调整获取的逻辑，兼容部分有标题的新闻

plugins/global_news/news_crawler.py

@@ -186,13 +186,14 @@ def abc():
                     continue
 
                 html = etree.HTML(response.text)
-                title = html.xpath('//div[@data-testid="prism-headline"]/h1/text()')
+                # 修改 xpath 以支持新的标题结构
+                title = html.xpath('//div[@data-testid="prism-headline"]/h1/text() | //div[@data-testid="prism-headline"]//span/text()')
 
                 if not title:
                     logger.warning(f'跳过视频或其他类型新闻: {full_url}')
                     continue
 
-                title = title[0]
+                title = title[0].strip()
                 msg += f'Title: {title}. Link: {full_url}\n'
                 count += 1
                 sleep(0.1)
@@ -234,13 +235,14 @@ def fox():
                     continue
 
                 html = etree.HTML(response.text)
-                title = html.xpath('//h1[@itemprop="headline"]/text()')
+                # 修改 xpath 以支持更多标题结构
+                title = html.xpath('//h1[@itemprop="headline"]/text() | //h1[@class="headline speakable"]/text() | //h1[@class="headline"]/text()')
 
                 if not title:
                     logger.warning(f'跳过视频或其他类型新闻: {url}')
                     continue
 
-                title = title[0]
+                title = title[0].strip()
                 msg += f'Title: {title}. Link: {url}\n'
                 count += 1
                 sleep(0.1)
@@ -304,4 +306,7 @@ def bbc():
 
     except Exception as e:
         logger.error(f"获取BBC新闻失败: {str(e)}")
-        return "获取新闻失败，请查看日志了解详情"
+        return "获取新闻失败，请查看日志了解详情"
+
+if __name__ == '__main__':
+    fox()