{ "openapi": "3.0.1", "info": { "title": "Douban Pro Scraper — Reviews, Discussions & Subject Data", "description": "Scrape long-form reviews, comments, and group discussions from Douban (豆瓣) — China's leading reviews + interest community. Movies, books, music, plus subject search. Built for Chinese-LLM training corpus, sentiment analysis, and academic NLP research. Pure HTTP, no auth.", "version": "0.1", "x-build-id": "7YcVLonBlEzDapfA0" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/zhorex~douban-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-zhorex-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/zhorex~douban-scraper/runs": { "post": { "operationId": "runs-sync-zhorex-douban-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/zhorex~douban-scraper/run-sync": { "post": { "operationId": "run-sync-zhorex-douban-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mode": { "title": "Mode", "enum": [ "subject_reviews", "subject_comments", "group_topic", "subject_search" ], "type": "string", "description": "What to scrape from Douban.", "default": "subject_reviews" }, "subjectUrls": { "title": "Subject URLs", "uniqueItems": true, "type": "array", "description": "Douban subject URLs (movies, books, or music). Used for subject_reviews and subject_comments modes. Examples: https://movie.douban.com/subject/1292052/, https://book.douban.com/subject/2567698/, https://music.douban.com/subject/1419463/. Note: some less-popular books have moved short-comments behind AJAX-only rendering — popular subjects (rating count > 10K) reliably serve inline comments.", "items": { "type": "string" } }, "topicUrls": { "title": "Group topic URLs", "uniqueItems": true, "type": "array", "description": "Douban group topic URLs. Used for group_topic mode. Example: https://www.douban.com/group/topic/319929381/. (Beta — group_topic mode works for most public groups but may fail on private or recently-moderated topics. Report issues at the Actor's Issues page.)", "items": { "type": "string" } }, "searchQuery": { "title": "Search query", "type": "string", "description": "Search query in Chinese or English. Used for subject_search mode." }, "searchType": { "title": "Search type", "enum": [ "all", "movie", "book", "music" ], "type": "string", "description": "Restrict subject_search to a single category. Note: book search returns up to ~10 discovery results per query; for bulk book review extraction, use subject_reviews mode with multiple subject URLs.", "default": "all" }, "maxResults": { "title": "Max results", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Max records to scrape per input URL / search query.", "default": 50 }, "maxRepliesPerTopic": { "title": "Max replies per topic (group_topic mode)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Cap on the number of replies attached to each group topic record.", "default": 50 }, "fetchFullReviewBody": { "title": "Fetch full review body", "type": "boolean", "description": "When true (default), each review record includes the full long-form body (extra request per review). Disable for faster, cheaper runs that only need the review meta + excerpt.", "default": true }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy settings. Douban WAFs the movie subdomain — residential proxies are strongly recommended.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "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 } } }, "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 } } } } } } } } } }