Update article_generator.py

article_generator.py

@@ -201,6 +201,30 @@ def process_heading(agent, h2_text, h3_for_this_h2, cached_responses):
     else:
         return (query, "No cached response found for this heading.")
 
+# IDとセクションを付与する関数
+def assign_ids_and_group_sections(html_content):
+    soup = BeautifulSoup(html_content, 'html.parser')
+    h2_elements = soup.find_all('h2')
+    section_id = 1
+    
+    for h2 in h2_elements:
+        section_div = soup.new_tag('div', **{'class': 'section', 'id': f'section-{section_id}'})
+        h2['id'] = f'h2-{section_id}'
+        section_div.append(h2.extract())
+
+        next_tag = h2.next_sibling
+        while next_tag and (next_tag.name != 'h2'):
+            if next_tag.name == 'h3':
+                h3_id = f'h3-{section_id}-{next_tag.get_text().split()[0]}'
+                next_tag['id'] = h3_id
+                section_div.append(next_tag.extract())
+            next_tag = next_tag.next_sibling
+
+        h2.insert_before(section_div)
+        section_id += 1
+
+    return str(soup)
+
 # 記事を生成する関数
 def generate_article(editable_output2):
     print("Starting article generation...")
@@ -311,8 +335,11 @@ def generate_article(editable_output2):
     print("Final generated article content:")  # 最終的な記事全体の内容を出力
     print(final_result)
 
+    # 生成された一時的な記事にIDとグループ化を付与
+    grouped_html = assign_ids_and_group_sections(final_result)
+
     # 重複を排除
-    final_result = remove_duplicates(final_result.split('\n'))
+    final_result = remove_duplicates(grouped_html.split('\n'))
 
     # 生成された初期記事を拡張
     h3_to_text = expand_section_with_gpt4(final_result, h3_texts, cached_responses)