{ "openapi": "3.0.1", "info": { "title": "Douban Scraper API – 豆瓣 Movies, Books, Reviews & Comments", "description": "Douban scraper API, no login: Douban movie, TV, book & music search, ratings & details (IMDb id, star distribution), short comments (短评), full reviews (影评), cast, photos, Top 250 & hot charts, group topics. Arrays, filters, only-new delta, lean JSON for AI agents. $0.002/row, $0.01/detail.", "version": "2.0", "x-build-id": "9tweBYIBaLAtjk9Ko" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/deadc0dex~douban-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-deadc0dex-douban-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/deadc0dex~douban-scraper/runs": { "post": { "operationId": "runs-sync-deadc0dex-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/deadc0dex~douban-scraper/run-sync": { "post": { "operationId": "run-sync-deadc0dex-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": { "operation": { "title": "Operation (Douban search, details, comments, reviews, charts, groups…)", "enum": [ "auto", "search", "subject_details", "comments", "reviews", "review_details", "celebrities", "photos", "charts", "explore", "group_search", "group_topics", "group_topic_details", "subject_research", "topic_search", "topic_replies", "review_replies", "capabilities" ], "type": "string", "description": "auto (default): keywords->search, subject URLs/ids->subject_details, review URLs->review_details, topic URLs->group_topic_details, group URLs->group_topics, charts->charts, tags->explore. subject_research = title -> detail + hot comments + reviews + free insights. topic_search = discussions across all groups. topic_replies / review_replies = topic/review URL -> row with replies[]. Also: comments 短评, reviews 影评, celebrities, photos, group_search, capabilities (free).", "default": "auto" }, "keywords": { "title": "Douban search keywords (movie, TV, book, music, group)", "type": "array", "description": "Search terms, one per item, for search (subjectType picks movie+TV, tv, book, music, all) or group_search. Chinese titles work best; English titles are auto-translated when known (The Wandering Earth -> 流浪地球). With comments/reviews/subject_details/celebrities/photos a keyword is resolved to its top hit (free).", "items": { "type": "string" } }, "urls": { "title": "Douban URLs (subject, review, group, topic, chart)", "type": "array", "description": "movie./book./music.douban.com/subject//, m.douban.com/movie/subject//, …/review//, www.douban.com/group//, www.douban.com/group/topic//, m.douban.com/subject_collection/. One per item; messy links are cleaned. Failed inputs return a free error row.", "items": { "type": "string" } }, "ids": { "title": "Douban IDs (subject, review, topic or group)", "type": "array", "description": "Bare ids: subject ids (26266893; movie/TV/book/music detected automatically), review ids for review_details, topic ids for group_topic_details, group ids or names (beijingzufang) for group_topics.", "items": { "type": "string" } }, "charts": { "title": "Douban charts (Top 250, now showing, hot TV, books, music)", "type": "array", "description": "Chart ids for operation charts, in rank order: movie_top250, movie_showing, movie_real_time_hotest, movie_weekly_best, movie_hot_gaia, tv_hot, tv_domestic, tv_american, tv_korean, tv_japanese, tv_animation, tv_variety_show, book_top250, book_fiction, book_hot, music_single, music_hot … (capabilities lists all 30). Aliases: top250, now_showing, kdrama.", "items": { "type": "string" } }, "tags": { "title": "Explore tags (genre, region, theme)", "type": "array", "description": "Douban tags for operation explore (movies or TV by tag): 科幻, 喜剧, 爱情, 悬疑, 动画, 美国, 日本, 韩剧, 美剧, 豆瓣高分, 经典, 冷门佳片… One task per item; combine tags with commas in one item (科幻,美国).", "items": { "type": "string" } }, "subjectType": { "title": "Subject type (movie, TV, book, music)", "enum": [ "movie", "tv", "book", "music", "all", "group" ], "type": "string", "description": "search: movie (default) = movies and TV series, tv = TV only, book, music, all = movie+book+music, group = group search. explore: movie or tv. Subject ops detect the type from the id/URL (hint only)." }, "maxItems": { "title": "Max billable rows (total)", "type": "integer", "description": "Maximum billable rows for the whole run, all inputs together. Default 100. Range 1-10000; larger values are capped." }, "maxItemsPerInput": { "title": "Max rows per input", "type": "integer", "description": "Cap