{ "openapi": "3.0.1", "info": { "title": "WeChat Official Account Scraper: Articles as Text & Markdown", "description": "WeChat Official Account (微信公众号) scraper: extract articles from mp.weixin.qq.com links or find them by keyword or account name. Title, account, publish time, text, Markdown, images. No login. $5 per 1,000 articles.", "version": "0.1", "x-build-id": "WzatxbeqoVm06YV0F" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/datagleaner~wechat-articles/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-datagleaner-wechat-articles", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/datagleaner~wechat-articles/runs": { "post": { "operationId": "runs-sync-datagleaner-wechat-articles", "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/datagleaner~wechat-articles/run-sync": { "post": { "operationId": "run-sync-datagleaner-wechat-articles", "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": { "articleUrls": { "title": "Article URLs", "type": "array", "description": "Public WeChat article links, for example https://mp.weixin.qq.com/s/AbCdEf... or https://mp.weixin.qq.com/s?__biz=...&mid=...&sn=.... Most reliable mode.", "items": { "type": "string" } }, "searchKeywords": { "title": "Search keywords", "type": "array", "description": "Find recent public articles by keyword, Chinese works best (for example 人工智能, 新能源汽车). Uses Sogou WeChat search, which returns at most about 100 articles per keyword.", "items": { "type": "string" } }, "accountNames": { "title": "Account names", "type": "array", "description": "Official Account display names, for example 36氪. Finds articles whose search results come from an account with that name, so a quiet account may return few articles. Account lookup is best effort.", "items": { "type": "string" } }, "maxArticles": { "title": "Max articles per keyword or account", "minimum": 1, "maximum": 100, "type": "integer", "description": "Upper bound for each keyword and each account. Article URLs are always all fetched. Sogou stops at about 100 per query.", "default": 20 }, "publishedWithin": { "title": "Published within", "enum": [ "", "day", "week", "month" ], "type": "string", "description": "Keep only keyword and account results published in the last day, week or month. Applied after search, so a narrow window may return fewer than the max. Does not affect article URLs.", "default": "" }, "includeContent": { "title": "Content formats", "type": "array", "description": "Which body formats to return: text, markdown, html. Images are always listed.", "items": { "type": "string", "enum": [ "text", "markdown", "html" ] }, "default": [ "text", "markdown" ] }, "requestDelaySeconds": { "title": "Delay between requests (seconds)", "minimum": 0.5, "maximum": 30, "type": "number", "description": "Base pause between requests; the actual pause is randomised up to 1.5x. Raise it if search starts returning verification pages.", "default": 1.5 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy (datacenter) by default: Sogou blocks keyword search from a single IP after a dozen or so articles. A new IP is used each time a session restarts.", "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 }, "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 } } } } } } } } } }