从 HTML 提取文章内容

POST

https://api.gugudata.com/ai/v1/articles/extractFromHtml

AI/模型

从已获取的 HTML 内容中提取文章标题、正文、摘要和站点信息。
接口标签：网页处理、LLM、内容提取、网页解析
详情页：https://www.gugudata.com/api/details/article-extract

请求参数

Query 参数

Body 参数application/json必填

示例

{
    "html": "",
    "url": "",
    "parserOptions": {}
}

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --globoff 'https://api.gugudata.com/ai/v1/articles/extractFromHtml?appkey=请前往 https://www.gugudata.com 购买' \
--header 'Content-Type: application/json' \
--data '{
    "html": "",
    "url": "",
    "parserOptions": {}
}'

返回响应

🟢200

application/json

接口正常响应。请求成功，业务状态请结合响应体中的自定义业务码判断。

Bodyapplication/json

示例

{
    "DataStatus": {
        "RequestParameter": "string",
        "StatusCode": 0,
        "StatusDescription": "string",
        "ResponseDateTime": "string",
        "DataTotalCount": 0
    },
    "Data": {
        "title": "string",
        "content": "string",
        "excerpt": "string",
        "byline": "string",
        "siteName": "string"
    }
}

🟠400

🟠401

🟠403

🟠404

🟠405

🟠415

🟠429

🔴500

🔴502

修改于 2026-07-29 04:50:00

上传知识库文档

DEMO