Release v1.0.56: Credential & Browser Profile Manager

scripts/util/platforms.py

@@ -1,145 +1,341 @@
-"""平台配置、别名解析、手机号校验。"""
-import re
+# -*- coding: utf-8 -*-
+"""
+Platform definitions and resolution.
 
-# 平台唯一配置表：只改这里即可。键 = 入库的 platform；label = 帮助/提示里的展示名；
-# prefix = 默认账号名「{prefix}{序号}号」，省略时等于 label；
-# aliases = 额外 CLI 称呼（英文键与 label 已自动参与解析，不必重复写）。
-# 登录检测：仅看页面 DOM。匹配 anchor 的标签页上出现「未登录」选择器则未登录；否则视为已登录。
-# - _LOGIN_LOGGED_OUT_DOM_GENERIC_SELECTORS：通用「登录」按钮/链接等（可被 login_skip_generic_logged_out_dom 关闭）。
-# - login_logged_out_selectors：按平台追加；误判时也可用 login_skip_generic_logged_out_dom + 仅平台自选。
-PLATFORMS = {
-    "sohu": {
-        "url": "https://mp.sohu.com",
-        "label": "搜狐号",
-        "prefix": "搜狐",
-        "aliases": ["搜狐"],
+Central authoritative registry for all platforms (logistics, LLM, content, etc.).
+Import and use PLATFORMS dict, resolve_platform_key(), and seed_platforms().
+"""
+import json
+import time
+from typing import Any, Optional
+
+from util.logging_config import get_skill_logger
+
+# ---------------------------------------------------------------------------
+# Platform specification fields:
+#   display_name       – Human-readable name (e.g. "Maersk")
+#   domain             – Business domain: logistics / llm / content / ecommerce / generic
+#   provider_code      – Supplier code (logistics); can be same as key
+#   default_url        – Default entry URL (empty string if none)
+#   aliases            – List of name aliases (Chinese/English, for CLI resolution)
+#   capabilities       – Dict of capability flags:
+#                        {"web": bool, "api_key": bool, "rpa": bool}
+# ---------------------------------------------------------------------------
+
+PLATFORMS: dict[str, dict[str, Any]] = {
+    # =========================================================================
+    # Logistics platforms
+    # =========================================================================
+    "maersk": {
+        "display_name": "Maersk",
+        "domain": "logistics",
+        "provider_code": "maersk",
+        "default_url": "https://www.maersk.com",
+        "aliases": ["马士基", "maersk", "Maersk"],
+        "capabilities": {"web": True, "api_key": False, "rpa": True},
     },
-    "toutiao": {
-        "url": "https://mp.toutiao.com/",
-        "label": "头条号",
-        "prefix": "头条",
-        "aliases": ["头条"],
+    "cosco": {
+        "display_name": "COSCO",
+        "domain": "logistics",
+        "provider_code": "cosco",
+        "default_url": "",
+        "aliases": ["中远海运", "COSCO", "cosco"],
+        "capabilities": {"web": True, "api_key": False, "rpa": True},
     },
-    "zhihu": {
-        "url": "https://www.zhihu.com",
-        "label": "知乎",
-        "aliases": ["知乎号"],
+    "msc": {
+        "display_name": "MSC",
+        "domain": "logistics",
+        "provider_code": "msc",
+        "default_url": "",
+        "aliases": ["MSC", "地中海航运"],
+        "capabilities": {"web": True, "api_key": False, "rpa": True},
     },
-    "wechat": {
-        "url": "https://mp.weixin.qq.com",
-        "label": "微信公众号",
-        "prefix": "微信",
-        "aliases": ["公众号", "微信"],
+    "cma_cgm": {
+        "display_name": "CMA CGM",
+        "domain": "logistics",
+        "provider_code": "cma_cgm",
+        "default_url": "",
+        "aliases": ["达飞", "CMA CGM", "cma cgm"],
+        "capabilities": {"web": True, "api_key": False, "rpa": True},
     },
-    "kimi": {
-        "url": "https://kimi.moonshot.cn",
-        "label": "Kimi",
-        "aliases": ["月之暗面"],
+    "evergreen": {
+        "display_name": "Evergreen",
+        "domain": "logistics",
+        "provider_code": "evergreen",
+        "default_url": "",
+        "aliases": ["长荣", "Evergreen", "evergreen"],
+        "capabilities": {"web": True, "api_key": False, "rpa": True},
     },
+    "cargo_wise": {
+        "display_name": "CargoWise",
+        "domain": "logistics",
+        "provider_code": "cargo_wise",
+        "default_url": "",
+        "aliases": ["CargoWise", "Cargo Wise", "cargo wise"],
+        "capabilities": {"web": True, "api_key": False, "rpa": True},
+    },
+    "freightos": {
+        "display_name": "Freightos",
+        "domain": "logistics",
+        "provider_code": "freightos",
+        "default_url": "",
+        "aliases": ["Freightos", "freightos"],
+        "capabilities": {"web": True, "api_key": True, "rpa": False},
+    },
+    "webcargo": {
+        "display_name": "WebCargo",
+        "domain": "logistics",
+        "provider_code": "webcargo",
+        "default_url": "",
+        "aliases": ["WebCargo", "web cargo"],
+        "capabilities": {"web": True, "api_key": True, "rpa": False},
+    },
+    "sinotrans": {
+        "display_name": "Sinotrans",
