mirror of
https://github.com/NanmiCoder/MediaCrawler.git
synced 2025-11-25 19:37:36 +08:00
be306c6f54
- 删除旧的async_db.py和async_sqlite_db.py实现 - 新增SQLAlchemy ORM模型和数据库会话管理 - 统一各平台存储实现到_store_impl.py文件 - 添加数据库初始化功能支持 - 更新.gitignore和pyproject.toml依赖配置 - 优化文件存储路径和命名规范
89 lines
2.5 KiB
Python
89 lines
2.5 KiB
Python
# 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。
|
|
|
|
|
|
import asyncio
|
|
import sys
|
|
from typing import Optional
|
|
|
|
import cmd_arg
|
|
import config
|
|
import db
|
|
from base.base_crawler import AbstractCrawler
|
|
from media_platform.bilibili import BilibiliCrawler
|
|
from media_platform.douyin import DouYinCrawler
|
|
from media_platform.kuaishou import KuaishouCrawler
|
|
from media_platform.tieba import TieBaCrawler
|
|
from media_platform.weibo import WeiboCrawler
|
|
from media_platform.xhs import XiaoHongShuCrawler
|
|
from media_platform.zhihu import ZhihuCrawler
|
|
|
|
|
|
class CrawlerFactory:
|
|
CRAWLERS = {
|
|
"xhs": XiaoHongShuCrawler,
|
|
"dy": DouYinCrawler,
|
|
"ks": KuaishouCrawler,
|
|
"bili": BilibiliCrawler,
|
|
"wb": WeiboCrawler,
|
|
"tieba": TieBaCrawler,
|
|
"zhihu": ZhihuCrawler,
|
|
}
|
|
|
|
@staticmethod
|
|
def create_crawler(platform: str) -> AbstractCrawler:
|
|
crawler_class = CrawlerFactory.CRAWLERS.get(platform)
|
|
if not crawler_class:
|
|
raise ValueError(
|
|
"Invalid Media Platform Currently only supported xhs or dy or ks or bili ..."
|
|
)
|
|
return crawler_class()
|
|
|
|
|
|
crawler: Optional[AbstractCrawler] = None
|
|
|
|
|
|
# persist-1<persist1@126.com>
|
|
# 原因：增加 --init-db 功能，用于数据库初始化。
|
|
# 副作用：无
|
|
# 回滚策略：还原此文件。
|
|
async def main():
|
|
# Init crawler
|
|
global crawler
|
|
|
|
# parse cmd
|
|
args = await cmd_arg.parse_cmd()
|
|
|
|
# init db
|
|
if args.init_db:
|
|
await db.init_db(args.init_db)
|
|
print(f"Database {args.init_db} initialized successfully.")
|
|
return # Exit the main function cleanly
|
|
|
|
|
|
|
|
crawler = CrawlerFactory.create_crawler(platform=config.PLATFORM)
|
|
await crawler.start()
|
|
|
|
|
|
def cleanup():
|
|
if crawler:
|
|
# asyncio.run(crawler.close())
|
|
pass
|
|
if config.SAVE_DATA_OPTION in ["db", "sqlite"]:
|
|
asyncio.run(db.close())
|
|
|
|
|
|
if __name__ == "__main__":
|
|
try:
|
|
asyncio.get_event_loop().run_until_complete(main())
|
|
finally:
|
|
cleanup()
|