人民日报增加域

schoolNewsCrawler/crawler/rmrb/RmrbCrawler.py

@@ -6,7 +6,7 @@ from loguru import logger
 import re
 import chardet
 from datetime import datetime, timedelta
-from bs4.element import NavigableString
+from bs4.element import NavigableString, Tag
 from urllib.parse import urlparse
 import json
 
@@ -70,6 +70,7 @@ class RmrbCrawler(BaseCrawler):
             "politics": self.parse_base_news_detail,
             "finance": self.parse_base_news_detail,
             "cpc": self.parse_cpc_news_detail,
+            "theory": self.parse_cpc_news_detail,
         }
     
     def search(self, key: str, total: int, news_type: int = 0) -> ResultDomain:
@@ -518,13 +519,11 @@ class RmrbCrawler(BaseCrawler):
 
             # 遍历 show_text 下的所有直接子节点（保持顺序）
             for child in content_div.children:
-                # 跳过纯文本节点（如换行、空格）
-                if isinstance(child, NavigableString):
+                # 只处理 Tag 类型的节点，跳过文本节点、注释等
+                if not isinstance(child, Tag):
                     continue
-
+                
                 tag_name = child.name
-                if tag_name is None:
-                    continue
 
                 # 情况1：检测是否是视频容器（根据 id 特征或内部结构）
                 video_tag = child.find('video') if tag_name != 'video' else child
@@ -578,7 +577,7 @@ class RmrbCrawler(BaseCrawler):
                         continue
 
                     # 情况2：检查是否包含人民网的 showPlayer 脚本（动态视频）
-                    script_tags = child.find_all('script', string=True)
+                    script_tags = child.find_all('script')
                     video_src = None
                     poster_url = None