{ "openapi": "3.0.1", "info": { "title": "Instagram Post Scraper & Comment Replies", "description": "Instagram Post Scraper & Comment Replies ā€” Scrape Instagram posts with captions, media details, likes, timestamps, and comments, including comment replies. Extract structured engagement data for content research, audience analysis, and social media insights.", "version": "0.2", "x-build-id": "X2tdd2la2OOcclhv1" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/api-empire~instagram-post-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-api-empire-instagram-post-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/api-empire~instagram-post-scraper/runs": { "post": { "operationId": "runs-sync-api-empire-instagram-post-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/api-empire~instagram-post-scraper/run-sync": { "post": { "operationId": "run-sync-api-empire-instagram-post-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "username" ], "properties": { "username": { "title": "šŸŽÆ Profiles or post links to scrape", "type": "array", "description": "šŸ“‹ **One target per row.** Mix freely:\n\nā€¢ šŸ‘¤ Username ā€” `natgeo`\nā€¢ šŸ”— Profile URL ā€” `https://www.instagram.com/natgeo/`\nā€¢ šŸ–¼ļø Post URL ā€” `https://www.instagram.com/p/SHORTCODE/`\nā€¢ šŸŽ¬ Reel / TV URL ā€” `https://www.instagram.com/reel/SHORTCODE/`\n\nšŸ’” Duplicates are collapsed automatically (`natgeo`, `@natgeo` and the profile URL count as one target).", "items": { "type": "string" } }, "resultsLimit": { "title": "šŸ”¢ How many posts per profile", "minimum": 1, "maximum": 100000, "type": "integer", "description": "šŸ§® **Maximum posts saved for each profile target.** Ignored for single post URLs (one URL = one row).\n\nā±ļø Instagram serves a **server-fixed 12 posts per feed request**, so 100 posts ā‰ˆ 9 feed calls before any comment work starts. Large numbers are slow, not blocked.", "default": 10 }, "maxComments": { "title": "šŸ’¬ Comments to collect per post", "minimum": 0, "maximum": 5000, "type": "integer", "description": "šŸŽÆ **Hard cap on top-level comments per post.**\n\nšŸ“„ Instagram serves roughly **13 comments per request** and ignores any larger page size, so:\nā€¢ `13` ā‰ˆ free (already inside the post page)\nā€¢ `50` ā‰ˆ 3 extra requests\nā€¢ `500` ā‰ˆ 38 extra requests\nā€¢ `5000` ā‰ˆ 380 extra requests\n\nā†Ŗļø With a session cookie the thread is filled from Instagram's **threaded** listing first (~15 comments per request, and it reports each comment's reply count) and topped up from the logged-out connection afterwards. Same cap, better data.\n\nšŸ§Š Set to **0** to skip comments entirely and scrape posts only.\nšŸ” Only applies when *Post detail level* is **Detailed** ā€” basic runs never fetch comments.", "default": 50 }, "onlyCommentsNewerThan": { "title": "šŸ• Only comments newer than", "type": "string", "description": "šŸ“† **Keep only comments posted after this moment (UTC).**\n\nāœ… Absolute tab ā†’ `2026-07-20` or a full ISO timestamp.\nāœ… Relative tab ā†’ `6 hours`, `3 days`, `1 week`, `2 months`, `1 year`.\n\nāš” **Why this is cheap:** Instagram serves comments strictly newest-first (verified in this build: **0 out-of-order pairs across 629 consecutive comments**), so the scraper stops the moment it crosses your cutoff instead of paging to the end. On a 4,000-comment post a 24-hour window is a handful of requests instead of hundreds.\n\nšŸ”• Leave empty to collect up to *Comments to collect per post* regardless of age.", "default": null }, "emitCommentsDataset": { "title": "šŸ—‚ļø Also write a flat comments table", "type": "boolean", "description": "šŸ“Š **On** ā†’ every comment is additionally written to a second dataset named `ig-comments-`, **one row per comment**, ready for a spreadsheet or a BI tool without unnesting the `latestComments` array.\n\nšŸ“Œ The main dataset is unchanged either way ā€” this is an extra, not a replacement. These extra rows are **not charged**; only saved posts are.", "default": true }, "includeReplies": { "title": "ā†Ŗļø Try to collect replies under each comment", "type": "boolean", "description": "āœ… **On** ā†’ when a session cookie is supplied, every comment's real reply count is read and the replies underneath it are fetched into `latestComments[].replies[]`.\nšŸ”• **Off** ā†’ replies are never attempted; `replies` stays `[]` and `repliesCount` stays `null`.