feat(baoyu-url-to-markdown): add defuddle.md API fallback, YouTube transcripts, and modular converter architecture

This commit is contained in:
Jim Liu 宝玉
2026-03-13 00:22:03 -05:00
parent 994e47d1be
commit 0279fa403d
8 changed files with 1190 additions and 923 deletions
@@ -0,0 +1,58 @@
import { JSDOM, VirtualConsole } from "jsdom";
import { Defuddle } from "defuddle/node";
import {
type ConversionResult,
type PageMetadata,
isMarkdownUsable,
normalizeMarkdown,
pickString,
} from "./markdown-conversion-shared.js";
export async function tryDefuddleConversion(
html: string,
url: string,
baseMetadata: PageMetadata
): Promise<{ ok: true; result: ConversionResult } | { ok: false; reason: string }> {
try {
const virtualConsole = new VirtualConsole();
virtualConsole.on("jsdomError", (error: Error & { type?: string }) => {
if (error.type === "css parsing" || /Could not parse CSS stylesheet/i.test(error.message)) {
return;
}
console.warn(`[url-to-markdown] jsdom: ${error.message}`);
});
const dom = new JSDOM(html, { url, virtualConsole });
const result = await Defuddle(dom, url, { markdown: true });
const markdown = normalizeMarkdown(result.content || "");
if (!isMarkdownUsable(markdown, html)) {
return { ok: false, reason: "Defuddle returned empty or incomplete markdown" };
}
return {
ok: true,
result: {
metadata: {
...baseMetadata,
title: pickString(result.title, baseMetadata.title) ?? "",
description: pickString(result.description, baseMetadata.description) ?? undefined,
author: pickString(result.author, baseMetadata.author) ?? undefined,
published: pickString(result.published, baseMetadata.published) ?? undefined,
coverImage: pickString(result.image, baseMetadata.coverImage) ?? undefined,
language: pickString(result.language, baseMetadata.language) ?? undefined,
},
markdown,
rawHtml: html,
conversionMethod: "defuddle",
variables: result.variables,
},
};
} catch (error) {
return {
ok: false,
reason: error instanceof Error ? error.message : String(error),
};
}
}