{ "data": { "id": "Ua3QPyCof7v3HFAEk", "actId": "VSfaWsBiswkFBVtAo", "userId": "IYgBDiXtHOijAaUel", "startedAt": "2026-10-26T16:20:33.307Z", "finishedAt": "2026-10-26T16:21:06.077Z", "status": "SUCCEEDED", "meta": { "origin": "CLI" }, "stats": { "durationMillis": 32629, "runTimeSecs": 32.629, "computeUnits": 0.03625444444444444, "imageSizeBytes": 3103337984 }, "options": { "useCache": true, "betaPackages": false, "memoryMbytes": 4096, "diskMbytes": 8192 }, "createdByOrganizationMemberUserId": "QYo53EZkJk0prePWY", "exitCode": 0, "inputSchema": "{\n \"title\": \"TikTok Post Scraper Input\",\n \"description\": \"Scrape TikTok posts, profiles, and comment threads without cookies. Paste post URLs or IDs, profile handles, or both.\",\n \"type\": \"object\",\n \"schemaVersion\": 1,\n \"properties\": {\n \"mode\": {\n \"title\": \"Mode\",\n \"type\": \"string\",\n \"description\": \"What to scrape: individual posts, a profile's newest posts, or comment threads on posts.\",\n \"editor\": \"select\",\n \"enum\": [\n \"posts\",\n \"profiles\",\n \"comments\"\n ],\n \"enumTitles\": [\n \"Posts by URL or ID\",\n \"Profiles (newest posts)\",\n \"Comments and replies\"\n ],\n \"default\": \"posts\",\n \"prefill\": \"posts\"\n },\n \"postUrls\": {\n \"title\": \"Post URLs or IDs\",\n \"type\": \"array\",\n \"description\": \"TikTok video/photo URLs, /v/ share links, embed links, vm.tiktok.com or vt.tiktok.com short links, or bare numeric post IDs. Duplicates are scraped once.\",\n \"editor\": \"stringList\",\n \"items\": {\n \"type\": \"string\"\n },\n \"prefill\": [\n \"https://www.tiktok.com/@khaby.lame/video/7574844184952081686\"\n ]\n },\n \"postIds\": {\n \"title\": \"Post IDs\",\n \"type\": \"array\",\n \"description\": \"Numeric TikTok post IDs (15-20 digits). Use this instead of, or in addition to, postUrls.\",\n \"editor\": \"stringList\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"profiles\": {\n \"title\": \"Profiles\",\n \"type\": \"array\",\n \"description\": \"TikTok usernames (@handle), profile URLs, or bare handles. Profiles mode returns up to 500 newest posts per profile; comments mode can use them as comment targets.\",\n \"editor\": \"stringList\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"maxItems\": {\n \"title\": \"Max rows\",\n \"type\": \"integer\",\n \"description\": \"Global cap on output rows. Posts mode counts posts; profiles mode counts posts; comments mode counts comments and replies. Status rows do not count.\",\n \"default\": 100,\n \"minimum\": 1,\n \"maximum\": 1000,\n \"prefill\": 1\n },\n \"maxDetail\": {\n \"title\": \"Max detail lookups\",\n \"type\": \"integer\",\n \"description\": \"How many posts get the slower page/detail enrichment (caption language, collect/repost counts, video tracks). Remaining posts use the fast embed record. Set to 1 for the smallest daily-test run.\",\n \"default\": 50,\n \"minimum\": 1,\n \"maximum\": 300,\n \"prefill\": 1\n },\n \"maxCommentsPerPost\": {\n \"title\": \"Max comments per post\",\n \"type\": \"integer\",\n \"description\": \"Maximum comments plus replies to keep for each post in comments mode, or to attach to each post when Include comments is on.\",\n \"default\": 100,\n \"minimum\": 1,\n \"maximum\": 1000,\n \"prefill\": 100\n },\n \"includeReplies\": {\n \"title\": \"Include replies\",\n \"type\": \"boolean\",\n \"description\": \"Fetch the reply thread under each root comment and include replies with their parent.\",\n \"default\": false,\n \"prefill\": false\n },\n \"includeComments\": {\n \"title\": \"Include comments\",\n \"type\": \"boolean\",\n \"description\": \"In posts/profiles mode, attach a comments array to each post. In comments mode, emit root comment rows (comments mode enables this automatically when both comment toggles are off).\",\n \"default\": false,\n \"prefill\": false\n },\n \"proxyConfiguration\": {\n \"title\": \"Proxy configuration\",\n \"type\": \"object\",\n \"description\": \"Optional. Leave empty to run directly; a proxy is not required. The actor falls back to an Apify datacenter proxy on a block signal.\",\n \"editor\": \"proxy\"\n },\n \"includeMediaUrls\": {\n \"title\": \"Include media URLs\",\n \"type\": \"boolean\",\n \"description\": \"Include signed video, cover, music, and slideshow image URLs plus mediaUrlExpiresAt. They typically expire in about 48 hours.\",\n \"default\": true,\n \"prefill\": true\n },\n \"validateMediaUrls\": {\n \"title\": \"Validate media URLs\",\n \"type\": \"boolean\",\n \"description\": \"Check the main media URL with a GET Range request (TikTok's CDN rejects HEAD) and add mediaUrlAccessible. Adds latency.\",\n \"default\": false,\n \"prefill\": false\n },\n \"includeAuthorStats\": {\n \"title\": \"Include author stats\",\n \"type\": \"boolean\",\n \"description\": \"Include follower, following, heart, and video counts in author and authorStats.\",\n \"default\": true,\n \"prefill\": true\n },\n \"includeHashtags\": {\n \"title\": \"Include hashtags\",\n \"type\": \"boolean\",\n \"description\": \"Include the hashtags array extracted from the caption.