+        "domain": "logistics",
+        "provider_code": "sinotrans",
+        "default_url": "",
+        "aliases": ["中外运", "Sinotrans", "sinotrans"],
+        "capabilities": {"web": True, "api_key": False, "rpa": True},
+    },
+    # =========================================================================
+    # LLM / AI platforms
+    # =========================================================================
     "deepseek": {
-        "url": "https://chat.deepseek.com",
-        "label": "DeepSeek",
+        "display_name": "DeepSeek",
+        "domain": "llm",
+        "provider_code": "deepseek",
+        "default_url": "https://chat.deepseek.com",
+        "aliases": ["DeepSeek", "deepseek"],
+        "capabilities": {"web": True, "api_key": True, "rpa": False},
     },
     "doubao": {
-        "url": "https://www.doubao.com",
-        "label": "豆包",
+        "display_name": "Doubao",
+        "domain": "llm",
+        "provider_code": "doubao",
+        "default_url": "https://www.doubao.com",
+        "aliases": ["豆包", "Doubao"],
+        "capabilities": {"web": True, "api_key": True, "rpa": False},
+    },
+    "kimi": {
+        "display_name": "Kimi",
+        "domain": "llm",
+        "provider_code": "kimi",
+        "default_url": "https://kimi.moonshot.cn",
+        "aliases": ["Kimi", "月之暗面"],
+        "capabilities": {"web": True, "api_key": True, "rpa": False},
     },
     "qianwen": {
-        "url": "https://tongyi.aliyun.com",
-        "label": "通义千问",
-        "prefix": "通义",
-        "aliases": ["通义", "千问"],
+        "display_name": "Qianwen",
+        "domain": "llm",
+        "provider_code": "qianwen",
+        "default_url": "https://tongyi.aliyun.com",
+        "aliases": ["通义千问", "通义", "千问", "Qianwen"],
+        "capabilities": {"web": True, "api_key": True, "rpa": False},
     },
     "yiyan": {
-        "url": "https://yiyan.baidu.com",
-        "label": "文心一言",
-        "prefix": "文心",
-        "aliases": ["文心", "一言"],
+        "display_name": "YiYan",
+        "domain": "llm",
+        "provider_code": "yiyan",
+        "default_url": "https://yiyan.baidu.com",
+        "aliases": ["文心一言", "文心", "一言", "YiYan"],
+        "capabilities": {"web": True, "api_key": True, "rpa": False},
     },
     "yuanbao": {
-        "url": "https://yuanbao.tencent.com",
-        "label": "腾讯元宝",
-        "prefix": "元宝",
-        "aliases": ["元宝"],
+        "display_name": "Yuanbao",
+        "domain": "llm",
+        "provider_code": "yuanbao",
+        "default_url": "https://yuanbao.tencent.com",
+        "aliases": ["腾讯元宝", "元宝", "Yuanbao"],
+        "capabilities": {"web": True, "api_key": True, "rpa": False},
     },
     "gemini": {
-        "url": "https://gemini.google.com",
-        "label": "Gemini",
-        "prefix": "Gemini",
-        "aliases": ["谷歌Gemini", "Google Gemini", "google gemini", "Bard"],
+        "display_name": "Gemini",
+        "domain": "llm",
+        "provider_code": "gemini",
+        "default_url": "https://gemini.google.com",
+        "aliases": ["Gemini", "谷歌Gemini", "Google Gemini", "Bard"],
+        "capabilities": {"web": True, "api_key": True, "rpa": False},
+    },
+    "minimax": {
+        "display_name": "MiniMax",
+        "domain": "llm",
+        "provider_code": "minimax",
+        "default_url": "",
+        "aliases": ["MiniMax", "minimax"],
+        "capabilities": {"web": True, "api_key": True, "rpa": False},
+    },
+    # =========================================================================
+    # Content platforms (carried forward from v1)
+    # =========================================================================
+    "sohu": {
+        "display_name": "搜狐号",
+        "domain": "content",
+        "provider_code": "sohu",
+        "default_url": "https://mp.sohu.com",
+        "aliases": ["搜狐", "搜狐号"],
+        "capabilities": {"web": True, "api_key": False, "rpa": False},
+    },
+    "toutiao": {
+        "display_name": "头条号",
+        "domain": "content",
+        "provider_code": "toutiao",
+        "default_url": "https://mp.toutiao.com/",
+        "aliases": ["头条", "头条号"],
+        "capabilities": {"web": True, "api_key": False, "rpa": False},
+    },
+    "zhihu": {
+        "display_name": "知乎",
+        "domain": "content",
+        "provider_code": "zhihu",
+        "default_url": "https://www.zhihu.com",
+        "aliases": ["知乎", "知乎号"],
+        "capabilities": {"web": True, "api_key": False, "rpa": False},
+    },
+    "wechat": {
+        "display_name": "微信公众号",
+        "domain": "content",
+        "provider_code": "wechat",
+        "default_url": "https://mp.weixin.qq.com",
+        "aliases": ["公众号", "微信", "微信公众号"],
+        "capabilities": {"web": True, "api_key": False, "rpa": False},
     },
 }
 
