{ "openapi": "3.0.1", "info": { "title": "LinkedIn Post Comments Scraper By Keyword & Engagement Filter", "description": "đŸ’Ŧ Scrape LinkedIn post comments & replies in bulk. 👍 Get likes, reactions, author names & profile links. 📅 Filter by date. 🔗 Add multiple posts at once. No login required by default.", "version": "0.1", "x-build-id": "o5fUU31IHUiDzD13X" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapio~linkedin-post-comments-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapio-linkedin-post-comments-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapio~linkedin-post-comments-scraper/runs": { "post": { "operationId": "runs-sync-scrapio-linkedin-post-comments-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapio~linkedin-post-comments-scraper/run-sync": { "post": { "operationId": "run-sync-scrapio-linkedin-post-comments-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "postUrls": { "title": "đŸŽ¯ LinkedIn posts to analyse", "type": "array", "description": "One or more LinkedIn post URLs, activity URNs or bare activity IDs. Example: https://www.linkedin.com/feed/update/urn:li:activity:7289521182721093633/ — each post is scanned separately. (The base key `startUrls` is still accepted.)", "default": [], "items": { "type": "string" } }, "commentsPerPost": { "title": "đŸ”ĸ Comments to scan per post", "minimum": 1, "maximum": 500, "type": "integer", "description": "How many top-level comments to pull per post BEFORE filtering. Logged-out the public page serves roughly 9-10; a li_at cookie raises the ceiling. Default 10.", "default": 10 }, "filterKeywords": { "title": "🔍 Must contain any of these words", "type": "array", "description": "Case-insensitive. A comment is kept only if its text contains at least one of these. Example: [\"pricing\", \"demo\", \"how much\"]. Leave empty to keep everything.", "default": [], "items": { "type": "string" } }, "excludeKeywords": { "title": "đŸšĢ Drop comments containing any of these", "type": "array", "description": "Case-insensitive. Useful for stripping congratulation noise. Example: [\"congrats\", \"great post\", \"thanks for sharing\"].", "default": [], "items": { "type": "string" } }, "minReactions": { "title": "👍 Minimum reactions on the comment", "minimum": 0, "type": "integer", "description": "Keep only comments with at least this many reactions. Exact per-comment reaction counts are read from the public post page. Example: 5. Default 0 (no threshold).", "default": 0 }, "minCommentLength": { "title": "📏 Minimum comment length (characters)", "minimum": 0, "type": "integer", "description": "The cheapest way to remove one-word replies and emoji-only comments. Example: 80. Default 0 (no threshold).", "default": 0 }, "excludeAuthorComments": { "title": "🙋 Exclude the post author's own comments", "type": "boolean", "description": "Drops comments written by the person who published the post — their replies are usually not leads. The author identity comes from the same page as the comments, so this costs no extra request.", "default": false }, "postedFrom": { "title": "📅 Comments posted on or after", "type": "string", "description": "Exact date range, made possible by the absolute comment timestamps this actor derives. Accepts 2025-01-27, an ISO timestamp, or a relative value like \"7 days\". Leave empty for no lower bound." }, "postedTo": { "title": "📅 Comments posted on or before", "type": "string", "description": "Upper bound of the date range. Accepts 2025-02-28, an ISO timestamp, or a relative value like \"1 day\". Leave empty for no upper bound." }, "postedLimit": { "title": "⏱ī¸ Quick age bucket", "enum": [ "any", "24h", "week", "month", "3months", "6months", "year" ], "type": "string", "description": "A coarse shortcut applied on top of the date range above. Leave as 'Any' when you use the exact range.", "default": "any" }, "minBuyingSignalScore": { "title": "đŸŽ¯ Minimum buying-signal score (0-100)", "minimum": 0, "maximum": 100, "type": "integer", "description": "Keep only comments scoring at least this much. 25+ = a real intent term fired, 50+ = several. Every kept row carries the matched terms and their weights so the number is auditable. Default 0 (keep all, still scored).", "default": 0 }, "buyingSignalKeywords": { "title": "➕ Extra buying-signal terms", "type": "array", "description": "Your own intent terms added to the built-in lexicon, each worth 20 points and reported by name in the score breakdown. Example: [\"switch from\", \"migrate off\", \"renewal\"].", "default": [], "items": { "type": "string" } }, "aiEnrichment": { "title": "🤖 Add AI sentiment, intent label & summary", "type": "boolean", "description": "OFF by default and entirely optional — it requires your own provider API key. The rule-based scoring above works without it; with AI off the three AI columns are null, never guessed.", "default": false }, "aiModel": { "title": "🧩 AI model / provider", "enum": [ "claude-haiku-4-5", "claude-sonnet-5", "claude-opus-4-8", "gpt-4o-mini", "gpt-4o", "gpt-4.1-mini", "o3-mini", "gemini-2.0-flash-lite", "gemini-2.0-flash", "gemini-2.5-flash", "grok-3-mini", "deepseek-chat", "sonar", "mistral-small-latest" ], "type": "string", "description": "Provider is auto-detected from the model name: claude-*=Anthropic, gpt-*/o1/o3=OpenAI, gemini-*=Google, grok-*=xAI, deepseek-*=DeepSeek, sonar*=Perplexity, mistral-*=Mistral. Cheap mini/flash/haiku models are plenty for classification.", "default": "claude-haiku-4-5" }, "aiApiKey": { "title": "🔑 Provider API key", "type": "string", "description": "Your own key for the provider chosen above. Falls back to the matching environment variable (ANTHROPIC_API_KEY, OPENAI_API_KEY, GEMINI_API_KEY, XAI_API_KEY, DEEPSEEK_API_KEY, PERPLEXITY_API_KEY, MISTRAL_API_KEY). Leave empty to keep AI off." }, "includeReplies": { "title": "↩ī¸ Include nested replies", "type": "boolean", "description": "Replies are only reachable through the authenticated engine, so this needs a li_at cookie. Logged-out the public page exposes no reply threads. (Base key `scrapeReplies` is still accepted.)", "default": false }, "authorDetailLevel": { "title": "👤 Commenter detail level", "enum": [ "short", "full" ], "type": "string", "description": "Full adds headline and profile picture on the authenticated engine. Logged-out, headlines are not exposed by LinkedIn and stay null. (Base key `profileScraperMode` is still accepted.)", "default": "short" }, "liAtCookie": { "title": "đŸĒ LinkedIn li_at cookie (optional escalation)", "type": "string", "description": "Optional. Without it the actor runs fully logged-out and returns the public comment slice. With it, the authenticated engine reaches the full comment list and nested replies. (Base key `liAt` is still accepted.)" }, "proxyConfiguration": { "title": "🌐 Proxy", "type": "object", "description": "Optional. The actor escalates direct → datacenter → residential on its own when LinkedIn throttles (HTTP 999)." } } }, "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 } } } } } } } } } }