\",\n \"default\": true,\n \"prefill\": true\n },\n \"includeMentions\": {\n \"title\": \"Include mentions\",\n \"type\": \"boolean\",\n \"description\": \"Include the mentions array extracted from the caption with text offsets.\",\n \"default\": true,\n \"prefill\": true\n },\n \"includeSubtitles\": {\n \"title\": \"Include subtitle and bitrate tracks\",\n \"type\": \"boolean\",\n \"description\": \"Include video.subtitleInfos, video.bitrateInfo, and video.volumeInfo (detail path only).\",\n \"default\": false,\n \"prefill\": false\n },\n \"includeRawFields\": {\n \"title\": \"Include raw TikTok fields\",\n \"type\": \"boolean\",\n \"description\": \"Include item_control, contents, effectStickers, and stickersOnItem from the detail payload. Legacy includeEffectStickers/includeItemControl/includeContents inputs map here.\",\n \"default\": false,\n \"prefill\": false\n }\n },\n \"required\": []\n}", "readme": "# TikTok Post Scraper\n\nPaste a TikTok link, a bare post ID, or a profile handle and get structured post data back: engagement counts, the creator's snapshot at scrape time, the sound, every hashtag and @mention, carousel images, and signed media URLs. The actor also reads comment threads, including replies, and can walk a profile's newest posts. No TikTok account, cookies, or login are required.\n\n## Three ways to use it\n\n| Mode | What you provide | What you get |\n|---|---|---|\n| **Posts** | Video/photo URLs, share links, or numeric IDs | One row per post |\n| **Profiles** | Handles, @names, or profile URLs | One row per newest post, up to 500 per profile |\n| **Comments** | Post URLs/IDs and/or profiles | One row per comment and reply, up to 1,000 per post |\n\nThe default run is the smallest useful one: one known slideshow post, embed-first, no comments.\n\n## What makes it useful\n\n- **Fast first, rich when asked.** Every post starts on TikTok's embed surface (~0.7 s). The slower page/detail path runs only for `maxDetail` posts, so bulk runs stay quick while the first rows still carry language, collect/repost counts, and video tracks.\n- **Slideshows stay slideshows.** Carousel posts are detected from both the embed shape (`imagePostInfo.displayImages`) and the detail shape (`imagePost.images`), so the images array is not lost when the fast path misses.\n- **Bare IDs work.** IDs are opened with a safe placeholder username instead of the `/video/` path that redirects to a 404.\n- **No silent holes.** Deleted, private, region-locked, or blocked inputs become explicit `recordType: \"status\"` rows with a reason, not an empty dataset.\n- **Honest media checks.** TikTok's video CDN rejects `HEAD`; the optional URL check uses a `GET Range` request and reports what actually answered.\n- **Deduplicated.** The same post ID from a URL, a short link, and an ID list is scraped once. Comments are deduplicated by comment ID.\n\n## Input\n\n| Field | Type | Default | Notes |\n|---|---|---|---|\n| `mode` | select | `posts` | `posts`, `profiles`, or `comments` |\n| `postUrls` | array | one slideshow prefill | Video/photo URLs, `/v/` and `/share/` links, embed links, `vm.tiktok.com`/`vt.tiktok.com`/`tiktok.com/t/` short links, or bare IDs |\n| `postIds` | array | – | 15–20 digit numeric IDs |\n| `profiles` | array | – | `@handle`, profile URL, or bare handle; up to 500 newest posts per profile |\n| `maxItems` | integer 1–1000 | `100` | Global row cap. Posts/profiles count posts; comments counts comments + replies |\n| `maxDetail` | integer 1–300 | `50` | How many posts get the slower page/detail enrichment |\n| `maxCommentsPerPost` | integer 1–1000 | `100` | Comments + replies kept per post |\n| `includeReplies` | boolean | `false` | Fetch reply threads under root comments |\n| `includeComments` | boolean | `false` | Attach a `comments` array in posts/profiles mode; emit root comment rows in comments mode |\n| `proxyConfiguration` | object | – | Optional. Direct requests are the default; AUTO datacenter is used on a block signal |\n| `includeMediaUrls` | boolean | `true` | Signed video/cover/music/image URLs and `mediaUrlExpiresAt` |\n| `validateMediaUrls` | boolean | `false` | Range GET probe → `mediaUrlAccessible` |\n| `includeAuthorStats` | boolean | `true` | `authorStats` and legacy author counts |\n| `includeHashtags` | boolean | `true` | Hashtags array |\n| `includeMentions` | boolean | `true` | Mentions array with offsets |\n| `includeSubtitles` | boolean | `false` | `video.subtitleInfos`, `bitrateInfo`, `volumeInfo` |\n| `includeRawFields` | boolean | `false` | `item_control`, `contents`, `effectStickers`, `stickersOnItem` |\n\n### Examples\n\nScrape one video and one carousel, with detail enrichment:\n\n```json\n{\n \"mode\": \"posts\",\n \"postUrls\": [\n \"https://www.tiktok.com/@natgeo/video/7683891628230315295\",\n \"https://www.tiktok.com/@nba/photo/7690755132400618783\"\n ],\n \"maxItems\": 2,\n \"maxDetail\": 2\n}\n```\n\nWalk a profile's newest posts:\n\n```json\n{\n \"mode\": \"profiles\",\n \"profiles\": [\"natgeo\"],\n \"maxItems\": 50,\n \"maxDetail\": 20\n}\n```\n\nRead comments and replies from a post:\n\n```json\n{\n \"mode\": \"comments\",\n \"postUrls\": [\"https://www.tiktok.com/@natgeo/video/7683891628230315295\"],\n \"maxCommentsPerPost\": 200,\n \"includeReplies\": true,\n \"maxItems\": 200\n}\n```\n\nBulk short links and IDs:\n\n```json\n{\n \"mode\": \"posts\",\n \"postUrls\": [\"https://vm.tiktok.com/ZMabc123/\"],\n \"postIds\": [\"7574844184952081686\"],\n \"maxItems\": 100\n}\n```\n\n## Output\n\nEvery record is omit-empty: absent fields are left out rather than returned as `null`, `\"\"`, or an empty array.