优化了文本解析的输出字段
This commit is contained in:
parent
c66273b393
commit
f6cff4e5c0
Binary file not shown.
@ -71,15 +71,22 @@ async def integrate_content(request: ContentIntegrationRequest) -> ContentIntegr
|
||||
document_info=result["document_info"],
|
||||
xhs_info=result["xhs_info"],
|
||||
integrated_content=result["integrated_content"],
|
||||
search_config=result["search_config"]
|
||||
search_config=result["search_config"],
|
||||
error_message=None # 成功时无错误信息
|
||||
)
|
||||
logger.info(f"内容整合成功，处理时间：{result['processing_time']}")
|
||||
else:
|
||||
from datetime import datetime
|
||||
response = ContentIntegrationResponse(
|
||||
success=False,
|
||||
timestamp=result["timestamp"],
|
||||
processing_time=result["processing_time"],
|
||||
error_message=result["error_message"]
|
||||
timestamp=result.get("timestamp", datetime.now().strftime("%Y%m%d_%H%M%S")),
|
||||
processing_time=result.get("processing_time", "0秒"),
|
||||
input_summary=result.get("input_summary"),
|
||||
document_info=result.get("document_info"),
|
||||
xhs_info=result.get("xhs_info"),
|
||||
integrated_content=result.get("integrated_content"),
|
||||
search_config=result.get("search_config"),
|
||||
error_message=result.get("error_message")
|
||||
)
|
||||
logger.error(f"内容整合失败：{result['error_message']}")
|
||||
|
||||
|
||||
@ -8,13 +8,8 @@ Core Module
|
||||
提供内容整合的核心服务，通过适配器模式与xhs_spider和document模块交互
|
||||
"""
|
||||
|
||||
# 导入主要服务
|
||||
from .content_integration_service import (
|
||||
ContentIntegrationService,
|
||||
ProcessingConfig,
|
||||
ProcessingResult,
|
||||
ProcessingStats
|
||||
)
|
||||
# 注意：ContentIntegrationService已移至api.services模块
|
||||
# 这里不再导入，以避免与API服务冲突
|
||||
|
||||
# 导入适配器
|
||||
from .xhs_adapter import XHSAdapter, XHSNote, XHSSearchResult
|
||||
@ -30,14 +25,6 @@ __author__ = "TravelContentCreator Team"
|
||||
|
||||
# 导出所有公共接口
|
||||
__all__ = [
|
||||
# 主要服务
|
||||
'ContentIntegrationService',
|
||||
|
||||
# 数据模型
|
||||
'ProcessingConfig',
|
||||
'ProcessingResult',
|
||||
'ProcessingStats',
|
||||
|
||||
# 适配器
|
||||
'XHSAdapter',
|
||||
'DocumentAdapter',
|
||||
@ -57,26 +44,4 @@ __all__ = [
|
||||
'__author__'
|
||||
]
|
||||
|
||||
# 便捷函数
|
||||
def create_integration_service(cookie_config_path: str = "cookies.json",
|
||||
media_storage_path: str = "media",
|
||||
enable_logging: bool = True) -> ContentIntegrationService:
|
||||
"""
|
||||
创建内容整合服务实例的便捷函数
|
||||
|
||||
Args:
|
||||
cookie_config_path: Cookie配置文件路径
|
||||
media_storage_path: 媒体存储路径
|
||||
enable_logging: 是否启用日志
|
||||
|
||||
Returns:
|
||||
ContentIntegrationService: 内容整合服务实例
|
||||
"""
|
||||
return ContentIntegrationService(
|
||||
cookie_config_path=cookie_config_path,
|
||||
media_storage_path=media_storage_path,
|
||||
enable_logging=enable_logging
|
||||
)
|
||||
|
||||
# 添加到导出列表
|
||||
__all__.append('create_integration_service')
|
||||
# 注意：ContentIntegrationService及相关模型已移至api.services模块
|
||||
|
||||
Binary file not shown.
