MediaCrawler/main.py

55 lines
1.4 KiB
Python
Raw Normal View History

2023-07-29 07:35:40 +00:00
import asyncio
import sys
import cmd_arg
import config
2023-07-29 07:35:40 +00:00
import db
2023-12-02 16:30:10 +00:00
from base.base_crawler import AbstractCrawler
from media_platform.bilibili import BilibiliCrawler
from media_platform.douyin import DouYinCrawler
from media_platform.kuaishou import KuaishouCrawler
2024-08-05 10:51:51 +00:00
from media_platform.tieba import TieBaCrawler
2023-12-24 09:57:48 +00:00
from media_platform.weibo import WeiboCrawler
from media_platform.xhs import XiaoHongShuCrawler
class CrawlerFactory:
2023-12-02 16:30:10 +00:00
CRAWLERS = {
"xhs": XiaoHongShuCrawler,
"dy": DouYinCrawler,
"ks": KuaishouCrawler,
2023-12-24 09:57:48 +00:00
"bili": BilibiliCrawler,
2024-08-05 10:51:51 +00:00
"wb": WeiboCrawler,
"tieba": TieBaCrawler
2023-12-02 16:30:10 +00:00
}
@staticmethod
2023-12-02 16:30:10 +00:00
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()
2024-08-05 10:51:51 +00:00
async def main():
# parse cmd
await cmd_arg.parse_cmd()
# init db
if config.SAVE_DATA_OPTION == "db":
await db.init_db()
crawler = CrawlerFactory.create_crawler(platform=config.PLATFORM)
await crawler.start()
2024-08-05 10:51:51 +00:00
if config.SAVE_DATA_OPTION == "db":
await db.close()
if __name__ == '__main__':
try:
2023-07-29 07:35:40 +00:00
# asyncio.run(main())
asyncio.get_event_loop().run_until_complete(main())
except KeyboardInterrupt:
sys.exit()