\n\n### Post rows (`recordType: \"post\"`)\n\n- `postId`, `postType` (`video`/`slideshow`), `postUrl`\n- `caption`, `textLanguage`, `createTime`, `createdAt`, `locationCreated`, `viewerRegion`\n- `author` — id, secUid, username, displayName, bio, verified, privateAccount, avatarUrl, roomId (legacy counts also live here)\n- `authorStats` — followerCount, followingCount, heartCount, videoCount\n- `stats` — playCount, likeCount, commentCount, shareCount, collectCount, repostCount (also kept as flat legacy fields)\n- `flags` — stitchEnabled, duetEnabled, shareEnabled, commentStatus, isAd, isAigc, isECVideo, privateItem, forFriend, originalItem, plus labels when present (also kept flat)\n- `music` — id, title, authorName, album, original, duration, shootDuration, licensing flags, dspLinks, playUrl, coverUrl\n- `video` — width, height, duration, ratio, definition, bitrate, codecType, format, size, videoQuality, playUrl, downloadAddr, cover, originCover, dynamicCover, optional subtitle/bitrate/volume tracks\n- `images` — ordered carousel objects: `ordinal`, `width`, `height`, `urlList`\n- `hashtags`, `mentions`\n- `mediaUrlExpiresAt`, optional `mediaUrlAccessible`\n- `source` (`embed`, `detail`, `ssr`, or `profile`), `scrapedAt`, `recordType`\n- Profiles mode adds `profileUsername`, `position`, and `isPinned` when the profile pinned the post\n- `comments` when `includeComments` is on: root comments, each optionally carrying a `replies` array\n\n### Comment rows (`recordType: \"comment\"` or `\"reply\"`)\n\n`commentId`, `postId`, `postUrl`, `text`, `createTime`, `createdAt`, `likeCount`, `replyCount`, `isPinnedByAuthor`, `isLikedByAuthor`, `isTranslatable`, `language`, `isReply`, `replyToCommentId`, `threadId`, `user` (id, secUid, username, displayName, avatarUrl, optional verified), `images`, `textExtra`, optional share link/stickers/labels, `source`, `scrapedAt`.\n\n### Status rows (`recordType: \"status\"`)\n\n`status` is one of `not_found`, `private`, `region`, or `blocked`, plus `input`, optional `postId`, `message`, `httpStatus`, `source`, and `scrapedAt`. Status rows are diagnostics and do not count toward `maxItems`.\n\n## Limits and behaviour\n\n- **Posts:** up to `maxItems` rows (1–1000). `maxDetail` caps the slower page/detail lookups (1–300).\n- **Profiles:** up to 500 newest posts per profile and `maxItems` rows overall. The profile feed normally comes from TikTok's itemList; if that XHR returns an empty body, the actor retries and then falls back to the creator itemList endpoint.\n- **Comments:** up to 1,000 comment + reply rows per post. TikTok's `total` counter is not used as a progress guarantee; the actor follows the cursor and stops after repeated empty windows.\n- **Pacing:** requests are spaced 1.2–2.0 s apart. HTTP 429 and 503 responses are retried with a 1.5–4.5 s backoff.\n- **Media URLs** are signed and typically expire in about 48 hours. `mediaUrlExpiresAt` tells you when.\n- **Private / deleted / region-locked posts** cannot be read without cookies; they produce a status row.\n- **Comments on deleted posts** may look identical to a post with no comments; the actor reports the post status it observed.\n\n## FAQ\n\n**Do I need a TikTok account or cookies?**\nNo. The actor uses public embed pages, the public video page, and unsigned comment endpoints.\n\n**Is a proxy required?**\nNo. Direct requests are the primary path. If TikTok blocks the request, the actor retries with an Apify datacenter proxy. A proxy is exposed only for users who want to supply their own.\n\n**Why do some rows have more fields than others?**\nThe embed path is fast but omits a few detail-only values (caption language, collect/repost counts, video tracks). Raise `maxDetail` to enrich more posts; the actor never fabricates a field it could not read.\n\n**How do I get only slideshows?**\nProvide slideshow URLs or IDs. Slideshow rows have `postType: \"slideshow\"` and an ordered `images` array. There is no separate slideshow-only mode because the same post-ID path covers videos and carousels.\n\n**Why is a row missing?**\nCheck the status view. Inputs that cannot be parsed, resolved, or read are reported there instead of disappearing.\n\n**Can I attach comments to post rows?**\nYes. Set `includeComments: true` in posts or profiles mode; set `includeReplies` too if you want reply threads nested under each root comment.\n\n**Is this affiliated with TikTok?**\nNo. This is an independent, third-party actor that reads publicly viewable TikTok content.