mirror of
https://github.com/JimLiu/baoyu-skills.git
synced 2026-07-12 05:51:44 +08:00
e5d6c8ec68
- New parsers/ module with pluggable rule system for site-specific HTML extraction - X status parser: extract tweet text, media, quotes, author from data-testid elements - X article parser: extract long-form article content with inline media - archive.ph parser: restore original URL and prefer #CONTENT container - Improved slug generation with stop words and content-aware slugs - Output path uses subdirectory structure (domain/slug/slug.md) - Fix: preserve anchor elements containing media in legacy converter - Fix: smarter title deduplication in markdown document builder
11 lines
330 B
TypeScript
11 lines
330 B
TypeScript
import { archivePhRuleParser } from "./archive-ph.js";
|
|
import { xArticleRuleParser } from "./x-article.js";
|
|
import { xStatusRuleParser } from "./x-status.js";
|
|
import type { UrlRuleParser } from "../types.js";
|
|
|
|
export const URL_RULE_PARSERS: UrlRuleParser[] = [
|
|
archivePhRuleParser,
|
|
xArticleRuleParser,
|
|
xStatusRuleParser,
|
|
];
|