feat(database): 优化数据库模型和连接管理

- 添加cryptography依赖用于加密功能
- 重构数据库模型字段类型和约束
- 增加数据库自动创建功能
- 改进数据库连接管理和错误处理
- 更新相关依赖文件(pyproject.toml, requirements.txt)
This commit is contained in:
persist-1
2025-09-06 06:08:28 +08:00
parent 0965bd6c96
commit b04f5bcd6f
6 changed files with 392 additions and 241 deletions

View File

@@ -1,16 +1,28 @@
from sqlalchemy import text
from sqlalchemy.ext.asyncio import create_async_engine, AsyncSession
from sqlalchemy.orm import sessionmaker
from contextlib import asynccontextmanager
from .models import Base
from config import SAVE_DATA_OPTION
import config
from config.db_config import mysql_db_config, sqlite_db_config
# Keep a cache of engines
_engines = {}
async def create_database_if_not_exists(db_type: str):
if db_type == "mysql" or db_type == "db":
# Connect to the server without a database
server_url = f"mysql+asyncmy://{mysql_db_config['user']}:{mysql_db_config['password']}@{mysql_db_config['host']}:{mysql_db_config['port']}"
engine = create_async_engine(server_url, echo=False)
async with engine.connect() as conn:
await conn.execute(text(f"CREATE DATABASE IF NOT EXISTS {mysql_db_config['db_name']}"))
await engine.dispose()
def get_async_engine(db_type: str = None):
if db_type is None:
db_type = SAVE_DATA_OPTION
db_type = config.SAVE_DATA_OPTION
if db_type in _engines:
return _engines[db_type]
@@ -31,14 +43,21 @@ def get_async_engine(db_type: str = None):
async def create_tables(db_type: str = None):
if db_type is None:
db_type = config.SAVE_DATA_OPTION
await create_database_if_not_exists(db_type)
engine = get_async_engine(db_type)
async with engine.begin() as conn:
await conn.run_sync(Base.metadata.create_all)
if engine:
async with engine.begin() as conn:
await conn.run_sync(Base.metadata.create_all)
@asynccontextmanager
async def get_session() -> AsyncSession:
engine = get_async_engine(SAVE_DATA_OPTION)
engine = get_async_engine(config.SAVE_DATA_OPTION)
if not engine:
yield None
return
AsyncSessionFactory = sessionmaker(engine, class_=AsyncSession, expire_on_commit=False)
session = AsyncSessionFactory()
try:

View File

@@ -1,4 +1,4 @@
from sqlalchemy import create_engine, Column, Integer, String, Text, BigInteger
from sqlalchemy import create_engine, Column, Integer, Text, String, BigInteger
from sqlalchemy.ext.declarative import declarative_base
from sqlalchemy.orm import sessionmaker
@@ -7,54 +7,54 @@ Base = declarative_base()
class BilibiliVideo(Base):
__tablename__ = 'bilibili_video'
id = Column(Integer, primary_key=True)
user_id = Column(String)
nickname = Column(String)
avatar = Column(String)
video_id = Column(BigInteger, nullable=False, index=True, unique=True)
video_url = Column(Text, nullable=False)
user_id = Column(BigInteger, index=True)
nickname = Column(Text)
avatar = Column(Text)
liked_count = Column(Integer)
add_ts = Column(BigInteger)
last_modify_ts = Column(BigInteger)
video_id = Column(String, index=True)
video_type = Column(String)
title = Column(String)
video_type = Column(Text)
title = Column(Text)
desc = Column(Text)
create_time = Column(BigInteger, index=True)
liked_count = Column(String)
disliked_count = Column(String)
video_play_count = Column(String)
video_favorite_count = Column(String)
video_share_count = Column(String)
video_coin_count = Column(String)
video_danmaku = Column(String)
video_comment = Column(String)
video_url = Column(String)
video_cover_url = Column(String)
source_keyword = Column(String, default='')
disliked_count = Column(Text)
video_play_count = Column(Text)
video_favorite_count = Column(Text)
video_share_count = Column(Text)
video_coin_count = Column(Text)
video_danmaku = Column(Text)
video_comment = Column(Text)
