1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
|
"""
批量对话内容提取脚本
用于处理千恋万花游戏脚本中的所有JSON文件，提取中文对话并转换为指定格式
"""
import json
import re
import os
import sys
import glob
from pathlib import Path
def extract_dialogues_from_json(json_file_path):
"""
从JSON文件中提取对话内容
Args:
json_file_path (str): JSON文件路径
Returns:
list: 提取的对话列表，格式为 [角色名, 简体中文对话, voice字符串]
"""
dialogues = []
try:
encodings = ['utf-8', 'utf-8-sig', 'gbk', 'shift_jis', 'cp932']
content = None
for encoding in encodings:
try:
with open(json_file_path, 'r', encoding=encoding) as file:
content = file.read()
print(f"成功使用 {encoding} 编码读取文件")
break
except UnicodeDecodeError:
continue
if content is None:
print("无法使用任何编码读取文件")
return []
try:
data = json.loads(content)
print("成功解析JSON数据")
except json.JSONDecodeError as e:
print(f"JSON解析错误: {e}")
return extract_dialogues_with_regex(content)
def find_dialogues(obj, path=[]):
if isinstance(obj, list):
for i, item in enumerate(obj):
if (isinstance(item, list) and len(item) >= 4 and
item[1] is None and
isinstance(item[2], list) and len(item[2]) >= 3):
if item[0] is None:
character_name = ""
elif isinstance(item[0], str):
character_name = item[0]
else:
character_name = ""
dialogue_array = item[2]
if len(dialogue_array) > 2 and isinstance(dialogue_array[2], list) and len(dialogue_array[2]) >= 2:
chinese_dialogue = dialogue_array[2][1]
chinese_character_name = ""
if len(dialogue_array) > 2 and isinstance(dialogue_array[2], list) and len(dialogue_array[2]) >= 1:
chinese_character_name = dialogue_array[2][0]
if not chinese_character_name and character_name:
chinese_character_name = character_name
voice_string = ""
if len(item) > 3 and isinstance(item[3], dict) and "voice" in item[3]:
voice_string = item[3]["voice"]
elif len(item) > 3 and isinstance(item[3], list) and len(item[3]) > 0 and isinstance(item[3][0], dict) and "voice" in item[3][0]:
voice_string = item[3][0]["voice"]
dialogues.append({
'character': chinese_character_name,
'dialogue': chinese_dialogue,
'voice': voice_string
})
find_dialogues(item, path + [i])
elif isinstance(obj, dict):
for key, value in obj.items():
find_dialogues(value, path + [key])
find_dialogues(data)
print(f"找到 {len(dialogues)} 个对话条目")
except Exception as e:
print(f"处理文件时出错: {e}")
import traceback
traceback.print_exc()
return []
return dialogues
def extract_dialogues_with_regex(content):
"""使用正则表达式提取对话内容（备用方法）"""
dialogues = []
pattern = r'\[\s*(?:"([^"]+)"|null)\s*,\s*null\s*,\s*\[(.*?)\]\s*,\s*\{(.*?)\}.*?\]'
matches = re.findall(pattern, content, re.DOTALL)
print(f"使用正则表达式找到 {len(matches)} 个匹配项")
for match in matches:
character_name = match[0] if match[0] else ""
dialogue_array_str = match[1]
voice_info = match[2]
simplified_pattern = r'"([^"]+)"\s*,\s*"([^"]+)'
dialogue_matches = re.findall(simplified_pattern, dialogue_array_str)
if len(dialogue_matches) >= 3:
simplified_chinese = dialogue_matches[2][1]
voice_match = re.search(r'"voice"\s*:\s*"([^"]+)"', voice_info)
voice_string = voice_match.group(1) if voice_match else ""
dialogues.append({
'character': character_name,
'dialogue': simplified_chinese,
'voice': voice_string
})
return dialogues
def convert_to_target_format(dialogues):
"""
将提取的对话转换为目标格式
Args:
