文档相关功能

deploy.ps1

@@ -1,59 +0,0 @@
-# 确保在项目根目录下执行此脚本
-
-# 7-Zip路径 - 请根据实际安装位置修改
-$7zipPath = "D:\7zip\7-Zip\7z.exe"  # 原始路径
-# $7zipPath = "C:\Program Files\7-Zip\7z.exe"  # 修改后的路径
-
-# 创建临时部署目录
-New-Item -Path "deploy_temp" -ItemType Directory -Force
-
-# 复制整个项目目录到临时目录
-Copy-Item -Path "role_based_system" -Destination "deploy_temp\" -Recurse -Force
-Copy-Item -Path "user_management" -Destination "deploy_temp\" -Recurse -Force
-Copy-Item -Path "manage.py" -Destination "deploy_temp\" -Force
-Copy-Item -Path "requirements.txt" -Destination "deploy_temp\" -Force
-Copy-Item -Path "*.md" -Destination "deploy_temp\" -Force -ErrorAction SilentlyContinue
-
-# 移除不需要的文件和目录
-Get-ChildItem -Path "deploy_temp" -Recurse -Filter "__pycache__" -Directory | Remove-Item -Recurse -Force
-Get-ChildItem -Path "deploy_temp" -Recurse -Filter "*.pyc" | Remove-Item -Force
-
-# 特别排除不需要的目录
-$excludeDirs = @(
-    ".git", ".idea", ".vscode", 
-    "venv", ".venv", "env", "__pycache__", "migrations"
-)
-
-foreach ($dir in $excludeDirs) {
-    Get-ChildItem -Path "deploy_temp" -Recurse -Directory -Filter $dir | 
-    Where-Object { $_.FullName -notmatch "\\migrations\\__pycache__" } | 
-    Remove-Item -Recurse -Force -ErrorAction SilentlyContinue
-}
-
-# 保留migrations目录但删除其中的pyc文件
-if (Test-Path "deploy_temp\user_management\migrations") {
-    Get-ChildItem -Path "deploy_temp\user_management\migrations" -Filter "*.pyc" | Remove-Item -Force
-    Get-ChildItem -Path "deploy_temp\user_management\migrations" -Directory -Filter "__pycache__" | Remove-Item -Recurse -Force
-}
-
-# 排除不需要的文件
-$excludeFiles = @(
-    "*.pyc", "*.pyo", "*.pyd", "*.so", "*.dll", 
-    "*.db", "*.sqlite3", "*.log", "*.zip", "*.tar.gz",
-    "local_settings.py", "*.bak"
-)
-
-foreach ($pattern in $excludeFiles) {
-    Get-ChildItem -Path "deploy_temp" -Recurse -Filter $pattern | Remove-Item -Force -ErrorAction SilentlyContinue
-}
-
-
-# 使用7-Zip打包
-& $7zipPath a -ttar knowledge_system.tar ".\deploy_temp\*"
-& $7zipPath a -tgzip knowledge_system.tar.gz knowledge_system.tar
-
-# 清理临时文件
-Remove-Item -Path "knowledge_system.tar" -Force
-Remove-Item -Path "deploy_temp" -Recurse -Force
-
-Write-Host "部署包已创建: knowledge_system.tar.gz" -ForegroundColor Green

feishu/feishu.py

@@ -2,6 +2,8 @@ import json
 import django
 import os
 import sys
+import pandas as pd
+from django.db import transaction
 
 # 设置 Django 环境
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
@@ -30,7 +32,7 @@ def extract_field_value(field_value):
     return field_value
 
 def save_to_database(record):
-    """保存记录到数据库"""
+    """从飞书多维表格保存记录到数据库"""
     fields = record.fields
     record_id = record.record_id
     
@@ -57,7 +59,7 @@ def save_to_database(record):
         'system_categories': extract_field_value(fields.get('系统展示的带货品类', [])),
         'actual_categories': extract_field_value(fields.get('实际高播放量带货品类', [])),
         'human_categories': fields.get('达人标想要货品类', ''),
-        'creator_base': '',  # 如果有这个字段，添加相应的处理
+        'creator_base': '',
         'notes': extract_field_value(fields.get('父记录', '')),
     }
     
@@ -131,7 +133,92 @@ def fetch_all_records(client, app_token, table_id, user_access_token):
     print(f"最终获取到 {len(total_records)} 条记录")
     return total_records
 
