def _parse_page(self, html):
text = ''
#html = html.replace('\n', '')
html = ' '.join(html).replace('\n', ' ').replace('\r', '')
f = open('kala', 'w')
f.write(html)
f.close
#r = re.compile('(.*?)<header>(*.?)</header>(.*?)<body>(.*?)</body>(.*?)')
r = re.compile('(.*?)<body>(.*?)</body>(.*?)')
m = r.match(html)
if m:
#header = m.group(2)
body = m.group(2)
else:
body = ''
r = re.compile('(.*?)<(.*?)>(.*?)</(.*?)>')
m = r.match(body)
if m.groups():
for n in m.groups()
t = m.group(1)
#text += t
print 'payload: ', t
return text