{ "openapi": "3.0.1", "info": { "title": "Weibo Scraper API: Posts, Comments, Hot Search & Profiles (微博)", "description": "Scrape Weibo (微博) with no login: keyword posts, hot search, comments, and public profiles (text, counts, author). Unsigned search returns about the first page per tab. For social listening and scheduled monitoring.", "version": "0.4", "x-build-id": "PdTTYgZUX19KP3ZaI" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/dheerajitbhu~weibo-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-dheerajitbhu-weibo-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/dheerajitbhu~weibo-scraper/runs": { "post": { "operationId": "runs-sync-dheerajitbhu-weibo-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/dheerajitbhu~weibo-scraper/run-sync": { "post": { "operationId": "run-sync-dheerajitbhu-weibo-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "mode" ], "properties": { "mode": { "title": "Mode", "enum": [ "search", "hot_search", "post_detail", "post_comments", "user_profile", "user_posts", "selftest" ], "type": "string", "description": "What to scrape. No login or cookie is needed in any mode.", "default": "search" }, "searchQueries": { "title": "Search keywords", "type": "array", "description": "Used in 'search' mode. If left empty, the run uses 小米 as a sample keyword.", "items": { "type": "string" } }, "searchTypes": { "title": "Search result types", "type": "array", "description": "Any of: top (综合), realtime (实时), hot (热门). Without login Weibo returns the first page (about 10 posts) of each type; results are merged and deduplicated.", "default": [ "top", "realtime", "hot" ], "items": { "type": "string" } }, "postUrls": { "title": "Post links or ids", "type": "array", "description": "Used in 'post_detail' and 'post_comments'. Example: https://weibo.com/1749127163/RnhdwmDmz, a numeric mid, or the short id.", "items": { "type": "string" } }, "userIds": { "title": "User ids", "type": "array", "description": "Used in 'user_profile' and 'user_posts'. Numeric uid or a weibo.com/u/ link.", "items": { "type": "string" } }, "maxResults": { "title": "Max posts per keyword / user (or hot-search rows)", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Upper bound. Without login Weibo returns about 10 posts per search type and about 10 latest posts per user.", "default": 50 }, "includeComments": { "title": "Also scrape comments", "type": "boolean", "description": "In 'search' and 'post_detail': also return each post's comments as rows (type 'comment'). Each comment is a billed row.", "default": false }, "maxComments": { "title": "Max comments per post", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Used in 'post_comments' and when 'Also scrape comments' is on. Comments are paged with Weibo's own cursor.", "default": 20 }, "expandLongText": { "title": "Expand long posts", "type": "boolean", "description": "Fetch the full text of posts Weibo truncates (one extra request per long post, no extra charge).", "default": true }, "outputFormat": { "title": "Output format", "enum": [ "standard", "compact" ], "type": "string", "description": "Dataset rows are always pushed and charged the same either way. 'compact' additionally writes OUTPUT_COMPACT to the run's key-value store: our lossless, token-optimized copy of the same rows, cheaper to hand to an LLM.", "default": "standard" }, "maxChargeUsd": { "title": "Maximum charge per run (USD)", "minimum": 0, "type": "number", "description": "Hard spending cap. The run stops cleanly before going over it; rows already delivered are kept.", "default": 5 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Default: Apify datacenter proxy. The actor handles the site's access protections automatically and is maintained against site changes. Pick RESIDENTIAL to use residential IPs from the start.", "default": { "useApifyProxy": true } }, "requestIntervalSecs": { "title": "Seconds between requests", "minimum": 0.5, "maximum": 10, "type": "number", "description": "Polite pacing. Faster pacing triggers Weibo's rate limits.", "default": 1 }, "outputMode": { "title": "Output mode", "enum": [ "all", "changesOnly" ], "type": "string", "description": "Default 'all' exports every row, every run. 'changesOnly' remembers the last run and exports only posts, comments, users, or hot-search keywords that are new, changed, or no longer found — handy on a schedule. Example: 'changesOnly' to track a hashtag or user's latest posts day over day instead of re-exporting everything.", "default": "all" }, "monitorKey": { "title": "Monitor name (optional)", "type": "string", "description": "Only used with 'changesOnly'. Names the saved baseline so scheduled runs compare against the right one. Leave blank to derive it automatically from your other inputs. Example: 'xiaomi-daily' if you run several monitors." }, "includeRemoved": { "title": "Report removed items", "type": "boolean", "description": "Only used with 'changesOnly'. When true (default), items no longer found are reported once as removed. Example: false to only see new/changed items.", "default": true }, "ignoreFields": { "title": "Fields to ignore when detecting changes (optional)", "type": "array", "description": "Only used with 'changesOnly'. Field names that should not, by themselves, trigger a 'changed' result. Example: [\"likesCount\", \"repostsCount\", \"commentsCount\"] to ignore engagement-count drift and only react to text/other edits.", "items": { "type": "string" } }, "labels": { "title": "Add AI labels", "type": "boolean", "description": "Adds AI brand-relevance and spam filtering to each post row (search, post_detail, user_posts — not comments/hot-search/profiles): a brandRelevant flag (only when 'Brand to match' is set) and a spam flag, each with a confidence score. Below a label's confidence cutoff it returns 'low_confidence' instead of a guess. Billed per post actually labeled, in addition to that row's own charge — see pricing.", "default": false }, "brandQuery": { "title": "Brand to match", "type": "string", "description": "Only used when 'Add AI labels' is on. Describe the brand/topic to check relevance against, e.g. 'Xiaomi (phones, Redmi, HyperOS)'. Leave blank to skip brand relevance and only check spam/ad." } } }, "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 } } } } } } } } } }