唯品会（品牌折扣折扣电商平台）的商品搜索功能（item_search接口，非官方命名）是获取折扣商品列表的核心入口，数据包含品牌折扣价、促销活动、销量热度等关键信息，对价格监控、竞品分析、促销选品等场景具有重要价值。由于平台无公开官方 API，开发者需通过页面解析或逆向工程实现搜索对接。本文系统讲解接口逻辑、参数解析、技术实现及促销场景适配策略，助你构建稳定的唯品会商品搜索系统。
一、接口基础认知（核心功能与场景）
二、对接前置准备（参数与 URL 结构）
三、接口调用流程（基于页面解析与动态接口）
四、代码实现示例（Python）
import requests
import time
import random
import re
import urllib.parse
from bs4 import BeautifulSoup
from fake_useragent import UserAgent
from typing import List, Dict
class VipSearchApi:
def __init__(self, proxy_pool: List[str] = None, cookie: str = ""):
self.base_url = "https://category.vip.com/suggest.php"
self.ua = UserAgent()
self.proxy_pool = proxy_pool # 代理池列表，如["http://ip:port", ...]
self.cookie = cookie # 登录态Cookie（用于完整价格和促销信息）
# 分类ID映射（简化版）
self.category_map = {
"男装-卫衣": "1005159_1234",
"女装-连衣裙": "1005160_5678",
"运动-运动鞋": "1005212_9012"
}
# 品牌ID映射（简化版）
self.brand_map = {
"Adidas": "1234",
"Nike": "5678",
"优衣库": "9012"
}
def _get_headers(self) -> Dict[str, str]:
"""生成随机请求头"""
headers = {
"User-Agent": self.ua.random,
"Referer": "https://www.vip.com/",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8"
}
if self.cookie:
headers["Cookie"] = self.cookie
return headers
def _get_proxy(self) -> Dict[str, str]:
"""随机获取代理"""
if self.proxy_pool and len(self.proxy_pool) > 0:
proxy = random.choice(self.proxy_pool)
return {"http": proxy, "https": proxy}
return None
def _clean_price(self, price_str: str) -> float:
"""清洗价格（去除¥、逗号等）"""
if not price_str:
return 0.0
price_str = re.sub(r"[^\d.]", "", price_str)
return float(price_str) if price_str else 0.0
def _clean_discount(self, discount_str: str) -> float:
"""清洗折扣力度（提取数字，如“2.5折”→2.5）"""
if not discount_str:
return 0.0
discount_num = re.search(r"\d+\.?\d*", discount_str)
return float(discount_num.group()) if discount_num else 0.0
def _clean_sales(self, sales_str: str) -> int:
"""清洗30天销量（提取数字，如“5000+”→5000）"""
if not sales_str:
return 0
sales_num = re.search(r"\d+", sales_str)
return int(sales_num.group()) if sales_num else 0
def _parse_item(self, item_soup) -> Dict[str, str]:
"""解析单条商品数据"""
# 提取商品ID
link = item_soup.select_one("a.goods-link")["href"] if item_soup.select_one("a.goods-link") else ""
product_id = re.search(r"/detail-(\d+)\.html", link).group(1) if link else ""
# 提取活动标签（多个标签用逗号拼接）
activity_tags = [tag.text.strip() for tag in item_soup.select(".activity-tag")]
return {
"product_id": product_id,
"title": item_soup.select_one(".goods-title")?.text.strip() or "",
"main_image": item_soup.select_one(".goods-img img")?.get("src") or "",
"url": f"https://detail.vip.com{link}" if link.startswith("/") else link,
"price": {
"discount": self._clean_price(item_soup.select_one(".discount-price")?.text or ""),
"original": self._clean_price(item_soup.select_one(".original-price")?.text or ""),
"discount_str": item_soup.select_one(".discount-price")?.text.strip() or "",
"original_str": item_soup.select_one(".original-price")?.text.strip() or "",
"discount_rate": self._clean_discount(item_soup.select_one(".discount-tag")?.text or ""),
"discount_rate_str": item_soup.select_one(".discount-tag")?.text.strip() or ""
},
"sales": {
"sales_count": self._clean_sales(item_soup.select_one(".sales-count")?.text or ""),
"sales_str": item_soup.select_one(".sales-count")?.text.strip() or "",
"good_rate": item_soup.select_one(".good-rate")?.text.strip() or ""
},
"brand": {
"name": item_soup.select_one(".brand-name")?.text.strip() or ""
},
"promotion": {
"tags": activity_tags,
"stock_status": item_soup.select_one(".stock-tag")?.text.strip() or ""
}
}
def _parse_page(self, html: str) -> List[Dict]:
"""解析页面的商品列表"""
soup = BeautifulSoup(html, "lxml")
# 商品列表容器（需根据实际页面结构调整）
item_list = soup.select("div.goods-item")
return [self._parse_item(item) for item in item_list if item]
def _get_total_pages(self, html: str) -> int:
"""获取总页数"""
soup = BeautifulSoup(html, "lxml")
page_box = soup.select_one(".pagination")
if not page_box:
return 1
# 提取最后一页页码
last_page = page_box.select("a")[-1].text.strip()
