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
+7 -45
View File
@@ -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):
+7 -65
View File
@@ -30,7 +30,7 @@ from sqlalchemy.orm import Session
from base.base_crawler import AbstractStore
from database.db_session import get_session
from database.models import XhsNote, XhsNoteComment, XhsCreator
from database.models import XhsNote, XhsNoteComment
from tools.async_file_writer import AsyncFileWriter
from tools.time_util import get_current_timestamp
@@ -137,10 +137,8 @@ class XhsDbStoreImplement(AbstractStore):
add_ts = int(get_current_timestamp())
last_modify_ts = int(get_current_timestamp())
note = XhsNote(
user_id=content_item.get("user_id"),
creator_hash=content_item.get("creator_hash"),
nickname=content_item.get("nickname"),
avatar=content_item.get("avatar"),
ip_location=content_item.get("ip_location"),
add_ts=add_ts,
last_modify_ts=last_modify_ts,
note_id=content_item.get("note_id"),
@@ -197,10 +195,8 @@ class XhsDbStoreImplement(AbstractStore):
add_ts = int(get_current_timestamp())
last_modify_ts = int(get_current_timestamp())
comment = XhsNoteComment(
user_id=comment_item.get("user_id"),
creator_hash=comment_item.get("creator_hash"),
nickname=comment_item.get("nickname"),
avatar=comment_item.get("avatar"),
ip_location=comment_item.get("ip_location"),
add_ts=add_ts,
last_modify_ts=last_modify_ts,
comment_id=comment_item.get("comment_id"),
@@ -231,54 +227,8 @@ class XhsDbStoreImplement(AbstractStore):
return result.first() is not None
async def store_creator(self, creator_item: Dict):
user_id = creator_item.get("user_id")
if not user_id:
return
async with get_session() as session:
if await self.creator_is_exist(session, user_id):
await self.update_creator(session, creator_item)
else:
await self.add_creator(session, creator_item)
async def add_creator(self, session: AsyncSession, creator_item: Dict):
add_ts = int(get_current_timestamp())
last_modify_ts = int(get_current_timestamp())
creator = XhsCreator(
user_id=creator_item.get("user_id"),
nickname=creator_item.get("nickname"),
avatar=creator_item.get("avatar"),
ip_location=creator_item.get("ip_location"),
add_ts=add_ts,
last_modify_ts=last_modify_ts,
desc=creator_item.get("desc"),
gender=creator_item.get("gender"),
follows=str(creator_item.get("follows")),
fans=str(creator_item.get("fans")),
interaction=str(creator_item.get("interaction")),
tag_list=json.dumps(creator_item.get("tag_list"))
)
session.add(creator)
async def update_creator(self, session: AsyncSession, creator_item: Dict):
user_id = creator_item.get("user_id")
last_modify_ts = int(get_current_timestamp())
update_data = {
"last_modify_ts": last_modify_ts,
"nickname": creator_item.get("nickname"),
"avatar": creator_item.get("avatar"),
"desc": creator_item.get("desc"),
"follows": str(creator_item.get("follows")),
"fans": str(creator_item.get("fans")),
"interaction": str(creator_item.get("interaction")),
"tag_list": json.dumps(creator_item.get("tag_list"))
}
stmt = update(XhsCreator).where(XhsCreator.user_id == user_id).values(**update_data)
await session.execute(stmt)
async def creator_is_exist(self, session: AsyncSession, user_id: str) -> bool:
stmt = select(XhsCreator).where(XhsCreator.user_id == user_id)
result = await session.execute(stmt)
return result.first() is not None
# 教学版:创作者个人资料不再落库
pass
async def get_all_content(self) -> List[Dict]:
async with get_session() as session:
@@ -345,16 +295,8 @@ class XhsMongoStoreImplement(AbstractStore):
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"[XhsMongoStoreImplement.store_creator] Saved creator {user_id} to MongoDB")
# 教学版:创作者个人资料不再落库
pass
class XhsExcelStoreImplement: