Skip to main content

crawlkit_parser/
lib.rs

1//! # crawlkit-parser
2//!
3//! HTML 解析与内容提取模块。
4//! 基于 `scraper`（html5ever）和 `dom_smoothie`（Readability 模式）实现。
5
6pub mod html;
7
8pub use html::{
9    Article, LinkSelectorType, extract_absolute_links, extract_article, extract_attributes,
10    extract_content, extract_content_by_selector, extract_links, extract_links_by_selector,
11    extract_links_by_xpath, extract_readable_content, extract_texts, resolve_url,
12    try_extract_links,
13};
14
15/// 重新导出 scraper 供上层 crate 构建 Element
16pub use scraper;
17
18/// 重新导出 skyscraper 供上层 crate 实现 XPath 元素回调
19pub use skyscraper;