xinhua_base

core/management/commands/crawl_xinhua.py

@@ -0,0 +1,23 @@
+from django.core.management.base import BaseCommand
+from core.models import Website
+from core.utils import crawl_xinhua_article
+
+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)
+        except Website.DoesNotExist:
+            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",
+        ]
+
+        for url in urls:
+            crawl_xinhua_article(url, website)