markdown to text python
Published on Aug. 22, 2023, 12:11 p.m.
markdown转换成纯文本:
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