import html2text as ht # pip install html2text
text_maker = ht.HTML2Text()
text_maker.bypass_tables = False
htmlfile = requests.get(npurl)#网页网址
htmlfile.encoding = 'gbk'
htmlpage = htmlfile.text
text = text_maker.handle(htmlpage)
md = text.split('#')import html2text as ht # pip install html2text