per keyword, chart, tag, subject or group. Default 20 (= maxItems when only maxItems is set). Range 1-2000. Douban guest caps: ~150 hot comments and ~40 reviews per subject, ~300 topics per group, 500 search/explore rows." }, "include": { "title": "Include: details, full review text, replies, insights", "type": "array", "description": "details = search/charts/explore rows -> full subject detail rows (billed as subject $0.01 instead of row $0.002). fullText = reviews with full body as Markdown (review $0.006 instead of comment $0.002). replies = replies[] (up to maxRepliesPerItem) inside full review / group topic rows, no extra charge. insights = one free analysis row per subject after comments/reviews (sentiment heuristic, top terms, regions).", "items": { "type": "string", "enum": [ "details", "fullText", "replies", "insights" ], "enumTitles": [ "Subject details for list rows", "Full review text (Markdown)", "Replies embedded in full reviews / topics", "Free insights row (comments/reviews)" ] } }, "fields": { "title": "Return only these fields", "type": "array", "description": "Projection: keep only these fields per data row (type always kept), e.g. [\"title\",\"rating\",\"ratingCount\"]. Also skips requests not needed (rating distribution / desc page). Empty = default set of outputMode. Full list: operation capabilities.", "items": { "type": "string" } }, "outputMode": { "title": "Output mode", "enum": [ "compact", "lean", "full" ], "type": "string", "description": "compact (default) = stable flat rows, every key present (null when unknown). lean = for LLM agents: no null/empty keys, no envelope (it is in the summary row once), compact dates, short texts cut at maxTextChars (300). full = all fields of the row type.", "default": "compact" }, "sortBy": { "title": "Sort by", "enum": [ "hot", "latest", "recommend", "time", "rating", "elite" ], "type": "string", "description": "comments/reviews: hot (default); latest = visible hot pool sorted newest first (Douban requires login for its newest feed). explore: recommend (default), hot, time, rating. group_topics: Douban default (latest activity), latest = newest posts, hot, elite. search/charts: rating = by rating." }, "minRating": { "title": "Min rating", "type": "number", "description": "Keep rows with rating >= this, applied before billing. Subjects (search, charts, explore, details): Douban score 0-10 (e.g. 8). Comments/reviews: stars 1-5 (e.g. 4). Rows without a rating are dropped when set." }, "maxRating": { "title": "Max rating", "type": "number", "description": "Keep rows with rating <= this. Same scales as minRating. Example: comments with maxRating 2 = 1-2 star complaints." }, "dateFrom": { "title": "Created from", "type": "string", "description": "comments, reviews, group topics, photos: keep items created on/after this date. 2026-10-01 (Beijing time), ISO date-time, or relative 7d / 24h / 4w. Applied before billing." }, "maxCostUsd": { "title": "Max cost (USD)", "type": "number", "description": "Stop before the run's charges would exceed this amount (e.g. 0.05). The run ends SUCCEEDED with the rows so far plus a free BUDGET_REACHED error row. Works together with Apify's max cost per run." }, "dryRun": { "title": "Dry run (free plan)", "type": "boolean", "description": "true = fetch and bill nothing: one free plan row per input (operation, queryUsed, estimated rows, event, cost, seconds) plus a summary. Check routing and cost first.", "default": false }, "deltaKey": { "title": "Delta key (monitoring)", "type": "string", "description": "Name of a memory shared by runs (e.g. top250-weekly). Rows get isNew; chart rows also previousRank and rankChange vs the last run with the same key. Combine with onlyNew. Stored in your named key-value store douban-delta-." }, "onlyNew": { "title": "Only new rows", "type": "boolean", "description": "true = skip (not billed) rows already returned by earlier runs with the same deltaKey (deltaKey \"default\" if empty), e.g. new comments, reviews or group topics since the last scheduled run.", "default": false }, "maxSubjects": { "title": "Research: subjects per keyword", "type": "integer", "description": "subject_research: how many top search hits per keyword to research. Default 1, range 1-10 (clamped)." }, "maxCommentsPerItem": { "title": "Research: short comments per subject", "type": "integer", "description": "subject_research: hot short comments per subject (billed as comment). Default 50, range 0-150 (Douban shows guests ~150). 