zoriya/v10
1
0
Fork 0
mirror of https://github.com/zoriya/v10.git synced 2026-08-16 02:45:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(site): skip error pages and strip styles in llms-markdown integration (#706)

Browse Source
This commit is contained in:
Darius Cepulis
2026-03-04 09:43:52 -06:00
committed by GitHub
parent f623e676f2
commit 1f030f0001
1 changed files with 11 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
site/integrations/llms-markdown.ts
+11 -1
View File
@@ -32,16 +32,26 @@ export default function llmsMarkdown(): AstroIntegration {
logger.info('Generating LLM-optimized markdown files...');
// Standalone error pages emit e.g. 404.html, not 404/index.html
const SKIP_PAGES = new Set(['404', '500']);
for (const page of pages) {
const { pathname } = page;
if (SKIP_PAGES.has(pathname.replace(/\/$/, ''))) continue;
try {
// Construct path to HTML file
const htmlPath = join(siteDir, pathname, 'index.html');
const html = await readFile(htmlPath, 'utf-8');
// Strip styles before JSDOM to avoid "Could not parse CSS stylesheet" warnings
const cleanHtml = html
.replace(/<style[\s\S]*?<\/style>/gi, '')
.replace(/<link[^>]*rel=["']stylesheet["'][^>]*\/?>/gi, '');
// Parse HTML with jsdom
const dom = new JSDOM(html);
const dom = new JSDOM(cleanHtml);
const document = dom.window.document;
// Check if page has llms content