Add Find weburl

core/management/commands/crawl_xinhua.py

@@ -1,21 +1,18 @@
 from django.core.management.base import BaseCommand
 from core.models import Website
-from core.utils import crawl_xinhua_article
+from core.utils import crawl_xinhua_list
 
 class Command(BaseCommand):
-    help = '爬取新华网文章示例'
+    help = '批量爬取新华网文章'
 
     def handle(self, *args, **options):
-        website_name = "新华网"
+        list_url = "https://www.news.cn/legal/index.html"
         try:
-            website = Website.objects.get(name=website_name)
+            website = Website.objects.get(base_url="https://www.news.cn/")
         except Website.DoesNotExist:
-            self.stdout.write(self.style.ERROR(f"网站 '{website_name}' 不存在，请先后台创建"))
+            self.stdout.write(self.style.ERROR("网站 https://www.news.cn/ 不存在，请先后台添加"))
             return
 
-        urls = [
-            "https://www.news.cn/legal/20250721/f340f7be3d5b4b938cbd6b9889b6fbdc/c.html",
-        ]
-
-        for url in urls:
-            crawl_xinhua_article(url, website)
+        self.stdout.write(f"开始爬取文章列表页: {list_url}")
+        crawl_xinhua_list(list_url, website)
+        self.stdout.write(self.style.SUCCESS("批量爬取完成"))