Open-source tool helps you convert PDF documents, web pages, etc., into Markdown

Anyone know how this compares to GROBID [1]? I&#x27;m looking at alternatives to GROBID as I&#x27;m not super pleased with its outputs. GROBID has a lot of great features for journal papers (reference extraction &#x2F; parsing), but I&#x27;m only interested in cleanly extracting the body. Also considering nougat [2] but I haven&#x27;t tried it yet.<p>[1] <a href="https:&#x2F;&#x2F;github.com&#x2F;kermitt2&#x2F;grobid">https:&#x2F;&#x2F;github.com&#x2F;kermitt2&#x2F;grobid</a><p>[2] <a href="https:&#x2F;&#x2F;github.com&#x2F;facebookresearch&#x2F;nougat">https:&#x2F;&#x2F;github.com&#x2F;facebookresearch&#x2F;nougat</a>

Nice tool, I&#x27;ve been using html2md[1] and such. It&#x27;s written in python and in beta so it&#x27;s probably not the best for processing static sites and such. But still useful<p>[1]: <a href="https:&#x2F;&#x2F;github.com&#x2F;suntong&#x2F;html2md">https:&#x2F;&#x2F;github.com&#x2F;suntong&#x2F;html2md</a>