Files
MediaCrawler/store/bilibili/_store_impl.py
程序员阿江(Relakkes) 9f4f8bf768 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)
2026-07-01 13:09:55 +08:00

388 lines
12 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# -*- coding: utf-8 -*-
# Copyright (c) 2025 relakkes@gmail.com
#
# This file is part of MediaCrawler project.
# Repository: https://github.com/NanmiCoder/MediaCrawler/blob/main/store/bilibili/_store_impl.py
# GitHub: https://github.com/NanmiCoder
# Licensed under NON-COMMERCIAL LEARNING LICENSE 1.1
#
# 声明:本代码仅供学习和研究目的使用。使用者应遵守以下原则:
# 1. 不得用于任何商业用途。
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
# 3. 不得进行大规模爬取或对平台造成运营干扰。
# 4. 应合理控制请求频率,避免给目标平台带来不必要的负担。
# 5. 不得用于任何非法或不当的用途。
#
# 详细许可条款请参阅项目根目录下的LICENSE文件。
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
# -*- coding: utf-8 -*-
# @Author : persist1@126.com
# @Time : 2025/9/5 19:34
# @Desc : Bilibili storage implementation class
import asyncio
import csv
import json
import os
import pathlib
from typing import Dict
import aiofiles
from sqlalchemy import select
from sqlalchemy.orm import sessionmaker
import config
from base.base_crawler import AbstractStore
from database.db_session import get_session
from database.models import BilibiliVideoComment, BilibiliVideo, BilibiliUpDynamic
from tools.async_file_writer import AsyncFileWriter
from tools import utils, words
from var import crawler_type_var
from database.mongodb_store_base import MongoDBStoreBase
class BiliCsvStoreImplement(AbstractStore):
def __init__(self):
self.file_writer = AsyncFileWriter(
crawler_type=crawler_type_var.get(),
platform="bili"
)
async def store_content(self, content_item: Dict):
"""
content CSV storage implementation
Args:
content_item:
Returns:
"""
await self.file_writer.write_to_csv(
item=content_item,
item_type="videos"
)
async def store_comment(self, comment_item: Dict):
"""
comment CSV storage implementation
Args:
comment_item:
Returns:
"""
await self.file_writer.write_to_csv(
item=comment_item,
item_type="comments"
)
async def store_creator(self, creator: Dict):
"""
creator CSV storage implementation
Args:
creator:
Returns:
"""
await self.file_writer.write_to_csv(
item=creator,
item_type="creators"
)
async def store_contact(self, contact_item: Dict):
"""
creator contact CSV storage implementation
Args:
contact_item: creator's contact item dict
Returns:
"""
await self.file_writer.write_to_csv(
item=contact_item,
item_type="contacts"
)
async def store_dynamic(self, dynamic_item: Dict):
"""
creator dynamic CSV storage implementation
Args:
dynamic_item: creator's contact item dict
Returns:
"""
await self.file_writer.write_to_csv(
item=dynamic_item,
item_type="dynamics"
)
class BiliDbStoreImplement(AbstractStore):
async def store_content(self, content_item: Dict):
"""
Bilibili content DB storage implementation
Args:
content_item: content item dict
"""
video_id = int(content_item.get("video_id"))
content_item["video_id"] = video_id
content_item["liked_count"] = int(content_item.get("liked_count", 0) or 0)
content_item["create_time"] = int(content_item.get("create_time", 0) or 0)
async with get_session() as session:
result = await session.execute(select(BilibiliVideo).where(BilibiliVideo.video_id == video_id))
video_detail = result.scalar_one_or_none()
if not video_detail:
content_item["add_ts"] = utils.get_current_timestamp()
content_item["last_modify_ts"] = utils.get_current_timestamp()
new_content = BilibiliVideo(**content_item)
session.add(new_content)
else:
content_item["last_modify_ts"] = utils.get_current_timestamp()
for key, value in content_item.items():
setattr(video_detail, key, value)
await session.commit()
async def store_comment(self, comment_item: Dict):
"""
Bilibili comment DB storage implementation
Args:
comment_item: comment item dict
"""
comment_id = int(comment_item.get("comment_id"))
comment_item["comment_id"] = comment_id
comment_item["video_id"] = int(comment_item.get("video_id", 0) or 0)
comment_item["create_time"] = int(comment_item.get("create_time", 0) or 0)
comment_item["like_count"] = str(comment_item.get("like_count", "0"))
comment_item["sub_comment_count"] = str(comment_item.get("sub_comment_count", "0"))
comment_item["parent_comment_id"] = str(comment_item.get("parent_comment_id", "0"))
async with get_session() as session:
result = await session.execute(select(BilibiliVideoComment).where(BilibiliVideoComment.comment_id == comment_id))
comment_detail = result.scalar_one_or_none()
if not comment_detail:
comment_item["add_ts"] = utils.get_current_timestamp()
comment_item["last_modify_ts"] = utils.get_current_timestamp()
new_comment = BilibiliVideoComment(**comment_item)
session.add(new_comment)
else:
comment_item["last_modify_ts"] = utils.get_current_timestamp()
for key, value in comment_item.items():
setattr(comment_detail, key, value)
await session.commit()
async def store_creator(self, creator: Dict):
# 教学版UP 主个人资料不再落库
pass
async def store_contact(self, contact_item: Dict):
# 教学版UP-粉丝关系表已移除,不再存储联系人信息
pass
async def store_dynamic(self, dynamic_item):
"""
Bilibili dynamic DB storage implementation
Args:
dynamic_item: dynamic item dict
"""
dynamic_id = int(dynamic_item.get("dynamic_id"))
dynamic_item["dynamic_id"] = dynamic_id
async with get_session() as session:
result = await session.execute(select(BilibiliUpDynamic).where(BilibiliUpDynamic.dynamic_id == dynamic_id))
dynamic_detail = result.scalar_one_or_none()
if not dynamic_detail:
dynamic_item["add_ts"] = utils.get_current_timestamp()
dynamic_item["last_modify_ts"] = utils.get_current_timestamp()
new_dynamic = BilibiliUpDynamic(**dynamic_item)
session.add(new_dynamic)
else:
dynamic_item["last_modify_ts"] = utils.get_current_timestamp()
for key, value in dynamic_item.items():
setattr(dynamic_detail, key, value)
await session.commit()
class BiliJsonStoreImplement(AbstractStore):
def __init__(self):
self.file_writer = AsyncFileWriter(
crawler_type=crawler_type_var.get(),
platform="bili"
)
async def store_content(self, content_item: Dict):
"""
content JSON storage implementation
Args:
content_item:
Returns:
"""
await self.file_writer.write_single_item_to_json(
item=content_item,
item_type="contents"
)
async def store_comment(self, comment_item: Dict):
"""
comment JSON storage implementation
Args:
comment_item:
Returns:
"""
await self.file_writer.write_single_item_to_json(
item=comment_item,
item_type="comments"
)
async def store_creator(self, creator: Dict):
"""
creator JSON storage implementation
Args:
creator:
Returns:
"""
await self.file_writer.write_single_item_to_json(
item=creator,
item_type="creators"
)
async def store_contact(self, contact_item: Dict):
"""
creator contact JSON storage implementation
Args:
contact_item: creator's contact item dict
Returns:
"""
await self.file_writer.write_single_item_to_json(
item=contact_item,
item_type="contacts"
)
async def store_dynamic(self, dynamic_item: Dict):
"""
creator dynamic JSON storage implementation
Args:
dynamic_item: creator's contact item dict
Returns:
"""
await self.file_writer.write_single_item_to_json(
item=dynamic_item,
item_type="dynamics"
)
class BiliJsonlStoreImplement(AbstractStore):
def __init__(self):
self.file_writer = AsyncFileWriter(
crawler_type=crawler_type_var.get(),
platform="bili"
)
async def store_content(self, content_item: Dict):
await self.file_writer.write_to_jsonl(
item=content_item,
item_type="contents"
)
async def store_comment(self, comment_item: Dict):
await self.file_writer.write_to_jsonl(
item=comment_item,
item_type="comments"
)
async def store_creator(self, creator: Dict):
await self.file_writer.write_to_jsonl(
item=creator,
item_type="creators"
)
async def store_contact(self, contact_item: Dict):
await self.file_writer.write_to_jsonl(
item=contact_item,
item_type="contacts"
)
async def store_dynamic(self, dynamic_item: Dict):
await self.file_writer.write_to_jsonl(
item=dynamic_item,
item_type="dynamics"
)
class BiliSqliteStoreImplement(BiliDbStoreImplement):
pass
class BiliMongoStoreImplement(AbstractStore):
"""Bilibili MongoDB storage implementation"""
def __init__(self):
self.mongo_store = MongoDBStoreBase(collection_prefix="bilibili")
async def store_content(self, content_item: Dict):
"""
Store video content to MongoDB
Args:
content_item: Video content data
"""
video_id = content_item.get("video_id")
if not video_id:
return
await self.mongo_store.save_or_update(
collection_suffix="contents",
query={"video_id": video_id},
data=content_item
)
utils.logger.info(f"[BiliMongoStoreImplement.store_content] Saved video {video_id} to MongoDB")
async def store_comment(self, comment_item: Dict):
"""
Store comment to MongoDB
Args:
comment_item: Comment data
"""
comment_id = comment_item.get("comment_id")
if not comment_id:
return
await self.mongo_store.save_or_update(
collection_suffix="comments",
query={"comment_id": comment_id},
data=comment_item
)
utils.logger.info(f"[BiliMongoStoreImplement.store_comment] Saved comment {comment_id} to MongoDB")
async def store_creator(self, creator_item: Dict):
# 教学版UP 主个人资料不再落库
pass
class BiliExcelStoreImplement:
"""Bilibili Excel storage implementation - Global singleton"""
def __new__(cls, *args, **kwargs):
from store.excel_store_base import ExcelStoreBase
return ExcelStoreBase.get_instance(
platform="bilibili",
crawler_type=crawler_type_var.get()
)