Add Support the other website

core/management/commands/crawl_rmrb.py

@@ -4,23 +4,62 @@ from core.utils import full_site_crawler
 
 
 class Command(BaseCommand):
-    help = "全站递归爬取 人民日报 https://www.peopleapp.com"
+    help = "全站递归爬取 人民日报及其子网站、客户端、新媒体平台"
 
-    def handle(self, *args, **kwargs):
-        website, created = Website.objects.get_or_create(
-            name="人民日报",
-            defaults={
-                'article_list_url': 'https://www.peopleapp.com/home',
-                'article_selector': 'a',
-                'base_url': 'https://www.peopleapp.com'
+    def add_arguments(self, parser):
+        parser.add_argument('--platform', type=str, default='all', 
+                          choices=['peopleapp', 'people', 'paper', 'all'],
+                          help='选择爬取平台: peopleapp(客户端), people(人民网), paper(报纸), all(全部)')
+
+    def handle(self, *args, **options):
+        platform = options['platform']
+        
+        # 人民日报各平台配置
+        platforms = {
+            'peopleapp': {
+                'name': '人民日报客户端',
+                'base_url': 'https://www.peopleapp.com',
+                'start_url': 'https://www.peopleapp.com/home',
+                'article_selector': 'a'
+            },
+            'people': {
+                'name': '人民网',
+                'base_url': 'https://www.people.com.cn',
+                'start_url': 'https://www.people.com.cn',
+                'article_selector': 'a'
+            },
+            'paper': {
+                'name': '人民日报报纸',
+                'base_url': 'http://paper.people.com.cn',
+                'start_url': 'http://paper.people.com.cn',
+                'article_selector': 'a'
             }
-        )
-        # 确保更新已存在的网站对象的base_url
-        if not created and not website.base_url:
-            website.base_url = 'https://www.peopleapp.com'
-            website.save()
+        }
+        
+        if platform == 'all':
+            target_platforms = platforms.values()
+        else:
+            target_platforms = [platforms[platform]]
+        
+        for platform_config in target_platforms:
+            website, created = Website.objects.get_or_create(
+                name=platform_config['name'],
+                defaults={
+                    'base_url': platform_config['base_url'],
+                    'article_list_url': platform_config['start_url'],
+                    'article_selector': platform_config['article_selector']
+                }
+            )
             
-        start_url = "https://www.peopleapp.com/home"
-        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")
+            # 确保更新已存在的网站对象的配置
+            if not created:
+                website.base_url = platform_config['base_url']
+                website.article_list_url = platform_config['start_url']
+                website.article_selector = platform_config['article_selector']
+                website.save()
+            
+            self.stdout.write(f"开始爬取: {platform_config['name']} - {platform_config['start_url']}")
+            full_site_crawler(platform_config['start_url'], website, max_pages=500)
+            self.stdout.write(f"完成爬取: {platform_config['name']}")
+        
+        self.stdout.write(self.style.SUCCESS("人民日报所有平台爬取完成"))