video_cover_url = Column(Text)
source_keyword = Column(Text, default='')
class BilibiliVideoComment(Base):
__tablename__ = 'bilibili_video_comment'
id = Column(Integer, primary_key=True)
user_id = Column(String)
nickname = Column(String)
sex = Column(String)
sign = Column(String)
avatar = Column(String)
user_id = Column(String(255))
nickname = Column(Text)
sex = Column(Text)
sign = Column(Text)
avatar = Column(Text)
add_ts = Column(BigInteger)
last_modify_ts = Column(BigInteger)
comment_id = Column(String, index=True)
video_id = Column(String, index=True)
comment_id = Column(BigInteger, index=True)
video_id = Column(BigInteger, index=True)
content = Column(Text)
create_time = Column(BigInteger)
sub_comment_count = Column(String)
parent_comment_id = Column(String)
like_count = Column(String, default='0')
sub_comment_count = Column(Text)
parent_comment_id = Column(String(255))
like_count = Column(Text, default='0')
class BilibiliUpInfo(Base):
__tablename__ = 'bilibili_up_info'
id = Column(Integer, primary_key=True)
user_id = Column(String, index=True)
nickname = Column(String)
sex = Column(String)
sign = Column(String)
avatar = Column(String)
user_id = Column(BigInteger, index=True)
nickname = Column(Text)
sex = Column(Text)
sign = Column(Text)
avatar = Column(Text)
add_ts = Column(BigInteger)
last_modify_ts = Column(BigInteger)
total_fans = Column(Integer)
@@ -65,25 +65,25 @@ class BilibiliUpInfo(Base):
class BilibiliContactInfo(Base):
__tablename__ = 'bilibili_contact_info'
id = Column(Integer, primary_key=True)
up_id = Column(String, index=True)
fan_id = Column(String, index=True)
up_name = Column(String)
fan_name = Column(String)
up_sign = Column(String)
fan_sign = Column(String)
up_avatar = Column(String)
fan_avatar = Column(String)
up_id = Column(BigInteger, index=True)
fan_id = Column(BigInteger, index=True)
up_name = Column(Text)
fan_name = Column(Text)
up_sign = Column(Text)
fan_sign = Column(Text)
up_avatar = Column(Text)
fan_avatar = Column(Text)
add_ts = Column(BigInteger)
last_modify_ts = Column(BigInteger)
class BilibiliUpDynamic(Base):
__tablename__ = 'bilibili_up_dynamic'
id = Column(Integer, primary_key=True)
dynamic_id = Column(String, index=True)
user_id = Column(String)
user_name = Column(String)
dynamic_id = Column(BigInteger, index=True)
user_id = Column(String(255))
user_name = Column(Text)
text = Column(Text)
type = Column(String)
type = Column(Text)
pub_ts = Column(BigInteger)
total_comments = Column(Integer)
total_forwards = Column(Integer)
@@ -94,296 +94,296 @@ class BilibiliUpDynamic(Base):
class DouyinAweme(Base):
__tablename__ = 'douyin_aweme'
id = Column(Integer, primary_key=True)
user_id = Column(String)
sec_uid = Column(String)
short_user_id = Column(String)
user_unique_id = Column(String)
nickname = Column(String)
avatar = Column(String)
user_signature = Column(String)
ip_location = Column(String)
user_id = Column(String(255))
sec_uid = Column(String(255))
short_user_id = Column(String(255))
user_unique_id = Column(String(255))
nickname = Column(Text)
avatar = Column(Text)
user_signature = Column(Text)
ip_location = Column(Text)
add_ts = Column(BigInteger)
last_modify_ts = Column(BigInteger)
aweme_id = Column(String, index=True)
aweme_type = Column(String)
title = Column(String)
aweme_id = Column(BigInteger, index=True)
aweme_type = Column(Text)
title = Column(Text)
desc = Column(Text)
create_time = Column(BigInteger, index=True)
liked_count = Column(String)
comment_count = Column(String)
share_count = Column(String)
collected_count = Column(String)
aweme_url = Column(String)
cover_url = Column(String)
video_download_url = Column(String)
