WebExtrator Intelligent Extraction API Integration Guide

POST https://api.acedata.cloud/webextrator/extract

Content extraction based on /webextrator/render. In addition to all parameters of the render interface, it additionally supports:

Field	Type	Required	Default	Description
expected_type	string	❌	markdown	Expected extraction output: markdown / article / text / links / structured
enable_llm	boolean	❌	false	Enable LLM post-processing (suitable for article / structured)
instruction	string	❌	-	LLM extraction instructions, e.g., "extract product title, price, specifications"

¶ Synchronous Response

{
  "success": true,
  "task_id": "550e8400-...",
  "trace_id": "550e8400-...",
  "started_at": "2026-05-02T10:30:00.123Z",
  "finished_at": "2026-05-02T10:30:08.789Z",
  "elapsed": 8.666,
  "data": {
    "kind": "extract",
    "expected_type": "article",
    "url": "https://example.com/post/1",
    "title": "示例文章",
    "author": "张三",
    "published_at": "2026-05-01",
    "content": "# 示例文章\n\n正文 ...",
    "summary": "本文介绍 ..."
  }
}

Asynchronous mode, error codes, and billing rules are exactly the same as /webextrator/render.

¶ Example: Extract Article Content (Enable LLM)

curl -X POST https://api.acedata.cloud/webextrator/extract \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://example.com/news/1",
    "expected_type": "article",
    "enable_llm": true
  }'

¶ Example: Async + Custom Structured Extraction

curl -X POST https://api.acedata.cloud/webextrator/extract \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://shop.example.com/item/123",
    "expected_type": "structured",
    "enable_llm": true,
    "instruction": "抽取商品标题、价格、库存、3 张主图 URL",
    "callback_url": "https://your-domain.com/wbx-callback"
  }'