@ -1,349 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
"""
|
||||
Content Integration Service
|
||||
内容整合服务
|
||||
|
||||
core模块的主要服务，通过适配器与xhs_spider和document模块交互
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
from typing import Dict, List, Optional, Any
|
||||
from dataclasses import dataclass, field
|
||||
from datetime import datetime
|
||||
import logging
|
||||
import uuid
|
||||
|
||||
from .xhs_adapter import XHSAdapter, XHSSearchResult
|
||||
from .document_adapter import DocumentAdapter, IntegratedContent
|
||||
from .cookie_manager import CookieManager
|
||||
from .media_manager import ImageStorageManager
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@dataclass
|
||||
class ProcessingConfig:
|
||||
"""处理配置"""
|
||||
keyword: str
|
||||
document_paths: Optional[List[str]] = None
|
||||
max_notes: int = 20
|
||||
output_format: str = "summary"
|
||||
download_media: bool = True
|
||||
custom_prompt: Optional[str] = None
|
||||
|
||||
@dataclass
|
||||
class ProcessingResult:
|
||||
"""处理结果"""
|
||||
task_id: str
|
||||
config: ProcessingConfig
|
||||
success: bool
|
||||
xhs_result: Optional[XHSSearchResult] = None
|
||||
document_result: Optional[IntegratedContent] = None
|
||||
final_content: str = ""
|
||||
error_message: str = ""
|
||||
processing_time: float = 0.0
|
||||
created_time: datetime = field(default_factory=datetime.now)
|
||||
|
||||
@dataclass
|
||||
class ProcessingStats:
|
||||
"""处理统计信息"""
|
||||
total_tasks: int = 0
|
||||
successful_tasks: int = 0
|
||||
failed_tasks: int = 0
|
||||
total_processing_time: float = 0.0
|
||||
average_processing_time: float = 0.0
|
||||
total_notes_processed: int = 0
|
||||
total_documents_processed: int = 0
|
||||
start_time: datetime = field(default_factory=datetime.now)
|
||||
last_updated: datetime = field(default_factory=datetime.now)
|
||||
|
||||
class ContentIntegrationService:
|
||||
"""内容整合服务"""
|
||||
|
||||
def __init__(self,
|
||||
cookie_config_path: str = "cookies.json",
|
||||
media_storage_path: str = "media",
|
||||
enable_logging: bool = True):
|
||||
"""
|
||||
初始化服务
|
||||
|
||||
Args:
|
||||
cookie_config_path: Cookie配置文件路径
|
||||
media_storage_path: 媒体存储路径
|
||||
enable_logging: 是否启用日志
|
||||
"""
|
||||
self.cookie_config_path = cookie_config_path
|
||||
self.media_storage_path = media_storage_path
|
||||
self.enable_logging = enable_logging
|
||||
|
||||
# 初始化适配器
|
||||
self.xhs_adapter = XHSAdapter(cookie_config_path)
|
||||
self.document_adapter = DocumentAdapter()
|
||||
|
||||
# 初始化管理器
|
||||
self.cookie_manager = CookieManager(cookie_config_path)
|
||||
self.media_manager = ImageStorageManager(media_storage_path)
|
||||
|
||||
# 结果存储和统计
|
||||
self.results: Dict[str, ProcessingResult] = {}
|
||||
self.stats = ProcessingStats()
|
||||
|
||||
logger.info("内容整合服务初始化完成")
|
||||
|
||||
async def process_content(self,
|
||||
keyword: str,
|
||||
document_paths: Optional[List[str]] = None,
|
||||
output_format: str = "summary",
|
||||
max_notes: int = 20,
|
||||
custom_prompt: Optional[str] = None) -> ProcessingResult:
|
||||
"""
|
||||
处理内容整合
|
||||
|
||||
Args:
|
||||
keyword: 搜索关键词
|
||||
