python html转markdown

python html转markdown

html2text

# pip3 install html2text
import html2text as ht

text_maker = ht.HTML2Text()
text_maker.bypass_tables = False

htmlfile = requests.get(URL)
htmlfile.encoding = 'utf-8'
soup = BeautifulSoup(htmlfile.text, 'html.parser')
content = soup.find(class_='post').text

text = text_maker.handle(content)

tomd

import tomd

htmlfile = requests.get(URL)
htmlfile.encoding = 'utf-8'
soup = BeautifulSoup(htmlfile.text, 'html.parser')
content = soup.find(class_='post').text

text = tomd.Tomd(content).markdown

pypandoc

import pypandoc

output = pypandoc.convert_text(
        htmlTxt,
        'md', format='html',
        extra_args=['--atx-headers'])

markdownload