{ "openapi": "3.0.1", "info": { "title": "Weibo Scraper — Posts, Comments, Profiles & Hot Search", "description": "Scrape Weibo (微博) posts by keyword with no page cap and a date range, plus comments, replies, likers, author profiles and hot search lists. No login, no cookie. Export JSON, CSV, Excel.", "version": "0.0", "x-build-id": "y9t2cGecvPCH4Qdn5" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/nice_dev~weibo-posts-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-nice_dev-weibo-posts-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/nice_dev~weibo-posts-scraper/runs": { "post": { "operationId": "runs-sync-nice_dev-weibo-posts-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/nice_dev~weibo-posts-scraper/run-sync": { "post": { "operationId": "run-sync-nice_dev-weibo-posts-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "query": { "title": "Search keyword", "maxLength": 200, "type": "string", "description": "Word or phrase, as typed in the Weibo search box (Chinese works best, e.g. `小米`; a `#topic#` searches that topic)." }, "searchQueries": { "title": "More search keywords", "maxItems": 100, "uniqueItems": true, "type": "array", "description": "Several keywords in one run: one search per keyword. Added to **Search keyword**; a post found by several searches is saved once.", "default": [], "items": { "type": "string" } }, "sortBy": { "title": "Search tab", "enum": [ "latest", "hot", "top" ], "type": "string", "description": "**Latest** = Weibo's real-time tab (实时), no depth cap, works with the date range. **Hot** (热门) and **Top** (综合) = Weibo's own ranking, about 10 posts per keyword (Weibo shows more only to logged-in users).", "default": "latest" }, "matchAllWords": { "title": "All words must match", "type": "boolean", "description": "Keep only posts that contain every word of the keyword (checked on the post text, the reposted text, the author name and the card title). The full long text of cut posts is read for this check, even when \"Full long text\" is off. Weibo's search also returns posts with only some of the words. Each post checked, kept or not, is charged the filter fee.", "default": false }, "searchAccounts": { "title": "Matching accounts", "type": "boolean", "description": "For every keyword, also save the accounts Weibo finds for it (用户 tab, the first 20; Weibo shows more only to logged-in users), as **Profile** rows. Charged as **Profile**.", "default": false }, "includeKeywordStats": { "title": "Keyword stats", "type": "boolean", "description": "For every keyword, also save its topic row (话题: discussions, reads, summary) and the number of participants, as one **Hot topic** row. 2 extra requests per keyword. Charged as **Hot topic**.", "default": false }, "startUrls": { "title": "Weibo URLs", "maxItems": 1000, "type": "array", "description": "Post URLs (`https://weibo.com//`, `https://m.weibo.cn/detail/`, `https://m.weibo.cn/status/`), account URLs (`https://weibo.com/u/`, `https://m.weibo.cn/u/`, `https://weibo.com/`) or search URLs (`https://s.weibo.com/weibo?q=...`, `https://m.weibo.cn/search?containerid=...`: the keyword is read from it). Max 1 000 URLs.", "default": [], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "postIds": { "title": "Post IDs", "maxItems": 1000, "uniqueItems": true, "type": "array", "description": "Posts by ID: the 16-digit number (`mid`, e.g. `5354231135473812`) or the short code (`bid`, e.g. `RmKNzmXZi`). One row per post, with comments / likers if ticked below.", "default": [], "items": { "type": "string" } }, "userIds": { "title": "Account IDs", "maxItems": 500, "uniqueItems": true, "type": "array", "description": "Accounts by numeric ID (`uid`, e.g. `1749127163`) or profile URL. See **Account data** for what is saved.", "default": [], "items": { "type": "string" } }, "accountData": { "title": "Account data", "type": "array", "description": "For each account (Account IDs, account URLs): its **latest posts** (Weibo shows the 10 most recent without login; more with your Weibo cookie) and / or its **profile** (exact follower count, bio, verification, account creation date, IP location, birthday, credit level; charged as **Profile**).", "items": { "type": "string", "enum": [ "posts", "profile" ], "enumTitles": [ "Latest posts (10, more with a cookie)", "Profile (charged as Profile)" ] }, "default": [ "posts" ] }, "maxPostsPerUser": { "title": "Posts per account", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Cap