from lxml.html import etree
content = "***************"
html = etree.HTML(str(content))
html_data = html.xpath('//span/text()|//p//text()|//section//text()')
datas = [data.replace("/r", "").replace("/n", '').replace('/t', '').replace('/xa0', '') for data in list(html_data)]
ori_content = ' '.join([d for d in datas if d])
原创文章，作者：ItWorker，如若转载，请注明出处：https://blog.ytso.com/tech/pnotes/279068.html