\n", "actorDefinition": { "actorSpecification": 1, "name": "tiktok-post-and-slideshow-detail-scraper", "title": "TikTok Post & Slideshow Detail Scraper", "description": "Scrape TikTok posts, profiles, and comment threads by URL or ID: engagement stats, author snapshot, music, slideshow images, hashtags, mentions, signed media, and replies. No cookies or proxy setup required.", "version": "2.0", "buildTag": "latest", "dockerfile": "./Dockerfile", "readme": "# TikTok Post Scraper\n\nPaste a TikTok link, a bare post ID, or a profile handle and get structured post data back: engagement counts, the creator's snapshot at scrape time, the sound, every hashtag and @mention, carousel images, and signed media URLs. The actor also reads comment threads, including replies, and can walk a profile's newest posts. No TikTok account, cookies, or login are required.\n\n## Three ways to use it\n\n| Mode | What you provide | What you get |\n|---|---|---|\n| **Posts** | Video/photo URLs, share links, or numeric IDs | One row per post |\n| **Profiles** | Handles, @names, or profile URLs | One row per newest post, up to 500 per profile |\n| **Comments** | Post URLs/IDs and/or profiles | One row per comment and reply, up to 1,000 per post |\n\nThe default run is the smallest useful one: one known slideshow post, embed-first, no comments.\n\n## What makes it useful\n\n- **Fast first, rich when asked.** Every post starts on TikTok's embed surface (~0.7 s). The slower page/detail path runs only for `maxDetail` posts, so bulk runs stay quick while the first rows still carry language, collect/repost counts, and video tracks.\n- **Slideshows stay slideshows.** Carousel posts are detected from both the embed shape (`imagePostInfo.displayImages`) and the detail shape (`imagePost.images`), so the images array is not lost when the fast path misses.\n- **Bare IDs work.** IDs are opened with a safe placeholder username instead of the `/video/` path that redirects to a 404.\n- **No silent holes.** Deleted, private, region-locked, or blocked inputs become explicit `recordType: \"status\"` rows with a reason, not an empty dataset.\n- **Honest media checks.** TikTok's video CDN rejects `HEAD`; the optional URL check uses a `GET Range` request and reports what actually answered.\n- **Deduplicated.** The same post ID from a URL, a short link, and an ID list is scraped once. Comments are deduplicated by comment ID.\n\n## Input\n\n| Field | Type | Default | Notes |\n|---|---|---|---|\n| `mode` | select | `posts` | `posts`, `profiles`, or `comments` |\n| `postUrls` | array | one slideshow prefill | Video/photo URLs, `/v/` and `/share/` links, embed links, `vm.tiktok.com`/`vt.tiktok.com`/`tiktok.com/t/` short links, or bare IDs |\n| `postIds` | array | – | 15–20 digit numeric IDs |\n| `profiles` | array | – | `@handle`, profile URL, or bare handle; up to 500 newest posts per profile |\n| `maxItems` | integer 1–1000 | `100` | Global row cap. Posts/profiles count posts; comments counts comments + replies |\n| `maxDetail` | integer 1–300 | `50` | How many posts get the slower page/detail enrichment |\n| `maxCommentsPerPost` | integer 1–1000 | `100` | Comments + replies kept per post |\n| `includeReplies` | boolean | `false` | Fetch reply threads under root comments |\n| `includeComments` | boolean | `false` | Attach a `comments` array in posts/profiles mode; emit root comment rows in comments mode |\n| `proxyConfiguration` | object | – | Optional. Direct requests are the default; AUTO datacenter is used on a block signal |\n| `includeMediaUrls` | boolean | `true` | Signed video/cover/music/image URLs and `mediaUrlExpiresAt` |\n| `validateMediaUrls` | boolean | `false` | Range GET probe → `mediaUrlAccessible` |\n| `includeAuthorStats` | boolean | `true` | `authorStats` and legacy author counts |\n| `includeHashtags` | boolean | `true` | Hashtags array |\n| `includeMentions` | boolean | `true` | Mentions array with offsets |\n| `includeSubtitles` | boolean | `false` | `video.subtitleInfos`, `bitrateInfo`, `volumeInfo` |\n| `includeRawFields` | boolean | `false` | `item_control`, `contents`, `effectStickers`, `stickersOnItem` |\n\n### Examples\n\nScrape one video and one carousel, with detail enrichment:\n\n```json\n{\n \"mode\": \"posts\",\n \"postUrls\": [\n \"https://www.tiktok.com/@natgeo/video/7683891628230315295\",\n \"https://www.tiktok.com/@nba/photo/7690755132400618783\"\n ],\n \"maxItems\": 2,\n \"maxDetail\": 2\n}\n```\n\nWalk a profile's newest posts:\n\n```json\n{\n \"mode\": \"profiles\",\n \"profiles\": [\"natgeo\"],\n \"maxItems\": 50,\n \"maxDetail\": 20\n}\n```\n\nRead comments and replies from a post:\n\n```json\n{\n \"mode\": \"comments\",\n \"postUrls\": [\"https://www.tiktok.com/@natgeo/video/7683891628230315295\"],\n \"maxCommentsPerPost\": 200,\n \"includeReplies\": true,\n \"maxItems\": 200\n}\n```\n\nBulk short links and IDs:\n\n```json\n{\n \"mode\": \"posts\",\n \"postUrls\": [\"https://vm.tiktok.com/ZMabc123/\"],\n \"postIds\": [\"7574844184952081686\"],\n \"maxItems\": 100\n}\n```\n\n## Output\n\nEvery record is omit-empty: absent fields are left out rather than returned as `null`, `\"\"`, or an empty array.