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)
This commit is contained in:
程序员阿江(Relakkes)
2026-07-01 13:09:55 +08:00
parent 8b4d8fcffa
commit 9f4f8bf768
26 changed files with 1426 additions and 822 deletions
+4 -4
View File
@@ -646,14 +646,14 @@ class BilibiliCrawler(AbstractCrawler):
"""
async with semaphore:
creator_unhandled_info: Dict = await self.bili_client.get_creator_info(creator_id)
# 教学版:仅保留动态所需的最少字段(内存临时用),不持久化创作者个人资料。
creator_info: Dict = {
"id": creator_id,
"name": creator_unhandled_info.get("name"),
"sign": creator_unhandled_info.get("sign"),
"avatar": creator_unhandled_info.get("face"),
}
await self.get_fans(creator_info, semaphore)
await self.get_followings(creator_info, semaphore)
# 教学版:不再爬取粉丝/关注列表(其他用户的个人信息),防骚扰。
# await self.get_fans(creator_info, semaphore)
# await self.get_followings(creator_info, semaphore)
await self.get_dynamics(creator_info, semaphore)
async def get_fans(self, creator_info: Dict, semaphore: asyncio.Semaphore):