MediaCrawler/main.py

71 lines
2.4 KiB
Python
Raw Normal View History

import argparse
2023-07-29 07:35:40 +00:00
import asyncio
import sys
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
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,
"wb": WeiboCrawler
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()
async def main():
# define command line params ...
parser = argparse.ArgumentParser(description='Media crawler program.')
2023-12-24 09:57:48 +00:00
parser.add_argument('--platform', type=str, help='Media platform select (xhs | dy | ks | bili | wb)',
choices=["xhs", "dy", "ks", "bili", "wb"], default=config.PLATFORM)
2023-07-29 07:35:40 +00:00
parser.add_argument('--lt', type=str, help='Login type (qrcode | phone | cookie)',
choices=["qrcode", "phone", "cookie"], default=config.LOGIN_TYPE)
parser.add_argument('--type', type=str, help='crawler type (search | detail | creator)',
choices=["search", "detail", "creator"], default=config.CRAWLER_TYPE)
parser.add_argument('--start', type=int, help='crawler type (number of start page)',
default=config.START_PAGE)
2024-04-13 05:48:29 +00:00
parser.add_argument('--keywords', type=str, help='crawler type (please input keywords)',
default=config.KEYWORDS)
# init db
if config.SAVE_DATA_OPTION == "db":
await db.init_db()
args = parser.parse_args()
2023-07-29 07:35:40 +00:00
crawler = CrawlerFactory.create_crawler(platform=args.platform)
crawler.init_config(
2023-07-29 07:35:40 +00:00
platform=args.platform,
login_type=args.lt,
crawler_type=args.type,
start_page=args.start,
2024-04-13 05:48:29 +00:00
keyword=args.keywords
)
await crawler.start()
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()