洋码头作为国内头部跨境电商平台，以 “海外直购” 为核心卖点，商品覆盖美妆、奢侈品、母婴、保健品等品类，其搜索功能（item_search接口，非官方命名）是获取跨境商品列表的核心入口。数据包含采购地、关税政策、物流时效等跨境特有字段，对跨境比价、消费趋势分析、选品决策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、技术实现及反爬策略，助你构建稳定的跨境商品列表获取系统。
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）
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 YangmatouSearchApi:
def __init__(self, proxy_pool: List[str] = None, cookie: str = ""):
self.base_url = "https://www.yangmatou.com/search/{keyword}"
self.api_url = "https://api.yangmatou.com/search" # 动态筛选接口
self.ua = UserAgent()
self.proxy_pool = proxy_pool # 代理池列表，如["http://ip:port", ...]
self.cookie = cookie # 登录态Cookie
self.secret_key = "xxx" # 从JS逆向获取的签名密钥（需实际破解）
# 分类ID映射（简化版）
self.category_map = {
"美妆护肤": "101",
"母婴用品": "203",
"奢侈品": "302",
"保健品": "401"
}
# 采购地编码映射（简化版）
self.area_map = {
"美国": "us",
"日本": "jp",
"法国": "fr",
"韩国": "kr"
}
def _get_headers(self) -> Dict[str, str]:
"""生成随机请求头"""
headers = {
"User-Agent": self.ua.random,
"Referer": "https://www.yangmatou.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 _generate_sign(self, params: Dict[str, str]) -> str:
"""生成动态接口签名（需根据实际JS逆向逻辑实现）"""
# 示例：按key排序后拼接+密钥，MD5加密
sorted_params = sorted(params.items(), key=lambda x: x[0])
sign_str = "&".join([f"{k}={v}" for k, v in sorted_params]) + self.secret_key
return hashlib.md5(sign_str.encode()).hexdigest()
def _clean_price(self, price_str: str) -> float:
"""清洗价格字符串"""
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_sales(self, sales_str: str) -> int:
"""清洗销量字符串（提取数字）"""
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.product-title")["href"]
item_id = re.search(r"/goods/(\d+)", link).group(1) if link else ""
# 提取版本信息（跨境核心字段）
title = item_soup.select_one(".product-title")?.text.strip() or ""
version = re.search(r"[美日法韩中]版", title).group() if re.search(r"[美日法韩中]版", title) else ""
return {
"item_id": item_id,
"title": title,
"main_image": item_soup.select_one(".product-img img")?.get("src") or "",
"url": f"https://www.yangmatou.com{link}" if link.startswith("/") else link,
"price": {
"current": self._clean_price(item_soup.select_one(".price-current")?.text.strip() or ""),
"original": self._clean_price(item_soup.select_one(".price-original")?.text.strip() or ""),
"tax_included": "含税" in (item_soup.select_one(".price-tag")?.text or "")
},
"cross_border": {
"purchase_area": item_soup.select_one(".purchase-area")?.text.strip() or "",
"logistics": item_soup.select_one(".logistics-tag")?.text.strip() or "",
"delivery_time": item_soup.select_one(".delivery-time")?.text.strip() or ""
},
"sales": {
"monthly": self._clean_sales(item_soup.select_one(".sales-count")?.text.strip() or ""),
"comment_count": self._clean_sales(item_soup.select_one(".comment-count")?.text.strip() or "")
},
"seller": {
"name": item_soup.select_one(".seller-name")?.text.strip() or "",
"level": item_soup.select_one(".seller-level")?.text.strip() or ""
},
"version": version # 版本信息（如“法版”）
}
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.product-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,
purchase_area: str = "",
logistics: str = "",
sort: str = "",
page_limit: int = 5) -> Dict:
"""
搜索洋码头商品列表
:param keyword: 搜索关键词
:param category: 分类名称（如“美妆护肤”）或分类ID
:param price_min: 最低价格（元）
:param price_max: 最高价格（元）
:param purchase_area: 采购地名称（如“法国”）或编码（如“fr”）
:param logistics: 物流类型（direct/bonded）
:param sort: 排序方式（sales/price_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:
cid = self.category_map[category]
else:
cid = category if category else ""
# 转换采购地名称为编码
if purchase_area in self.area_map:
area_code = self.area_map[purchase_area]
else:
area_code = purchase_area if purchase_area 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 cid:
params["categoryId"] = cid
if price_min is not None:
params["priceMin"] = price_min
if price_max is not None:
params["priceMax"] = price_max
if area_code:
params["purchaseArea"] = area_code
if logistics:
params["logistics"] = logistics
if sort:
params["sort"] = sort
# 构建URL（简单筛选用页面URL，复杂筛选用API）
if encoded_keyword:
url = self.base_url.format(keyword=encoded_keyword)
else:
url = f"https://www.yangmatou.com/category/{cid}" # 无关键词时用分类页
# 发送请求（带随机延迟）
time.sleep(random.uniform(3, 5)) # 跨境平台延迟需更高
headers = self._get_headers()
proxy = self._get_proxy()
response = requests.get(
url=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item_id）
seen_ids = set()
unique_items = []
for item in all_items:
if item["item_id"] not in seen_ids:
seen_ids.add(item["item_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}
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）
COOKIE = "user_id=xxx; token=xxx; session_id=xxx"
# 初始化API客户端（需补充secret_key，通过JS逆向获取）
search_api = YangmatouSearchApi(proxy_pool=PROXIES, cookie=COOKIE)
# 搜索“兰蔻小黑瓶”，分类“美妆护肤”，价格500-1000元，采购地法国，直邮，按销量降序，最多3页
result = search_api.item_search(
keyword="兰蔻小黑瓶",
category="美妆护肤",
price_min=500,
price_max=1000,
purchase_area="法国",
logistics="direct",
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']['current']}（{'含税' if item['price']['tax_included'] else '不含税'}） | 原价：￥{item['price']['original']}")
print(f"跨境信息：{item['cross_border']['logistics']} | 采购地：{item['cross_border']['purchase_area']} | 时效：{item['cross_border']['delivery_time']}")
print(f"版本：{item['version']} | 月销：{item['sales']['monthly']}件 | 评价：{item['sales']['comment_count']}条")
print(f"卖家：{item['seller']['name']}（等级：{item['seller']['level']}）")
print(f"详情页：{item['url']}")
else:
print(f"搜索失败：{result['error_msg']}（错误码：{result.get('code')}）")