-
-
Save nabeel-shakeel/bc7d32f719aa9cc1198fefdbea15c042 to your computer and use it in GitHub Desktop.
html to markdown
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from html2text import HTML2Text | |
| from textwrap import dedent | |
| from trafilatura import extract | |
| import re | |
| def get_md(cts, extractor='h2t'): | |
| h2t = HTML2Text(bodywidth=5000) | |
| h2t.ignore_links = True | |
| h2t.mark_code = True | |
| h2t.ignore_images = True | |
| res = h2t.handle(cts) | |
| def _f(m): return f'```\n{dedent(m.group(1))}\n```' | |
| return re.sub(r'\[code]\s*\n(.*?)\n\[/code]', _f, res or '', flags=re.DOTALL).strip() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment