{"type": "article", "title": "When HTML parsing fails: using LLMs to extract messy web data", "publisher": "Web Pulse", "url": "https://wpnews.pro/news/when-html-parsing-fails-using-llms-to-extract-messy-web-data", "original_source": "https://dev.to/__c1b9e06dc90a7e0a676b/when-html-parsing-fails-using-llms-to-extract-messy-web-data-20ab", "published": "2026-06-05T08:34:43+00:00", "accessed": "2026-06-05", "id": "when-html-parsing-fails-using-llms-to-extract-messy-web-data"}