This commit is contained in:
Ubuntu
2026-07-03 16:58:28 +08:00
commit 32b43f85bd
6240 changed files with 1987678 additions and 0 deletions
+493
View File
@@ -0,0 +1,493 @@
#!/usr/bin/env python3
"""
Fumamx API Client - 基于抓取的实际 API 生成
支持自动登录刷新 Token
"""
import json
import requests
import time
from pathlib import Path
from typing import Dict, Optional, List, Any
from urllib.parse import urljoin
from . import config
from .auth import refresh_auth, load_tokens, AuthError
class FumamxClient:
"""孚盟MX API 客户端 - 贸易数据模块
认证优先级:
1. 使用传入的 cookie_file 中的 cookies
2. 使用缓存的 tokens (通过 Playwright 登录获得)
3. 自动触发 Playwright 登录获取新 tokens
"""
BASE_URL = "https://www.fumamx.com"
def __init__(self, cookie_file: str = "/home/ubuntu/fumamx_cookies.txt", auto_login: bool = True):
self.cookie_file = cookie_file
self.session = requests.Session()
self.cookies = {}
self.common_params = {}
self.auto_login = auto_login
self._auth_refreshed = False
# 尝试加载认证信息
if not self._load_cookies() and auto_login:
# Cookie 加载失败,尝试使用缓存的 token
if not self._load_cached_tokens():
# 缓存也没有,触发自动登录
self._do_auto_login()
self._init_common_params()
def _load_cookies(self) -> bool:
"""从 JSON 文件加载 cookies
Returns:
bool: 是否成功加载
"""
try:
if not Path(self.cookie_file).exists():
return False
with open(self.cookie_file, 'r') as f:
cookie_list = json.load(f)
for cookie in cookie_list:
name = cookie.get('name')
value = cookie.get('value')
if name and value:
self.cookies[name] = value
self.session.cookies.set(name, value)
print(f"✓ 已加载 {len(self.cookies)} 个 cookies")
return True
except Exception as e:
print(f"⚠ 加载 cookies 失败: {e}")
return False
def _load_cached_tokens(self) -> bool:
"""从缓存加载 tokens 和 cookies
Returns:
bool: 是否成功加载
"""
tokens = load_tokens()
if not tokens:
return False
has_tokens = tokens.get('accessToken') and tokens.get('individualAccessToken')
if has_tokens:
print("✓ 使用缓存的 tokens")
# 同时加载缓存的 cookies (如 _t)
cached_cookies = tokens.get('cookies', {})
for name, value in cached_cookies.items():
self.cookies[name] = value
self.session.cookies.set(name, value)
if cached_cookies:
print(f"✓ 已加载 {len(cached_cookies)} 个缓存 cookies")
return has_tokens
def _do_auto_login(self) -> bool:
"""触发自动登录获取新 tokens 和 cookies
Returns:
bool: 是否登录成功
"""
if self._auth_refreshed:
return False # 避免循环刷新
try:
print("⚠ Cookie/Token 无效,正在自动登录...")
result = refresh_auth()
if result['success']:
self._auth_refreshed = True
# 加载登录获得的 cookies 到 session
login_cookies = result.get('cookies', {})
for name, value in login_cookies.items():
self.cookies[name] = value
self.session.cookies.set(name, value)
if login_cookies:
print(f"✓ 已加载 {len(login_cookies)} 个登录 cookies")
# 重新加载 tokens
self._load_cached_tokens()
return True
else:
print(f"✗ 自动登录失败: {result.get('error')}")
return False
except AuthError as e:
print(f"✗ 自动登录需要 Playwright: {e}")
print(" 请运行: pip install playwright && playwright install chromium")
return False
except Exception as e:
print(f"✗ 自动登录出错: {e}")
return False
def _init_common_params(self):
"""初始化公共参数(优先使用缓存/自动登录获取的 token)"""
# 优先使用缓存的 tokens
tokens = load_tokens()
access_token = tokens.get('accessToken') if tokens else None
individual_token = tokens.get('individualAccessToken') if tokens else None
# 如果没有缓存的,使用配置文件中的
if not access_token:
access_token = config.ACCESS_TOKEN
if not individual_token:
individual_token = config.INDIVIDUAL_ACCESS_TOKEN
self.common_params = {
'accessToken': access_token,
'individualAccessToken': individual_token,
'_filterCompanyId': config.COMPANY_ID,
'isV5': 'true',
'isV5AndNewMail': 'true',
'isNewArchCompany': 'true',
'languageForMX5': 'zh-cn',
'operating_terminal': 'pc_网页端',
'event_source': 'MX',
}
def _headers(self) -> Dict[str, str]:
"""构造请求头"""
return {
'Accept': 'application/json, text/plain, */*',
'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
'Content-Type': 'application/json;charset=UTF-8',
'Origin': self.BASE_URL,
'Referer': f"{self.BASE_URL}/",
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36',
'X-Requested-With': 'XMLHttpRequest',
}
def _build_url(self, path: str) -> str:
"""构建完整 URL"""
if path.startswith('http'):
return path
return f"{self.BASE_URL}{path}"
def _merge_params(self, extra_params: Optional[Dict] = None) -> Dict:
"""合并公共参数和额外参数"""
params = self.common_params.copy()
params['_@#time'] = int(time.time() * 1000)
if extra_params:
params.update(extra_params)
# 过滤 None 值
return {k: v for k, v in params.items() if v is not None}
def get(self, path: str, params: Optional[Dict] = None) -> Dict:
"""GET 请求"""
url = self._build_url(path)
merged_params = self._merge_params(params)
response = self.session.get(
url,
headers=self._headers(),
params=merged_params,
timeout=30
)
response.raise_for_status()
return response.json()
def post(self, path: str, data: Optional[Dict] = None) -> Dict:
"""POST 请求"""
url = self._build_url(path)
merged_params = self._merge_params()
response = self.session.post(
url,
headers=self._headers(),
params=merged_params,
json=data,
timeout=30
)
response.raise_for_status()
return response.json()
# ============ 贸易数据 - 公司搜索 ============
def search_company(self, keyword: str, page: int = 1, page_size: int = 10) -> Dict:
"""搜索公司/企业
对应端点: POST /pcapi/findServer/standard/company
"""
data = {
"selectedKey": [],
"searchType": "all",
"activeType": "company",
"inputValue": keyword,
"keyword": [keyword],
"FyStr": keyword,
"productFy": [keyword],
"currentValue": "input",
"language": ["en", "ru", "pt", "spa"],
"selectCountry": [],
"searchMode": 0,
"country": [],
"industry": [],
"employeesLevel": [],
"founded": [],
"priceRange": [],
"filterCust": 0,
"filterView": 0,
"excludeGovernment": False,
"excludeSchool": False,
"excludeForwarder": False,
"excludeBank": False,
"excludeCn": True,
"page": page,
"size": page_size
}
return self.post("/pcapi/findServer/standard/company", data)
# ============ 贸易数据 - 进口企业 ============
def import_enterprise(self, company_name: str, country: str = "") -> Dict:
"""获取进口企业数据
对应端点: POST /pcapi/tradeData/api/V2/TradeCompany/ImpEnterprise
"""
data = {
"companyName": company_name,
"country": country,
"page": 1,
"pageSize": 20
}
return self.post("/pcapi/tradeData/api/V2/TradeCompany/ImpEnterprise", data)
def import_enterprise_stats(self, company_name: str) -> Dict:
"""获取进口企业统计
对应端点: POST /pcapi/tradeData/api/V1/TradeCompany/ImpEnterpriseStatistics
"""
data = {"companyName": company_name}
return self.post("/pcapi/tradeData/api/V1/TradeCompany/ImpEnterpriseStatistics", data)
# ============ 贸易数据 - 出口企业 ============
def export_enterprise(self, company_name: str, country: str = "") -> Dict:
"""获取出口企业数据
对应端点: POST /pcapi/tradeData/api/V2/TradeCompany/ExpEnterprise
"""
data = {
"companyName": company_name,
"country": country,
"page": 1,
"pageSize": 20
}
return self.post("/pcapi/tradeData/api/V2/TradeCompany/ExpEnterprise", data)
def export_enterprise_stats(self, company_name: str) -> Dict:
"""获取出口企业统计
对应端点: POST /pcapi/tradeData/api/V1/TradeCompany/ExpEnterpriseStatistics
"""
data = {"companyName": company_name}
return self.post("/pcapi/tradeData/api/V1/TradeCompany/ExpEnterpriseStatistics", data)
# ============ 贸易数据 - 产品分析 ============
def company_agg_data(self, company_name: str) -> Dict:
"""获取公司聚合数据
对应端点: POST /pcapi/tradeData/api/V2/TradeProduct/getCompanyAggData
"""
data = {"companyName": company_name}
return self.post("/pcapi/tradeData/api/V2/TradeProduct/getCompanyAggData", data)
def hs_code_analysis(self, hs_code: str) -> Dict:
"""HS 编码分析
对应端点: POST /pcapi/tradeData/api/V2/TradeProduct/HsCodeAnalysis
"""
data = {"hsCode": hs_code}
return self.post("/pcapi/tradeData/api/V2/TradeProduct/HsCodeAnalysis", data)
def export_enterprise_analysis(self, company_name: str) -> Dict:
"""出口企业分析
对应端点: POST /pcapi/tradeData/api/V2/TradeProduct/ExpEnterpriseAnalysis
"""
data = {"companyName": company_name}
return self.post("/pcapi/tradeData/api/V2/TradeProduct/ExpEnterpriseAnalysis", data)
def company_analysis_agg(self, company_name: str) -> Dict:
"""公司分析聚合数据
对应端点: POST /pcapi/tradeData/api/V2/TradeProduct/getCompanyAnalysisAggData
"""
data = {"companyName": company_name}
