first commit

2026-09-03 15:35:23 +08:00
commit 9b26161bcf
510 changed files with 29402 additions and 0 deletions
@@ -0,0 +1,114 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+读取 db/menu_map.json, 构建功能树写入 SQLite(features 表)。
+层级: level0=顶层模块, level1=分组, level2=菜单页(叶子)
+并为每个叶子分配期望截图路径 screenshots/<序号_模块>/<分组>/<序号_名称>.jpg
+
+menu_map.json 结构(由实时爬取生成):
+{
+  "<模块名>": {
+     "loc": "落地页URL",
+     "desc": "模块释义(可选)",
+     "understanding": "开发理解(可选)",
+     "groups": [ {"title": "分组名", "items": [ {"name":"页名","href":"/路径","desc":"","understanding":""}, ...] } ],
+     "single": {"name":"页名","href":"/路径"}   # 无侧边栏的单页模块(可选)
+  },
+  ...
+}
+"""
+import json, os, re, sqlite3
+
+BASE = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+MAP = os.path.join(BASE, "db", "menu_map.json")
+DB = os.path.join(BASE, "db", "research.db")
+ORIGIN = "https://s-demob.xinrenxinshi.show"
+
+
+def sanitize(s):
+    s = re.sub(r'[\\/:*?"<>|]', "_", s or "").strip()
+    return s[:40] or "page"
+
+
+def full_url(href):
+    if not href:
+        return ""
+    if href.startswith("http"):
+        return href
+    return ORIGIN + (href if href.startswith("/") else "/" + href)
+
+
+def main():
+    data = json.load(open(MAP, encoding="utf-8"))
+    conn = sqlite3.connect(DB)
+    conn.row_factory = sqlite3.Row
+    cur = conn.cursor()
+    cur.execute("DELETE FROM features")
+
+    def up(obj):
+        keys = list(obj.keys()); cols = ",".join(keys); ph = ",".join(["?"] * len(keys))
+        cur.execute(f"INSERT OR REPLACE INTO features ({cols}) VALUES ({ph})", [obj[k] for k in keys])
+
+    for mi, module in enumerate(data.keys(), 1):
+        v = data[module]
+        mod_key = f"mod::{module}"
+        seq_mod = f"{mi:02d}_{sanitize(module)}"
+        up(dict(node_key=mod_key, parent_key="", level=0, name=module,
+                full_path=module, url=v.get("loc", ""),
+                description=v.get("desc", f"{module}模块。"),
+                understanding=v.get("understanding", ""), sort_order=mi, keep=1))
+
+        groups = v.get("groups", [])
+        single = v.get("single")
+        flat_items = v.get("items")
+        # 扁平模式: 模块直接挂功能页(level2), 无中间分组层
+        if not groups and flat_items:
+            for ii, it in enumerate(flat_items, 1):
+                nm = it["name"]; href = it.get("href", "")
+                leaf_key = f"{module}::{href or nm}"
+                rel = f"screenshots/{seq_mod}/{ii:02d}_{sanitize(nm)}.jpg"
+                up(dict(node_key=leaf_key, parent_key=mod_key, level=2, name=nm,
+                        full_path=f"{module} / {nm}", url=full_url(href),
+                        description=it.get("desc", f"{module}模块下「{nm}」相关功能页。"),
+                        understanding=it.get("understanding", ""),
+                        screenshot_path=rel, sort_order=ii, keep=1))
+            continue
+        if not groups and single:
+            nm = single["name"]; href = single.get("href", "")
+            leaf_key = f"{module}::{href or nm}"
+            rel = f"screenshots/{seq_mod}/{sanitize(nm)}.jpg"
+            up(dict(node_key=leaf_key, parent_key=mod_key, level=2, name=nm,
+                    full_path=f"{module} / {nm}", url=full_url(href),
+                    description=single.get("desc", f"{module}模块下「{nm}」相关功能页。"),
+                    understanding=single.get("understanding", ""),
+                    screenshot_path=rel, sort_order=1, keep=1))
+            continue
+
+        gi = 0
+        for g in groups:
+            gtitle = g.get("title") or "常规"
+            gi += 1
+            grp_key = f"{mod_key}::grp::{gi}_{gtitle}"
+            up(dict(node_key=grp_key, parent_key=mod_key, level=1, name=gtitle,
+                    full_path=f"{module} / {gtitle}", url="",
+                    description=f"{module}模块下「{gtitle}」功能分组。",
+                    understanding="", sort_order=gi, keep=1))
+            for ii, it in enumerate(g.get("items", []), 1):
+                nm = it["name"]; href = it.get("href", "")
+                leaf_key = f"{module}::{href or (gtitle + '/' + nm)}"
+                rel = f"screenshots/{seq_mod}/{sanitize(gtitle)}/{ii:02d}_{sanitize(nm)}.jpg"
+                up(dict(node_key=leaf_key, parent_key=grp_key, level=2, name=nm,
+                        full_path=f"{module} / {gtitle} / {nm}", url=full_url(href),
+                        description=it.get("desc", f"{module}模块下「{nm}」相关功能页。"),
+                        understanding=it.get("understanding", ""),
+                        screenshot_path=rel, sort_order=ii, keep=1))
+    conn.commit()
+    for lv in (0, 1, 2):
+        n = cur.execute("SELECT COUNT(*) FROM features WHERE level=?", (lv,)).fetchone()[0]
+        print(f"level{lv}: {n}")
+    print("total:", cur.execute("SELECT COUNT(*) FROM features").fetchone()[0])
+    conn.close()
+
+
+if __name__ == "__main__":
+    main()