urllib program
import urllib.request
def countHead(url):
page = urllib.request.urlopen(url)
numHeadLines = 0
line = page.readline().decode('utf-8')
while '<HEAD>' not in line:
line = page.readline().decode('utf-8')
line = page.readline().decode('utf-8')
while '</HEAD>' not in line:
numHeadLines = numHeadLines + 1
line = page.readline().decode('utf-8')
line = page.readline().decode('utf-8')
while "<BODY>" not in line:
line = page.readline().decode('utf-8')
line = page.readline().decode('utf-8')
while line != "" and "</BODY>" not in line:
print (line[:-1])
line = page.readline().decode('utf-8')
print ("number of lines in header = ", numHeadLines)
page.close()
url = "http://people.cornellcollege.edu/tdelaubenfels/home.htm"
countHead(url)