document_paths: 文档路径列表
|
||||
output_format: 输出格式
|
||||
max_notes: 最大笔记数量
|
||||
custom_prompt: 自定义提示词
|
||||
|
||||
Returns:
|
||||
ProcessingResult: 处理结果
|
||||
"""
|
||||
task_id = str(uuid.uuid4())
|
||||
start_time = datetime.now()
|
||||
|
||||
config = ProcessingConfig(
|
||||
keyword=keyword,
|
||||
document_paths=document_paths,
|
||||
max_notes=max_notes,
|
||||
output_format=output_format,
|
||||
custom_prompt=custom_prompt
|
||||
)
|
||||
|
||||
result = ProcessingResult(
|
||||
task_id=task_id,
|
||||
config=config,
|
||||
success=False
|
||||
)
|
||||
|
||||
try:
|
||||
# 1. 搜索小红书内容（如果有关键词）
|
||||
xhs_result = None
|
||||
if keyword:
|
||||
logger.info(f"开始搜索小红书内容: {keyword}")
|
||||
xhs_result = self.xhs_adapter.search_notes(
|
||||
keyword=keyword,
|
||||
max_notes=max_notes,
|
||||
|
||||
)
|
||||
result.xhs_result = xhs_result
|
||||
logger.info(f"小红书搜索完成，找到 {len(xhs_result.notes)} 条笔记")
|
||||
|
||||
# 2. 处理文档内容（如果有文档）
|
||||
document_result = None
|
||||
if document_paths:
|
||||
logger.info(f"开始处理文档: {len(document_paths)} 个文件")
|
||||
document_result = self.document_adapter.integrate_documents(document_paths)
|
||||
result.document_result = document_result
|
||||
logger.info(f"文档处理完成，总长度: {document_result.total_length}")
|
||||
|
||||
# 3. 整合内容
|
||||
final_content = self._integrate_content(
|
||||
xhs_result=xhs_result,
|
||||
document_result=document_result,
|
||||
output_format=output_format,
|
||||
custom_prompt=custom_prompt
|
||||
)
|
||||
result.final_content = final_content
|
||||
|
||||
# 4. 下载媒体文件（如果需要）
|
||||
if config.download_media and xhs_result:
|
||||
await self._download_media(xhs_result)
|
||||
|
||||
result.success = True
|
||||
logger.info(f"任务 {task_id} 处理完成")
|
||||
|
||||
except Exception as e:
|
||||
result.error_message = str(e)
|
||||
logger.error(f"任务 {task_id} 处理失败: {e}")
|
||||
|
||||
# 计算处理时间
|
||||
result.processing_time = (datetime.now() - start_time).total_seconds()
|
||||
|
||||
# 存储结果和更新统计
|
||||
self.results[task_id] = result
|
||||
self._update_statistics(result)
|
||||
|
||||
return result
|
||||
|
||||
async def batch_process(self,
|
||||
tasks: List[Dict[str, Any]],
|
||||
output_format: str = "summary") -> List[ProcessingResult]:
|
||||
"""
|
||||
批量处理任务
|
||||
|
||||
Args:
|
||||
tasks: 任务列表，每个任务包含keyword和document_paths
|
||||
output_format: 输出格式
|
||||
|
||||
Returns:
|
||||
List[ProcessingResult]: 处理结果列表
|
||||
"""
|
||||
results = []
|
||||
|
||||
# 并发处理任务
|
||||
async def process_task(task_config):
|
||||
return await self.process_content(
|
||||
keyword=task_config.get("keyword", ""),
|
||||
document_paths=task_config.get("document_paths"),
|
||||
output_format=output_format,
|
||||
max_notes=task_config.get("max_notes", 20),
|
||||
custom_prompt=task_config.get("custom_prompt")
|
||||
)
|
||||
|
||||
# 使用asyncio.gather并发执行
|
||||
tasks_coroutines = [process_task(task) for task in tasks]
|
||||
results = await asyncio.gather(*tasks_coroutines, return_exceptions=True)
|
||||
|
||||
# 处理异常结果
|
||||
processed_results = []
|
||||
for i, result in enumerate(results):
|
||||
if isinstance(result, Exception):
|
||||
error_result = ProcessingResult(