\n\nšŸ“Š Two counters are always published side by side: `repliesDeclared` (what Instagram says is there) and `repliesCollected` (what came back). **Collected is normally ~78-86% of declared** ā€” deleted, hidden and spam-filtered replies stay inside Instagram's own count. We publish both instead of implying completeness.\n\nšŸ§­ Either way the run continues and every post row reports a `replyAccessStatus` column, so you always know which of the two happened.", "default": true }, "maxRepliesPerComment": { "title": "šŸ”¢ Max replies per comment", "minimum": 0, "maximum": 1000, "type": "integer", "description": "šŸŽÆ **Cap on replies fetched under a single comment.** Requests are only spent on comments Instagram actually reports as having replies ā€” comments it reports as having none cost nothing.\n\nšŸ“„ Replies arrive **6-9 per request** and the page size cannot be raised, so a 116-reply thread costs about 13 requests. The largest thread measured on this build: **declared 116 ā†’ 99 fetched over 13 pages**.\n\n0ļøāƒ£ Set to **0** to disable reply fetching entirely (same as turning the switch above off).", "default": 50 }, "sessionId": { "title": "šŸ”‘ Your Instagram `sessionid` cookie (optional)", "type": "string", "description": "šŸŖ **Paste the `sessionid` cookie from a logged-in instagram.com browser tab.** Either form is accepted: the **bare cookie value**, or the **whole cookie string** (`sessionid=...; csrftoken=...`). The log tells you which one was read ā€” never the value itself.\n\nšŸ” Stored encrypted by Apify. It is never written to the dataset, never written to the log, and never sent anywhere except Instagram.\n\nāœ… **Verified end to end on this build**, not inherited from a spec: the session is proved alive once at the start of the run (and the account id is derived from it at runtime); a live session then returned **239 real replies out of 293 declared on a single post**, deepest thread 116 ā†’ 99.\n\nāš ļø If Instagram rejects the cookie the scraper says so once, **drops it and finishes the run logged out** ā€” it never retries in a loop, never fails the run, and never turns an unknown reply count into a zero.\n\nšŸ’” Everything except replies works perfectly without this field." }, "skipPinnedPosts": { "title": "šŸ“Œ Leave out pinned posts", "type": "boolean", "description": "šŸ“Œ **On** ā†’ posts pinned to the top of the profile grid are dropped.\n\nšŸ› ļø **Fixed in this build:** the pin flag is now matched against **the profile you are scraping**. The original logic matched it against the post's owner, so collaboration posts that were pinned on *somebody else's* grid were silently deleted from your results (measured precision 1 in 3 over 200 posts).", "default": false }, "onlyPostsNewerThan": { "title": "šŸ—“ļø Only posts newer than", "type": "string", "description": "šŸ“† **Keep only posts published after this moment (UTC).**\n\nāœ… Absolute tab ā†’ `2026-07-20` or a full ISO timestamp.\nāœ… Relative tab ā†’ `12 hours`, `3 days`, `1 week`, `2 months`, `1 year`.\n\nšŸ› ļø **Fixed in this build:** week / hour / minute values used to be discarded and the filter simply switched itself off without telling you. They now work, and an unreadable value stops the run with a clear message instead of silently returning unfiltered data. Instagram's feed is also not perfectly chronological, so paging continues a short way past the cutoff rather than stopping on the very first older post.\n\nšŸ”• Leave empty for no cutoff.", "default": null }, "dataDetailLevel": { "title": "šŸ”¬ Post detail level", "enum": [ "detailedData", "basicData" ], "type": "string", "description": "āš” **Basic** ā†’ posts only, straight from the feed. 2 requests per 12 posts. No comments, no alt text.\nšŸ”¬ **Detailed** ā†’ adds the comment thread, alt text, carousel child links, music info and paid-partnership flag. Costs one extra page request per post plus the comment paging you asked for.\n\nšŸ’µ **Both levels cost exactly the same per saved row** ā€” the difference is speed and completeness, not price.", "default": "detailedData" }, "proxyConfiguration": { "title": "šŸŒ Proxy configuration", "type": "object", "description": "šŸ›”ļø **Which proxy the run goes through.** Defaults to Apify Residential.\n\nšŸ’° Measured on this base: an Apify **datacenter** group returned exactly the same 36 of 36 rows as residential on the profile feed, so switching to datacenter is a legitimate cost saving rather than a downgrade.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "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 } } } } } } } } } }