Deal with utf8 bom encoding problem. from http://stackoverflow.com/questions/13590749/reading-unicode-file-data-with-bom-chars-in-python

deal_with_bom_utf8.py

import codecs
import chardet

bytes = min(32, os.path.getsize(filename))
raw = open(filename, 'rb').read(bytes)

if raw.startswith(codecs.BOM_UTF8):
    encoding = 'utf-8-sig'
else:
    result = chardet.detect(raw)
    encoding = result['encoding']

infile = codecs.open(filename, mode, encoding=encoding)
data = infile.read()
infile.close()

print(data)