<?xml version="1.0" encoding="UTF-8"?><urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"><url><loc>https://mbrenndoerfer.com/writing/document-extraction-html-parsing-boilerplate-removal-trafilatura/document-extraction</loc><lastmod>2026-01-09T10:34:55.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/document-extraction-html-parsing-boilerplate-removal-trafilatura/why-document-extraction-is-hard</loc><lastmod>2026-01-09T10:34:55.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/document-extraction-html-parsing-boilerplate-removal-trafilatura/html-parsing-fundamentals</loc><lastmod>2026-01-09T10:34:55.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/document-extraction-html-parsing-boilerplate-removal-trafilatura/content-extraction-approaches</loc><lastmod>2026-01-09T10:34:55.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/document-extraction-html-parsing-boilerplate-removal-trafilatura/trafilatura-industrial-strength-extraction</loc><lastmod>2026-01-09T10:34:55.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/document-extraction-html-parsing-boilerplate-removal-trafilatura/other-extraction-tools</loc><lastmod>2026-01-09T10:34:55.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/document-extraction-html-parsing-boilerplate-removal-trafilatura/pdf-and-other-document-formats</loc><lastmod>2026-01-09T10:34:55.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/document-extraction-html-parsing-boilerplate-removal-trafilatura/building-a-reliable-extraction-pipeline</loc><lastmod>2026-01-09T10:34:55.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/document-extraction-html-parsing-boilerplate-removal-trafilatura/comparing-extraction-tools</loc><lastmod>2026-01-09T10:34:55.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/document-extraction-html-parsing-boilerplate-removal-trafilatura/visualizations</loc><lastmod>2026-01-09T10:34:55.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/document-extraction-html-parsing-boilerplate-removal-trafilatura/limitations-and-practical-considerations</loc><lastmod>2026-01-09T10:34:55.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/document-extraction-html-parsing-boilerplate-removal-trafilatura/summary</loc><lastmod>2026-01-09T10:34:55.000Z</lastmod></url><url><loc>https://mbrenndoerfer.com/writing/document-extraction-html-parsing-boilerplate-removal-trafilatura/quiz</loc><lastmod>2026-01-09T10:34:55.000Z</lastmod></url></urlset>