Skip to content

Instantly share code, notes, and snippets.

What would you like to do?
Markdown to Plaintext in Python
from bs4 import BeautifulSoup
from markdown import markdown
def markdown_to_text(markdown_string):
""" Converts a markdown string to plaintext """
# md -> html -> text since BeautifulSoup can extract text cleanly
html = markdown(markdown_string)
# remove code snippets
html = re.sub(r'<pre>(.*?)</pre>', ' ', html)
html = re.sub(r'<code>(.*?)</code >', ' ', html)
# extract text
soup = BeautifulSoup(html, "html.parser")
text = ''.join(soup.findAll(text=True))
return text
Copy link

hemikak commented Aug 19, 2018

 html = re.sub(r'<code>(.*?)</code>', ' ', html)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment