Files
green_classroom/core/management/commands/crawl_dongfangyancao.py
2025-08-11 22:20:19 +08:00

21 lines
756 B
Python

# core/management/commands/crawl_dongfangyancao.py
from django.core.management.base import BaseCommand
from core.models import Website
from core.utils import full_site_crawler
class Command(BaseCommand):
help = "全站递归爬取 东方烟草报"
def handle(self, *args, **kwargs):
website, created = Website.objects.get_or_create(
name="东方烟草报",
defaults={
'article_list_url': 'https://www.eastobacco.com/',
'article_selector': 'a'
}
)
start_url = "https://www.eastobacco.com/"
self.stdout.write(f"开始全站爬取: {start_url}")
full_site_crawler(start_url, website, max_pages=500)
self.stdout.write("爬取完成")