holy后端

2026-08-04 14:02:45 +08:00
commit 175b38138e
25 changed files with 3752 additions and 0 deletions
--- a/rule_service.py
+++ b/rule_service.py
@@ -0,0 +1,103 @@
+from pathlib import Path
+from typing import Any
+
+from flask import Request
+
+from config import Config
+from database import json_dumps, json_loads, now_iso
+from task_service import TaskError
+
+
+RULE_DIR = Config.FILE_STORAGE_PATH / "rules"
+RULE_HTML_PATH = RULE_DIR / "current.html"
+RULE_META_PATH = RULE_DIR / "current.json"
+
+
+def _ensure_rule_dir() -> None:
+    RULE_DIR.mkdir(parents=True, exist_ok=True)
+
+
+def _read_text(path: Path) -> str:
+    return path.read_text(encoding="utf-8")
+
+
+def get_rule_document() -> dict[str, Any]:
+    """读取当前规则 HTML 的公开元数据。"""
+
+    if not RULE_HTML_PATH.exists():
+        return {
+            "exists": False,
+            "title": "",
+            "filename": "",
+            "updated_at": None,
+            "size_bytes": 0,
+            "html_url": "/api/v1/rules/current.html",
+        }
+    metadata = json_loads(_read_text(RULE_META_PATH)) if RULE_META_PATH.exists() else {}
+    stat = RULE_HTML_PATH.stat()
+    return {
+        "exists": True,
+        "title": metadata.get("title") or "小红书问一问收录规则探索",
+        "filename": metadata.get("filename") or RULE_HTML_PATH.name,
+        "updated_at": metadata.get("updated_at"),
+        "size_bytes": stat.st_size,
+        "html_url": "/api/v1/rules/current.html",
+    }
+
+
+def get_rule_html_path() -> Path:
+    if not RULE_HTML_PATH.exists():
+        raise TaskError("RULE_NOT_FOUND", "当前没有已上传的规则 HTML", 404)
+    return RULE_HTML_PATH
+
+
+def save_rule_document(request: Request) -> dict[str, Any]:
+    """保存当前规则 HTML；支持 multipart 文件、JSON html 字段和 text/html 原文。"""
+
+    filename = "current.html"
+    title = "小红书问一问收录规则探索"
+    html = ""
+    uploaded = request.files.get("file")
+    if uploaded:
+        filename = uploaded.filename or filename
+        html = uploaded.read().decode("utf-8")
+        title = request.form.get("title") or title
+    else:
+        payload = request.get_json(silent=True)
+        if isinstance(payload, dict):
+            html = str(payload.get("html") or "")
+            filename = str(payload.get("filename") or filename)
+            title = str(payload.get("title") or title)
+        else:
+            html = request.get_data(as_text=True) or ""
+            title = request.args.get("title") or title
+            filename = request.args.get("filename") or filename
+
+    if not html.strip():
+        raise TaskError("RULE_HTML_REQUIRED", "html 内容不能为空", 400)
+    if "<html" not in html.lower() and "<!doctype html" not in html.lower():
+        raise TaskError("RULE_HTML_INVALID", "请上传完整 HTML 文档", 400)
+
+    _ensure_rule_dir()
+    updated_at = now_iso()
+    RULE_HTML_PATH.write_text(html, encoding="utf-8")
+    RULE_META_PATH.write_text(
+        json_dumps({
+            "title": title,
+            "filename": filename,
+            "updated_at": updated_at,
+        }),
+        encoding="utf-8",
+    )
+    return get_rule_document()
+
+
+def delete_rule_document() -> dict[str, Any]:
+    """删除当前规则 HTML 和元数据。"""
+
+    deleted = False
+    for path in (RULE_HTML_PATH, RULE_META_PATH):
+        if path.exists():
+            path.unlink()
+            deleted = True
+    return {"deleted": deleted, **get_rule_document()}