{ "openapi": "3.0.1", "info": { "title": "Douban Reviews Scraper: 豆瓣 Movie, TV, Book & Music Reviews", "description": "Scrape full-length Douban (豆瓣) reviews of movies, TV, books and music: complete Chinese review text, 1 to 5 star rating, helpful votes, date and the title reviewed. Great for Chinese AI training and sentiment data. No login. $5 per 1,000 reviews.", "version": "0.0", "x-build-id": "rOtKa9hrmcylNpHnQ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/forgedata~douban-reviews-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-forgedata-douban-reviews-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/forgedata~douban-reviews-scraper/runs": { "post": { "operationId": "runs-sync-forgedata-douban-reviews-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/forgedata~douban-reviews-scraper/run-sync": { "post": { "operationId": "run-sync-forgedata-douban-reviews-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": { "source": { "title": "Where to get reviews", "enum": [ "recent", "popular", "latest", "urls" ], "type": "string", "description": "Recently updated reviews come from Douban's own sitemaps and reach the largest volume. Popular and newest use Douban's public review feeds (a few hundred per category). Or paste specific review URLs.", "default": "recent" }, "includeMovies": { "title": "Movies & TV (影评 / 剧评)", "type": "boolean", "description": "Include movie and TV reviews from movie.douban.com.", "default": true }, "includeBooks": { "title": "Books (书评)", "type": "boolean", "description": "Include book reviews from book.douban.com.", "default": true }, "includeMusic": { "title": "Music (乐评)", "type": "boolean", "description": "Include album reviews from music.douban.com.", "default": true }, "maxReviews": { "title": "Max reviews", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Stop after saving this many reviews. You pay only for reviews saved.", "default": 100 }, "reviewUrls": { "title": "Review URLs", "type": "array", "description": "Used when 'Only the review URLs I paste' is selected. Example: https://movie.douban.com/review/1000369/", "default": [], "items": { "type": "string" } }, "minRating": { "title": "Minimum star rating", "minimum": 0, "maximum": 5, "type": "integer", "description": "Keep only reviews rated at least this many stars (1 to 5). 0 keeps all, including unrated reviews.", "default": 0 }, "minLength": { "title": "Minimum review length (characters)", "minimum": 0, "type": "integer", "description": "Skip reviews shorter than this. Useful for training data.", "default": 0 }, "sitemapStart": { "title": "Start at sitemap file", "minimum": 0, "type": "integer", "description": "Recently updated mode reads Douban's sitemap files in order. Raise this to pull a different batch of reviews on later runs (each file holds about 49,000 reviews).", "default": 0 } } }, "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 } } } } } } } } } }