music_download_url = Column(String)
note_download_url = Column(String)
source_keyword = Column(String, default='')
liked_count = Column(Text)
comment_count = Column(Text)
share_count = Column(Text)
collected_count = Column(Text)
aweme_url = Column(Text)
cover_url = Column(Text)
video_download_url = Column(Text)
music_download_url = Column(Text)
note_download_url = Column(Text)
source_keyword = Column(Text, default='')
class DouyinAwemeComment(Base):
__tablename__ = 'douyin_aweme_comment'
id = Column(Integer, primary_key=True)
user_id = Column(String)
sec_uid = Column(String)
short_user_id = Column(String)
user_unique_id = Column(String)
nickname = Column(String)
avatar = Column(String)
user_signature = Column(String)
ip_location = Column(String)
user_id = Column(String(255))
sec_uid = Column(String(255))
short_user_id = Column(String(255))
user_unique_id = Column(String(255))
nickname = Column(Text)
avatar = Column(Text)
user_signature = Column(Text)
ip_location = Column(Text)
add_ts = Column(BigInteger)
last_modify_ts = Column(BigInteger)
comment_id = Column(String, index=True)
aweme_id = Column(String, index=True)
comment_id = Column(BigInteger, index=True)
aweme_id = Column(BigInteger, index=True)
content = Column(Text)
create_time = Column(BigInteger)
sub_comment_count = Column(String)
parent_comment_id = Column(String)
like_count = Column(String, default='0')
pictures = Column(String, default='')
sub_comment_count = Column(Text)
parent_comment_id = Column(String(255))
like_count = Column(Text, default='0')
pictures = Column(Text, default='')
class DyCreator(Base):
__tablename__ = 'dy_creator'
id = Column(Integer, primary_key=True)
user_id = Column(String)
nickname = Column(String)
avatar = Column(String)
ip_location = Column(String)
user_id = Column(String(255))
nickname = Column(Text)
avatar = Column(Text)
ip_location = Column(Text)
add_ts = Column(BigInteger)
last_modify_ts = Column(BigInteger)
desc = Column(Text)
gender = Column(String)
follows = Column(String)
fans = Column(String)
interaction = Column(String)
videos_count = Column(String)
gender = Column(Text)
follows = Column(Text)
fans = Column(Text)
interaction = Column(Text)
videos_count = Column(String(255))
class KuaishouVideo(Base):
__tablename__ = 'kuaishou_video'
id = Column(Integer, primary_key=True)
user_id = Column(String)
nickname = Column(String)
avatar = Column(String)
user_id = Column(String(255))
nickname = Column(Text)
avatar = Column(Text)
add_ts = Column(BigInteger)
last_modify_ts = Column(BigInteger)
video_id = Column(String, index=True)
video_type = Column(String)
title = Column(String)
video_id = Column(BigInteger, index=True)
video_type = Column(Text)
title = Column(Text)
desc = Column(Text)
create_time = Column(BigInteger, index=True)
liked_count = Column(String)
viewd_count = Column(String)
video_url = Column(String)
video_cover_url = Column(String)
video_play_url = Column(String)
source_keyword = Column(String, default='')
liked_count = Column(Text)
viewd_count = Column(Text)
video_url = Column(Text)
video_cover_url = Column(Text)
video_play_url = Column(Text)
source_keyword = Column(Text, default='')
class KuaishouVideoComment(Base):
__tablename__ = 'kuaishou_video_comment'
id = Column(Integer, primary_key=True)
user_id = Column(String)
nickname = Column(String)
avatar = Column(String)
user_id = Column(Integer)
nickname = Column(Text)
avatar = Column(Text)
add_ts = Column(BigInteger)
last_modify_ts = Column(BigInteger)
comment_id = Column(String, index=True)
video_id = Column(String, index=True)
comment_id = Column(BigInteger, index=True)
video_id = Column(BigInteger, index=True)
content = Column(Text)
