Some basic python encoding/decoding/unicode examples

python_encoding_examples.py

string_with_utf8 = "T\xc3\xa4ter" # str, no unicode
correct_unicode = string_with_utf8.decode("utf-8") # interpret string as utf-8
print repr(correct_unicode) # T\xe4ter, correct unicode string

string_with_utf8_new = correct_unicode.encode("utf-8") # make a utf-8 str()
print repr(string_with_utf8_new) # equals repr(string_with_utf8), str()

#correct_unicode.encode("ascii") # UnicodeEncodeError becuase ascii has no representation for this char!

bad_unicode = unicode("T\xc3\xa4ter")
print repr(bad_unicode) #u'T\xc3\xa4ter' not interpreted as utf-8, so:

correct_unicode = unicode("T\xc3\xa4ter", "utf-8") # make a unicode string from a utf-8 representation
print repr(correct_unicode) # u'T\xe4ter', nice!