Chris
import urllib2
url = 'www.someurl.com'
f = urllib2.urlopen(url)
data = f.read()
# if it is not in the pagecode, how do i get the encoding of the page?
pageencoding = '???'
xmlencoding = 'whatever i parsed out of the file'
htmlmetaencoding = 'whatever i parsed out of the metatag'
f.close()
try:
data = data.decode(pageencoding)
except:
try:
data = data.decode(xmlencoding)
except:
try:
data = data.decode(htmlmetaencoding)
except:
try:
data = data.encode('UTF-8')
except:
flag = true
for char in data:
if 127 < ord(char) < 160:
flag = false
if flag:
try:
data = data.encode('latin-1')
except:
pass
try:
data = data.encode('cp1252')
except:
pass
try:
data = data.encode('latin-1')
except:
pass
data = data.encode("ascii", "xmlcharrefreplace")-- http://mail.python.org/mailman/listinfo/python-list