create_time = Column(BigInteger)
sub_comment_count = Column(String)
sub_comment_count = Column(Text)
class WeiboNote(Base):
__tablename__ = 'weibo_note'
id = Column(Integer, primary_key=True)
user_id = Column(String)
nickname = Column(String)
avatar = Column(String)
gender = Column(String)
profile_url = Column(String)
ip_location = Column(String, default='')
user_id = Column(String(255))
nickname = Column(Text)
avatar = Column(Text)
gender = Column(Text)
profile_url = Column(Text)
ip_location = Column(Text, default='')
add_ts = Column(BigInteger)
last_modify_ts = Column(BigInteger)
note_id = Column(String, index=True)
note_id = Column(BigInteger, index=True)
content = Column(Text)
create_time = Column(BigInteger, index=True)
create_date_time = Column(String, index=True)
liked_count = Column(String)
comments_count = Column(String)
shared_count = Column(String)
note_url = Column(String)
source_keyword = Column(String, default='')
create_date_time = Column(BigInteger, index=True)
liked_count = Column(Text)
comments_count = Column(Text)
shared_count = Column(Text)
note_url = Column(Text)
source_keyword = Column(Text, default='')
class WeiboNoteComment(Base):
__tablename__ = 'weibo_note_comment'
id = Column(Integer, primary_key=True)
user_id = Column(String)
nickname = Column(String)
avatar = Column(String)
gender = Column(String)
profile_url = Column(String)
ip_location = Column(String, default='')
user_id = Column(String(255))
nickname = Column(Text)
avatar = Column(Text)
gender = Column(Text)
profile_url = Column(Text)
ip_location = Column(Text, default='')
add_ts = Column(BigInteger)
last_modify_ts = Column(BigInteger)
comment_id = Column(String, index=True)
note_id = Column(String, index=True)
comment_id = Column(BigInteger, index=True)
note_id = Column(BigInteger, index=True)
content = Column(Text)
create_time = Column(BigInteger)
create_date_time = Column(String, index=True)
comment_like_count = Column(String)
sub_comment_count = Column(String)
parent_comment_id = Column(String)
create_date_time = Column(BigInteger, index=True)
comment_like_count = Column(Text)
sub_comment_count = Column(Text)
parent_comment_id = Column(String(255))
class WeiboCreator(Base):
__tablename__ = 'weibo_creator'
id = Column(Integer, primary_key=True)
user_id = Column(String)
nickname = Column(String)
avatar = Column(String)
ip_location = Column(String)
user_id = Column(String(255))
nickname = Column(Text)
avatar = Column(Text)
ip_location = Column(Text)
add_ts = Column(BigInteger)
last_modify_ts = Column(BigInteger)
desc = Column(Text)
gender = Column(String)
follows = Column(String)
fans = Column(String)
tag_list = Column(String)
gender = Column(Text)
follows = Column(Text)
fans = Column(Text)
tag_list = Column(Text)
class XhsCreator(Base):
__tablename__ = 'xhs_creator'
id = Column(Integer, primary_key=True)
user_id = Column(String)
nickname = Column(String)
avatar = Column(String)
ip_location = Column(String)
user_id = Column(String(255))
nickname = Column(Text)
avatar = Column(Text)
ip_location = Column(Text)
add_ts = Column(BigInteger)
last_modify_ts = Column(BigInteger)
desc = Column(Text)
gender = Column(String)
follows = Column(String)
fans = Column(String)
interaction = Column(String)
tag_list = Column(String)
gender = Column(Text)
follows = Column(Text)
fans = Column(Text)
interaction = Column(Text)
tag_list = Column(Text)
class XhsNote(Base):
__tablename__ = 'xhs_note'
id = Column(Integer, primary_key=True)
user_id = Column(String)
nickname = Column(String)
avatar = Column(String)
ip_location = Column(String)
user_id = Column(String(255))
nickname = Column(Text)
avatar = Column(Text)
