1 Star 0 Fork 1

wallacelee/MediaCrawler

forked from sunkai/MediaCrawler 
加入 Gitee
与超过 1200万 开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)
免费加入
文件
克隆/下载
main.py 1.40 KB
一键复制 编辑 原始数据 按行查看 历史
NanmiCoder 提交于 2024-08-05 18:51 . feat: 百度贴吧架子 & 登录done
import asyncio
import sys
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
class CrawlerFactory:
CRAWLERS = {
"xhs": XiaoHongShuCrawler,
"dy": DouYinCrawler,
"ks": KuaishouCrawler,
"bili": BilibiliCrawler,
"wb": WeiboCrawler,
"tieba": TieBaCrawler
}
@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()
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()
if config.SAVE_DATA_OPTION == "db":
await db.close()
if __name__ == '__main__':
try:
# asyncio.run(main())
asyncio.get_event_loop().run_until_complete(main())
except KeyboardInterrupt:
sys.exit()
Loading...
马建仓 AI 助手
尝试更多
代码解读
代码找茬
代码优化
1
https://gitee.com/wallacelee/MediaCrawler.git
git@gitee.com:wallacelee/MediaCrawler.git
wallacelee
MediaCrawler
MediaCrawler
main

搜索帮助