chore: initial commit

scripts/analyze_customers.py

@@ -0,0 +1,124 @@
+#!/usr/bin/env python3
+"""
+分析 Funstat 查询结果，生成高质量客户清单
+"""
+
+import json
+from datetime import datetime
+
+# 读取查询结果
+with open('funstat_query_results.json', 'r', encoding='utf-8') as f:
+    results = json.load(f)
+
+# 提取所有用户
+all_users = []
+for result in results:
+    for item in result['parsed_data']:
+        if item['usernames']:
+            for username in item['usernames']:
+                all_users.append({
+                    'username': username,
+                    'display_name': item['raw_text'].split('[')[1].split(']')[0] if '[' in item['raw_text'] else 'Unknown',
+                    'keyword': result['keyword'],
+                    'keyword_type': result['type'],
+                    'group_link': item['group_links'][-1] if len(item['group_links']) > 1 else '',
+                    'raw_text': item['raw_text']
+                })
+
+print(f"{'='*80}")
+print(f"📊 007翻译客户分析报告")
+print(f"{'='*80}\n")
+
+print(f"📋 总览:")
+print(f"  - 发现用户总数: {len(all_users)}")
+print(f"  - 去重后: {len(set(u['username'] for u in all_users))}\n")
+
+# 按关键词类型分类
+type_stats = {}
+for user in all_users:
+    t = user['keyword_type']
+    if t not in type_stats:
+        type_stats[t] = []
+    type_stats[t].append(user)
+
+print(f"📊 按痛点/需求分类:\n")
+for t, users in type_stats.items():
+    print(f"  {t}: {len(users)} 个用户")
+    for user in users[:3]:
+        print(f"    • @{user['username']} ({user['display_name']}) - 关键词: {user['keyword']}")
+    if len(users) > 3:
+        print(f"    ... 还有 {len(users)-3} 个")
+    print()
+
+# 高价值客户识别
+print(f"\n{'='*80}")
+print(f"💎 高价值客户（优先级排序）")
+print(f"{'='*80}\n")
+
+# 规则1: 竞品用户（最高优先级）
+competitors = [u for u in all_users if 'kt' in u['display_name'].lower() or 'kt' in u['username'].lower() or 'fanyi' in u['username'].lower() or '翻译' in u['display_name']]
+if competitors:
+    print(f"🔥🔥🔥 S级 - 竞品用户/翻译从业者 ({len(competitors)} 个):")
+    for user in competitors:
+        print(f"  ⭐ @{user['username']} ({user['display_name']})")
+        print(f"     关键词: {user['keyword']} | 群组: {user['group_link']}")
+    print()
+
+# 规则2: 痛点表达者（高优先级）
+pain_users = [u for u in all_users if u['keyword_type'] == '痛点类']
+print(f"🔥🔥 A级 - 痛点表达者 ({len(pain_users)} 个):")
+top_pain = pain_users[:5]
+for user in top_pain:
+    print(f"  • @{user['username']} ({user['display_name']})")
+    print(f"    痛点: {user['keyword']} | 群组: {user['group_link']}")
+print(f"  ... 还有 {len(pain_users)-5} 个\n" if len(pain_users) > 5 else "")
+
+# 规则3: 需求表达者
+need_users = [u for u in all_users if u['keyword_type'] == '需求类']
+if need_users:
+    print(f"🔥 B级 - 需求表达者 ({len(need_users)} 个):")
+    for user in need_users:
+        print(f"  • @{user['username']} ({user['display_name']})")
+        print(f"    需求: {user['keyword']} | 群组: {user['group_link']}")
+    print()
+
+# 规则4: 对比研究者
+compare_users = [u for u in all_users if u['keyword_type'] == '对比类']
+if compare_users:
+    print(f"🔥 B级 - 对比研究者 ({len(compare_users)} 个):")
+    for user in compare_users:
+        print(f"  • @{user['username']} ({user['display_name']})")
+        print(f"    对比: {user['keyword']} | 群组: {user['group_link']}")
+    print()
+
+# 导出客户清单
+output = {
+    'generated_at': datetime.now().isoformat(),
+    'total_users': len(all_users),
+    'unique_users': len(set(u['username'] for u in all_users)),
+    'by_priority': {
+        'S级_竞品用户': [{'username': u['username'], 'name': u['display_name'], 'keyword': u['keyword'], 'group': u['group_link']} for u in competitors],
+        'A级_痛点用户': [{'username': u['username'], 'name': u['display_name'], 'keyword': u['keyword'], 'group': u['group_link']} for u in pain_users],
+        'B级_需求用户': [{'username': u['username'], 'name': u['display_name'], 'keyword': u['keyword'], 'group': u['group_link']} for u in need_users],
+        'B级_对比用户': [{'username': u['username'], 'name': u['display_name'], 'keyword': u['keyword'], 'group': u['group_link']} for u in compare_users],
+    }
+}
+
+with open('高质量客户清单.json', 'w', encoding='utf-8') as f:
+    json.dump(output, f, ensure_ascii=False, indent=2)
+
+print(f"\n{'='*80}")
+print(f"✅ 分析完成！")
+print(f"{'='*80}")
+print(f"\n📁 输出文件:")
+print(f"  1. 高质量客户清单.json - 结构化数据")
+print(f"  2. 此报告已输出到屏幕\n")
+
+print(f"📝 建议行动:")
+print(f"  1. 优先联系 S级客户（竞品用户）")
+print(f"  2. 针对 A级客户的痛点定制话术")
+print(f"  3. B级客户可以批量触达")
+print(f"\n💡 预估转化率:")
+print(f"  - S级: 40-50%")
+print(f"  - A级: 25-35%")
+print(f"  - B级: 15-25%")