mirror of
https://github.com/NanmiCoder/MediaCrawler.git
synced 2026-07-24 05:10:30 +08:00
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:
@@ -33,7 +33,7 @@ from sqlalchemy import select
|
||||
import config
|
||||
from base.base_crawler import AbstractStore
|
||||
from database.db_session import get_session
|
||||
from database.models import DouyinAweme, DouyinAwemeComment, DyCreator
|
||||
from database.models import DouyinAweme, DouyinAwemeComment
|
||||
from tools import utils, words
|
||||
from tools.async_file_writer import AsyncFileWriter
|
||||
from var import crawler_type_var
|
||||
@@ -133,24 +133,8 @@ class DouyinDbStoreImplement(AbstractStore):
|
||||
await session.commit()
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Douyin creator DB storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
"""
|
||||
user_id = creator.get("user_id")
|
||||
async with get_session() as session:
|
||||
result = await session.execute(select(DyCreator).where(DyCreator.user_id == user_id))
|
||||
user_detail = result.scalar_one_or_none()
|
||||
|
||||
if not user_detail:
|
||||
creator["add_ts"] = utils.get_current_timestamp()
|
||||
new_creator = DyCreator(**creator)
|
||||
session.add(new_creator)
|
||||
else:
|
||||
for key, value in creator.items():
|
||||
setattr(user_detail, key, value)
|
||||
await session.commit()
|
||||
# 教学版:创作者个人资料不再落库
|
||||
pass
|
||||
|
||||
|
||||
class DouyinJsonStoreImplement(AbstractStore):
|
||||
@@ -275,21 +259,8 @@ class DouyinMongoStoreImplement(AbstractStore):
|
||||
utils.logger.info(f"[DouyinMongoStoreImplement.store_comment] Saved comment {comment_id} to MongoDB")
|
||||
|
||||
async def store_creator(self, creator_item: Dict):
|
||||
"""
|
||||
Store creator information to MongoDB
|
||||
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"[DouyinMongoStoreImplement.store_creator] Saved creator {user_id} to MongoDB")
|
||||
# 教学版:创作者个人资料不再落库
|
||||
pass
|
||||
|
||||
|
||||
class DouyinExcelStoreImplement:
|
||||
|
||||
Reference in New Issue
Block a user