arreglado cuestion de polemica

spiders/daily/cuestionDePolemica/cuestionDePolemica/spiders/noticias.py

@@ -42,43 +42,23 @@ class NoticiasSpider(scrapy.Spider):
 
         for post in data:
             try:
-                # Validar contenido
                 content = post.get('content', {}).get('rendered', '').strip()
-                if not remove_tags(content):
-                    self.logger.warning(f"Skipped post {post.get('id')}: No meaningful content.")
-                    continue
+                if content:
+                    class_list = post.get('class_list', {})
+                    topic = None
+                    if isinstance(class_list, dict):
+                        topic = class_list.get('7', '').split("category-")[1] if '7' in class_list else None
 
-                # Obtener categoría del artículo
-                class_list = post.get('class_list', {})
-                topic = None
-                if isinstance(class_list, dict):
-                    topic = class_list.get('7', '').split("category-")[1] if '7' in class_list else None
-
-                # Preparar item
-                item = CuestiondepolemicaItem()
-                item['date'] = post.get('date')
-                item['title'] = remove_tags(post.get('title', {}).get('rendered', ''))
-                item['text'] = remove_tags(content)
-                item['topic'] = topic
-                item['url'] = post.get('link')
-
-                # Enlace al autor
-                author_link = post.get('_links', {}).get('author', [{}])[0].get('href', None)
-                if author_link:
-                    yield scrapy.Request(url=author_link, callback=self.parse_author, meta={'item': item})
-                else:
-                    item['author'] = 'Unknown'
+                    # Preparar item
+                    item = CuestiondepolemicaItem()
+                    item['date'] = post.get('date')
+                    item['title'] = remove_tags(post.get('title', {}).get('rendered', ''))
+                    item['text'] = remove_tags(content)
+                    item['topic'] = topic
+                    item['url'] = post.get('link')
+                    print(item['title'])
                     yield item
             except Exception as e:
                 self.logger.error(f"Error processing post {post.get('id')}: {e}")
                 continue
-
-    def parse_author(self, response):
-        """Procesa la información del autor de un artículo."""
-        try:
-            item = response.meta['item']  # Recupera el item pasado a través de meta
-            author_data = json.loads(response.text)
-            item['author'] = author_data.get('name', 'Unknown')
-            yield item  # Devuelve el item completo con el nombre del autor incluido
-        except Exception as e:
-            self.logger.error(f"Failed to parse author data: {e}")
+