crawlrs 0.2.0

crawlrs - Enterprise-grade web scraping and crawling platform built with Rust
Documentation
// Copyright (c) 2025-2026 Kirky.X🌠
// SPDX-License-Identifier: Apache-2.0

use serde::{Deserialize, Serialize};

/// `POST /v1/map` 请求 DTO(语义对齐孤儿 forge 文件 `presentation/forge_api/map.rs`)
#[derive(Debug, Clone, Deserialize, Serialize)]
#[serde(deny_unknown_fields)]
pub struct MapRequestDto {
    /// 站点 URL(提取 origin 后抓取 `{origin}/sitemap.xml`)
    pub url: String,
    /// include 白名单通配(`*`/`?`),先于 exclude 应用
    #[serde(default, skip_serializing_if = "Option::is_none")]
    pub include_patterns: Option<Vec<String>>,
    /// exclude 黑名单通配(`*`/`?`)
    #[serde(default, skip_serializing_if = "Option::is_none")]
    pub exclude_patterns: Option<Vec<String>>,
    /// 返回链接上限(缺省 1000)
    #[serde(default, skip_serializing_if = "Option::is_none")]
    pub limit: Option<u32>,
}

/// `POST /v1/map` 响应 DTO:去重后的链接(保 sitemap 出现顺序)
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct MapResponseDto {
    pub links: Vec<String>,
}