-def main():
+def update_from_excel(excel_file_path):
+    """从Excel文件更新数据库记录"""
+    try:
+        print(f"开始读取Excel文件: {excel_file_path}")
+        df = pd.read_excel(excel_file_path)
+        
+        if 'Handle' not in df.columns:
+            print("错误: Excel文件中缺少'Handle'列")
+            return
+        
+        update_count = 0
+        skip_count = 0
+        error_count = 0
+        
+        # 获取可更新的字段列表
+        excluded_fields = {'id', 'record_id', 'created_at', 'updated_at'}
+        model_fields = {f.name for f in FeishuCreator._meta.get_fields()} - excluded_fields
+        valid_columns = set(df.columns) & model_fields
+        
+        print(f"可更新的列: {valid_columns}")
+        
+        with transaction.atomic():
+            for index, row in df.iterrows():
+                try:
+                    handle = str(row['Handle']).strip()
+                    if not handle:
+                        print(f"跳过第{index+2}行: Handle为空")
+                        skip_count += 1
+                        continue
+                    
+                    # 查找现有记录
+                    creator = FeishuCreator.objects.filter(handle=handle).first()
+                    if not creator:
+                        print(f"跳过Handle为'{handle}'的记录: 数据库中不存在")
+                        skip_count += 1
+                        continue
+                    
+                    # 准备更新数据
+                    update_data = {}
+                    for column in valid_columns:
+                        if column == 'Handle':
+                            continue
+                        
+                        value = row[column]
+                        if pd.isna(value):
+                            continue
+                        
+                        # 处理特殊类型
+                        if isinstance(value, (list, dict)):
+                            value = json.dumps(value)
+                        elif isinstance(value, (int, float)):
+                            if column in ['fans_count']:
+                                value = int(value)
+                            else:
+                                value = str(value)
+                        else:
+                            value = str(value).strip()
+                        
+                        if value:
+                            update_data[column] = value
+                    
+                    # 更新记录
+                    if update_data:
+                        for field, value in update_data.items():
+                            setattr(creator, field, value)
+                        creator.save()
+                        update_count += 1
+                        print(f"已更新Handle为'{handle}'的记录")
+                    else:
+                        skip_count += 1
+                        print(f"跳过Handle为'{handle}'的记录: 无需更新")
+                        
+                except Exception as e:
+                    error_count += 1
+                    print(f"处理Handle'{handle}'时出错: {str(e)}")
+        
+        print("\nExcel更新完成！统计信息：")
+        print(f"更新记录数：{update_count}")
+        print(f"跳过记录数：{skip_count}")
+        print(f"错误记录数：{error_count}")
+        
+    except Exception as e:
+        print(f"处理Excel文件时出错: {str(e)}")
+
+def sync_from_feishu():
+    """从飞书多维表格同步数据"""
     # 创建client
     client = lark.Client.builder() \
         .enable_set_token(True) \
@@ -143,15 +230,13 @@ def main():
     TABLE_ID = "tbl3oikG3F8YYtVA"
     USER_ACCESS_TOKEN = "u-ecM5BmzKx4uHz3sG0FouQSk1l9kxgl_3Xa00l5Ma24Jy"
 
-    # 获取所有记录
+    print("开始从飞书同步数据...")
-    print("开始获取所有记录...")
     all_records = fetch_all_records(client, APP_TOKEN, TABLE_ID, USER_ACCESS_TOKEN)
 
     if not all_records:
         print("未获取到任何记录")
         return
 
-    # 更新数据库
     print("\n开始更新数据库...")
     created_count = 0
     updated_count = 0
@@ -162,7 +247,7 @@ def main():
         if creator:
             if created:
                 created_count += 1
-                if created_count % 10 == 0:  # 每10条才打印一次，避免输出过多
+                if created_count % 10 == 0:
                     print(f"已创建 {created_count} 条记录...")
             else:
                 updated_count += 1
@@ -172,13 +257,34 @@ def main():
             error_count += 1
             print(f"处理记录失败")
 
-    # 打印统计信息
+    print("\n飞书同步完成！统计信息：")
-    print("\n更新完成！统计信息：")
     print(f"新建记录：{created_count}")
     print(f"更新记录：{updated_count}")
     print(f"错误记录：{error_count}")
     print(f"总记录数：{len(all_records)}")
 
+def main():
+    """主函数"""
+    if len(sys.argv) < 2:
+        print("使用方法:")
+        print("1. 从飞书同步: python feishu.py sync")
+        print("2. 从Excel更新: python feishu.py excel <excel文件路径>")
+        return
+        
+    command = sys.argv[1]
+    
+    if command == 'sync':
+        sync_from_feishu()
+    elif command == 'excel':
+        if len(sys.argv) != 3:
+            print("使用方法: python feishu.py excel <excel文件路径>")
+            return
+        excel_file_path = sys.argv[2]
+        update_from_excel(excel_file_path)
+    else:
+        print("无效的命令。使用方法:")
+        print("1. 从飞书同步: python feishu.py sync")
+        print("2. 从Excel更新: python feishu.py excel <excel文件路径>")
 
 if __name__ == "__main__":
     main()

user_management/migrations/0004_knowledgebasedocument.py

@@ -0,0 +1,35 @@
+# Generated by Django 5.1.5 on 2025-03-31 14:03
+
+import django.db.models.deletion
+import uuid
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('user_management', '0003_alter_feishucreator_handle'),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name='KnowledgeBaseDocument',
+            fields=[
+                ('id', models.UUIDField(default=uuid.uuid4, editable=False, primary_key=True, serialize=False)),
+                ('document_id', models.CharField(max_length=100, verbose_name='文档ID')),
+                ('document_name', models.CharField(max_length=255, verbose_name='文档名称')),
+                ('external_id', models.CharField(max_length=100, verbose_name='外部文档ID')),
+                ('status', models.CharField(choices=[('active', '有效'), ('deleted', '已删除')], default='active', max_length=20, verbose_name='状态')),
+                ('create_time', models.DateTimeField(auto_now_add=True, verbose_name='创建时间')),
+                ('update_time', models.DateTimeField(auto_now=True, verbose_name='更新时间')),
+                ('knowledge_base', models.ForeignKey(on_delete=django.db.models.deletion.CASCADE, related_name='kb_documents', to='user_management.knowledgebase', verbose_name='知识库')),
+            ],
+            options={
+                'verbose_name': '知识库文档',
+                'verbose_name_plural': '知识库文档',
+                'db_table': 'knowledge_base_documents',
+                'indexes': [models.Index(fields=['knowledge_base', 'status'], name='knowledge_b_knowled_a4db1b_idx'), models.Index(fields=['document_id'], name='knowledge_b_documen_dab90f_idx'), models.Index(fields=['external_id'], name='knowledge_b_externa_b0060c_idx')],
+                'unique_together': {('knowledge_base', 'document_id')},
+            },
+        ),
+    ]

user_management/models.py

@@ -669,3 +669,41 @@ class FeishuCreator(models.Model):
         db_table = 'feishu_creators'
         verbose_name = '创作者数据'
         verbose_name_plural = '创作者数据'
+
+class KnowledgeBaseDocument(models.Model):
+    """知识库文档关联模型"""
+    id = models.UUIDField(primary_key=True, default=uuid.uuid4, editable=False)
+    knowledge_base = models.ForeignKey(
+        'KnowledgeBase', 
+        on_delete=models.CASCADE,
+        related_name='kb_documents',
+        verbose_name='知识库'
+    )
+    document_id = models.CharField(max_length=100, verbose_name='文档ID')
+    document_name = models.CharField(max_length=255, verbose_name='文档名称')
+    external_id = models.CharField(max_length=100, verbose_name='外部文档ID')
+    status = models.CharField(
+        max_length=20, 
+        default='active',
+        choices=[
+            ('active', '有效'),
+            ('deleted', '已删除')
+        ],
+        verbose_name='状态'
+    )
+    create_time = models.DateTimeField(auto_now_add=True, verbose_name='创建时间')
+    update_time = models.DateTimeField(auto_now=True, verbose_name='更新时间')
+
+    class Meta:
+        db_table = 'knowledge_base_documents'
+        unique_together = ['knowledge_base', 'document_id']
+        indexes = [
+            models.Index(fields=['knowledge_base', 'status']),
+            models.Index(fields=['document_id']),
+            models.Index(fields=['external_id'])
+        ]
+        verbose_name = '知识库文档'
+        verbose_name_plural = '知识库文档'
+
+    def __str__(self):
+        return f"{self.knowledge_base.name} - {self.document_name}"