获取lxml中标签内的所有文本

尝试：

def stringify_children(node):    from lxml.etree import tostring    from itertools import chain    parts = ([node.text] + list(chain(*([c.text, tostring(c), c.tail] for c in node.getchildren()))) + [node.tail])    # filter removes possible Nones in texts and tails    return ''.join(filter(None, parts))

例：

from lxml import etreenode = etree.fromstring("""<content>Text outside tag <div>Text <em>inside</em> tag</div></content>""")stringify_children(node)

产生：

'nText outside tag <div>Text <em>inside</em> tag</div>n'