Get the html under a tag using htmlparser python

Question

I want to get whole html under a tag and using HTMLParser. I am able to currently get the data between the tags and following is my code

class LinksParser(HT         


        

Answer 1

One could use xml.etree.ElementTree.TreeBuilder to exploit etree API for finding/manipulating the element:

import sys
from HTMLParser import HTMLParser
from xml.etree import cElementTree as etree

class 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)

Output

My First Heading
My first 

paragraph.

To print without the parent (root) tag:

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