ip_location = Column(Text)
add_ts = Column(BigInteger)
last_modify_ts = Column(BigInteger)
note_id = Column(String, index=True)
type = Column(String)
title = Column(String)
note_id = Column(BigInteger, index=True)
type = Column(Text)
title = Column(Text)
desc = Column(Text)
video_url = Column(String)
video_url = Column(Text)
time = Column(BigInteger, index=True)
last_update_time = Column(BigInteger)
liked_count = Column(String)
collected_count = Column(String)
comment_count = Column(String)
share_count = Column(String)
liked_count = Column(Text)
collected_count = Column(Text)
comment_count = Column(Text)
share_count = Column(Text)
image_list = Column(Text)
tag_list = Column(Text)
note_url = Column(String)
source_keyword = Column(String, default='')
xsec_token = Column(String)
note_url = Column(Text)
source_keyword = Column(Text, default='')
xsec_token = Column(Text)
class XhsNoteComment(Base):
__tablename__ = 'xhs_note_comment'
id = Column(Integer, primary_key=True)
user_id = Column(String)
nickname = Column(String)
avatar = Column(String)
ip_location = Column(String)
user_id = Column(String(255))
nickname = Column(Text)
avatar = Column(Text)
ip_location = Column(Text)
add_ts = Column(BigInteger)
last_modify_ts = Column(BigInteger)
comment_id = Column(String, index=True)
comment_id = Column(BigInteger, index=True)
create_time = Column(BigInteger, index=True)
note_id = Column(String)
note_id = Column(String(255))
content = Column(Text)
sub_comment_count = Column(Integer)
pictures = Column(Text)
parent_comment_id = Column(String)
like_count = Column(String)
parent_comment_id = Column(String(255))
like_count = Column(Text)
class TiebaNote(Base):
__tablename__ = 'tieba_note'
id = Column(Integer, primary_key=True)
note_id = Column(String, index=True)
title = Column(String)
note_id = Column(BigInteger, index=True)
title = Column(Text)
desc = Column(Text)
note_url = Column(String)
publish_time = Column(String, index=True)
user_link = Column(String, default='')
user_nickname = Column(String, default='')
user_avatar = Column(String, default='')
tieba_id = Column(String, default='')
tieba_name = Column(String)
tieba_link = Column(String)
note_url = Column(Text)
publish_time = Column(BigInteger, index=True)
user_link = Column(Text, default='')
user_nickname = Column(Text, default='')
user_avatar = Column(Text, default='')
tieba_id = Column(Integer, default='')
tieba_name = Column(Text)
tieba_link = Column(Text)
total_replay_num = Column(Integer, default=0)
total_replay_page = Column(Integer, default=0)
ip_location = Column(String, default='')
ip_location = Column(Text, default='')
add_ts = Column(BigInteger)
last_modify_ts = Column(BigInteger)
source_keyword = Column(String, default='')
source_keyword = Column(Text, default='')
class TiebaComment(Base):
__tablename__ = 'tieba_comment'
id = Column(Integer, primary_key=True)
comment_id = Column(String, index=True)
parent_comment_id = Column(String, default='')
comment_id = Column(BigInteger, index=True)
parent_comment_id = Column(String(255), default='')
content = Column(Text)
user_link = Column(String, default='')
user_nickname = Column(String, default='')
user_avatar = Column(String, default='')
tieba_id = Column(String, default='')
tieba_name = Column(String)
tieba_link = Column(String)
publish_time = Column(String, index=True)
ip_location = Column(String, default='')
user_link = Column(Text, default='')
user_nickname = Column(Text, default='')
user_avatar = Column(Text, default='')
tieba_id = Column(String(255), default='')
tieba_name = Column(Text)
tieba_link = Column(Text)
publish_time = Column(BigInteger, index=True)
ip_location = Column(Text, default='')
