孔夫子旧书网 API 实战：古籍与二手书数据获取及接口调用方案

孔夫子旧书网作为国内知名的古籍、二手书交易平台，其商品数据对于图书收藏、学术研究及二手书电商系统具有重要价值。本文将详细介绍孔夫子平台接口的调用方法，涵盖认证机制、搜索参数配置、数据解析及反爬策略，并提供可直接使用的 Python 代码实现，帮助开发者合规获取古籍和二手书数据。

一、孔夫子平台接口基础信息

孔夫子旧书网提供的开放接口主要包括图书搜索、商品详情、店铺信息等功能，其中/api/v1/books/search是获取图书列表的核心接口，特别适用于古籍、珍本、二手书的检索。

接口特点：

采用 API Key 认证机制，部分接口需要商业合作授权
支持按书名、作者、出版社、年代、品相等级等多维度筛选
包含古籍特有的版本信息、刻印年代、装帧形式等字段
提供卖家信誉、交易记录等二手书交易关键数据

接口端点：https://api.kongfz.com/api/v1/books/search

二、认证机制与核心参数

1. 认证方式

孔夫子接口采用简单直接的 API Key 认证：

在孔夫子开发者平台注册并申请应用，获取 API Key
在所有请求的 Header 中携带X-API-Key参数
商业用户可申请更高权限的 Secret Key 进行签名认证

2. 核心搜索参数

keyword：搜索关键字（书名、作者、ISBN 等，必填）
category：图书分类（古籍 / 二手书 / 期刊等，可选）
year_min/year_max：出版年代范围（可选）
condition：品相等级（1-10 级，10 为全新，可选）
price_min/price_max：价格区间（可选）
publisher：出版社（可选）
sort：排序方式（price_asc/price_desc/time_desc/credit_desc）
page：页码（默认 1）
limit：每页条数（1-20，默认 10）
rare：是否仅显示珍本（true/false，可选）

