{ "openapi": "3.0.1", "info": { "title": "Instagram Scraper", "description": "Fast no-login Instagram scraper. Extract profiles, posts, reels, comments, hashtags, locations, tagged feeds and audio reels. Paste URLs or search by keyword โ€” clean structured JSON. Works on any post age via 5-tier HTML fallback. Date filter, dedup, parallel race, residential proxy.", "version": "1.0", "x-build-id": "TaS29VJuwczCXdtOo" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/vortex_data~instagram-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-vortex_data-instagram-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/vortex_data~instagram-scraper/runs": { "post": { "operationId": "runs-sync-vortex_data-instagram-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/vortex_data~instagram-scraper/run-sync": { "post": { "operationId": "run-sync-vortex_data-instagram-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "directUrls": { "title": "1๏ธโƒฃ Paste Instagram URLs here", "uniqueItems": true, "type": "array", "description": "Paste exact Instagram URLs here. This is the best place to start.\n\n**No cookies needed in normal Apify runs**\n- ๐Ÿ‘ค Public profile: `instagram.com/{username}/` โ€” choose Posts, Reels, or Details\n- ๐Ÿ–ผ๏ธ Public post: `instagram.com/p/{shortcode}/` โ€” choose Posts, Details, or Comments\n- ๐ŸŽž๏ธ Public reel: `instagram.com/reel/{shortcode}/` โ€” choose Reels, Details, or Comments\n- ๐ŸŽต Audio page: `instagram.com/reels/audio/{audio_id}/` โ€” choose Posts/Reels or Details\n\n**Cookies required on Apify**\n- ๐Ÿ”Ž Keyword Search โ€” use the Search field below and paste cookies\n- #๏ธโƒฃ Hashtag URL: `instagram.com/explore/tags/{tag}/`\n- ๐Ÿ“ Location URL: `instagram.com/explore/locations/{id}/`\n- ๐ŸŽฌ Reels tab URL: `instagram.com/{username}/reels/`\n- ๐Ÿท๏ธ Tagged URL: `instagram.com/{username}/tagged/`\n- ๐Ÿ”’ Private, age-limited, login-walled, or hidden pages\n\nIf you paste a cookies-required URL without cookies, the actor will skip it before scraping and show a clear message instead of returning a confusing 0-result run.", "items": { "type": "string", "pattern": "^https?://(www\\.)?instagram\\.com/" } }, "resultsType": { "title": "2๏ธโƒฃ Choose what you want", "enum": [ "posts", "reels", "details", "comments" ], "type": "string", "description": "Choose the dataset you want.\n\n**No-cookie combinations**\n- Profile URL + Posts: recent public posts\n- Profile URL + Reels: public reels when Instagram exposes them in the profile feed\n- Profile URL + Details: profile information\n- Post/Reel URL + Details: one post or reel\n- Post/Reel URL + Comments: comments available from the public page preview\n- Audio URL + Posts/Reels or Details: reels using that audio or audio details\n\n**Cookies-required combinations**\n- Hashtag URL + Posts/Reels/Details\n- Location URL + Posts/Reels/Details\n- `/username/reels/` + Posts/Reels/Details\n- `/username/tagged/` + Posts/Reels\n- Any Keyword Search result\n\n**Important:** Comments works only with a direct post/reel URL: `/p/...`, `/reel/...`, or `/tv/...`.", "default": "posts" }, "resultsLimit": { "title": "๐Ÿ”ข Results per URL", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Maximum records to extract from each URL. For example, with `100` and 2 profile URLs you'll get up to 200 posts.", "default": 10 }, "maxTotalResults": { "title": "๐Ÿ’ธ Max total results (cost safety)", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Optional hard cap on the **total** records emitted by this run, no matter how many URLs you provide. Use this to keep cost predictable โ€” e.g. set `1000` to never spend more than 1000 records' worth of credit. Leave empty for no overall cap." }, "onlyPostsNewerThan": { "title": "๐Ÿ“… Only newer than", "pattern": "^(\\d{4})-(0[1-9]|1[0-2])-(0[1-9]|[12]\\d|3[01])(T[0-2]\\d:[0-5]\\d(:[0-5]\\d)?(\\.\\d+)?Z?)?$|^\\d+\\s*(minute|hour|day|week|month|year)s?$", "type": "string", "description": "Optional date filter โ€” skip posts older than this. The actor stops paging as soon as it crosses the cutoff, which makes the run faster.\n\n**Accepted formats**\n- `2026-01-15` (calendar date, UTC)\n- `2026-01-15T10:00:00Z` (full ISO time)\n- `1 day`, `2 weeks`, `3 months`, `1 year` (relative)" }, "addParentData": { "title": "๐Ÿท๏ธ Add source info to each result", "type": "boolean", "description": "If you scrape multiple sources at once, turn this on to add a `dataSource` field to every record (`profile`, `hashtag`, `location`, `post`, or `comments`) plus the parent username / tag / location id. Useful when merging results in a spreadsheet.", "default": false }, "dedupResults": { "title": "๐Ÿงน Remove duplicate posts", "type": "boolean", "description": "When the same post appears in multiple sources (e.g. a hashtag feed and the author's profile), keep only the first one. Recommended.", "default": true }, "sessionCookies": { "title": "๐Ÿ” Instagram cookies (only for locked features)", "type": "string", "description": "Leave empty when scraping only:\n- public profile URLs;\n- public post/reel URLs;\n- comments on a public post/reel URL;\n- audio URLs.\n\nPaste your own Instagram cookies when using:\n- Keyword Search;\n- hashtag URLs;\n- location URLs;\n- `/username/reels/` URLs;\n- `/username/tagged/` URLs;\n- private, age-limited, login-walled, or hidden pages.\n\n**How to copy cookies from Chrome / Edge**\n1. Open `instagram.com` and log in to your own account.\n2. Open the Instagram page you want to scrape, or open Instagram search if you want Keyword Search.\n3. Press `F12`, or right-click the page and choose **Inspect**.\n4. Open the **Network** tab and enable **Preserve log** if it is available.\n5. Refresh the Instagram page with `Ctrl+R`.\n6. Click the main document request: `www.instagram.com` or the request named like the username / page path. Do not click image, CSS, JavaScript, GraphQL, or analytics requests.\n7. Open **Headers** -> **Request Headers**.\n8. Find **Cookie** and copy the full value. Copy only the value after `Cookie:`, not the word `Cookie:`.\n9. Paste that value here.\n\nCorrect format:\n`sessionid=...; csrftoken=...; ds_user_id=...; mid=...`\n\nIf you cannot find **Cookie**, keep DevTools open on Network, refresh again, click the request with Type `document` / `doc`, and check **Request Headers**. Do not copy `Set-Cookie` from Response Headers.\n\nYou can also paste JSON from Cookie-Editor or a Netscape cookie export. Cookies are sensitive and work like a password: use only your own Instagram account cookies and do not share them." }, "search": { "title": "๐Ÿ”Ž Keyword Search (cookies required)", "type": "string", "description": "Leave this empty for no-cookie runs.\n\nUse Search only when you also paste your own Instagram cookies above. Instagram blocks logged-out keyword search.\n\nExamples: `travel`, `nasa`, `musk`." }, "searchType": { "title": "๐ŸŽฏ Search target", "enum": [ "hashtag", "profile", "place" ], "type": "string", "description": "Only used when Search query is filled and Instagram cookies are provided. Ignored for direct URLs.", "default": "hashtag" }, "searchLimit": { "title": "๐Ÿ”ข Search matches to scrape", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many profiles, hashtags, or places to take from Search. Direct URLs do not use this setting.", "default": 10 }, "concurrency": { "title": "โšก Speed: parallel URLs", "minimum": 1, "maximum": 32, "type": "integer", "description": "How many URLs to scrape at the same time. Higher = faster, but more likely to hit rate limits.", "default": 4 }, "requestRetryBudget": { "title": "๐Ÿ” Retries per request", "minimum": 0, "maximum": 20, "type": "integer", "description": "If a single request fails (network blip, 500, 429), how many times to retry it before giving up. Each retry uses a fresh IP.", "default": 3 }, "urlRetryBudget": { "title": "๐Ÿ” Retries per URL", "minimum": 0, "maximum": 50, "type": "integer", "description": "How many failed pages we'll tolerate inside one URL (e.g. while paginating through 1,000 posts) before skipping that URL.", "default": 5 }, "globalRateLimitBudget": { "title": "๐Ÿ›‘ Stop after too many rate limits", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Total 429 (rate-limit) responses allowed across the whole run before the actor aborts. Stops runaway costs if Instagram is blocking us hard.", "default": 50 } } }, "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 } } } } } } } } } }