-# 未登录页共性：主行动点含「登录」——submit 按钮、Element 主按钮、Semi 文案、标题、通栏主按钮等，Playwright :has-text 可覆盖多数站点。
-_LOGIN_LOGGED_OUT_DOM_GENERIC_SELECTORS = (
-    'button:has-text("登录")',
-    'role=button[name="登录"]',
-    'a:has-text("登录")',
-    'h4:has-text("登录")',
-    'span.semi-button-content:has-text("登录")',
-)
-
-
-def _build_platform_derived():
-    urls = {}
-    name_prefix = {}
-    primary_cn = {}
-    alias_to_key = {}
-
-    def _register_alias(alias: str, key: str) -> None:
-        if not alias or not str(alias).strip():
-            return
-        a = str(alias).strip()
-        if a not in alias_to_key:
-            alias_to_key[a] = key
-        lo = a.lower()
-        if lo not in alias_to_key:
-            alias_to_key[lo] = key
+# ---------------------------------------------------------------------------
+# Derived alias map
+# ---------------------------------------------------------------------------
 
+def _build_alias_map() -> dict[str, str]:
+    """Build a case-insensitive flat alias -> key map."""
+    m: dict[str, str] = {}
     for key, spec in PLATFORMS.items():
-        urls[key] = spec["url"]
-        primary_cn[key] = spec["label"]
-        name_prefix[key] = (spec.get("prefix") or spec["label"]).strip() or key
-        _register_alias(key, key)
-        _register_alias(spec["label"], key)
-        for a in spec.get("aliases") or []:
-            _register_alias(a, key)
-
-    return urls, name_prefix, primary_cn, alias_to_key
+        # Register the key itself (lowercase)
+        m[key.lower()] = key
+        # Register all aliases (original + lowercase)
+        for alias in [spec["display_name"]] + spec.get("aliases", []):
+            a = str(alias).strip()
+            if a:
+                m[a] = key
+                m[a.lower()] = key
+    return m
 
 
-PLATFORM_URLS, _PLATFORM_NAME_CN, _PLATFORM_PRIMARY_CN, _PLATFORM_ALIAS_TO_KEY = _build_platform_derived()
+_PLATFORM_ALIAS_MAP = _build_alias_map()
 
 
-def resolve_platform_key(name: str):
-    """将用户输入解析为内部 platform 键；无法识别返回 None。"""
-    if name is None:
+def resolve_platform_key(name: str) -> Optional[str]:
+    """
+    Resolve user input to a canonical platform key.
+    Supports: key, display_name, any alias. Case-insensitive.
+    Returns None if unrecognized.
+    """
+    if not name:
         return None
     s = str(name).strip()
     if not s:
         return None
     sl = s.lower()
-    if sl in PLATFORM_URLS:
+    # Direct key match
+    if sl in PLATFORMS:
         return sl
-    return _PLATFORM_ALIAS_TO_KEY.get(s)
+    # Alias map
+    if sl in _PLATFORM_ALIAS_MAP:
+        return _PLATFORM_ALIAS_MAP[sl]
+    if s in _PLATFORM_ALIAS_MAP:
+        return _PLATFORM_ALIAS_MAP[s]
+    return None
 