\n\n### Post rows (`recordType: \"post\"`)\n\n- `postId`, `postType` (`video`/`slideshow`), `postUrl`\n- `caption`, `textLanguage`, `createTime`, `createdAt`, `locationCreated`, `viewerRegion`\n- `author` — id, secUid, username, displayName, bio, verified, privateAccount, avatarUrl, roomId (legacy counts also live here)\n- `authorStats` — followerCount, followingCount, heartCount, videoCount\n- `stats` — playCount, likeCount, commentCount, shareCount, collectCount, repostCount (also kept as flat legacy fields)\n- `flags` — stitchEnabled, duetEnabled, shareEnabled, commentStatus, isAd, isAigc, isECVideo, privateItem, forFriend, originalItem, plus labels when present (also kept flat)\n- `music` — id, title, authorName, album, original, duration, shootDuration, licensing flags, dspLinks, playUrl, coverUrl\n- `video` — width, height, duration, ratio, definition, bitrate, codecType, format, size, videoQuality, playUrl, downloadAddr, cover, originCover, dynamicCover, optional subtitle/bitrate/volume tracks\n- `images` — ordered carousel objects: `ordinal`, `width`, `height`, `urlList`\n- `hashtags`, `mentions`\n- `mediaUrlExpiresAt`, optional `mediaUrlAccessible`\n- `source` (`embed`, `detail`, `ssr`, or `profile`), `scrapedAt`, `recordType`\n- Profiles mode adds `profileUsername`, `position`, and `isPinned` when the profile pinned the post\n- `comments` when `includeComments` is on: root comments, each optionally carrying a `replies` array\n\n### Comment rows (`recordType: \"comment\"` or `\"reply\"`)\n\n`commentId`, `postId`, `postUrl`, `text`, `createTime`, `createdAt`, `likeCount`, `replyCount`, `isPinnedByAuthor`, `isLikedByAuthor`, `isTranslatable`, `language`, `isReply`, `replyToCommentId`, `threadId`, `user` (id, secUid, username, displayName, avatarUrl, optional verified), `images`, `textExtra`, optional share link/stickers/labels, `source`, `scrapedAt`.\n\n### Status rows (`recordType: \"status\"`)\n\n`status` is one of `not_found`, `private`, `region`, or `blocked`, plus `input`, optional `postId`, `message`, `httpStatus`, `source`, and `scrapedAt`. Status rows are diagnostics and do not count toward `maxItems`.\n\n## Limits and behaviour\n\n- **Posts:** up to `maxItems` rows (1–1000). `maxDetail` caps the slower page/detail lookups (1–300).\n- **Profiles:** up to 500 newest posts per profile and `maxItems` rows overall. The profile feed normally comes from TikTok's itemList; if that XHR returns an empty body, the actor retries and then falls back to the creator itemList endpoint.\n- **Comments:** up to 1,000 comment + reply rows per post. TikTok's `total` counter is not used as a progress guarantee; the actor follows the cursor and stops after repeated empty windows.\n- **Pacing:** requests are spaced 1.2–2.0 s apart. HTTP 429 and 503 responses are retried with a 1.5–4.5 s backoff.\n- **Media URLs** are signed and typically expire in about 48 hours. `mediaUrlExpiresAt` tells you when.\n- **Private / deleted / region-locked posts** cannot be read without cookies; they produce a status row.\n- **Comments on deleted posts** may look identical to a post with no comments; the actor reports the post status it observed.\n\n## FAQ\n\n**Do I need a TikTok account or cookies?**\nNo. The actor uses public embed pages, the public video page, and unsigned comment endpoints.\n\n**Is a proxy required?**\nNo. Direct requests are the primary path. If TikTok blocks the request, the actor retries with an Apify datacenter proxy. A proxy is exposed only for users who want to supply their own.\n\n**Why do some rows have more fields than others?**\nThe embed path is fast but omits a few detail-only values (caption language, collect/repost counts, video tracks). Raise `maxDetail` to enrich more posts; the actor never fabricates a field it could not read.\n\n**How do I get only slideshows?**\nProvide slideshow URLs or IDs. Slideshow rows have `postType: \"slideshow\"` and an ordered `images` array. There is no separate slideshow-only mode because the same post-ID path covers videos and carousels.\n\n**Why is a row missing?**\nCheck the status view. Inputs that cannot be parsed, resolved, or read are reported there instead of disappearing.\n\n**Can I attach comments to post rows?**\nYes. Set `includeComments: true` in posts or profiles mode; set `includeReplies` too if you want reply threads nested under each root comment.\n\n**Is this affiliated with TikTok?**\nNo. This is an independent, third-party actor that reads publicly viewable TikTok content.