191 lines
7.4 KiB
Python
191 lines
7.4 KiB
Python
#!/usr/bin/env python3
|
||
# -*- coding: utf-8 -*-
|
||
|
||
"""
|
||
内容整合API模型
|
||
"""
|
||
|
||
from typing import List, Optional, Dict, Any, Union
|
||
from pydantic import BaseModel, Field, field_validator, model_validator
|
||
from typing import Dict
|
||
|
||
|
||
class Base64Document(BaseModel):
|
||
"""Base64编码的文档模型"""
|
||
filename: str = Field(..., description="文件名")
|
||
content: str = Field(..., description="Base64编码的文件内容")
|
||
mime_type: str = Field(..., description="文件MIME类型")
|
||
|
||
|
||
class ContentIntegrationRequest(BaseModel):
|
||
"""内容整合请求模型"""
|
||
documents: Optional[List[Base64Document]] = Field(default=None, description="Base64编码的文档列表")
|
||
keywords: Optional[List[str]] = Field(default=None, description="搜索关键词列表")
|
||
cookies: Optional[str] = Field(default=None, description="小红书Cookie字符串")
|
||
|
||
# 小红书搜索配置
|
||
sort_type: Optional[int] = Field(default=2, ge=0, le=4, description="排序方式: 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: Optional[int] = Field(default=2, ge=0, le=2, description="笔记类型: 0不限, 1视频笔记, 2普通笔记")
|
||
note_time: Optional[int] = Field(default=0, ge=0, le=3, description="笔记时间: 0不限, 1一天内, 2一周内, 3半年内")
|
||
note_range: Optional[int] = Field(default=0, ge=0, le=3, description="笔记范围: 0不限, 1已看过, 2未看过, 3已关注")
|
||
pos_distance: Optional[int] = Field(default=0, ge=0, le=2, description="位置距离: 0不限, 1同城, 2附近")
|
||
query_num: Optional[int] = Field(default=10, ge=1, le=50, description="每个关键词搜索的笔记数量")
|
||
|
||
# 文档校验
|
||
@field_validator('documents')
|
||
def validate_documents(cls, v):
|
||
if v is not None and not v:
|
||
raise ValueError("如果提供文档，列表不能为空")
|
||
return v
|
||
|
||
# 关键词校验
|
||
@field_validator('keywords')
|
||
def validate_keywords(cls, v):
|
||
if v is not None:
|
||
if not v:
|
||
raise ValueError("如果提供关键词，列表不能为空")
|
||
cleaned = list({k.strip() for k in v if k.strip()})
|
||
if not cleaned:
|
||
raise ValueError("关键词列表不能全为空")
|
||
return cleaned
|
||
return v
|
||
|
||
# Cookie校验
|
||
@field_validator('cookies')
|
||
def validate_cookies(cls, v):
|
||
if v is not None:
|
||
if not v.strip():
|
||
raise ValueError("如果提供Cookie，不能为空")
|
||
return v.strip()
|
||
return v
|
||
|
||
# 跨字段校验
|
||
@model_validator(mode='after')
|
||
def validate_request(cls, values):
|
||
has_documents = values.documents is not None
|
||
has_keywords = values.keywords is not None
|
||
has_cookies = values.cookies is not None
|
||
|
||
if not has_documents and not (has_keywords and has_cookies):
|
||
raise ValueError("必须提供文档或(关键词和Cookie)中的至少一项")
|
||
|
||
if has_keywords and not has_cookies:
|
||
raise ValueError("提供关键词时必须提供Cookie")
|
||
|
||
if has_cookies and not has_keywords:
|
||
raise ValueError("提供Cookie时必须提供关键词")
|
||
|
||
return values
|
||
|
||
class Config:
|
||
json_schema_extra = {
|
||
"example": {
|
||
"documents": [
|
||
{
|
||
"filename": "travel_guide.pdf",
|
||
"content": "base64_encoded_content_here",
|
||
"mime_type": "application/pdf"
|
||
}
|
||
],
|
||
"keywords": ["北京旅游", "故宫攻略", "长城一日游"],
|
||