on the latest posts saved per account. Weibo shows at most 10 to visitors; to go above 10 (up to 1 000), give your Weibo cookie below.", "default": 10 }, "maxVideosPerUser": { "title": "Videos per account", "minimum": 0, "maximum": 20, "type": "integer", "description": "Also save the video posts of each account (video tab, about 20; Weibo shows more only to logged-in users), as **Post** rows. 0 = none.", "default": 0 }, "cookie": { "title": "Your Weibo cookie (optional)", "type": "string", "description": "Leave empty and everything works as a visitor. Give the cookie of YOUR Weibo account to read an account's feed beyond its first 10 posts (**Posts per account** above 10) or its follower and following lists (**Followers per account**, **Following per account** below): Weibo shows these only to logged-in users. How to copy it: log in to weibo.com in your browser, open the developer tools (F12) › Network, click any request to weibo.com and copy the whole `Cookie` request header; it must contain `SUB=`. A `SUB=...` value alone also works. Your account is used for these requests only; we never store or log it. Not tested with a real account yet: tell us in the Issues tab if something fails. Use an account of your own: Weibo may ask it to log in again after heavy use." }, "maxFollowersPerUser": { "title": "Followers per account (needs your cookie)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Save the followers of each account above (and of each account URL): one **Follower** row each (name, ID, followers, verification, bio fields Weibo shows in lists), newest first as Weibo lists them. Needs your Weibo cookie (see **Your Weibo cookie**): the run refuses to start without it. Charged as **Follower**, only when this is above 0. 0 = off. Not tested with a real account yet.", "default": 0 }, "maxFollowingPerUser": { "title": "Following per account (needs your cookie)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Save the accounts each account above (and each account URL) follows: one **Follower** row each, marked `following` in **Type**. Needs your Weibo cookie (see **Your Weibo cookie**): the run refuses to start without it. Charged as **Follower**, only when this is above 0. 0 = off. Not tested with a real account yet.", "default": 0 }, "includeHotSearch": { "title": "Hot search list", "type": "boolean", "description": "Save the current hot lists chosen below: one **Hot topic** row per entry (rank, title, heat, label 热 / 新 / 沸, category, time on the list, and the change since the previous run with the same **Memory key**). Charged as **Hot topic**.", "default": false }, "hotBoards": { "title": "Hot lists", "type": "array", "description": "Which lists to read: **Hot search** (热搜, about 50), **Entertainment** (文娱, 50), **Life** (生活, 50), **Topics** (话题榜: topic pages ranked, with reads, discussions and summary; paged).", "items": { "type": "string", "enum": [ "realtime", "entertainment", "life", "topics" ], "enumTitles": [ "Hot search (热搜)", "Entertainment (文娱)", "Life (生活)", "Topics (话题榜)" ] }, "default": [ "realtime" ] }, "maxPostsPerHotTopic": { "title": "Posts per hot topic", "minimum": 0, "maximum": 1000, "type": "integer", "description": "With **Hot search list**: also search the posts of each hot topic (latest first), up to N per topic. 0 = topics only.", "default": 0 }, "maxHotTopics": { "title": "Hot topics", "minimum": 1, "maximum": 500, "type": "integer", "description": "How many entries of each hot list to keep, from the top (Hot search, Entertainment and Life have about 50; Topics is paged).", "default": 50 }, "includeHotTimeline": { "title": "Hot posts feed", "type": "boolean", "description": "Also save the posts of Weibo's hot feed (热门微博, the trending posts of the day), up to **Max results**.", "default": false }, "hotChannels": { "title": "Hot feed channels", "maxItems": 66, "uniqueItems": true, "type": "array", "description": "With **Hot posts feed**: which channels of the feed to read, by name (`财经`, `科技`, `汽车`, `体育`, `数码`, `房产`, `国际`, `游戏`…, 66 in all) or by channel ID (`group_id`). Empty = the main hot feed only.", "default": [], "items": { "type": "string" } }, "includeComments": { "title": "Comments", "type": "boolean", "description": "Save the comments of each post: one **Comment** row each (text, date, likes, reply count, floor, region of the commenter, commenter's name, ID and verification). Charged as **Comment**.", "default": false }, "maxCommentsPerPost": { "title": "Comments per post", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Cap on the comments saved per post (20 per page read). 