refactor: 教学版移除全平台用户个人信息采集与持久化

- 用户 ID 转为匿名 creator_hash，昵称中间脱敏，IP/头像/主页/签名/性别不再采集
- 覆盖 xhs/weibo/bilibili/douyin/kuaishou/tieba/zhihu 7 个平台
- 删除 7 张 creator 档案 ORM 表，15 张内容/评论表新增 creator_hash 列
- B 站禁用粉丝/关注/联系人列表抓取
- 新增 tools/user_hash.py 与 4 个平台的 mock+SQLite 端到端测试

测试: pytest tests/test_no_user_info.py tests/test_weibo_no_user_info.py tests/test_douyin_no_user_info.py tests/test_kuaishou_no_user_info.py (21 passed)

store/weibo/__init__.py

@@ -25,6 +25,7 @@
 import re
 from typing import List
 
+from tools.user_hash import anonymize_user_id, mask_nickname
 from var import source_keyword_var
 
 from .weibo_store_media import *
@@ -78,11 +79,13 @@ async def update_weibo_note(note_item: Dict):
     if not note_item:
         return
 
-    mblog: Dict = note_item.get("mblog")
-    user_info: Dict = mblog.get("user")
+    mblog: Dict = note_item.get("mblog") or {}
+    user_info: Dict = mblog.get("user") or {}
     note_id = mblog.get("id")
     content_text = mblog.get("text")
     clean_text = re.sub(r"<.*?>", "", content_text)
+    # 教学版：原始 user_id 匿名化为 creator_hash，昵称脱敏；
+    # 不采集头像/主页链接/性别/IP 归属地等可定位真人的信息。
     save_content_item = {
         # Weibo information
         "note_id": note_id,
@@ -94,14 +97,10 @@ async def update_weibo_note(note_item: Dict):
         "shared_count": str(mblog.get("reposts_count", 0)),
         "last_modify_ts": utils.get_current_timestamp(),
         "note_url": f"https://m.weibo.cn/detail/{note_id}",
-        "ip_location": mblog.get("region_name", "").replace("发布于 ", ""),
 
-        # User information
-        "user_id": str(user_info.get("id")),
-        "nickname": user_info.get("screen_name", ""),
-        "gender": user_info.get("gender", ""),
-        "profile_url": user_info.get("profile_url", ""),
-        "avatar": user_info.get("profile_image_url", ""),
+        # 创作者信息（匿名化/脱敏，不含原始 user_id/avatar/gender/profile_url/ip_location）
+        "creator_hash": anonymize_user_id(user_info.get("id")),
+        "nickname": mask_nickname(user_info.get("screen_name", "")),
         "source_keyword": source_keyword_var.get(),
     }
     utils.logger.info(f"[store.weibo.update_weibo_note] weibo note id:{note_id}, title:{save_content_item.get('content')[:24]} ...")
@@ -137,9 +136,11 @@ async def update_weibo_note_comment(note_id: str, comment_item: Dict):
     if not comment_item or not note_id:
         return
     comment_id = str(comment_item.get("id"))
-    user_info: Dict = comment_item.get("user")
+    user_info: Dict = comment_item.get("user") or {}
     content_text = comment_item.get("text")
     clean_text = re.sub(r"<.*?>", "", content_text)
+    # 教学版：原始 user_id 匿名化为 creator_hash，昵称脱敏；
+    # 不采集头像/主页链接/性别/IP 归属地等可定位真人的信息。
     save_comment_item = {
         "comment_id": comment_id,
         "create_time": utils.rfc2822_to_timestamp(comment_item.get("created_at")),
@@ -149,15 +150,11 @@ async def update_weibo_note_comment(note_id: str, comment_item: Dict):
         "sub_comment_count": str(comment_item.get("total_number", 0)),
         "comment_like_count": str(comment_item.get("like_count", 0)),
         "last_modify_ts": utils.get_current_timestamp(),
-        "ip_location": comment_item.get("source", "").replace("来自", ""),
         "parent_comment_id": comment_item.get("rootid", ""),
 
-        # User information
-        "user_id": str(user_info.get("id")),
-        "nickname": user_info.get("screen_name", ""),
-        "gender": user_info.get("gender", ""),
-        "profile_url": user_info.get("profile_url", ""),
-        "avatar": user_info.get("profile_image_url", ""),
+        # 创作者信息（匿名化/脱敏，不含原始 user_id/avatar/gender/profile_url/ip_location）
+        "creator_hash": anonymize_user_id(user_info.get("id")),
+        "nickname": mask_nickname(user_info.get("screen_name", "")),
     }
     utils.logger.info(f"[store.weibo.update_weibo_note_comment] Weibo note comment: {comment_id}, content: {save_comment_item.get('content', '')[:24]} ...")
     await WeibostoreFactory.create_store().store_comment(comment_item=save_comment_item)
@@ -180,6 +177,8 @@ async def update_weibo_note_image(picid: str, pic_content, extension_file_name):
 async def save_creator(user_id: str, user_info: Dict):
     """
     Save creator information to local
+    教学版：为防骚扰不再采集/持久化创作者个人信息（昵称/性别/头像/简介/IP/粉丝数等），
+    此入口保留为空操作以兼容调用方。user_id 仅在调用方局部用于抓取该创作者的微博。
     Args:
         user_id:
         user_info:
@@ -187,17 +186,5 @@ async def save_creator(user_id: str, user_info: Dict):
     Returns:
 
