utf8编码

def main():
    fin = open('utf8.txt', 'r', encoding='utf_8')
    fout = open('utf8.html', 'w')    
    outbytes = bytearray()    
    for line in fin:
        for c in line:
            if ord(c) > 127:
                outbytes += bytes('&#{:04d}'.format(ord(c)), encoding='utf_8')
            else: outbytes.append(ord(c))
    outstr = str(outbytes, encoding='utf_8')    
    print(outstr, file=fout)
    print(outstr) #&#1641(&#0865&#3663&#0815&#0865&#3663)&#1782
    print("Done.")       

if __name__ == "__main__": main()