{ "openapi": "3.0.1", "info": { "title": "Chinese AI Training Corpus Engine", "description": "Turn China's public web into AI-training-ready text. Pulls Weibo, Bilibili, Xueqiu, Douban & RedNote, then deduplicates, quality-scores, PII-scrubs and provenance-stamps every document. From $0.025/doc, pay-as-you-go. For LLM training-data teams, data vendors & academic NLP researchers.", "version": "0.1", "x-build-id": "4v1oT5isGRsbSvakO" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/zhorex~chinese-corpus-engine/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-zhorex-chinese-corpus-engine", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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~chinese-corpus-engine/runs": { "post": { "operationId": "runs-sync-zhorex-chinese-corpus-engine", "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~chinese-corpus-engine/run-sync": { "post": { "operationId": "run-sync-zhorex-chinese-corpus-engine", "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": [ "corpus_pull", "dedup_merge", "provenance_audit" ], "type": "string", "description": "corpus_pull scrapes fresh documents. dedup_merge and provenance_audit run the pipeline over datasets you already own (set inputDatasetIds) — no scraping, cheaper per record.", "default": "corpus_pull" }, "topics": { "title": "Topics / keywords", "type": "array", "description": "Search keywords fanned out to every selected source. Mix brands, categories, and themes for corpus diversity. Required in corpus_pull mode.", "items": { "type": "string" } }, "sources": { "title": "Sources", "type": "array", "description": "weibo / bilibili / xueqiu / douban are HTTP sources billed at the corpus-doc rate. rednote is a browser source — it only runs when 'Include browser sources' is enabled and bills at the higher corpus-doc-browser rate.", "items": { "type": "string", "enum": [ "weibo", "bilibili", "xueqiu", "douban", "rednote" ] }, "default": [ "weibo", "bilibili", "xueqiu", "douban" ] }, "maxDocs": { "title": "Max documents (raise for bulk corpus pulls)", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Global cap on BILLABLE documents per run. Typical patterns: 500-1,000 to evaluate corpus quality, 10,000-50,000 for an SFT dataset build, 100,000+ for a foundation-corpus pull. Only documents passing the quality floor, char floor, and dedup are counted or charged — rejects are free. See the Pricing tab for per-document cost.", "default": 1000 }, "minQuality": { "title": "Minimum quality score", "enum": [ "0.0", "0.2", "0.35", "0.5", "0.65" ], "type": "string", "description": "Documents scoring below this (0-1 heuristic: length, charset, diversity, punctuation sanity, sentence structure) are dropped — not returned, not billed.", "default": "0.35" }, "minCharCount": { "title": "Minimum characters per document", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Documents whose cleaned text is shorter than this are dropped — not returned, not billed.", "default": 40 }, "languages": { "title": "Language filter", "type": "array", "description": "Keep only documents detected as these languages.", "items": { "type": "string", "enum": [ "zh-CN", "mixed", "en" ] }, "default": [ "zh-CN", "mixed" ] }, "includeBrowserSources": { "title": "Include browser sources (RedNote) — higher-priced event", "type": "boolean", "description": "Enables JS-rendered sources (currently RedNote full post bodies). These need a headless browser + residential proxy and bill at the corpus-doc-browser rate instead of corpus-doc. Recommended run memory with this on: 4096 MB.", "default": false }, "piiScrub": { "title": "PII scrub", "type": "boolean", "description": "Replace emails, phone numbers, Chinese resident IDs (checksum-validated), and passport numbers in document text with [EMAIL]/[PHONE]/[CN_ID]/[PASSPORT] tokens. Counts are always reported per document in the pii field.", "default": true }, "deltaStateKey": { "title": "Corpus refresh key (delta state)", "type": "string", "description": "Set a stable key (e.g. 'ev-corpus-weekly') to make scheduled runs grow one corpus: documents already collected under this key are skipped — not returned, not billed." }, "inputDatasetIds": { "title": "Input dataset IDs (dedup_merge / provenance_audit)", "type": "array", "description": "Dataset IDs from this actor or any Chinese Digital Intelligence Suite actor to re-process. Ignored in corpus_pull mode.", "items": { "type": "string" } }, "cookieStrings": { "title": "Cookie strings (optional, per platform)", "type": "object", "description": "Optional logged-in cookies keyed by platform name to improve recall and rate limits, e.g. {\"xueqiu\": \"xq_a_token=...\"}. Never stored or logged." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Datacenter works for Weibo/Bilibili/Xueqiu. Douban and RedNote work best with RESIDENTIAL (country CN).", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }