201 lines
6.6 KiB
Python
201 lines
6.6 KiB
Python
#!/usr/bin/env python3
|
||
# -*- coding: utf-8 -*-
|
||
|
||
"""
|
||
内容整合API路由
|
||
"""
|
||
|
||
import logging
|
||
import tempfile
|
||
import os
|
||
import base64
|
||
from fastapi import APIRouter, HTTPException
|
||
from typing import Dict, Any
|
||
|
||
from api.models.content_integration import (
|
||
ContentIntegrationRequest,
|
||
ContentIntegrationResponse
|
||
)
|
||
from api.services.content_integration_service import ContentIntegrationService
|
||
|
||
logger = logging.getLogger(__name__)
|
||
|
||
router = APIRouter(prefix="/content-integration", tags=["content-integration"])
|
||
|
||
# 全局服务实例
|
||
integration_service = ContentIntegrationService()
|
||
|
||
|
||
@router.post("/integrate", response_model=ContentIntegrationResponse)
|
||
async def integrate_content(request: ContentIntegrationRequest) -> ContentIntegrationResponse:
|
||
"""
|
||
整合文档和小红书笔记内容
|
||
|
||
该接口将：
|
||
1. 处理用户上传的base64编码文档（支持PDF、Word、图片等格式）
|
||
2. 根据关键词搜索小红书相关笔记（可选）
|
||
3. 使用LLM将两者整合成综合性旅游资料
|
||
|
||
Args:
|
||
request: 整合请求参数
|
||
|
||
Returns:
|
||
整合结果
|
||
|
||
Raises:
|
||
HTTPException: 当请求参数无效或处理失败时
|
||
"""
|
||
temp_files = []
|
||
try:
|
||
# 创建临时文件处理base64文档
|
||
if request.documents:
|
||
for doc in request.documents:
|
||
try:
|
||
# 从base64内容中提取实际内容（跳过data:image/jpeg;base64,这样的前缀）
|
||
content = doc.content
|
||
if ',' in content:
|
||
content = content.split(',', 1)[1]
|
||
|
||
# 创建临时文件
|
||
suffix = os.path.splitext(doc.filename)[1]
|
||
if not suffix:
|
||
# 根据MIME类型推断后缀
|
||
mime_to_ext = {
|
||
'text/plain': '.txt',
|
||
'application/pdf': '.pdf',
|
||
'application/msword': '.doc',
|
||
'application/vnd.openxmlformats-officedocument.wordprocessingml.document': '.docx',
|
||
'image/jpeg': '.jpg',
|
||
'image/png': '.png'
|
||
}
|
||
suffix = mime_to_ext.get(doc.mime_type, '.bin')
|
||
|
||
with tempfile.NamedTemporaryFile(delete=False, suffix=suffix) as temp_file:
|
||
# 解码base64内容并写入临时文件
|
||
try:
|
||
decoded_content = base64.b64decode(content)
|
||
temp_file.write(decoded_content)
|
||
temp_files.append(temp_file.name)
|
||
logger.info(f"成功保存临时文件: {temp_file.name}")
|
||
except Exception as e:
|
||
logger.error(f"Base64解码失败: {e}")
|
||
raise HTTPException(
|
||
status_code=400,
|
||
detail=f"文档 {doc.filename} 的Base64内容无效: {str(e)}"
|
||
)
|
||
except Exception as e:
|
||
logger.error(f"处理文档 {doc.filename} 失败: {e}")
|
||
raise HTTPException(
|
||
status_code=400,
|
||
detail=f"文档 {doc.filename} 处理失败: {str(e)}"
|
||
)
|
||
|
||
logger.info(f"收到内容整合请求：文档 {len(temp_files) if temp_files else 0} 个，关键词 {len(request.keywords) if request.keywords else 0} 个")
|
||
|
||
# 调用服务层处理
|
||
result = await integration_service.integrate_content(
|
||
document_paths=temp_files,
|
||
keywords=request.keywords or [],
|
||
cookies=request.cookies or "",
|
||
sort_type=request.sort_type,
|
||
note_type=request.note_type,
|
||
note_time=request.note_time,
|
||
note_range=request.note_range,
|
||
pos_distance=request.pos_distance,
|
||
query_num=request.query_num
|
||
)
|
||
|
||
return result
|
||
|
||
except Exception as e:
|
||
logger.error(f"内容整合接口异常：{e}", exc_info=True)
|
||
raise HTTPException(
|
||
status_code=500,
|
||
detail=f"内容整合处理失败：{str(e)}"
|
||
)
|
||
finally:
|
||
# 清理临时文件
|
||
for temp_file in temp_files:
|
||
try:
|
||
if os.path.exists(temp_file):
|
||
os.unlink(temp_file)
|
||
except Exception as e:
|
||
logger.error(f"清理临时文件 {temp_file} 失败: {e}")
|
||
|
||
|
||
@router.get("/health")
|
||
async def health_check() -> Dict[str, str]:
|
||
"""
|
||
健康检查接口
|
||
|
||
Returns:
|
||
服务状态信息
|
||
"""
|
||
try:
|
||
# 检查服务是否正常初始化
|
||
if not integration_service:
|
||
raise Exception("服务未正确初始化")
|
||
|
||
return {
|
||
"status": "healthy",
|
||
"service": "content-integration",
|
||
"message": "内容整合服务运行正常"
|
||
}
|
||
except Exception as e:
|
||
logger.error(f"健康检查失败：{e}")
|
||
raise HTTPException(
|
||
status_code=503,
|
||
detail=f"服务不可用：{str(e)}"
|
||
)
|
||
|
||
|
||
@router.get("/config/options")
|
||
async def get_config_options() -> Dict[str, Any]:
|
||
"""
|
||
获取配置选项说明
|
||
|
||
Returns:
|
||
各配置项的可选值和说明
|
||
"""
|
||
return {
|
||
"sort_type": {
|
||
"0": "综合排序",
|
||
"1": "最新",
|
||
"2": "最多点赞",
|
||
"3": "最多评论",
|
||
"4": "最多收藏"
|
||
},
|
||
"note_type": {
|
||
"0": "不限",
|
||
"1": "视频笔记",
|
||
"2": "普通笔记"
|
||
},
|
||
"note_time": {
|
||
"0": "不限",
|
||
"1": "一天内",
|
||
"2": "一周内",
|
||
"3": "半年内"
|
||
},
|
||
"note_range": {
|
||
"0": "不限",
|
||
"1": "已看过",
|
||
"2": "未看过",
|
||
"3": "已关注"
|
||
},
|
||
"pos_distance": {
|
||
"0": "不限",
|
||
"1": "同城",
|
||
"2": "附近"
|
||
},
|
||
"query_num": "每个关键词搜索的笔记数量（1-50）",
|
||
"supported_document_formats": [
|
||
"PDF (.pdf)",
|
||
"Word (.docx, .doc)",
|
||
"PowerPoint (.pptx, .ppt)",
|
||
"Excel (.xlsx, .xls)",
|
||
"Text (.txt)",
|
||
"Markdown (.md)",
|
||
"Images (.jpg, .jpeg, .png, .gif, .bmp, .tiff)",
|
||
"CSV (.csv)"
|
||
]
|
||
} |