3. 响应数据结构

total：总结果数
page/limit：分页信息
books：图书列表数组
filters：可用筛选条件

三、完整代码实现

以下是 Python 实现的孔夫子旧书网图书搜索功能，包含 API 调用、数据解析和反爬策略：

import requests
import time
import random
from typing import Dict, List, Optional, Any
from user_agent import generate_user_agent
import logging# 配置日志
logging.basicConfig(level=logging.INFO,format='%(asctime)s - %(levelname)s - %(message)s'
)
logger = logging.getLogger('kongfz_api')class KongfzBookAPI:def __init__(self, api_key: str, use_proxy: bool = False, proxy_pool: List[str] = None):"""初始化孔夫子旧书网API客户端:param api_key: 平台申请的API Key:param use_proxy: 是否使用代理:param proxy_pool: 代理IP池列表"""self.api_key = api_keyself.base_url = "https://api.kongfz.com"self.search_endpoint = "/api/v1/books/search"self.detail_endpoint = "/api/v1/books/detail"self.max_limit = 20  # 最大每页条数self.use_proxy = use_proxyself.proxy_pool = proxy_pool or []self.session = self._init_session()def _init_session(self) -> requests.Session:"""初始化请求会话，配置持久连接"""session = requests.Session()session.headers.update({"Accept": "application/json","Content-Type": "application/json","X-API-Key": self.api_key,"Connection": "keep-alive"})return sessiondef _get_random_headers(self) -> Dict[str, str]:"""生成随机请求头，降低反爬风险"""return {"User-Agent": generate_user_agent(),"Accept-Language": random.choice(["zh-CN,zh;q=0.9", "zh-TW,zh;q=0.9,en;q=0.8"]),"Referer": "https://www.kongfz.com/"}def _get_proxy(self) -> Optional[Dict[str, str]]:"""从代理池获取随机代理"""if self.use_proxy and self.proxy_pool:proxy = random.choice(self.proxy_pool)return {"http": proxy, "https": proxy}return Nonedef search_books(self,keyword: str,category: Optional[str] = None,year_min: Optional[int] = None,year_max: Optional[int] = None,condition: Optional[int] = None,price_min: Optional[float] = None,price_max: Optional[float] = None,publisher: Optional[str] = None,sort: str = "time_desc",page: int = 1,limit: int = 10) -> Dict[str, Any]:"""搜索孔夫子旧书网图书:param keyword: 搜索关键字:param category: 图书分类:param year_min: 最小出版年份:param year_max: 最大出版年份:param condition: 品相等级(1-10):param price_min: 最低价格:param price_max: 最高价格:param publisher: 出版社:param sort: 排序方式:param page: 页码:param limit: 每页条数:return: 搜索结果"""# 限制每页最大条数limit = min(limit, self.max_limit)# 构建查询参数params: Dict[str, Any] = {"keyword": keyword,"sort": sort,"page": page,"limit": limit}# 添加可选参数if category:params["category"] = categoryif year_min is not None:params["year_min"] = year_minif year_max is not None:params["year_max"] = year_maxif condition is not None:params["condition"] = conditionif price_min is not None:params["price_min"] = price_minif price_max is not None:params["price_max"] = price_maxif publisher:params["publisher"] = publisher# 准备请求配置headers = self._get_random_headers()proxy = self._get_proxy()try:# 随机延迟，模拟人类行为time.sleep(random.uniform(0.8, 1.5))# 发送请求response = self.session.get(f"{self.base_url}{self.search_endpoint}",params=params,headers=headers,proxies=proxy,timeout=15)response.raise_for_status()# 解析响应result = response.json()# 处理API错误if result.get("code") != 0:logger.error(f"API错误: {result.get('msg')}")return {"success": False,"error_code": result.get("code"),"error_msg": result.get("msg")}# 解析搜索结果return self._parse_search_result(result.get("data", {}))except requests.exceptions.RequestException as e:logger.error(f"请求异常: {str(e)}")return {"success": False,"error_msg": f"请求异常: {str(e)}"}except Exception as e:logger.error(f"处理响应失败: {str(e)}")return {"success": False,"error_msg": f"处理响应失败: {str(e)}"}def _parse_search_result(self, raw_data: Dict[str, Any]) -> Dict[str, Any]:"""解析搜索结果为结构化数据"""# 分页信息pagination = {"total": raw_data.get("total", 0),"page": raw_data.get("page", 1),"limit": raw_data.get("limit", 10),"pages": (raw_data.get("total", 0) + raw_data.get("limit", 10) - 1) // raw_data.get("limit", 10)}# 解析图书列表books = []for item in raw_data.get("books", []):# 处理古籍特有的版本信息ancient_info = Noneif item.get("is_ancient"):ancient_info = {"edition": item.get("ancient_edition"),  # 版本"engraving_year": item.get("engraving_year"),  # 刻印年代"binding": item.get("binding"),  # 装帧"seal_info": item.get("seal_info")  # 钤印信息}books.append({"book_id": item.get("id"),"title": item.get("title"),"author": item.get("author"),"publisher": item.get("publisher"),"publish_year": item.get("publish_year"),"category": item.get("category"),"is_ancient": item.get("is_ancient", False),  # 是否古籍"ancient_info": ancient_info,"condition": {"level": item.get("condition_level"),  # 品相等级"description": item.get("condition_desc")  # 品相描述},"price": {"current": item.get("price"),"original": item.get("original_price"),"currency": "CNY"},"seller": {"id": item.get("seller_id"),"name": item.get("seller_name"),"credit": item.get("seller_credit"),  # 信誉等级"score": item.get("seller_score")  # 好评率},"images": {"main": item.get("main_image"),"thumbnail": item.get("thumbnail")},"url": item.get("url"),"tags": item.get("tags", [])})# 解析可用筛选条件filters = self._parse_filters(raw_data.get("filters", {}))return {"success": True,"pagination": pagination,"books": books,"filters": filters}def _parse_filters(self, raw_filters: Dict[str, Any]) -> Dict[str, Any]:"""解析筛选条件"""filters = {}# 分类筛选if "categories" in raw_filters:filters["categories"] = [{"id": item.get("id"), "name": item.get("name"), "count": item.get("count")}for item in raw_filters["categories"]]# 品相筛选if "conditions" in raw_filters:filters["conditions"] = [{"level": item.get("level"), "name": item.get("name"), "count": item.get("count")}for item in raw_filters["conditions"]]# 年代筛选if "years" in raw_filters:filters["years"] = raw_filters["years"]return filtersdef batch_search(self,keyword: str,max_pages: int = 3,**kwargs) -> Dict[str, Any]:"""批量获取多页搜索结果:param keyword: 搜索关键字:param max_pages: 最大获取页数:param**kwargs: 其他搜索参数:return: 合并的搜索结果"""all_books = []current_page = 1total_pages = 1while current_page <= max_pages and current_page <= total_pages:logger.info(f"搜索第 {current_page} 页，关键字: {keyword}")# 搜索当前页result = self.search_books(keyword=keyword,page=current_page,**kwargs)if not result.get("success"):return result# 收集图书数据all_books.extend(result.get("books", []))# 更新分页信息pagination = result.get("pagination", {})total_pages = pagination.get("pages", 1)# 准备下一页current_page += 1# 增加页数间隔，降低反爬风险if current_page <= max_pages:time.sleep(random.uniform(1.5, 2.5))return {"success": True,"total_books": len(all_books),"books": all_books,"summary": {"total_available": pagination.get("total", 0),"fetched_pages": current_page - 1}}# 使用示例
if __name__ == "__main__":# 替换为你的API KeyAPI_KEY = "your_api_key"# 代理配置（可选）PROXY_POOL = [# "http://ip1:port",# "http://ip2:port"]# 初始化API客户端kongfz_api = KongfzBookAPI(api_key=API_KEY,use_proxy=False,  # 根据需要开启proxy_pool=PROXY_POOL)# 示例1：搜索古籍ancient_result = kongfz_api.search_books(keyword="论语",category="ancient",  # 古籍分类year_min=1949,year_max=2023,condition=8,  # 8级及以上品相sort="price_asc",page=1,limit=10)if ancient_result["success"]:print(f"古籍搜索: 找到 {ancient_result['pagination']['total']} 本相关图书")if ancient_result["books"]:book = ancient_result["books"][0]print(f"书名: {book['title']}")print(f"作者: {book['author']}")print(f"价格: {book['price']['current']}元")print(f"品相: {book['condition']['level']}级 - {book['condition']['description']}")if book["is_ancient"]:print(f"版本: {book['ancient_info']['edition']}")# 示例2：批量搜索二手书# batch_result = kongfz_api.batch_search(#     keyword="鲁迅全集",#     category="secondhand",  # 二手书分类#     price_min=50,#     price_max=500,#     max_pages=2# )# # if batch_result["success"]:#     print(f"\n批量搜索: 共获取 {batch_result['total_books']} 本图书")