Add download media

2025-08-11 13:28:32 +08:00
parent 4e5e35b4fa
commit da1b8d98e4
4 changed files with 63 additions and 9 deletions
--- a/core/management/commands/init.py
+++ b/core/management/commands/init.py
--- a/core/management/commands/crawl_xinhua.py
+++ b/core/management/commands/crawl_xinhua.py
@@ -6,7 +6,6 @@ class Command(BaseCommand):
    help = '爬取新华网文章示例'

    def handle(self, *args, **options):
-        # 假设你事先在后台建了“新华网”这个Website实例
        website_name = "新华网"
        try:
            website = Website.objects.get(name=website_name)
@@ -14,7 +13,6 @@ class Command(BaseCommand):
            self.stdout.write(self.style.ERROR(f"网站 '{website_name}' 不存在，请先后台创建"))
            return

-        # 这里写你想爬取的文章URL列表，可以循环多篇
        urls = [
            "https://www.news.cn/legal/20250721/f340f7be3d5b4b938cbd6b9889b6fbdc/c.html",
        ]