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/xhs/__init__.py

@@ -25,6 +25,7 @@ from typing import List
 
 import config
 from var import source_keyword_var
+from tools.user_hash import anonymize_user_id, mask_nickname
 
 from .xhs_store_media import *
 from ._store_impl import *
@@ -113,14 +114,12 @@ async def update_xhs_note(note_item: Dict):
         "video_url": video_url,  # Note video url
         "time": note_item.get("time"),  # Note publish time
         "last_update_time": note_item.get("last_update_time", 0),  # Note last update time
-        "user_id": user_info.get("user_id"),  # User ID
-        "nickname": user_info.get("nickname"),  # User nickname
-        "avatar": user_info.get("avatar"),  # User avatar
+        "creator_hash": anonymize_user_id(user_info.get("user_id")),  # 创作者匿名哈希(不存原始 user_id)
+        "nickname": mask_nickname(user_info.get("nickname")),  # 用户昵称(已脱敏)
         "liked_count": interact_info.get("liked_count"),  # Like count
         "collected_count": interact_info.get("collected_count"),  # Collection count
         "comment_count": interact_info.get("comment_count"),  # Comment count
         "share_count": interact_info.get("share_count"),  # Share count
-        "ip_location": note_item.get("ip_location", ""),  # IP location
         "image_list": ','.join([img.get('url', '') for img in image_list]),  # Image URLs
         "tag_list": ','.join([tag.get('name', '') for tag in tag_list if tag.get('type') == 'topic']),  # Tags
         "last_modify_ts": utils.get_current_timestamp(),  # Last modification timestamp (Generated by MediaCrawler, mainly used to record the latest update time of a record in DB storage)
@@ -165,12 +164,10 @@ async def update_xhs_note_comment(note_id: str, comment_item: Dict):
     local_db_item = {
         "comment_id": comment_id,  # Comment ID
         "create_time": comment_item.get("create_time"),  # Comment time
-        "ip_location": comment_item.get("ip_location"),  # IP location
         "note_id": note_id,  # Note ID
         "content": comment_item.get("content"),  # Comment content
-        "user_id": user_info.get("user_id"),  # User ID
-        "nickname": user_info.get("nickname"),  # User nickname
-        "avatar": user_info.get("image"),  # User avatar
+        "creator_hash": anonymize_user_id(user_info.get("user_id")),  # 创作者匿名哈希(不存原始 user_id)
+        "nickname": mask_nickname(user_info.get("nickname")),  # 用户昵称(已脱敏)
         "sub_comment_count": comment_item.get("sub_comment_count", 0),  # Sub-comment count
         "pictures": ",".join(comment_pictures),  # Comment pictures
         "parent_comment_id": target_comment.get("id", 0),  # Parent comment ID
@@ -191,43 +188,8 @@ async def save_creator(user_id: str, creator: Dict):
     Returns:
 
     """
-    user_info = creator.get('basicInfo', {})
-
-    follows = 0
-    fans = 0
-    interaction = 0
-    for i in creator.get('interactions'):
-        if i.get('type') == 'follows':
-            follows = i.get('count')
-        elif i.get('type') == 'fans':
-            fans = i.get('count')
-        elif i.get('type') == 'interaction':
-            interaction = i.get('count')
-
-    def get_gender(gender):
-        if gender == 1:
-            return 'Female'
-        elif gender == 0:
-            return 'Male'
-        else:
-            return None
-
-    local_db_item = {
-        'user_id': user_id,  # User ID
-        'nickname': user_info.get('nickname'),  # Nickname
-        'gender': get_gender(user_info.get('gender')),  # Gender
-        'avatar': user_info.get('images'),  # Avatar
-        'desc': user_info.get('desc'),  # Personal description
-        'ip_location': user_info.get('ipLocation'),  # IP location
-        'follows': follows,  # Following count
-        'fans': fans,  # Fans count
-        'interaction': interaction,  # Interaction count
-        'tag_list': json.dumps({tag.get('tagType'): tag.get('name')
-                                for tag in creator.get('tags')}, ensure_ascii=False),  # Tags
-        "last_modify_ts": utils.get_current_timestamp(),  # Last modification timestamp (Generated by MediaCrawler, mainly used to record the latest update time of a record in DB storage)
-    }
-    utils.logger.info(f"[store.xhs.save_creator] creator:{local_db_item}")
-    await XhsStoreFactory.create_store().store_creator(local_db_item)
+    # 教学版：创作者个人资料(昵称/性别/头像/IP/粉丝数等)不再落库，防骚扰。
+    return
 
 
 async def update_xhs_note_image(note_id, pic_content, extension_file_name):