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
| import json
import os
from datetime import datetime
def extract_conversation_messages(mapping, start_node_id="root"):
"""
从mapping的树形结构中递归提取对话消息
"""
messages = []
current_node_id = start_node_id
visited_nodes = set()
while current_node_id and current_node_id in mapping and current_node_id not in visited_nodes:
visited_nodes.add(current_node_id)
current_node = mapping[current_node_id]
message_data = current_node.get("message")
if message_data and isinstance(message_data, dict):
fragments = message_data.get("fragments", [])
files = message_data.get("files", [])
if files and isinstance(files, list):
for file_info in files:
if isinstance(file_info, dict):
file_content = f"\n\n[文件: {file_info.get('file_name', 'unnamed')}]\n{file_info.get('content', '')}\n"
messages.append({
"role": "system",
"content": file_content,
"type": "FILE_ATTACHMENT"
})
for fragment in fragments:
if not isinstance(fragment, dict):
continue
if "type" not in fragment:
continue
fragment_type = fragment.get("type")
if fragment_type == "REQUEST":
role = "user"
elif fragment_type == "RESPONSE":
role = "assistant"
elif fragment_type == "THINK":
role = "assistant_think"
else:
continue
content = fragment.get("content", "")
messages.append({
"role": role,
"content": content,
"type": fragment_type,
"inserted_at": message_data.get("inserted_at", "")
})
children = current_node.get("children", [])
if children and isinstance(children, list):
current_node_id = children[0]
else:
current_node_id = None
return messages
def json_to_obsidian():
json_path = "新建 文本文档.txt"
output_folder = r"C:\Users\dog\Documents\Obsidian Vault\deepseek"
os.makedirs(output_folder, exist_ok=True)
try:
with open(json_path, 'r', encoding='utf-8') as f:
data = json.load(f)
print(f"成功加载JSON数据")
except Exception as e:
print(f"加载JSON文件失败: {e}")
return
if isinstance(data, dict):
conversations = [data]
elif isinstance(data, list):
conversations = data
else:
print("错误：不支持的JSON数据格式")
return
print(f"开始处理 {len(conversations)} 个对话...")
successful_count = 0
skipped_count = 0
error_count = 0
for index, conversation in enumerate(conversations):
if not isinstance(conversation, dict):
print(f"跳过非字典类型的对话 {index}")
skipped_count += 1
continue
conv_id = conversation.get("id", f"unknown_{index}")
title = conversation.get("title", f"Conversation {conv_id}")
inserted_at = conversation.get("inserted_at", "")
mapping = conversation.get("mapping", {})
print(f"\n[{index + 1}/{len(conversations)}] 处理: {title}")
try:
messages = extract_conversation_messages(mapping)
except Exception as e:
print(f" 提取消息时出错: {e}")
error_count += 1
continue
if not messages:
print(f" 跳过空对话")
skipped_count += 1
continue
valid_title = "".join(c for c in str(title) if c not in '<>:"/\\|?*').strip()
if not valid_title or len(valid_title) > 100:
valid_title = f"conversation_{conv_id[:8]}"
if len(valid_title) > 50:
valid_title = valid_title[:50] + "..."
filename = f"{valid_title}.md"
filepath = os.path.join(output_folder, filename)
counter = 1
original_filepath = filepath
while os.path.exists(filepath):
filename = f"{valid_title}_{counter}.md"
filepath = os.path.join(output_folder, filename)
counter += 1
time_str = "Unknown time"
if inserted_at:
try:
if isinstance(inserted_at, str):
time_part = inserted_at.split('T')[0] if 'T' in inserted_at else inserted_at
time_str = time_part
except:
time_str = str(inserted_at)[:19]
try:
md_content = f"# {title}\n\n"
md_content += f"**Conversation ID:** `{conv_id}` \n"
md_content += f"**Created:** {time_str}\n\n"
md_content += "---\n\n"
for msg in messages:
if msg["role"] == "user":
md_content += f"### 👤 User\n\n"
elif msg["role"] == "assistant":
md_content += f"### 🤖 Assistant\n\n"
elif msg["role"] == "assistant_think":
md_content += f"### 🤖 Assistant (内部思考)\n\n"
elif msg["role"] == "system":
md_content += f"### 📎 文件附件\n\n"
content = msg['content']
if content.strip().startswith(('<?php', '<script', 'FROM ', 'RUN ', '#!/')):
language = 'php' if '<?php' in content else 'dockerfile' if 'FROM ' in content else 'javascript' if '<script' in content else ''
md_content += f"```{language}\n{content}\n```\n\n"
else:
md_content += f"{content}\n\n"
md_content += "---\n\n"
with open(filepath, 'w', encoding='utf-8') as md_file:
md_file.write(md_content)
print(f" 成功创建: {filename} ({len(messages)} 条消息)")
successful_count += 1
except Exception as e:
print(f" 创建文件失败: {e}")
error_count += 1
print(f"\n=== 处理完成 ===")
print(f"总对话数: {len(conversations)}")
print(f"成功导出: {successful_count}")
print(f"跳过: {skipped_count}")
print(f"错误: {error_count}")
print(f"输出文件夹: {output_folder}")
if __name__ == "__main__":
json_to_obsidian()
|