feat: 小红书笔记搜索,评论获取done

docs: update docs

Create .gitattributes

Update README.md
This commit is contained in:
NanmiCoder
2023-06-09 20:41:53 +08:00
committed by Relakkes
parent bca6a27717
commit e82dcae02f
20 changed files with 1548 additions and 0 deletions

37
main.py Normal file
View File

@@ -0,0 +1,37 @@
import sys
import asyncio
import argparse
from media_platform.douyin import DouYinCrawler
from media_platform.xhs import XiaoHongShuCrawler
class CrawlerFactory:
@staticmethod
def create_crawler(platform: str):
if platform == "xhs":
return XiaoHongShuCrawler()
elif platform == "dy":
return DouYinCrawler()
else:
raise ValueError("Invalid Media Platform Currently only supported xhs or douyin ...")
async def main():
# define command line params ...
parser = argparse.ArgumentParser(description='Media crawler program.')
parser.add_argument('--platform', type=str, help='Media platform select (xhs|dy)...', default="xhs")
parser.add_argument('--keywords', type=str, help='Search note/page keywords...', default="健身")
args = parser.parse_args()
crawler = CrawlerFactory().create_crawler(platform=args.platform)
crawler.init_config(
keywords=args.keywords,
)
await crawler.start()
if __name__ == '__main__':
try:
asyncio.run(main())
except KeyboardInterrupt:
sys.exit()