 
-def _normalize_phone_digits(phone: str) -> str:
-    """从输入中提取数字串，供号段规则校验与入库去重（不对外承诺可随意夹杂符号）。"""
-    d = re.sub(r"\D", "", (phone or "").strip())
-    if d.startswith("86") and len(d) >= 13:
-        d = d[2:]
-    return d
+def get_platform(key: str) -> Optional[dict[str, Any]]:
+    """Return the full platform spec dict for a validated key."""
+    return PLATFORMS.get(key)
 
 
-def _is_valid_cn_mobile11(digits: str) -> bool:
-    """中国大陆 11 位手机号：1 开头，第二位 3–9，共 11 位数字。"""
-    return bool(re.fullmatch(r"1[3-9]\d{9}", digits or ""))
+def list_platforms(domain: Optional[str] = None) -> list[dict[str, Any]]:
+    """List all platforms, optionally filtered by domain.
+    Returns a list of dicts with metadata."""
+    result = []
+    for key, spec in PLATFORMS.items():
+        if domain and spec["domain"] != domain:
+            continue
+        result.append({
+            "platform_key": key,
+            "display_name": spec["display_name"],
+            "domain": spec["domain"],
+            "provider_code": spec.get("provider_code"),
+            "default_url": spec.get("default_url", ""),
+            "aliases": spec.get("aliases", []),
+            "capabilities": spec.get("capabilities", {}),
+            "enabled": True,
+        })
+    return result
+
+
+def seed_platforms(conn) -> None:
+    """
+    Upsert all platform definitions into the 'platforms' table.
+    Must be called after init_db() in the same connection lifecycle.
+    """
+    log = get_skill_logger()
+    log.info("platform_seed_start")
+    cur = conn.cursor()
+    now = int(time.time())
+    upsert_count = 0
+    for key, spec in PLATFORMS.items():
+        aliases_json = json.dumps(spec.get("aliases", []), ensure_ascii=False)
+        capabilities_json = json.dumps(spec.get("capabilities", {}), ensure_ascii=False)
+        cur.execute(
+            """
+            INSERT INTO platforms (platform_key, display_name, domain, provider_code,
+                                   default_url, aliases_json, capabilities_json,
+                                   enabled, created_at, updated_at)
+            VALUES (?, ?, ?, ?, ?, ?, ?, 1, ?, ?)
+            ON CONFLICT(platform_key) DO UPDATE SET
+                display_name   = excluded.display_name,
+                domain         = excluded.domain,
+                provider_code  = excluded.provider_code,
+                default_url    = excluded.default_url,
+                aliases_json   = excluded.aliases_json,
+                capabilities_json = excluded.capabilities_json,
+                enabled        = 1,
+                updated_at     = excluded.updated_at
+            """,
+            (
+                key,
+                spec["display_name"],
+                spec["domain"],
+                spec.get("provider_code"),
+                spec.get("default_url", ""),
+                aliases_json,
+                capabilities_json,
+                now,
+                now,
+            ),
+        )
+        upsert_count += 1
+    conn.commit()
+    log.info("platform_seed_done count=%s", upsert_count)
+
+
+# ---------------------------------------------------------------------------
+# Legacy compatibility helpers (for old account_service v1 code references)
+# ---------------------------------------------------------------------------
+
+# Kept for backward compatibility so old imports don't break immediately.
+# New code should use PLATFORMS dict directly and resolve_platform_key().
+_PLATFORM_PRIMARY_CN: dict[str, str] = {
+    k: spec["display_name"] for k, spec in PLATFORMS.items()
+}
+PLATFORM_URLS: dict[str, str] = {
+    k: (spec.get("default_url") or "") for k, spec in PLATFORMS.items()
+}
 
 
 def _platform_list_cn_for_help() -> str:
-    """帮助文案：一行中文展示名（不重复内部键）。"""
-    parts = []
-    for k in sorted(PLATFORM_URLS.keys()):
-        parts.append(_PLATFORM_PRIMARY_CN.get(k, k))
-    return "、".join(parts)
+    """帮助文案：一行展示名，供 CLI 用法提示。"""
+    return "、".join(
+        spec["display_name"] for _k, spec in sorted(
+            PLATFORMS.items(), key=lambda x: x[1]["display_name"]
+        )
+    )

scripts/util/runtime_paths.py

@@ -1,4 +1,7 @@
-"""数据目录、profile 路径、CLI 路径调试输出。"""
+# -*- coding: utf-8 -*-
+"""
+Data directory, profile path, CLI path debugging output.
+"""
 import os
 import re
 import sys
@@ -6,21 +9,20 @@ from typing import Optional
 
 from jiangchang_skill_core.runtime_env import get_data_root, get_user_id
 from util.constants import SKILL_SLUG
-from util.platforms import _PLATFORM_PRIMARY_CN
 