     """
-    local_db_item = {
-        'user_id': user_id,
-        'nickname': user_info.get('screen_name'),
-        'gender': 'Female' if user_info.get('gender') == "f" else 'Male',
-        'avatar': user_info.get('avatar_hd'),
-        'desc': user_info.get('description'),
-        'ip_location': user_info.get("source", "").replace("来自", ""),
-        'follows': user_info.get('follow_count', ''),
-        'fans': user_info.get('followers_count', ''),
-        'tag_list': '',
-        "last_modify_ts": utils.get_current_timestamp(),
-    }
-    utils.logger.info(f"[store.weibo.save_creator] creator:{local_db_item}")
-    await WeibostoreFactory.create_store().store_creator(local_db_item)
+    # 教学版：创作者个人信息均不采集不持久化
+    return

store/weibo/_store_impl.py

@@ -35,7 +35,7 @@ from sqlalchemy.ext.asyncio import AsyncSession
 
 import config
 from base.base_crawler import AbstractStore
-from database.models import WeiboCreator, WeiboNote, WeiboNoteComment
+from database.models import WeiboNote, WeiboNoteComment
 from tools import utils, words
 from tools.async_file_writer import AsyncFileWriter
 from database.db_session import get_session
@@ -58,6 +58,13 @@ def calculate_number_of_files(file_store_path: str) -> int:
         return 1
 
 
+def _filter_model_fields(model_cls, item: Dict) -> Dict:
+    """只保留目标 ORM 模型已有的列，避免把已删除/多余字段（如 avatar/gender/
+    profile_url/ip_location/user_id）传给 ORM 构造而报错。教学版兜底保护。"""
+    allowed = {col.name for col in model_cls.__table__.columns}
+    return {k: v for k, v in item.items() if k in allowed}
+
+
 class WeiboCsvStoreImplement(AbstractStore):
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
@@ -88,13 +95,14 @@ class WeiboCsvStoreImplement(AbstractStore):
     async def store_creator(self, creator: Dict):
         """
         Weibo creator CSV storage implementation
+        教学版：不采集/持久化创作者个人信息，空操作。
         Args:
             creator:
 
         Returns:
 
         """
-        await self.writer.write_to_csv(item_type="creators", item=creator)
+        pass
 
 
 class WeiboDbStoreImplement(AbstractStore):
@@ -108,6 +116,8 @@ class WeiboDbStoreImplement(AbstractStore):
         Returns:
 
         """
+        # 教学版兜底：过滤掉已删除/多余字段，确保不会把 user_id/avatar 等传给 ORM
+        content_item = _filter_model_fields(WeiboNote, content_item)
         note_id = int(content_item.get("note_id"))
         content_item["note_id"] = note_id
         async with get_session() as session:
@@ -135,6 +145,8 @@ class WeiboDbStoreImplement(AbstractStore):
         Returns:
 
         """
+        # 教学版兜底：过滤掉已删除/多余字段，确保不会把 user_id/avatar 等传给 ORM
+        comment_item = _filter_model_fields(WeiboNoteComment, comment_item)
         comment_id = int(comment_item.get("comment_id"))
         comment_item["comment_id"] = comment_id
         comment_item["note_id"] = int(comment_item.get("note_id", 0) or 0)
@@ -162,29 +174,14 @@ class WeiboDbStoreImplement(AbstractStore):
     async def store_creator(self, creator: Dict):
         """
         Weibo creator DB storage implementation
+        教学版：不采集/持久化创作者个人信息，空操作（WeiboCreator 表已删除）。
         Args:
             creator:
 
         Returns:
 
         """
-        user_id = int(creator.get("user_id"))
-        creator["user_id"] = user_id
-        async with get_session() as session:
-            stmt = select(WeiboCreator).where(WeiboCreator.user_id == user_id)
-            res = await session.execute(stmt)
-            db_creator = res.scalar_one_or_none()
-            if db_creator:
-                db_creator.last_modify_ts = utils.get_current_timestamp()
-                for key, value in creator.items():
-                    if hasattr(db_creator, key):
-                        setattr(db_creator, key, value)
-            else:
-                creator["add_ts"] = utils.get_current_timestamp()
-                creator["last_modify_ts"] = utils.get_current_timestamp()
-                db_creator = WeiboCreator(**creator)
-                session.add(db_creator)
-            await session.commit()
+        pass
 
 
 class WeiboJsonStoreImplement(AbstractStore):
@@ -217,13 +214,14 @@ class WeiboJsonStoreImplement(AbstractStore):
     async def store_creator(self, creator: Dict):
         """
         creator JSON storage implementation
+        教学版：不采集/持久化创作者个人信息，空操作。
         Args:
             creator:
 
         Returns:
 
         """
-        await self.writer.write_single_item_to_json(item_type="creators", item=creator)
+        pass
 
 
 class WeiboJsonlStoreImplement(AbstractStore):
@@ -238,7 +236,8 @@ class WeiboJsonlStoreImplement(AbstractStore):
         await self.writer.write_to_jsonl(item_type="comments", item=comment_item)
 
     async def store_creator(self, creator: Dict):
-        await self.writer.write_to_jsonl(item_type="creators", item=creator)
+        # 教学版：不采集/持久化创作者个人信息，空操作。
+        pass
 
 
 class WeiboSqliteStoreImplement(WeiboDbStoreImplement):
@@ -291,19 +290,11 @@ class WeiboMongoStoreImplement(AbstractStore):
     async def store_creator(self, creator_item: Dict):
         """
         Store creator information to MongoDB
+        教学版：不采集/持久化创作者个人信息，空操作。
         Args:
             creator_item: Creator data
         """
-        user_id = creator_item.get("user_id")
-        if not user_id:
-            return
-
-        await self.mongo_store.save_or_update(
-            collection_suffix="creators",
-            query={"user_id": user_id},
-            data=creator_item
-        )
-        utils.logger.info(f"[WeiboMongoStoreImplement.store_creator] Saved creator {user_id} to MongoDB")
+        pass
 
 
 class WeiboExcelStoreImplement: