{ "openapi": "3.0.1", "info": { "title": "Instagram Post Engagement Scraper – Commenters & Engagement", "description": "Analyze who engaged with a set of Instagram posts: extract every comment (id, username, text, likes, timestamp) and report like/comment counts. Public data only by default, no login.\nOptional Instagram cookies also resolve who liked - which is a unique feature!", "version": "0.1", "x-build-id": "iylvpk1xfOqrOIWM1" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/automation_nerd~instagram-post-engagement-actor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-automation_nerd-instagram-post-engagement-actor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/automation_nerd~instagram-post-engagement-actor/runs": { "post": { "operationId": "runs-sync-automation_nerd-instagram-post-engagement-actor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/automation_nerd~instagram-post-engagement-actor/run-sync": { "post": { "operationId": "run-sync-automation_nerd-instagram-post-engagement-actor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "posts" ], "properties": { "posts": { "title": "Posts", "type": "array", "description": "Instagram posts to analyze. Paste full post/reel URLs (https://www.instagram.com/p/SHORTCODE/) or bare shortcodes. Each post is analyzed independently and produces one dataset item.", "items": { "type": "string" } }, "maxComments": { "title": "Max comments per post", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Upper bound on how many comments to fetch per post (pagination stops there). Lower = faster and cheaper. Instagram itself caps public comment access at roughly 500 top-level comments per post.", "default": 200 }, "includeReplies": { "title": "Include reply threads", "type": "boolean", "description": "Also fetch the replies under each top-level comment. More thorough for engagement analysis, but slower and uses more requests.", "default": false }, "onlyDataAfter": { "title": "Only comments after (date/time)", "type": "string", "description": "Optional. Keep only comments posted AFTER this moment; older ones are skipped and counted in 'skippedCommentCount'. Accepts a date (2026-07-01), an ISO datetime (2026-07-01T14:30:00Z) or a Unix timestamp. Note: applies to COMMENTS only — Instagram's likers list has no timestamp, so likers can't be date-filtered." }, "cookies": { "title": "Instagram cookies (optional — unlocks likers)", "type": "string", "description": "OPTIONAL. Leave empty for public scraping (comments + like/comment counts). Provide your Instagram login to ALSO get the LIKERS of each post (the users who liked it), which Instagram hides from anonymous requests. Three accepted formats: (1) the JSON export from the Cookie-Editor browser extension while on instagram.com [recommended — one click 'Export']; (2) a cookie header string like 'sessionid=...; csrftoken=...; ds_user_id=...'; (3) just your 'sessionid' value. The actor needs sessionid (ds_user_id is derived from it automatically). Secret field: Apify stores it encrypted and never shows it in the log, input or dataset. Use an account you control; in authenticated mode all requests run on a single pinned proxy IP." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Instagram blocks datacenter IPs. Use Apify Residential proxies (default). You can pick a country to match your audience.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } }, "maxConcurrency": { "title": "Max concurrency (parallel posts)", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many posts to scrape in parallel. Higher = faster, but a higher chance of hitting Instagram rate limits. Each post uses its own rotating proxy IP.", "default": 3 }, "maxRequestRetries": { "title": "Max retries per post", "minimum": 0, "maximum": 8, "type": "integer", "description": "How often to retry a post on a transient error (rate limit / 5xx / connection / block). Reported per item as 'attempts'.", "default": 3 }, "commentsDocId": { "title": "Comments GraphQL doc_id (advanced)", "type": "string", "description": "Advanced/optional. The actor fetches comments via Instagram's logged-out GraphQL query, which uses a numeric doc_id that Instagram rotates every few weeks. Leave empty to use the built-in default. If comments stop coming back, open a public post in a logged-out browser, find the Network request with x-fb-friendly-name = PolarisLoggedOutDesktopWWWPostCommentsPaginationQuery, and paste its doc_id here." }, "debug": { "title": "Debug logging", "type": "boolean", "description": "Log every Instagram API request URL and its response status (→ GET … / ← 302 …). Useful to inspect exactly what is called and where a block happens. Same as running with APIFY_LOG_LEVEL=DEBUG.", "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 } } } } } } } } } }