From d23d526629559b6f97d6e65f3c233fcf154f28ff Mon Sep 17 00:00:00 2001
From: hz4th_coder <hz4th_coder@tphai.com>
Date: Mon, 13 Jul 2026 23:51:23 +0800
Subject: [PATCH] =?UTF-8?q?=E4=BF=AE=E5=A4=8D=E6=90=9C=E7=B4=A2=E5=92=8C?=
 =?UTF-8?q?=E9=87=8D=E5=A4=8D=E6=A3=80=E6=9F=A5=E9=97=AE=E9=A2=98?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

1. 搜索文章时增加URL字段搜索，解决重复抓取问题
2. 优化搜索结果解析，多获取几个结果确保返回足够数量
---
 models/database.py         |  8 ++++----
 services/search_service.py | 13 +++++++++----
 2 files changed, 13 insertions(+), 8 deletions(-)

diff --git a/models/database.py b/models/database.py
index 38ce08b..89cb3a0 100644
--- a/models/database.py
+++ b/models/database.py
@@ -157,16 +157,16 @@ class Database:
             if category:
                 cursor.execute('''
                     SELECT * FROM articles 
-                    WHERE (product_names LIKE ? OR keywords LIKE ? OR summary LIKE ? OR content LIKE ?)
+                    WHERE (product_names LIKE ? OR keywords LIKE ? OR summary LIKE ? OR content LIKE ? OR url LIKE ?)
                     AND category = ?
                     ORDER BY fetch_date DESC
-                ''', (f'%{keyword}%', f'%{keyword}%', f'%{keyword}%', f'%{keyword}%', category))
+                ''', (f'%{keyword}%', f'%{keyword}%', f'%{keyword}%', f'%{keyword}%', f'%{keyword}%', category))
             else:
                 cursor.execute('''
                     SELECT * FROM articles 
-                    WHERE product_names LIKE ? OR keywords LIKE ? OR summary LIKE ? OR content LIKE ?
+                    WHERE product_names LIKE ? OR keywords LIKE ? OR summary LIKE ? OR content LIKE ? OR url LIKE ?
                     ORDER BY fetch_date DESC
-                ''', (f'%{keyword}%', f'%{keyword}%', f'%{keyword}%', f'%{keyword}%'))
+                ''', (f'%{keyword}%', f'%{keyword}%', f'%{keyword}%', f'%{keyword}%', f'%{keyword}%'))
             return [dict(row) for row in cursor.fetchall()]
     
     def get_article_by_id(self, article_id):
diff --git a/services/search_service.py b/services/search_service.py
index 6635cea..63c45eb 100644
--- a/services/search_service.py
+++ b/services/search_service.py
@@ -157,12 +157,17 @@ class SearchService:
                 if match:
                     title = match.group(1)
                     ref = match.group(2)
-                    # 放宽过滤条件：只要不是纯域名格式就保留
-                    if not (title.endswith('.com') or title.endswith('.cn') or title.endswith('.net')):
+                    # 过滤纯域名格式
+                    is_domain = (title.endswith('.com') or title.endswith('.cn') or 
+                                 title.endswith('.net') or title.endswith('.org') or
+                                 title.endswith('.edu') or title.endswith('.gov'))
+                    if not is_domain:
                         refs.append((title, ref))
         
-        # 获取每个结果的 URL
-        for title, ref in refs[:max_results]:
+        # 获取每个结果的 URL，多获取几个以防解析失败
+        for title, ref in refs[:max_results + 5]:
+            if len(results) >= max_results:
+                break
             url = self._get_link_url(ref)
             if url and 'bing.com/search' not in url:  # 过滤搜索结果页本身的链接
                 results.append({