sub_comment_count = Column(Integer, default=0)
note_id = Column(String, index=True)
note_url = Column(String)
note_id = Column(BigInteger, index=True)
note_url = Column(Text)
add_ts = Column(BigInteger)
last_modify_ts = Column(BigInteger)
class TiebaCreator(Base):
__tablename__ = 'tieba_creator'
id = Column(Integer, primary_key=True)
user_id = Column(String)
user_name = Column(String)
nickname = Column(String)
avatar = Column(String)
ip_location = Column(String)
user_id = Column(String(255))
user_name = Column(Text)
nickname = Column(Text)
avatar = Column(Text)
ip_location = Column(Text)
add_ts = Column(BigInteger)
last_modify_ts = Column(BigInteger)
gender = Column(String)
follows = Column(String)
fans = Column(String)
registration_duration = Column(String)
gender = Column(Text)
follows = Column(Text)
fans = Column(Text)
registration_duration = Column(Text)
class ZhihuContent(Base):
__tablename__ = 'zhihu_content'
id = Column(Integer, primary_key=True)
content_id = Column(String, index=True)
content_type = Column(String)
content_id = Column(BigInteger, index=True)
content_type = Column(Text)
content_text = Column(Text)
content_url = Column(String)
question_id = Column(String)
title = Column(String)
content_url = Column(Text)
question_id = Column(String(255))
title = Column(Text)
desc = Column(Text)
created_time = Column(String, index=True)
updated_time = Column(String)
created_time = Column(BigInteger, index=True)
updated_time = Column(Text)
voteup_count = Column(Integer, default=0)
comment_count = Column(Integer, default=0)
source_keyword = Column(String)
user_id = Column(String)
user_link = Column(String)
user_nickname = Column(String)
user_avatar = Column(String)
user_url_token = Column(String)
source_keyword = Column(Text)
user_id = Column(String(255))
user_link = Column(Text)
user_nickname = Column(Text)
user_avatar = Column(Text)
user_url_token = Column(Text)
add_ts = Column(BigInteger)
last_modify_ts = Column(BigInteger)
@@ -395,33 +395,33 @@ class ZhihuContent(Base):
class ZhihuComment(Base):
__tablename__ = 'zhihu_comment'
id = Column(Integer, primary_key=True)
comment_id = Column(String, index=True)
parent_comment_id = Column(String)
comment_id = Column(BigInteger, index=True)
parent_comment_id = Column(String(255))
content = Column(Text)
publish_time = Column(String, index=True)
ip_location = Column(String)
publish_time = Column(BigInteger, index=True)
ip_location = Column(Text)
sub_comment_count = Column(Integer, default=0)
like_count = Column(Integer, default=0)
dislike_count = Column(Integer, default=0)
content_id = Column(String, index=True)
content_type = Column(String)
user_id = Column(String)
user_link = Column(String)
user_nickname = Column(String)
user_avatar = Column(String)
content_id = Column(BigInteger, index=True)
content_type = Column(Text)
user_id = Column(String(255))
user_link = Column(Text)
user_nickname = Column(Text)
user_avatar = Column(Text)
add_ts = Column(BigInteger)
last_modify_ts = Column(BigInteger)
class ZhihuCreator(Base):
__tablename__ = 'zhihu_creator'
id = Column(Integer, primary_key=True)
user_id = Column(String, unique=True, index=True)
user_link = Column(String)
user_nickname = Column(String)
user_avatar = Column(String)
url_token = Column(String)
gender = Column(String)
ip_location = Column(String)
user_id = Column(Integer, unique=True, index=True)
user_link = Column(Text)
user_nickname = Column(Text)
user_avatar = Column(Text)
url_token = Column(Text)
gender = Column(Text)
ip_location = Column(Text)
follows = Column(Integer, default=0)
fans = Column(Integer, default=0)
anwser_count = Column(Integer, default=0)

Binary file not shown.