0 = all comments Weibo shows.", "default": 50 }, "commentSort": { "title": "Comment order", "enum": [ "latest", "hot" ], "type": "string", "description": "**Latest** = newest comments first. **Hot** = Weibo's most liked comments first.", "default": "hot" }, "includeReplies": { "title": "Replies to comments", "type": "boolean", "description": "With **Comments**: also save the replies to each comment, as **Comment** rows marked `isReply` with their parent comment ID.", "default": false }, "maxRepliesPerComment": { "title": "Replies per comment", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Cap on the replies saved per comment. 0 = all replies.", "default": 20 }, "includeLikers": { "title": "Likers", "type": "boolean", "description": "Save the accounts that liked each post: one **Liker** row each (name, ID, followers, verification, liked when). Charged as **Liker**.", "default": false }, "maxLikersPerPost": { "title": "Likers per post", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Cap on the likers saved per post. 0 = all likers Weibo shows.", "default": 50 }, "includeAuthorProfiles": { "title": "Author profiles", "type": "boolean", "description": "Add one **Profile** row for each new post author (exact follower count, bio, verification, account creation date, IP location, birthday, credit level; 2 extra requests per author, each author once per run). Charged as **Profile**.", "default": false }, "includeContacts": { "title": "Contacts (e-mail, phone, WeChat, QQ)", "type": "boolean", "description": "Find e-mails, phone numbers, WeChat / QQ ids and business-contact lines in the account bio and verification text of post authors, profiles, likers, followers and accounts followed; charged per row where at least one is found. Charged as **Contact**. No extra request. Off = the six contact fields stay empty.", "default": false }, "includeSentiment": { "title": "Sentiment (tone score)", "type": "boolean", "description": "Add a tone score of each post and each comment or reply, from -1 (negative) to +1 (positive), and a label (negative, neutral, positive). Computed on the text already read, no extra request; with the full long text option, on the full text. Chinese text only: a text with no Chinese character gets no score and is not charged. Charged as **Sentiment** per row scored. Profiles, likers, followers and hot topics get no score. Off = the two sentiment columns stay empty.", "default": false }, "fetchFullText": { "title": "Full long text", "type": "boolean", "description": "Weibo cuts posts longer than about 140 characters (`isLongText`). Tick to read the full text of each cut post (1 extra request per cut post). Charged as **Full text** per post completed. Off = the cut text, marked `textTruncated`.", "default": false }, "maxItems": { "title": "Max results", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Maximum number of posts saved for the whole run (after deduplication and filters). Comments, likers, profiles and hot topics have their own caps above. 0 = no limit.", "default": 100 }, "maxItemsPerQuery": { "title": "Max posts per search", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Cap for EACH keyword, hot topic or search URL, so that the first search cannot use up the whole **Max results** budget. 0 = no per-search cap.", "default": 0 }, "postedAfter": { "title": "Posted after", "type": "string", "description": "Only posts published on or after this date, Beijing time (UTC+8): `2026-09-01`, or a period before now such as `7 days`, `24 hours`, `2 weeks`. Reads the post's publication date. The keyword search stops as soon as it reaches older posts." }, "postedBefore": { "title": "Posted before", "type": "string", "description": "Only posts published on or before this date, Beijing time (the whole day is included), or older than a period such as `30 days`. The keyword search starts directly at this date (it does not read the newer posts)." }, "excludeKeywords": { "title": "Exclude keywords", "maxItems": 50, "uniqueItems": true, "type": "array", "description": "Drop the posts whose text, reposted text or author name contains one of these words (case ignored). The full long text of cut posts is read for this check, even when \"Full long text\" is off.", "default": [], "items": { "type": "string" } }, "originalOnly": { "title": "Original