.message}`);171 }172 }173
174 // Scrape by search queries175 if (searchQueries.length > 0 && !authToken) {176 console.log('\nNote: Search requires Bluesky credentials. Provide blueskyHandle and blueskyPassword in input to enable search.');177 console.log('Profile scraping (handles) works without credentials.');178 }179
180 for (const query of searchQueries) {181 if (!authToken) {182 console.log(`Skipping search "${query}" — authentication required.`);183 continue;184 }185 console.log(`\nSearching: "${query}"`);186 try {187 let collected = 0;188 let cursor = null;189
190 while (collected < maxPostsPerSource) {191 const remaining = maxPostsPerSource - collected;192 const results = await searchPosts(query, remaining, cursor);193 const posts = results.posts || [];194
195 if (posts.length === 0) break;196
197 for (const post of posts) {198 const postData = extractPostData(post);199 postData._type = 'POST';200 postData.source = `search:${query}`;201 postData.scrapedAt = new Date().toISOString();202 await Actor.pushData(postData);203 collected++;204 }205
206 cursor = results.cursor;207 if (!cursor) break;208 }209
210 console.log(`Collected ${collected} posts for "${query}"`);211 } catch (e) {212 console.error(`Error searching "${query}": ${e.message}`);213 }214 }215} catch (e) {216 console.error(`Fatal error: ${e.message}`);217}218
219await Actor.exit();