return int(last_page) if last_page.isdigit() else 1
def item_search(self,
keyword: str = "",
category: str = "",
price_min: float = None,
price_max: float = None,
discount: float = None,
brand: str = "",
activity: int = 0,
sort: str = "",
page_limit: int = 5) -> Dict:
"""
搜索唯品会商品列表
:param keyword: 搜索关键词
:param category: 分类名称（如“男装-卫衣”）或分类ID
:param price_min: 最低折扣价（元）
:param price_max: 最高折扣价（元）
:param discount: 最高折扣（如3表示≤3折）
:param brand: 品牌名称（如“Adidas”）或品牌ID
:param activity: 活动类型（1=限时秒杀，2=满减，0=全部）
:param sort: 排序方式（sales/discount_asc等）
:param page_limit: 最大页数（默认5）
:return: 标准化搜索结果
"""
try:
# 1. 参数预处理
if not keyword and not category:
return {"success": False, "error_msg": "关键词（keyword）和分类（category）至少需提供一个"}
# 转换分类名称为ID
if category in self.category_map:
cat_id = self.category_map[category]
else:
cat_id = category if category else ""
# 转换品牌名称为ID
brand_id = self.brand_map.get(brand, "") if brand else ""
# 编码关键词
encoded_keyword = urllib.parse.quote(keyword, encoding="utf-8") if keyword else ""
all_items = []
current_page = 1
while current_page <= page_limit:
# 构建参数
params = {
"page": current_page
}
if encoded_keyword:
params["keyword"] = encoded_keyword
if cat_id:
params["cat_id"] = cat_id
if price_min is not None:
params["price_min"] = price_min
if price_max is not None:
params["price_max"] = price_max
if discount is not None:
params["discount"] = discount
if brand_id:
params["brand_id"] = brand_id
if activity in (0, 1, 2, 3):
params["activity"] = activity
if sort:
params["sort"] = sort
# 发送请求（带随机延迟）
time.sleep(random.uniform(3, 5)) # 唯品会反爬严格，延迟需更高
headers = self._get_headers()
proxy = self._get_proxy()
response = requests.get(
url=self.base_url,
params=params,
headers=headers,
proxies=proxy,
timeout=10
)
response.raise_for_status()
html = response.text
# 解析当前页商品
items = self._parse_page(html)
if not items:
break # 无数据，终止分页
all_items.extend(items)
# 获取总页数（仅第一页需要）
if current_page == 1:
total_pages = self._get_total_pages(html)
# 修正最大页数（不超过page_limit和50）
total_pages = min(total_pages, page_limit, 50)
if total_pages < current_page:
break
# 若当前页是最后一页，终止
if current_page >= total_pages:
break
current_page += 1
# 去重（基于product_id）
seen_ids = set()
unique_items = []
for item in all_items:
if item["product_id"] not in seen_ids:
seen_ids.add(item["product_id"])
unique_items.append(item)
return {
"success": True,
"total": len(unique_items),
"page_processed": current_page,
"items": unique_items
}
except requests.exceptions.HTTPError as e:
if "403" in str(e):
return {"success": False, "error_msg": "触发反爬，建议更换代理或Cookie", "code": 403}
if "401" in str(e):
return {"success": False, "error_msg": "需要登录，请提供有效Cookie", "code": 401}
return {"success": False, "error_msg": f"HTTP错误: {str(e)}", "code": response.status_code}
except Exception as e:
return {"success": False, "error_msg": f"搜索失败: {str(e)}", "code": -1}
# 使用示例
if __name__ == "__main__":
# 代理池（替换为有效代理）
PROXIES = [
"http://123.45.67.89:8888",
"http://98.76.54.32:8080"
]
# 登录态Cookie（从浏览器获取，用于完整价格）
COOKIE = "vip_access_token=xxx; userid=xxx; vip_guid=xxx"
# 初始化API客户端
search_api = VipSearchApi(proxy_pool=PROXIES, cookie=COOKIE)
# 搜索“Adidas卫衣”，分类“男装-卫衣”，价格100-200元，折扣≤3折，限时秒杀，销量降序，最多3页
result = search_api.item_search(
keyword="Adidas卫衣",
category="男装-卫衣",
price_min=100,
price_max=200,
discount=3,
brand="Adidas",
activity=1,
sort="sales",
page_limit=3
)
if result["success"]:
print(f"搜索成功：共找到 {result['total']} 件商品，处理 {result['page_processed']} 页")
for i, item in enumerate(result["items"][:5]): # 打印前5条
print(f"\n商品 {i+1}:")
print(f"标题：{item['title'][:50]}...") # 截断长标题
print(f"价格：{item['price']['discount_str']}（原价{item['price']['original_str']}） | {item['price']['discount_rate_str']}")
print(f"销量：30天已售{item['sales']['sales_count']}件 | 好评率{item['sales']['good_rate']}")
print(f"促销：{', '.join(item['promotion']['tags'])} | 库存：{item['promotion']['stock_status']}")
print(f"品牌：{item['brand']['name']}")
print(f"详情页：{item['url']}")
else:
print(f"搜索失败：{result['error_msg']}（错误码：{result.get('code')}）")