\n", "input": { "title": "TikTok Post Scraper Input", "description": "Scrape TikTok posts, profiles, and comment threads without cookies. Paste post URLs or IDs, profile handles, or both.", "type": "object", "schemaVersion": 1, "properties": { "mode": { "title": "Mode", "type": "string", "description": "What to scrape: individual posts, a profile's newest posts, or comment threads on posts.", "editor": "select", "enum": [ "posts", "profiles", "comments" ], "enumTitles": [ "Posts by URL or ID", "Profiles (newest posts)", "Comments and replies" ], "default": "posts", "prefill": "posts" }, "postUrls": { "title": "Post URLs or IDs", "type": "array", "description": "TikTok video/photo URLs, /v/ share links, embed links, vm.tiktok.com or vt.tiktok.com short links, or bare numeric post IDs. Duplicates are scraped once.", "editor": "stringList", "items": { "type": "string" }, "prefill": [ "https://www.tiktok.com/@khaby.lame/video/7574844184952081686" ] }, "postIds": { "title": "Post IDs", "type": "array", "description": "Numeric TikTok post IDs (15-20 digits). Use this instead of, or in addition to, postUrls.", "editor": "stringList", "items": { "type": "string" } }, "profiles": { "title": "Profiles", "type": "array", "description": "TikTok usernames (@handle), profile URLs, or bare handles. Profiles mode returns up to 500 newest posts per profile; comments mode can use them as comment targets.", "editor": "stringList", "items": { "type": "string" } }, "maxItems": { "title": "Max rows", "type": "integer", "description": "Global cap on output rows. Posts mode counts posts; profiles mode counts posts; comments mode counts comments and replies. Status rows do not count.", "default": 100, "minimum": 1, "maximum": 1000, "prefill": 1 }, "maxDetail": { "title": "Max detail lookups", "type": "integer", "description": "How many posts get the slower page/detail enrichment (caption language, collect/repost counts, video tracks). Remaining posts use the fast embed record. Set to 1 for the smallest daily-test run.", "default": 50, "minimum": 1, "maximum": 300, "prefill": 1 }, "maxCommentsPerPost": { "title": "Max comments per post", "type": "integer", "description": "Maximum comments plus replies to keep for each post in comments mode, or to attach to each post when Include comments is on.", "default": 100, "minimum": 1, "maximum": 1000, "prefill": 100 }, "includeReplies": { "title": "Include replies", "type": "boolean", "description": "Fetch the reply thread under each root comment and include replies with their parent.", "default": false, "prefill": false }, "includeComments": { "title": "Include comments", "type": "boolean", "description": "In posts/profiles mode, attach a comments array to each post. In comments mode, emit root comment rows (comments mode enables this automatically when both comment toggles are off).", "default": false, "prefill": false }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. Leave empty to run directly; a proxy is not required. The actor falls back to an Apify datacenter proxy on a block signal.", "editor": "proxy" }, "includeMediaUrls": { "title": "Include media URLs", "type": "boolean", "description": "Include signed video, cover, music, and slideshow image URLs plus mediaUrlExpiresAt. They typically expire in about 48 hours.", "default": true, "prefill": true }, "validateMediaUrls": { "title": "Validate media URLs", "type": "boolean", "description": "Check the main media URL with a GET Range request (TikTok's CDN rejects HEAD) and add mediaUrlAccessible. Adds latency.", "default": false, "prefill": false }, "includeAuthorStats": { "title": "Include author stats", "type": "boolean", "description": "Include follower, following, heart, and video counts in author and authorStats.", "default": true, "prefill": true }, "includeHashtags": { "title": "Include hashtags", "type": "boolean", "description": "Include the hashtags array extracted from the caption.", "default": true, "prefill": true }, "includeMentions": { "title": "Include mentions", "type": "boolean", "description": "Include the mentions array extracted from the caption with text offsets.", "default": true, "prefill": true }, "includeSubtitles": { "title": "Include subtitle and bitrate tracks", "type": "boolean", "description": "Include video.subtitleInfos, video.bitrateInfo, and video.volumeInfo (detail path only).", "default": false, "prefill": false }, "includeRawFields": { "title": "Include raw TikTok fields", "type": "boolean", "description": "Include item_control, contents, effectStickers, and stickersOnItem from the detail payload. Legacy includeEffectStickers/includeItemControl/includeContents inputs map here.", "default": false, "prefill": false } }, "required": [] }, "output": { "actorOutputSchemaVersion": 1, "title": "TikTok Post Scraper Output", "description": "Post rows with engagement stats, author snapshot, music, media, hashtags/mentions; comment rows with replies; and explicit status rows for unavailable inputs.", "properties": { "dataset": { "type": "string", "title": "Dataset", "description": "All records: posts, comments/replies, and status rows. Use the dataset views to switch between them.", "template": "{{links.apiDefaultDatasetUrl}}/items" } } }, "categories": [ "SOCIAL_MEDIA" ], "defaultMemoryMbytes": 2048, "minMemoryMbytes": 1024, "storages": { "dataset": { "actorSpecification": 1, "title": "TikTok Posts, Profiles & Comments", "views": { "overview": { "title": "Posts Overview", "description": "One row per post with engagement metrics, author snapshot, and the extraction source.", "transformation": { "fields": [ "postId", "postUrl", "postType", "caption", "createdAt", "playCount", "likeCount", "commentCount", "shareCount", "author", "recordType", "source", "scrapedAt" ] }, "display": { "component": "table", "properties": { "postId": { "label": "Post ID", "format": "text" }, "postUrl": { "label": "Post URL", "format": "link" }, "postType": { "label": "Type", "format": "text" }, "caption": { "label": "Caption", "format": "text" }, "createdAt": { "label": "Created At", "format": "text" }, "playCount": { "label": "Plays", "format": "number" }, "likeCount": { "label": "Likes", "format": "number" }, "commentCount": { "label": "Comments", "format": "number" }, "shareCount": { "label": "Shares", "format": "number" }, "author": { "label": "Author", "format": "object" }, "recordType": { "label": "Record", "format": "text" }, "source": { "label": "Source", "format": "text" }, "scrapedAt": { "label": "Scraped At", "format": "text" } } } }, "comments": { "title": "Comments & Replies", "description": "Comment rows emitted by comments mode. Reply rows carry isReply=true.", "transformation": { "fields": [ "recordType", "postId", "postUrl", "commentId", "text", "user", "likeCount", "replyCount", "isReply", "createdAt", "language", "source", "scrapedAt" ] }, "display": { "component": "table", "properties": { "recordType": { "label": "Type", "format": "text" }, "postId": { "label": "Post ID", "format": "text" }, "postUrl": { "label": "Post URL", "format": "link" }, "commentId": { "label": "Comment ID", "format": "text" }, "text": { "label": "Text", "format": "text" }, "user": { "label": "User", "format": "object" }, "likeCount": { "label": "Likes", "format": "number" }, "replyCount": { "label": "Replies", "format": "number" }, "isReply": { "label": "Is Reply", "format": "boolean" }, "createdAt": { "label": "Created At", "format": "text" }, "language": { "label": "Language", "format": "text" }, "source": { "label": "Source", "format": "text" }, "scrapedAt": { "label": "Scraped At", "format": "text" } } } }, "status": { "title": "Unavailable Inputs", "description": "Explicit not_found/private/region/blocked status rows. These do not count toward Max rows.", "transformation": { "fields": [ "recordType", "status", "input", "postId", "message", "httpStatus", "source", "scrapedAt" ] }, "display": { "component": "table", "properties": { "recordType": { "label": "Record", "format": "text" }, "status": { "label": "Status", "format": "text" }, "input": { "label": "Input", "format": "text" }, "postId": { "label": "Post ID", "format": "text" }, "message": { "label": "Message", "format": "text" }, "httpStatus": { "label": "HTTP", "format": "number" }, "source": { "label": "Source", "format": "text" }, "scrapedAt": { "label": "Scraped At", "format": "text" } } } } }, "fields": { "recordType": { "type": "string", "title": "Record Type", "description": "post, comment, reply, or status" }, "source": { "type": "string", "title": "Source", "description": "Extraction path: embed, detail, ssr, profile, comment_api, or short" }, "scrapedAt": { "type": "string", "title": "Scraped At", "description": "ISO 8601 UTC timestamp when this row was built" }, "status": { "type": "string", "title": "Status", "description": "Diagnostic status for a failed input: not_found, private, region, or blocked" }, "input": { "type": "string", "title": "Input", "description": "The original input that produced a status row" }, "message": { "type": "string", "title": "Message", "description": "Human-readable reason for a status row" }, "httpStatus": { "type": "integer", "title": "HTTP Status", "description": "Last HTTP status observed for a failed input" }, "postId": { "type": "string", "title": "Post ID", "description": "TikTok's unique post/video ID (string to preserve 64-bit precision)" }, "postType": { "type": "string", "title": "Post Type", "description": "video or slideshow" }, "postUrl": { "type": "string", "title": "Post URL", "description": "Canonical TikTok post URL" }, "profileUsername": { "type": "string", "title": "Profile Username", "description": "Profile that produced this row in profiles mode" }, "position": { "type": "integer", "title": "Position", "description": "1-based position within the profile feed" }, "isPinned": { "type": "boolean", "title": "Is Pinned", "description": "Whether the profile has pinned this post" }, "caption": { "type": "string", "title": "Caption", "description": "Post caption including hashtags and mentions" }, "textLanguage": { "type": "string", "title": "Text Language", "description": "Detected caption language code (detail path)" }, "locationCreated": { "type": "string", "title": "Location Created", "description": "Creator-set ISO country code" }, "viewerRegion": { "type": "string", "title": "Request Region", "description": "Egress region TikTok inferred for the request; not the post's location" }, "createTime": { "type": "integer", "title": "Create Time (Unix)", "description": "Unix timestamp (seconds) when the post was created" }, "createdAt": { "type": "string", "title": "Created At", "description": "ISO 8601 UTC datetime when the post was