-
import { XMLParser, XMLBuilder } from 'fast-xml-parser'; import fs from 'fs'; import path from 'path'; interface Sitemap { urlset: { url: { loc: string; changefreq: string; priority: number }[]; }; } async function trimXML() { const sitemapPath = path.resolve( '..', 'blog-website', 'build', 'sitemap.xml' ); console.log(`Loading ${sitemapPath}`); const sitemapXml = await fs.promises.readFile(sitemapPath, 'utf8'); const parser = new XMLParser({ ignoreAttributes: false, }); let sitemap: Sitemap = parser.parse(sitemapXml); const rootUrl = 'https://blog.johnnyreilly.com'; const filteredUrls = sitemap.urlset.url.filter( (url) => url.loc !== `${rootUrl}/tags` && !url.loc.startsWith(rootUrl + '/tags/') && !url.loc.startsWith(rootUrl + '/page/') ); console.log( `Reducing ${sitemap.urlset.url.length} urls to ${filteredUrls.length} urls` ); sitemap.urlset.url = filteredUrls; const builder = new XMLBuilder({ format: false, ignoreAttributes: false }); const shorterSitemapXml = builder.build(sitemap); console.log(`Saving ${sitemapPath}`); await fs.promises.writeFile(sitemapPath, shorterSitemapXml); } trimXML();
-
InfluxDB
InfluxDB – Built for High-Performance Time Series Workloads. InfluxDB 3 OSS is now GA. Transform, enrich, and act on time series data directly in the database. Automate critical tasks and eliminate the need to move data externally. Download now.
-
fast-xml-parser
Validate XML, Parse XML and Build XML rapidly without C/C++ based libraries and no callback.
After experimenting with a few different XML parsers I settled on fast-xml-parser. It's fast, it's simple and it's well maintained. It also handles XML namespaces and attributes well. (This appears to be rare in XML parsers.)
