116 lines
3.9 KiB
Python
116 lines
3.9 KiB
Python
#!/usr/bin/env python3
|
||
"""完整搜索翻译相关用户并保存到文件"""
|
||
|
||
import sys
|
||
sys.path.insert(0, '.')
|
||
from server import FunstatMCPServer
|
||
import asyncio
|
||
import re
|
||
import json
|
||
from datetime import datetime
|
||
|
||
async def main():
|
||
server = FunstatMCPServer()
|
||
await server.initialize()
|
||
|
||
results = []
|
||
seen = set()
|
||
|
||
keywords = [
|
||
'翻译', 'translation', 'translate', 'translator', 'translators',
|
||
'译者', '翻译组', '翻译团队', '字幕组', '汉化', '汉化组',
|
||
'subtitle', 'subtitles', 'fansub', 'scanlation',
|
||
'localization', '本地化', 'interpreting', 'interpretation',
|
||
'translation group', 'subtitle group', 'translation team'
|
||
]
|
||
|
||
print(f"🔍 开始搜索 {len(keywords)} 个关键词")
|
||
print(f"⚠️ 每个关键词返回最多15条结果（funstat BOT限制）")
|
||
print(f"💡 通过多关键词覆盖更多用户")
|
||
print("")
|
||
|
||
for i, kw in enumerate(keywords, 1):
|
||
print(f"[{i:2d}/{len(keywords)}] {kw:25s}", end=' ', flush=True)
|
||
try:
|
||
res = await server.send_command_and_wait(f'/search {kw}', use_cache=False)
|
||
|
||
ids = re.findall(r'`(\d+)`', res)
|
||
usernames = re.findall(r'@(\w+)', res) + re.findall(r't\.me/(\w+)', res)
|
||
|
||
new_count = 0
|
||
for uid in ids:
|
||
key = f"ID:{uid}"
|
||
if key not in seen:
|
||
seen.add(key)
|
||
results.append({'type': 'id', 'value': uid, 'keyword': kw})
|
||
new_count += 1
|
||
|
||
for username in usernames:
|
||
if username:
|
||
key = f"@{username}"
|
||
if key not in seen:
|
||
seen.add(key)
|
||
results.append({'type': 'username', 'value': username, 'keyword': kw})
|
||
new_count += 1
|
||
|
||
print(f"+{new_count:2d} → 总计: {len(results):3d}")
|
||
await asyncio.sleep(0.5)
|
||
|
||
except Exception as e:
|
||
print(f"失败: {e}")
|
||
|
||
# 保存文件
|
||
txt_file = '/Users/lucas/chat--1003255561049/translation_users.txt'
|
||
json_file = '/Users/lucas/chat--1003255561049/translation_users.json'
|
||
|
||
with open(txt_file, 'w', encoding='utf-8') as f:
|
||
f.write("=" * 80 + "\n")
|
||
f.write("翻译相关用户/群组完整列表\n")
|
||
f.write("=" * 80 + "\n")
|
||
f.write(f"总数: {len(results)} 条\n")
|
||
f.write(f"搜索时间: {datetime.now()}\n")
|
||
f.write(f"数据来源: funstat BOT (@openaiw_bot)\n")
|
||
f.write("=" * 80 + "\n\n")
|
||
|
||
for i, item in enumerate(results, 1):
|
||
if item['type'] == 'id':
|
||
f.write(f"{i:4d}. ID: {item['value']:15s} (来源: {item['keyword']})\n")
|
||
else:
|
||
f.write(f"{i:4d}. @{item['value']:30s} (来源: {item['keyword']})\n")
|
||
|
||
with open(json_file, 'w', encoding='utf-8') as f:
|
||
json.dump({
|
||
'total': len(results),
|
||
'timestamp': str(datetime.now()),
|
||
'results': results
|
||
}, f, ensure_ascii=False, indent=2)
|
||
|
||
print("")
|
||
print("=" * 80)
|
||
print(f"✅ 搜索完成！共找到 {len(results)} 条独特记录")
|
||
print("=" * 80)
|
||
print(f"📄 文本文件: {txt_file}")
|
||
print(f"📄 JSON文件: {json_file}")
|
||
print("")
|
||
|
||
# 显示前100条
|
||
print("📋 前 100 条结果:")
|
||
print("")
|
||
for i, item in enumerate(results[:100], 1):
|
||
if item['type'] == 'id':
|
||
print(f"{i:3d}. ID: {item['value']}")
|
||
else:
|
||
print(f"{i:3d}. @{item['value']}")
|
||
|
||
if len(results) > 100:
|
||
print(f"\n... 还有 {len(results) - 100} 条记录，请查看文件")
|
||
|
||
await server.client.disconnect()
|
||
|
||
print(f"\n🎯 最终统计: {len(results)} 条独特记录")
|
||
print(f"📊 ID数量: {sum(1 for r in results if r['type'] == 'id')}")
|
||
print(f"👤 用户名数量: {sum(1 for r in results if r['type'] == 'username')}")
|
||
|
||
if __name__ == '__main__':
|
||
asyncio.run(main())
|