def dom2text(dom, ignore_images=True, ignore_emphasis=True, ignore_tables=True):
from lxml import etree
import html2text
htt = html2text.HTML2Text()
htt.body_width = 0
htt.ignore_images = ignore_images
htt.ignore_emphasis = ignore_emphasis
htt.ignore_tables = ignore_tables
return htt.handle(etree.tostring(dom).decode())
评论列表
文章目录