{ "openapi": "3.0.1", "info": { "title": "Douban Scraper - 豆瓣 Movie & Book Reviews, Comments, No Login", "description": "Analyze Chinese audience opinion on movies, TV, books and music. Douban (豆瓣) scraper, no login: short comments with star ratings, full-text long reviews with author and date, subject info and search. Paste subject URLs or search. From $4.49 per 1,000 comments.", "version": "0.1", "x-build-id": "WrY3wTTcp3uap2f71" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/reportable_broth~douban-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-reportable_broth-douban-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/reportable_broth~douban-scraper/runs": { "post": { "operationId": "runs-sync-reportable_broth-douban-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/reportable_broth~douban-scraper/run-sync": { "post": { "operationId": "run-sync-reportable_broth-douban-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": { "subjectUrls": { "title": "Douban URLs", "type": "array", "description": "Movie, TV, book or music pages (e.g. https://movie.douban.com/subject/1292052/, https://book.douban.com/subject/2567698/). Review URLs (…/review/1000369/) return that review's full text.", "items": { "type": "string" } }, "searchQueries": { "title": "Search queries", "type": "array", "description": "Search Douban by title, person or keyword, e.g. 三体, 宫崎骏, 村上春树.", "items": { "type": "string" } }, "searchType": { "title": "Search in", "enum": [ "movie", "book" ], "type": "string", "description": "Movies (includes TV series) or books.", "default": "movie" }, "maxSearchResults": { "title": "Max search results per query", "minimum": 1, "maximum": 200, "type": "integer", "description": "Each result is one row with title, year, rating, rating count and link.", "default": 20 }, "scrapeTopSearchResults": { "title": "Also scrape comments/reviews for the top N search results", "minimum": 0, "maximum": 50, "type": "integer", "description": "0 = search results only. 3 = also pull comments and reviews (per the settings below) for the first 3 results of each query.", "default": 0 }, "maxComments": { "title": "Max short comments per subject", "minimum": 0, "maximum": 200, "type": "integer", "description": "Short comments (短评) with star rating, likes, date and user, sorted by Douban's 'hot' order. Douban shows logged-out visitors about 100-150 per subject. 0 = skip.", "default": 100 }, "maxReviews": { "title": "Max long reviews per subject", "minimum": 0, "maximum": 80, "type": "integer", "description": "Long reviews (影评/书评). Douban shows logged-out visitors about 40 per subject. 0 = skip.", "default": 20 }, "fullReviewText": { "title": "Full review text", "type": "boolean", "description": "Open each review for the complete text (often 1,000-5,000 characters) instead of the short excerpt. One extra request per review.", "default": true }, "includeSubjectInfo": { "title": "Include subject info row", "type": "boolean", "description": "One free row per movie/book with title, rating, rating count, genres, directors/authors, intro and Douban's total comment/review counts.", "default": true }, "onlyNew": { "title": "Only new (monitor mode)", "type": "boolean", "description": "Remember comments and reviews from earlier runs with the same input and skip them. Use with a schedule to track new reactions to a film or book.", "default": false }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Residential recommended. Responses are small JSON, so proxy traffic is tiny.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } }, "requestGapSecs": { "title": "Seconds between requests", "type": "string", "description": "Politeness delay. Raise it if you see many retries in the log.", "default": "0.8" } } }, "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 } } } } } } } } } }