Determine charset encoding from byte sequence and known unicode codepoint

find_encoding.py

#!/usr/bin/env python
import click

codepoint_hex = click.prompt("Enter a unicode codepoint (hex) for a known character")
encoded_bytes = click.prompt("Enter the bytes corresponding to the same character in an unknown encoding, in hex")
encoded_bytes = bytearray.fromhex(encoded_bytes)

codepoint_dec =  int(codepoint_hex, 16)
unicode_char =  chr(codepoint_dec)
click.echo("The unicode characters is: %s" % unicode_char)
possible_encodings = ["ascii", "big5", "big5hkscs", "cp037", "cp424", "cp437", "cp500", "cp720", "cp737", "cp775", "cp850", "cp852", "cp855", "cp856", "cp857", "cp858", "cp860", "cp861", "cp862", "cp863", "cp864", "cp865", "cp866", "cp869", "cp874", "cp875", "cp932", "cp949", "cp950", "cp1006", "cp1026", "cp1140", "cp1250", "cp1251", "cp1252", "cp1253", "cp1254", "cp1255", "cp1256", "cp1257", "cp1258", "euc_jp", "euc_jis_2004", "euc_jisx0213", "euc_kr", "gb2312", "gbk", "gb18030", "hz", "iso2022_jp", "iso2022_jp_1", "iso2022_jp_2", "iso2022_jp_2004", "iso2022_jp_3", "iso2022_jp_ext", "iso2022_kr", "latin_1", "iso8859_2", "iso8859_3", "iso8859_4", "iso8859_5", "iso8859_6", "iso8859_7", "iso8859_8", "iso8859_9", "iso8859_10", "iso8859_13", "iso8859_14", "iso8859_15", "iso8859_16", "johab", "koi8_r", "koi8_u", "mac_cyrillic", "mac_greek", "mac_iceland", "mac_latin2", "mac_roman", "mac_turkish", "ptcp154", "shift_jis", "shift_jis_2004", "shift_jisx0213", "utf_32", "utf_32_be", "utf_32_le", "utf_16", "utf_16_be", "utf_16_le", "utf_7", "utf_8", "utf_8_sig"]
for encoding in possible_encodings:
    try:
        if unicode_char.encode(encoding) == encoded_bytes:
            click.echo("charset is %s" % encoding)
            break
    except UnicodeEncodeError:
        continue

Suppose you have some text in an unknown encoding. For a specific letter in that text, you may be able to guess what the corresponding unicode symbol should be. This script allows you to enter the code point for that character, and the byte sequence that is assumed to be that character in an unknown encoding. It will then go through all known encodings and print the name of the first encoding where the encoded symbol results in the desired bytes.