{ "openapi": "3.0.1", "info": { "title": "Chinese to Markdown｜微信公众号/头条/新浪/知乎 → RAG-ready MD", "description": "Paste WeChat 公众号 / Toutiao / Sina / Zhihu URLs → clean LLM-ready Markdown. Optional RAG chunks. $0.002/article; failed URLs free. Built for AI agents.", "version": "0.1", "x-build-id": "Kaz0yteDbl01vKQ8p" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ahuang~chinese-article-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ahuang-chinese-article-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/ahuang~chinese-article-to-markdown/runs": { "post": { "operationId": "runs-sync-ahuang-chinese-article-to-markdown", "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/ahuang~chinese-article-to-markdown/run-sync": { "post": { "operationId": "run-sync-ahuang-chinese-article-to-markdown", "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": [ "startUrls" ], "properties": { "startUrls": { "title": "Article URLs｜文章链接", "type": "array", "description": "Article URLs. Supported: WeChat 公众号 (mp.weixin.qq.com/s/...) — full support; Sina 新浪 (news.sina.com.cn) — full support; Toutiao 头条 (toutiao.com/article/...) — LIMITED (text articles only; videos / 微头条 / deleted may fail; image URLs expire); Zhihu 知乎 (zhuanlan.zhihu.com/p/...) — LIMITED (many articles blocked). Douban 豆瓣 is NOT supported (unsupported-site error, not charged). Failed URLs are not charged.\n文章 URL。支持：微信公众号（完整支持）、新浪（完整支持）、今日头条（有限：仅图文；视频/微头条/已删可能失败；图片链接会过期）、知乎（有限：大量文章会被拦截）。豆瓣不支持（返回不支持错误，不计费）。失败不计费。", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "outputFormat": { "title": "Output format｜输出格式", "enum": [ "markdown", "json", "jsonl" ], "type": "string", "description": "markdown (default): core fields — url, title, author, date, word_count, images, markdown. json: also site, fetchedUrl, image_count; WeChat adds account, original_author.\nmarkdown（默认）：核心字段。json：额外含 site、fetchedUrl、image_count；公众号另含 account、original_author。\njsonl: same core fields as markdown, and the whole result is also saved as one JSONL file (key-value store record RESULTS.jsonl).\njsonl：字段同 markdown，并把全部结果另存为 JSONL 文件（KV 存储记录 RESULTS.jsonl）。", "default": "markdown" }, "maxConcurrency": { "title": "Max concurrency｜最大并发", "minimum": 1, "maximum": 20, "type": "integer", "description": "Parallel HTTP fetches (1–20, default 5). Lower this if a site rate-limits you.\n并行 HTTP 请求数（1–20，默认 5）。若站点限流请调低。", "default": 5 }, "chunking": { "title": "RAG chunking｜按 token 切块", "type": "boolean", "description": "Split each article into token-sized chunks for embedding. Each chunk becomes one dataset item with heading_path, chunk_index, token_count, overlap_tokens, text and source metadata (url, title, author, date, site); all chunks are also saved as RESULTS.jsonl in the key-value store. Tokens counted with tiktoken cl100k_base. Billing is still per successfully extracted article.\n把每篇文章按 token 切块，便于向量化。每块一条 dataset 记录，含 heading_path、chunk_index、token_count、来源元数据；全部块另存为 KV 记录 RESULTS.jsonl。token 用 tiktoken cl100k_base 计数。仍按成功文章计费。", "default": false }, "chunkSize": { "title": "Chunk size (tokens)｜块大小", "minimum": 64, "maximum": 8192, "type": "integer", "description": "Max tokens per chunk (64–8192, default 512). Chunks split on Markdown headings first, then paragraphs, then sentences.\n每块最大 token 数，优先按标题、段落、句子切。", "default": 512 }, "chunkOverlap": { "title": "Chunk overlap (tokens)｜重叠", "minimum": 0, "maximum": 4096, "type": "integer", "description": "Tokens repeated from the end of the previous chunk within the same section (0 to chunkSize/2, default 64). No overlap across headings.\n同一小节内与上一块重叠的 token 数（0 到 chunkSize/2）。跨标题不重叠。", "default": 64 } } }, "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 } } } } } } } } } }