Fix chinadaily bug : Support more packages

core/management/commands/crawl_china.py

@@ -3,6 +3,7 @@ from core.models import Website
 from core.utils import full_site_crawler
 
 
+# jimmy.fang-20250815: 因URL问题，移除中国网-省份
 class Command(BaseCommand):
     help = "全站递归爬取 中国网主网及中国网一省份，不转发二级子网站"
 
@@ -22,12 +23,12 @@ class Command(BaseCommand):
                 'start_url': 'http://www.china.com.cn',
                 'article_selector': 'a'
             },
-            'province': {
-                'name': '中国网一省份',
-                'base_url': 'http://www.china.com.cn',
-                'start_url': 'http://www.china.com.cn/province',
-                'article_selector': 'a'
-            }
+            # 'province': {
+            #     'name': '中国网一省份',
+            #     'base_url': 'http://www.china.com.cn',
+            #     'start_url': 'http://www.china.com.cn/province',
+            #     'article_selector': 'a'
+            # }
         }
 
         if platform == 'all':

core/management/commands/crawl_chinadaily.py

@@ -9,7 +9,7 @@ class Command(BaseCommand):
     def add_arguments(self, parser):
         parser.add_argument('--platform', type=str, default='all',
                             choices=['chinadaily', 'mobile', 'all'],
-                            help='选择爬取平台: chinadaily(中国日报), mobile(移动端), all(全部)')
+                            help='选择爬取平台: chinadaily(中国日报), all(全部)')
 
     def handle(self, *args, **options):
         platform = options['platform']
@@ -22,12 +22,7 @@ class Command(BaseCommand):
                 'start_url': 'https://www.chinadaily.com.cn',
                 'article_selector': 'a'
             },
-            'mobile': {
-                'name': '中国日报移动端',
-                'base_url': 'https://m.chinadaily.com.cn',
-                'start_url': 'https://m.chinadaily.com.cn',
-                'article_selector': 'a'
-            }
+
         }
 
         if platform == 'all':