0 = none." }, "maxReviewsPerItem": { "title": "Research: reviews per subject", "type": "integer", "description": "subject_research: reviews per subject. Default 10, range 0-40 (Douban guest cap ~40). Billed as comment (list row) or review with include fullText. 0 = none." }, "maxRepliesPerItem": { "title": "Replies per review / topic", "type": "integer", "description": "With include replies: replies embedded per full review or group topic (nested review replies flattened, replyToId/replyToName set). Default 20, range 0-200. No extra charge." }, "matchTerms": { "title": "Match terms (keep rows mentioning any)", "type": "array", "description": "Keep only comments/reviews/topics whose text mentions any term (case-insensitive) and count each term in the insights row. Filtering happens after fetching and before billing: dropped rows are not billed, but fetch work is the same.", "items": { "type": "string" } }, "minRatingCount": { "title": "Min number of ratings (subjects)", "type": "integer", "description": "Skip subjects with fewer Douban ratings (search, charts, explore, subject_research). Rows without a rating count are skipped too." }, "insights": { "title": "Insights row (free)", "type": "boolean", "description": "subject_research: free insights row per subject is on unless false. Other comments/reviews runs: true adds it (same as include insights)." }, "dateTo": { "title": "Created until", "type": "string", "description": "Keep items created on/before this date. Same formats as dateFrom." }, "stars": { "title": "Exact stars (comments/reviews)", "type": "array", "description": "Keep comments/reviews with exactly these star ratings, e.g. [\"1\",\"2\"]. Applied before billing.", "items": { "type": "string" } }, "strictMatch": { "title": "Strict keyword match (topic_search, group_search)", "type": "boolean", "description": "Douban group search is fuzzy: 小米SU7 also returns topics that only say 小米. true = keep only topics (group names) whose title contains the keyword, spaces and case ignored, or every part of it (小米 + SU7); mixed keywords are also searched by their Latin part. Filtered before billing. Default false." }, "textContains": { "title": "Text contains (any)", "type": "array", "description": "Keep rows whose title/text/abstract contains at least one of these words (case-insensitive), checked before billing.", "items": { "type": "string" } }, "leanFormat": { "title": "Lean format", "enum": [ "rows", "table" ], "type": "string", "description": "Only with outputMode lean. rows (default) = dataset rows. table = also one tab-separated table per row type in the summary row (leanTable, when < 20 KB) and key-value record LEAN_TABLE.", "default": "rows" }, "maxTextChars": { "title": "Max text characters", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Cut text, abstract, intro and description to this many characters (ends with …, row gets truncated: true). Default 300 in lean mode, no cut otherwise. When set, also cuts full review/topic bodies (contentMarkdown)." }, "expandQuery": { "title": "Translate English keywords", "type": "boolean", "description": "English titles/names are mapped to Chinese with a curated dictionary (~950 entries: The Wandering Earth -> 流浪地球, Harry Potter -> 哈利波特, Jay Chou -> 周杰伦). queryUsed shows the term searched. false = search the keyword as typed.", "default": true }, "dedupe": { "title": "De-duplicate", "type": "boolean", "description": "Drop rows already returned earlier in the run (same type + id), e.g. when two keywords find the same movie.", "default": true }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. Default: no proxy (Douban's mobile API answers Apify IPs directly); if Douban rate-limits the IP, the Actor slows down and switches to Apify Proxy by itself ({\"useApifyProxy\":false} forbids that). Set {\"useApifyProxy\":true} to always use a proxy." }, "maxRequestRetries": { "title": "Max retries per request", "type": "integer", "description": "Retries with backoff on rate limits or server errors (0-6). Login walls are not retried.", "default": 3 }, "requestDelayMs": { "title": "Delay between requests (ms)", "type": "integer", "description": "Minimum spacing between request starts (0-5000). Default 0 = up to 8 requests in flight; after a Douban rate limit the Actor slows itself to 3 in flight and 300 ms spacing. Raise (e.g. 500) only for very large runs.", "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 } } } } } } } } } }