python Beautifulsoup count element which has no content http://stackoverflow.com/questions/26770378/python-beautifulsoup-count-element-which-has-no-content

soup_counter.py

from bs4 import BeautifulSoup
import re

def count(html):
  soup = BeautifulSoup(html)

  total = 0
  for node in soup.find_all(True):
    inner_html = "".join([str(x) for x in node.contents])
    if node.name and re.match('^\\s*$', inner_html):
      total = total + 1

  return total

soup_counter_test.py

import unittest
import soup_counter

class SoupCounterTest(unittest.TestCase):
  def test_count(self):
    html = """
    <dl>
        <dt class="details-row-7">Overall</dt>
        <dd id="c0r11" class=" alternate details-row-7">
            <div class="foo"></div>
            <div class="bar">
            </div>
            <div class="foobar"><i class="icon icon-home">  </i></div>
            <div class="mobile-headings">Overall</div>
            <div class="mobile-value">
                <div class="ca-rating-star" data-size="1">
                    <i class="icon-star icon-1x" style="color: #FF9900"></i>
                    <i class="icon-star icon-1x" style="color: #FF9900"></i>
                    <i class="icon-star icon-1x" style="color: #FF9900"></i>
                    <i class="icon-star icon-1x" style="color: #FF9900"></i>
                    <i class="icon-star-empty icon-1x" style="color: #FF9900"></i>
                </div>
            </div>
        </dd>
    </dl>
    """
    count = soup_counter.count(html)

    self.assertEquals(count, 8)

if __name__ == '__main__':
    unittest.main()