dialogues (list): 提取的对话列表
Returns:
list: 转换后的对话列表
"""
formatted_dialogues = []
for dialogue in dialogues:
character = dialogue['character']
text = dialogue['dialogue']
voice = dialogue['voice']
if character:
formatted = f"{character}：{text}"
else:
formatted = text
if voice:
formatted += f" [{voice}.ogg]"
formatted_dialogues.append(formatted)
return formatted_dialogues
def process_json_file(input_file_path, output_file_path=None):
"""
处理单个JSON文件
Args:
input_file_path (str): 输入JSON文件路径
output_file_path (str, optional): 输出文件路径，如果为None则打印到控制台
"""
print(f"正在处理文件: {input_file_path}")
dialogues = extract_dialogues_from_json(input_file_path)
if not dialogues:
print("未找到符合条件的对话内容")
return 0
print(f"找到 {len(dialogues)} 个对话")
formatted_dialogues = convert_to_target_format(dialogues)
if output_file_path:
with open(output_file_path, 'w', encoding='utf-8') as f:
for dialogue in formatted_dialogues:
f.write(dialogue + '\n')
print(f"结果已保存到: {output_file_path}")
else:
print("\n转换后的对话内容:")
print("=" * 50)
for i, dialogue in enumerate(formatted_dialogues, 1):
print(f"{i}. {dialogue}")
return len(dialogues)
def batch_process_all_json_files(input_directory, output_directory):
"""
批量处理所有JSON文件
Args:
input_directory (str): 输入目录路径
output_directory (str): 输出目录路径
"""
os.makedirs(output_directory, exist_ok=True)
json_files = []
json_files.extend(glob.glob(os.path.join(input_directory, "**", "*.json"), recursive=True))
json_files.extend(glob.glob(os.path.join(input_directory, "*.json")))
json_files = list(set(json_files))
print(f"找到 {len(json_files)} 个JSON文件")
total_dialogues = 0
processed_files = 0
for json_file in json_files:
try:
file_name = os.path.basename(json_file)
output_file_name = file_name.replace('.json', '_dialogues.txt')
output_file_path = os.path.join(output_directory, output_file_name)
dialogue_count = process_json_file(json_file, output_file_path)
total_dialogues += dialogue_count
processed_files += 1
print(f"已完成 {processed_files}/{len(json_files)} 个文件")
print("-" * 50)
except Exception as e:
print(f"处理文件 {json_file} 时出错: {e}")
continue
print(f"\n批量处理完成！")
print(f"成功处理 {processed_files}/{len(json_files)} 个文件")
print(f"总共提取 {total_dialogues} 个对话条目")
summary_file = os.path.join(output_directory, "processing_summary.txt")
with open(summary_file, 'w', encoding='utf-8') as f:
f.write("批量对话处理汇总报告\n")
f.write("=" * 50 + "\n")
f.write(f"处理时间: {os.path.getctime(__file__)}\n")
f.write(f"输入目录: {input_directory}\n")
f.write(f"输出目录: {output_directory}\n")
f.write(f"找到的JSON文件总数: {len(json_files)}\n")
f.write(f"成功处理的文件数: {processed_files}\n")
f.write(f"总共提取的对话条目数: {total_dialogues}\n")
f.write("\n处理的文件列表:\n")
for json_file in json_files:
file_name = os.path.basename(json_file)
output_file_name = file_name.replace('.json', '_dialogues.txt')
f.write(f"- {file_name} -> {output_file_name}\n")
print(f"汇总报告已保存到: {summary_file}")
def main():
"""主函数"""
input_directory = r"C:\Users\lgf\Desktop\galageimu\千恋万花"
output_directory = r"C:\Users\lgf\Desktop\galageimu\千恋万花\aaa"
print("开始批量处理所有JSON文件...")
print(f"输入目录: {input_directory}")
print(f"输出目录: {output_directory}")
print("=" * 60)
batch_process_all_json_files(input_directory, output_directory)
if __name__ == "__main__":
main()
|