"cookies": "a1=your_cookie_value; web_session=your_session_value",
|
||
"sort_type": 2,
|
||
"note_type": 2,
|
||
"note_time": 0,
|
||
"note_range": 0,
|
||
"pos_distance": 0,
|
||
"query_num": 10
|
||
}
|
||
}
|
||
|
||
|
||
class DocumentInfo(BaseModel):
|
||
"""文档信息模型"""
|
||
file_path: str = Field(..., description="文件路径")
|
||
file_type: str = Field(..., description="文件类型")
|
||
content_length: int = Field(..., description="内容长度")
|
||
|
||
|
||
class XHSInfo(BaseModel):
|
||
"""小红书信息模型"""
|
||
total_notes: int = Field(..., description="笔记总数")
|
||
authors: List[str] = Field(..., description="作者列表")
|
||
total_interactions: int = Field(..., description="总互动数")
|
||
|
||
|
||
class SearchConfig(BaseModel):
|
||
"""搜索配置模型"""
|
||
sort_type: int = Field(..., description="排序方式")
|
||
note_type: int = Field(..., description="笔记类型")
|
||
note_time: int = Field(..., description="笔记时间")
|
||
note_range: int = Field(..., description="笔记范围")
|
||
pos_distance: int = Field(..., description="位置距离")
|
||
query_num: int = Field(..., description="每个关键词搜索的笔记数量")
|
||
|
||
|
||
class InputSummary(BaseModel):
|
||
"""输入摘要模型"""
|
||
document_count: int = Field(..., description="文档数量")
|
||
xhs_notes_count: int = Field(..., description="小红书笔记数量")
|
||
keywords: List[str] = Field(..., description="关键词列表")
|
||
|
||
|
||
class DocumentInfoDetail(BaseModel):
|
||
"""详细文档信息模型"""
|
||
documents: List[DocumentInfo] = Field(..., description="文档列表")
|
||
integrated_text_length: int = Field(..., description="整合文本长度")
|
||
|
||
|
||
class ContentIntegrationResponse(BaseModel):
|
||
"""内容整合响应模型"""
|
||
success: bool = Field(..., description="是否成功")
|
||
timestamp: str = Field(..., description="时间戳")
|
||
processing_time: str = Field(..., description="处理时间")
|
||
|
||
# 成功时的字段
|
||
input_summary: Optional[InputSummary] = Field(None, description="输入摘要")
|
||
document_info: Optional[DocumentInfoDetail] = Field(None, description="文档信息")
|
||
xhs_info: Optional[XHSInfo] = Field(None, description="小红书信息")
|
||
integrated_content: Optional[str] = Field(None, description="整合后的内容")
|
||
search_config: Optional[SearchConfig] = Field(None, description="搜索配置")
|
||
|
||
# 失败时的字段
|
||
error_message: Optional[str] = Field(None, description="错误信息")
|
||
|
||
class Config:
|
||
schema_extra = {
|
||
"example": {
|
||
"success": True,
|
||
"timestamp": "20250715_143022",
|
||
"processing_time": "45.32秒",
|
||
"input_summary": {
|
||
"document_count": 2,
|
||
"xhs_notes_count": 25,
|
||
"keywords": ["北京旅游", "故宫攻略"]
|
||
},
|
||
"document_info": {
|
||
"documents": [
|
||
{
|
||
"file_path": "uploads/travel_guide.pdf",
|
||
"file_type": "pdf",
|
||
"content_length": 5420
|
||
}
|
||
],
|
||
"integrated_text_length": 8650
|
||
},
|
||
"xhs_info": {
|
||
"total_notes": 25,
|
||
"authors": ["旅游达人小王", "北京导游张三"],
|
||
"total_interactions": 15420
|
||
},
|
||
"integrated_content": "# 北京旅游全攻略...",
|
||
"search_config": {
|
||
"sort_type": 2,
|
||
"note_type": 2,
|
||
"note_time": 0,
|
||
"note_range": 0,
|
||
"pos_distance": 0,
|
||
"query_num": 10
|
||
}
|
||
}
|
||
} |