return self.post("/pcapi/tradeData/api/V2/TradeProduct/getCompanyAnalysisAggData", data)
def export_compare_lose_analysis(self, company_name: str, compare_company: str) -> Dict:
"""出口对比流失分析
对应端点: POST /pcapi/tradeData//api/V2/TradeProduct/ExpEnterpriseCompareLoseAnalysis
"""
data = {
"companyName": company_name,
"compareCompany": compare_company
}
return self.post("/pcapi/tradeData//api/V2/TradeProduct/ExpEnterpriseCompareLoseAnalysis", data)
def export_compare_new_analysis(self, company_name: str, compare_company: str) -> Dict:
"""出口对比新增分析
对应端点: POST /pcapi/tradeData//api/V2/TradeProduct/ExpEnterpriseCompareNewAnalysis
"""
data = {
"companyName": company_name,
"compareCompany": compare_company
}
return self.post("/pcapi/tradeData//api/V2/TradeProduct/ExpEnterpriseCompareNewAnalysis", data)
def export_country_analysis(self, country: str) -> Dict:
"""出口国家分析
对应端点: POST /pcapi/tradeData/api/V2/TradeProduct/ExpCountryAnalysis
"""
data = {"country": country}
return self.post("/pcapi/tradeData/api/V2/TradeProduct/ExpCountryAnalysis", data)
def country_analysis_data(self, country: str) -> Dict:
"""国家分析数据
对应端点: POST /pcapi/tradeData/api/V2/TradeProduct/getCountryAnalysisData
"""
data = {"country": country}
return self.post("/pcapi/tradeData/api/V2/TradeProduct/getCountryAnalysisData", data)
# ============ 贸易详情 ============
def trade_detail_full(self, trade_no: str, source_country: str = "", reg_date: str = "", in_out: str = "") -> Dict:
"""获取完整贸易详情
对应端点: GET /pcapi/tradeData/api/V2/Trade/TradeDetailFull
"""
return self.get("/pcapi/tradeData/api/V2/Trade/TradeDetailFull", {
"tradeNo": trade_no,
"sourceCountry": source_country,
"regDate": reg_date,
"inOut": in_out,
"sourceType": "1"
})
# ============ 用户/账户 ============
def get_trade_source_countries(self) -> Dict:
"""获取贸易来源国家列表
对应端点: GET /pcapi/tradeData/api/V2/Account/GetTradeSourceCountrys
"""
return self.get("/pcapi/tradeData/api/V2/Account/GetTradeSourceCountrys")
# ============ 企业详情 API ============
def get_company_info(self, company_id: str, domain: str) -> Dict:
"""获取公司详细信息
对应端点: GET /pcapi/findServer/find/getMxCompanyInfo
包含: 地址、电话、员工数、行业等信息
"""
params = {
"id": company_id,
"domain": domain,
}
return self.get("/pcapi/findServer/find/getMxCompanyInfo", params)
def get_company_contacts(self, company_id: str, domain: str) -> Dict:
"""获取公司联系人列表
对应端点: GET /pcapi/findServer/find/mxStaffList
包含: 姓名、邮箱、职位、LinkedIn、电话等
"""
params = {
"id": company_id,
"domain": domain,
}
return self.get("/pcapi/findServer/find/mxStaffList", params)
def get_company_phones(self, domain: str) -> Dict:
"""获取公司电话/图片信息
对应端点: GET /pcapi/findServer/find/spiderDomainImage
包含: 电话、图片等爬虫抓取的信息
"""
params = {
"domain": domain,
}
return self.get("/pcapi/findServer/find/spiderDomainImage", params)
# ============ 其他 ============
def wap_label_list(self, wid: str = "330204727296") -> Dict:
"""获取标签列表
对应端点: GET /pcapi/v1/waplabellist
"""
return self.get("/pcapi/v1/waplabellist", {
"wid": wid,
"format": "mx"
})
def check_sse_exist(self) -> Dict:
"""检查 SSE 是否存在
对应端点: GET /v1/isSseExist
"""
return self.get("/v1/isSseExist")
# ============ 通用 API 探测 ============
def probe_api(self, endpoint: str) -> Dict:
"""探测任意 API 端点"""
try:
return self.get(endpoint)
except Exception as e:
return {"error": str(e), "endpoint": endpoint}
def call_api(self, method: str, path: str, data: Optional[Dict] = None, params: Optional[Dict] = None) -> Dict:
"""通用 API 调用"""
if method.upper() == "GET":
return self.get(path, params)
elif method.upper() == "POST":
return self.post(path, data)
else:
raise ValueError(f"不支持的 HTTP 方法: {method}")
def check_auth(self) -> bool:
"""检查当前认证是否有效
Returns:
bool: 认证是否有效
"""
try:
result = self.search_company("test", page=1, page_size=1)
return result.get("code") == "0"
except Exception:
return False
def refresh_if_needed(self) -> bool:
"""如果需要,刷新认证
Returns:
bool: 刷新后认证是否有效
"""
if self.check_auth():
return True
if not self.auto_login:
return False
print("⚠ 认证失效,尝试自动刷新...")
if self._do_auto_login():
self._init_common_params() # 重新初始化参数
return self.check_auth()
return False