posts only", "type": "boolean", "description": "Drop reposts (转发): keep only posts written by their author.", "default": false }, "contentType": { "title": "Media", "enum": [ "all", "pictures", "videos", "media" ], "type": "string", "description": "Keep only the posts with pictures, with a video, or with either.", "default": "all" }, "verifiedOnly": { "title": "Verified authors only", "type": "boolean", "description": "Keep only posts by verified accounts (orange or blue V: people, media, brands, institutions).", "default": false }, "excludePromoted": { "title": "Exclude ads", "type": "boolean", "description": "Drop the promoted posts (ads) Weibo mixes into the results.", "default": false }, "minLikes": { "title": "Min likes", "minimum": 0, "maximum": 1000000000, "type": "integer", "description": "Keep only posts with at least this many likes. 0 = no minimum.", "default": 0 }, "minReposts": { "title": "Min reposts", "minimum": 0, "maximum": 1000000000, "type": "integer", "description": "Keep only posts with at least this many reposts. 0 = no minimum.", "default": 0 }, "minComments": { "title": "Min comments", "minimum": 0, "maximum": 1000000000, "type": "integer", "description": "Keep only posts with at least this many comments. 0 = no minimum.", "default": 0 }, "minFollowers": { "title": "Min author followers", "minimum": 0, "maximum": 1000000000, "type": "integer", "description": "Keep only posts whose author has at least this many followers (as shown on the post: `2.7万` = 27 000). 0 = no minimum.", "default": 0 }, "provinces": { "title": "Posted from (provinces)", "maxItems": 50, "uniqueItems": true, "type": "array", "description": "Keep only posts published from these provinces or regions, as Weibo shows them under the post (`发布于 广东`): Chinese (`广东`, `北京`) or English (`Guangdong`, `Beijing`). Posts without a region are dropped.", "default": [], "items": { "type": "string" } }, "onlyNew": { "title": "Only new posts", "type": "boolean", "description": "Skip the posts that a previous run (same **Memory key**) already delivered: they are not saved and not charged, and their comments / likers are not read again. Each keyword search stops at the oldest post delivered by the previous run (after a run cut short by its maximum cost, its timeout or an abort, the older posts it missed are given too). First run = everything is new.", "default": false }, "stateKey": { "title": "Memory key", "pattern": "^[a-zA-Z0-9_-]{1,64}$", "maxLength": 64, "type": "string", "description": "Name of the memory used by **Only new posts**. Give each schedule / task its own key (e.g. `xiaomi-watch`) so that they do not share their memory. Letters, digits, `-` and `_`.", "default": "default" }, "resetState": { "title": "Reset the memory", "type": "boolean", "description": "Forget everything remembered under this **Memory key** before the run: this run returns (and charges) every post again. Untick it afterwards.", "default": false }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy or your own proxies. Keep the default Apify proxy: it is included in the price. The residential Apify proxy is not available in this Actor.", "default": { "useApifyProxy": true } }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Maximum number of requests processed in parallel.", "default": 4 }, "maxRequestsPerMinute": { "title": "Max requests per minute", "minimum": 10, "maximum": 600, "type": "integer", "description": "Most requests to Weibo in any 60 seconds, all of them counted (search, comments, likers, profiles, long text). Lower it if the log shows HTTP 418 / 429 (Weibo's rate limit).", "default": 120 }, "minRequestIntervalMs": { "title": "Min delay between requests", "minimum": 0, "maximum": 60000, "type": "integer", "description": "Smallest gap between two requests, in milliseconds. Unlike the per-minute rate, this spreads the requests evenly instead of letting them go out in a burst. 0 = no gap.", "default": 0 }, "maxRequestRetries": { "title": "Max request retries", "minimum": 0, "maximum": 20, "type": "integer", "description": "Retries per request before it is marked as failed. A request Weibo turns away (418 / 429, visitor page) is retried with a fresh visitor session and proxy up to 10 times without using up these retries.", "default": 5 }, "debugLog": { "title": "Debug log", "type": "boolean", "description": "Include debug messages in the run log.", "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }