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

//! 正文提取模块(content-processing R2/R3 -)
//!
//! 模块结构:
//! - `traits`:`ContentExtractor` trait + `ExtractedContent` + `PageType`
//! - `css_rule_extractor`:`CssRuleExtractor` 兜底实现(无 feature 依赖)
//! - `trafilatura_extractor`:`TrafilaturaExtractor` 主路径(gated `trafilatura`)
//! - `dom_smoothie_extractor`:`DomSmoothieExtractor` 性能回退(gated `dom-smoothie`)
//! - `quality_gate`:prose 质量度量与硬门槛判定(降级阶梯 F7)
//! - `facade`:`ContentExtractionFacade` 优先级路由 + 质量门裁决 + LLM 回退
//!
//! 特性门控策略
//! - `trafilatura`:启用 trafilatura 实现
//! - `dom-smoothie`:启用 dom_smoothie 实现
//! - `extractors`:聚合两者
//! - 三特性均关闭时 Facade 退化为 CssRule 兜底(编译通过,功能可用)

pub mod quality_gate;
pub use quality_gate::{ProseMetrics, QualityGateConfig};

pub mod traits;
pub use traits::{ContentExtractor, ExtractError, ExtractedContent, PageType, Result};

pub mod css_rule_extractor;
pub use css_rule_extractor::CssRuleExtractor;

#[cfg(feature = "trafilatura")]
pub mod trafilatura_extractor;
#[cfg(feature = "trafilatura")]
pub use trafilatura_extractor::TrafilaturaExtractor;

#[cfg(feature = "dom-smoothie")]
pub mod dom_smoothie_extractor;
#[cfg(feature = "dom-smoothie")]
pub use dom_smoothie_extractor::DomSmoothieExtractor;

pub mod facade;
pub use facade::ContentExtractionFacade;