created" }, "playCount": { "type": "integer", "title": "Play Count", "description": "Legacy flat play count" }, "likeCount": { "type": "integer", "title": "Like Count", "description": "Legacy flat like count" }, "commentCount": { "type": "integer", "title": "Comment Count", "description": "Legacy flat comment count" }, "shareCount": { "type": "integer", "title": "Share Count", "description": "Legacy flat share count" }, "collectCount": { "type": "integer", "title": "Collect Count", "description": "Legacy flat collect count" }, "repostCount": { "type": "integer", "title": "Repost Count", "description": "Legacy flat repost count" }, "stitchEnabled": { "type": "boolean", "title": "Stitch Enabled", "description": "Legacy flat flag" }, "shareEnabled": { "type": "boolean", "title": "Share Enabled", "description": "Legacy flat flag" }, "duetEnabled": { "type": "boolean", "title": "Duet Enabled", "description": "Legacy flat flag" }, "commentStatus": { "type": "integer", "title": "Comment Status", "description": "Legacy flat flag (0=all, 1=friends, 2=none)" }, "isAd": { "type": "boolean", "title": "Is Ad", "description": "Legacy flat flag" }, "isAigc": { "type": "boolean", "title": "Is AIGC", "description": "Legacy flat flag" }, "isECVideo": { "type": "boolean", "title": "Is E-Commerce Video", "description": "Legacy flat flag" }, "privateItem": { "type": "boolean", "title": "Private Item", "description": "Legacy flat flag" }, "forFriend": { "type": "boolean", "title": "For Friend", "description": "Legacy flat flag" }, "originalItem": { "type": "boolean", "title": "Original Item", "description": "Legacy flat flag" }, "diversificationLabels": { "type": "array", "title": "Diversification Labels", "items": { "type": "string" } }, "channelTags": { "type": "array", "title": "Channel Tags", "items": { "type": "string" } }, "warnInfo": { "type": "array", "title": "Warn Info" }, "poi": { "type": "object", "title": "Point of Interest" }, "AIGCDescription": { "type": "string", "title": "AIGC Description" }, "adLabelVersion": { "type": "integer", "title": "Ad Label Version" }, "mediaUrlExpiresAt": { "type": "string", "title": "Media URL Expires At", "description": "ISO 8601 UTC expiry of the signed media URLs (~48 hours)" }, "mediaUrlAccessible": { "type": "boolean", "title": "Media URL Accessible", "description": "Result of the Range GET probe when validateMediaUrls is on" }, "author": { "type": "object", "title": "Author", "description": "Creator snapshot at scrape time (legacy flat stats included)" }, "authorStats": { "type": "object", "title": "Author Stats", "description": "Grouped follower/following/heart/video counts", "properties": { "followerCount": { "type": "integer" }, "followingCount": { "type": "integer" }, "heartCount": { "type": "integer" }, "videoCount": { "type": "integer" } } }, "stats": { "type": "object", "title": "Post Stats", "description": "Grouped engagement counts", "properties": { "playCount": { "type": "integer" }, "likeCount": { "type": "integer" }, "commentCount": { "type": "integer" }, "shareCount": { "type": "integer" }, "collectCount": { "type": "integer" }, "repostCount": { "type": "integer" } } }, "flags": { "type": "object", "title": "Post Flags", "description": "Grouped visibility, interaction, ad, and AI flags" }, "music": { "type": "object", "title": "Music" }, "video": { "type": "object", "title": "Video" }, "images": { "type": "array", "title": "Slideshow Images", "description": "Ordered carousel images with ordinal, dimensions, and signed urls", "items": { "type": "object" } }, "hashtags": { "type": "array", "title": "Hashtags", "items": { "type": "object" } }, "mentions": { "type": "array", "title": "Mentions", "items": { "type": "object" } }, "comments": { "type": "array", "title": "Comments", "description": "Comments attached to a post row, each optionally carrying a replies array", "items": { "type": "object" } }, "commentId": { "type": "string", "title": "Comment ID" }, "text": { "type": "string", "title": "Comment Text" }, "user": { "type": "object", "title": "Commenter" }, "replyCount": { "type": "integer", "title": "Reply Count" }, "isPinnedByAuthor": { "type": "boolean", "title": "Pinned By Author" }, "isLikedByAuthor": { "type": "boolean", "title": "Liked By Author" }, "isReply": { "type": "boolean", "title": "Is Reply" }, "replyToCommentId": { "type": "string", "title": "Reply To Comment ID" }, "threadId": { "type": "string", "title": "Thread ID" }, "language": { "type": "string", "title": "Language" }, "textExtra": { "type": "array", "title": "Text Extra" }, "item_control": { "type": "object", "title": "Item Control" }, "contents": { "type": "array", "title": "Contents" }, "effectStickers": { "type": "array", "title": "Effect Stickers" }, "stickersOnItem": { "type": "array", "title": "Stickers On Item" } } } } }, "buildNumber": "2.0.1", "imageDigest": "672bdbc690cf2200d33a5c87464234b54f5844c7720f0bc328e5eedff92138b4", "actVersion": { "sourceType": "SOURCE_FILES", "buildTag": "latest", "versionNumber": "2.0" }, "usage": { "ACTOR_COMPUTE_UNITS": 0.03625444444444444 } } }