Ugly python script which extracts the text from tb_Quest_Scripts_eng.res file of Soulworker into a json file.

qscript_read.py

import os
import json
import codecs

def read_block(f):
	block_size = 0
	index = int.from_bytes(bytes(f.read(4)), byteorder='little')
	block_size += 4
	len1 = int.from_bytes(bytes(f.read(2)), byteorder='little')
	block_size += 2
	str1 = codecs.decode(bytes(f.read(len1 * 2)), encoding='utf-8', errors='replace').replace('\0', '')
	block_size += len1 * 2

	len2 = int.from_bytes(bytes(f.read(2)), byteorder='little')
	block_size += 2
	str2 = codecs.decode(bytes(f.read(len2 * 2)), encoding='utf-8', errors='replace').replace('\0', '')
	block_size += len2 * 2

	len3 = int.from_bytes(bytes(f.read(2)), byteorder='little')
	block_size += 2
	str3 = codecs.decode(bytes(f.read(len3 * 2)), encoding='utf-8', errors='replace').replace('\0', '')
	block_size += len3 * 2

	len4 = int.from_bytes(bytes(f.read(2)), byteorder='little')
	block_size += 2
	str4 = codecs.decode(bytes(f.read(len4 * 2)), encoding='utf-8', errors='replace').replace('\0', '')
	block_size += len4 * 2

	len5 = int.from_bytes(bytes(f.read(2)), byteorder='little')
	block_size += 2
	str5 = codecs.decode(bytes(f.read(len5* 2)), encoding='utf-8', errors='replace').replace('\0', '')
	block_size += len5 * 2

	return {"index": index, "str1": str1, "str2": str2, "str3": str3, "str4": str4, "str5": str5, "size": block_size}

fname = "tb_Quest_Script_eng.res"
fsize = os.path.getsize(fname)
entries = []
with open("tb_Quest_Script_eng.res", "rb") as f:
	try:
		entry_count = int.from_bytes(f.read(4), byteorder='little')
		fsize -= 4
		while entry_count > 0:
			block = read_block(f)
			fsize -= block["size"]
			entry_count -= 1
			entries.append(block)

	except Exception as e:
		print(e)
with open('sw_quests.json', 'w', encoding='utf-8') as c:
	json.dump(entries, c, ensure_ascii=False, indent=4)

print('done')

This script cannot display Chinese, Japanese, Korean and some symbols correctly after extracting the text. Can anyone modify the code so that they can display correctly?

Oh come on, you can do it yourself! You only need to modify it to make it read 3 bytes instead of 2 😃