使用htmlparser python获取标签下的html

可以使用

xml.etree.ElementTree.TreeBuilder

<span>

import sysfrom HTMLParser import HTMLParserfrom xml.etree import cElementTree as etreeclass linksParser(HTMLParser):  def __init__(self):      HTMLParser.__init__(self)      self.tb = etree.TreeBuilder()  def handle_starttag(self, tag, attributes):      self.tb.start(tag, dict(attributes))  def handle_endtag(self, tag):      self.tb.end(tag)  def handle_data(self, data):      self.tb.data(data)  def close(self):      HTMLParser.close(self)      return self.tb.close()parser = linksParser()parser.feed(sys.stdin.read())root = parser.close()span = root.find(".//span[@itemprop='description']")etree.ElementTree(span).write(sys.stdout)

输出量

<span itemprop="description"><h1>My First Heading</h1><p>My first <br /><br />paragraph.</p></span>

要在没有父（根）

<span>

sys.stdout.write(span.text)for child in span:    sys.stdout.write(etree.tostring(child)) # add encoding="unipre" on Python 3