htmlParse.py

# To run this, download the BeautifulSoup zip file
# http://www.py4e.com/code3/bs4.zip
# and unzip it in the same directory as this file

from urllib.request import urlopen
from bs4 import BeautifulSoup
import ssl
import re

# Ignore SSL certificate errors
ctx = ssl.create_default_context()
ctx.check_hostname = False
ctx.verify_mode = ssl.CERT_NONE

url = input('Enter - ') # http://py4e-data.dr-chuck.net/comments_2381078.html
html = urlopen(url, context=ctx).read()
soup = BeautifulSoup(html, "html.parser")
numberOfSpanTags = 0
total = 0

# Retrieve all of the anchor tags
tags = soup('span')
for tag in tags:
    # Look at the parts of a tag
    numberOfSpanTags = numberOfSpanTags + 1
    numbers = re.findall("[0-9]+", tag.contents[0])
    print('TAG:', tag)
    print('URL:', tag.get('href', None))
    print('Contents:', tag.contents[0])
    print('Attrs:', tag.attrs)
    for number in numbers:
        total = total + int(number)
print('Number of span tags:', numberOfSpanTags)
print('Total:', total)