This code to extract data from the html files based on class information

extracttext.py

inputfilename='file.html'
data=urllib2.urlopen(inputfilename)
soup = BeautifulSoup(data)
data=soup.prettify()
soup = BeautifulSoup(data)
ti=soup.findAll(attrs={'class':'pno'})
for t in ti:
     t.extract()     
ti=soup.findAll(attrs={'class':'subhead'})
for t in ti:
     t.extract()     
lines=[]
for s in soup(text=True):
     s=s.strip().replace('\t','')
     print s