Get the html under a tag using htmlparser python

问题

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(HTMLParser):
  def __init__(self):
    HTMLParser.__init__(self)
    self.recording = 0
    self.data = ''

  def handle_starttag(self, tag, attributes):
    if tag != 'span':
      return
    if self.recording:
      self.recording += 1
      return
    for name, value in attributes:
      if name == 'itemprop' and value == 'description':
        break
    else:
      return
    self.recording = 1

  def handle_endtag(self, tag):
    if tag == 'span' and self.recording:
      self.recording -= 1

  def handle_data(self, data):
    if self.recording:
      self.data += data

I also want the html tags inside the input for example

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

when provided as input would only give me the data with out tags. Is there any method with which I can get whole html between the tags?

回答1:

One could use xml.etree.ElementTree.TreeBuilder to exploit etree API for finding/manipulating the <span> 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

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

To print without the parent (root) <span> tag:

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

回答2:

Here's something that gets the job done based on the test data you provided with minimal changes to your existing code (assuming it's basically doing what you want already). You'd probably want to expand it to deal with self-closing tags in a more robust way:

from HTMLParser import HTMLParser

class LinksParser(HTMLParser):
    def __init__(self):
        HTMLParser.__init__(self)
        self.recording = 0
        self.data = ''
        self.self_closing_tags = ("br",)

    def handle_starttag(self, tag, attributes):
        if tag not in ('span',) + self.self_closing_tags:
            self.data += "<%s" % (tag,)
            if attributes:
                self.data += " " + " ".join('%s="%s"' % (k, v) for k, v in attributes)
            self.data += ">"
            return
        if self.recording:
            self.recording += 1
            return
        for name, value in attributes:
            if name == 'itemprop' and value == 'description':
                break
        else:
            return
        self.recording = 1 

    def handle_endtag(self, tag):
        if tag == 'span' and self.recording:
             self.recording -= 1
        elif tag in self.self_closing_tags:
             self.data += "<%s/"> % (tag,)
        else:
             self.data += "</%s>" % (tag,)

    def handle_data(self, data):
        if self.recording:
            self.data += data

Given this as input:

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

the output is:

<h1>My First Heading</h1>
<p>My first <br/><br/>paragraph.</p>

来源：https://stackoverflow.com/questions/13334044/get-the-html-under-a-tag-using-htmlparser-python

标签

python

html-parsing