|
||||
task_id=str(uuid.uuid4()),
|
||||
config=ProcessingConfig(keyword=tasks[i].get("keyword", "")),
|
||||
success=False,
|
||||
error_message=str(result)
|
||||
)
|
||||
processed_results.append(error_result)
|
||||
else:
|
||||
processed_results.append(result)
|
||||
|
||||
return processed_results
|
||||
|
||||
def _integrate_content(self,
|
||||
xhs_result: Optional[XHSSearchResult],
|
||||
document_result: Optional[IntegratedContent],
|
||||
output_format: str,
|
||||
custom_prompt: Optional[str]) -> str:
|
||||
"""
|
||||
整合内容
|
||||
|
||||
Args:
|
||||
xhs_result: 小红书搜索结果
|
||||
document_result: 文档处理结果
|
||||
output_format: 输出格式
|
||||
custom_prompt: 自定义提示词
|
||||
|
||||
Returns:
|
||||
str: 整合后的内容
|
||||
"""
|
||||
content_parts = []
|
||||
|
||||
# 添加小红书内容
|
||||
if xhs_result and xhs_result.notes:
|
||||
xhs_content = "\n".join([
|
||||
f"标题: {note.title}\n内容: {note.content}\n作者: {note.author}\n"
|
||||
for note in xhs_result.notes[:5] # 只取前5条
|
||||
])
|
||||
content_parts.append(f"=== 小红书相关内容 ===\n{xhs_content}")
|
||||
|
||||
# 添加文档内容
|
||||
if document_result and document_result.integrated_text:
|
||||
content_parts.append(f"=== 文档相关内容 ===\n{document_result.integrated_text}")
|
||||
|
||||
# 合并内容
|
||||
if not content_parts:
|
||||
return "没有找到相关内容"
|
||||
|
||||
combined_content = "\n\n".join(content_parts)
|
||||
|
||||
# 根据输出格式转换内容
|
||||
if self.document_adapter.is_available():
|
||||
try:
|
||||
formatted_content = self.document_adapter.transform_content(
|
||||
combined_content,
|
||||
output_format
|
||||
)
|
||||
return formatted_content
|
||||
except Exception as e:
|
||||
logger.error(f"内容格式转换失败: {e}")
|
||||
|
||||
# 简单格式化
|
||||
return self._simple_format(combined_content, output_format)
|
||||
|
||||
def _simple_format(self, content: str, output_format: str) -> str:
|
||||
"""简单的内容格式化"""
|
||||
if output_format == "summary":
|
||||
return f"摘要:\n{content[:500]}..."
|
||||
elif output_format == "blog_post":
|
||||
return f"# 博客文章\n\n{content}"
|
||||
elif output_format == "travel_guide":
|
||||
return f"# 旅游攻略\n\n{content}"
|
||||
else:
|
||||
return content
|
||||
|
||||
async def _download_media(self, xhs_result: XHSSearchResult):
|
||||
"""下载媒体文件"""
|
||||
try:
|
||||
for note in xhs_result.notes:
|
||||
# 下载图片
|
||||
for image_url in note.images:
|
||||
await self.media_manager.download_image(image_url, note.note_id)
|
||||
|
||||
# 下载视频
|
||||
for video_url in note.videos:
|
||||
await self.media_manager.download_video(video_url, note.note_id)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"媒体下载失败: {e}")
|
||||
|
||||
def _update_statistics(self, result: ProcessingResult):
|
||||
"""更新统计信息"""
|
||||
self.stats.total_tasks += 1
|
||||
self.stats.total_processing_time += result.processing_time
|
||||
|
||||
if result.success:
|
||||
self.stats.successful_tasks += 1
|
||||
if result.xhs_result:
|
||||
self.stats.total_notes_processed += len(result.xhs_result.notes)
|
||||
if result.document_result:
|
||||
self.stats.total_documents_processed += len(result.document_result.documents)
|
||||
else:
|
||||
self.stats.failed_tasks += 1
|
||||
|
||||
# 计算平均处理时间
|