 
-def get_skill_data_dir():
+def get_skill_data_dir() -> str:
     path = os.path.join(get_data_root(), get_user_id(), SKILL_SLUG)
     os.makedirs(path, exist_ok=True)
     return path
 
 
-def get_db_path():
+def get_db_path() -> str:
     return os.path.join(get_skill_data_dir(), "account-manager.db")
 
 
-def _runtime_paths_debug_text():
-    """供排查「为何 list 没数据」：终端未注入环境变量时会落到 _anon 等默认目录，与网关里用的库不是同一个文件。"""
+def _runtime_paths_debug_text() -> str:
+    """For debugging: print current data path info to stderr."""
     env_root = (os.getenv("JIANGCHANG_DATA_ROOT") or "").strip() or "(未设置)"
     env_uid = (os.getenv("JIANGCHANG_USER_ID") or "").strip() or "(未设置→使用 _anon)"
     return (
@@ -33,8 +35,8 @@ def _runtime_paths_debug_text():
     )
 
 
-def _maybe_print_paths_debug_cli():
-    """设置 JIANGCHANG_ACCOUNT_DEBUG_PATHS=1 时，每次执行子命令前在 stderr 打印路径。"""
+def _maybe_print_paths_debug_cli() -> None:
+    """Set JIANGCHANG_ACCOUNT_DEBUG_PATHS=1 to print paths in stderr."""
     v = (os.getenv("JIANGCHANG_ACCOUNT_DEBUG_PATHS") or "").strip().lower()
     if v in ("1", "true", "yes", "on"):
         print(_runtime_paths_debug_text(), file=sys.stderr)
@@ -49,7 +51,7 @@ _WIN_RESERVED_NAMES = frozenset(
 
 
 def _fs_safe_segment(name: str, fallback: str) -> str:
-    """单级目录名：去掉 Windows 非法字符，避免末尾点/空格；空则用 fallback。"""
+    """Single directory segment: strip Windows-unsafe chars; empty -> fallback."""
     t = _WIN_FS_FORBIDDEN.sub("_", (name or "").strip())
     t = t.rstrip(" .")
     if not t:
@@ -59,22 +61,33 @@ def _fs_safe_segment(name: str, fallback: str) -> str:
     return t
 
 
-def get_default_profile_dir(
-    platform_key: str, phone: Optional[str], account_id: Optional[int] = None
+def get_default_profile_dir_for_web(
+    platform_key: str,
+    label: str,
+    login_id: Optional[str] = None,
+    domain: str = "generic",
 ) -> str:
     """
-    默认可读路径：profiles/<平台展示名>/<手机号>/（便于在资源管理器中辨认）。
-    无手机号时退化为 profiles/<平台展示名>/no_phone_<id>/。
+    Generate a browser profile directory path.
+
+    Structure:
+      {DATA_ROOT}/{USER_ID}/account-manager/profiles/{domain}/{platform_key}/{safe_label}[_{login_id_suffix]/
+
+    This keeps profiles organized by domain and platform for easy
+    identification in file explorer.
     """
-    label = _PLATFORM_PRIMARY_CN.get(platform_key, platform_key or "account")
-    label_seg = _fs_safe_segment(label, _fs_safe_segment(platform_key or "", "platform"))
-    ph = (phone or "").strip()
-    if ph:
-        phone_seg = _fs_safe_segment(ph, f"id_{account_id}" if account_id is not None else "phone")
-    else:
-        phone_seg = _fs_safe_segment(
-            "", f"no_phone_{account_id}" if account_id is not None else "no_phone"
-        )
-    path = os.path.join(get_skill_data_dir(), "profiles", label_seg, phone_seg)
+    label_seg = _fs_safe_segment(label, platform_key)
+    login_suffix = ""
+    if login_id:
+        safe_login = _fs_safe_segment(login_id, "")
+        if safe_login:
+            login_suffix = f"_{safe_login[:16]}"
+    path = os.path.join(
+        get_skill_data_dir(),
+        "profiles",
+        _fs_safe_segment(domain, "generic"),
+        _fs_safe_segment(platform_key, "unknown"),
+        f"{label_seg}{login_suffix}",
+    )
     os.makedirs(path, exist_ok=True)
     return path