||||
if self.stats.total_tasks > 0:
|
||||
self.stats.average_processing_time = (
|
||||
self.stats.total_processing_time / self.stats.total_tasks
|
||||
)
|
||||
|
||||
self.stats.last_updated = datetime.now()
|
||||
|
||||
def get_statistics(self) -> ProcessingStats:
|
||||
"""获取处理统计信息"""
|
||||
return self.stats
|
||||
|
||||
def get_result(self, task_id: str) -> Optional[ProcessingResult]:
|
||||
"""获取处理结果"""
|
||||
return self.results.get(task_id)
|
||||
|
||||
def get_all_results(self) -> Dict[str, ProcessingResult]:
|
||||
"""获取所有处理结果"""
|
||||
return self.results.copy()
|
||||
|
||||
def clear_results(self):
|
||||
"""清空处理结果"""
|
||||
self.results.clear()
|
||||
|
||||
def get_status(self) -> Dict[str, Any]:
|
||||
"""获取服务状态"""
|
||||
return {
|
||||
"xhs_adapter": self.xhs_adapter.get_status(),
|
||||
"document_adapter": self.document_adapter.get_status(),
|
||||
"cookie_manager": self.cookie_manager.get_status() if hasattr(self.cookie_manager, 'get_status') else {},
|
||||
"media_manager": self.media_manager.get_status() if hasattr(self.media_manager, 'get_status') else {},
|
||||
"statistics": self.stats,
|
||||
"total_results": len(self.results)
|
||||
}
|
||||
@ -21,24 +21,47 @@
|
||||
{
|
||||
"attractions": [
|
||||
{
|
||||
"name": "景区/酒店名称",
|
||||
"name": "景区名称",
|
||||
"address": "景区详细地址",
|
||||
"trafficInfo": "交通指南详细信息",
|
||||
"description": "景区空泛描述信息",
|
||||
"advantage": "景区最大优势",
|
||||
"highlight": "景区亮点描述",
|
||||
"products": [
|
||||
{
|
||||
"product_name": "产品套餐名称",
|
||||
"usage_rules": "产品使用规则详细说明",
|
||||
"product_name": "产品名称",
|
||||
"originPrice": "原始价格",
|
||||
"realPrice": "实际价格",
|
||||
"packageInfo": "产品详情完整描述",
|
||||
"salesPeriod": "销售周期信息",
|
||||
"stock": "库存数量",
|
||||
"usage_rules": {
|
||||
"rules": "使用规则详细说明",
|
||||
"surcharge": "加价说明",
|
||||
"reservation": "预约规则",
|
||||
"refund": "退改政策",
|
||||
"discounts": "优惠内容"
|
||||
},
|
||||
"transportation": {
|
||||
"guide": "交通指南",
|
||||
"guide": "交通指南详细信息",
|
||||
"address": "详细地址"
|
||||
},
|
||||
"price": "产品价格信息",
|
||||
"key_advantages": "产品最突出优势",
|
||||
"key_advantages": "产品最大优势描述",
|
||||
"highlights": "产品亮点详细描述",
|
||||
"detailed_description": [
|
||||
"1. 详细描述项目1",
|
||||
"2. 详细描述项目2",
|
||||
"..."
|
||||
"1. 游泳池尺寸：长xx米，宽xx米，深xx米",
|
||||
"2. 泳池特色：如无边泳池、恒温泳池等",
|
||||
"3. 开放时间：xx:xx-xx:xx",
|
||||
"4. 适合人群：儿童/成人等",
|
||||
"5. 安全设施：救生员配置等",
|
||||
"6. 周边景点：xxx景点距离xx米",
|
||||
"7. 风景描述：如海景、山景等",
|
||||
"8. 小贴士：需要携带的物品等",
|
||||
"9. 游玩路线建议",
|
||||
"10. 推荐游玩时长"
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
Binary file not shown.
@ -342,7 +342,7 @@ class ContentPromptBuilder(BasePromptBuilder):
|
||||
style_filename = topic.get("style", "")
|
||||
style_content = self._find_and_read_file(style_filename, self.resource_config.style.paths) or "通用风格"
|
||||
|
||||
demand_filename = topic.get("target_audience", "")
|
||||
demand_filename = topic.get("targetAudience", "")
|
||||
demand_content = self._find_and_read_file(demand_filename, self.resource_config.demand.paths) or "通用用户画像"
|
||||
|
||||
object_name = topic.get("object", "")
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user