fix(api): 超时按单条处理避免中途结束

api_browser.py

@@ -233,9 +233,11 @@ class APIBrowser:
         if not self.logged_in:
             return [], 0, None
 
-        try:
         if base_url and page > 1:
             url = re.sub(r'page=\d+', f'page={page}', base_url)
+        elif page > 1:
+            # 兼容兜底：若没有 next_url（极少数情况下页面不提供“下一页”链接），尝试直接拼 page 参数
+            url = f"{BASE_URL}/admin/center.aspx?bz={bz}&page={page}"
         else:
             url = f"{BASE_URL}/admin/center.aspx?bz={bz}"
 
@@ -290,13 +292,8 @@ class APIBrowser:
             self.last_total_records = 0
         return articles, total_pages, next_page_url
 
-        except Exception as e:
-            self.log(f"[API] 获取列表失败: {str(e)}")
-            return [], 0, None
-
     def get_article_attachments(self, article_href: str):
         """获取文章的附件列表"""
-        try:
         if not article_href.startswith('http'):
             url = f"{BASE_URL}/admin/{article_href}"
         else:
@@ -330,9 +327,6 @@ class APIBrowser:
 
         return attachments
 
-        except Exception as e:
-            return []
-
     def mark_read(self, attach_id: str, channel_id: str = '1') -> bool:
         """通过访问下载链接标记已读"""
         download_url = f"{BASE_URL}/tools/download.ashx?site=main&id={attach_id}&channel_id={channel_id}"
@@ -383,9 +377,19 @@ class APIBrowser:
             total_attachments = 0
             page = 1
             base_url = None
+            skipped_items = 0
+            skipped_pages = 0
+            consecutive_failures = 0
+            max_consecutive_failures = 3
 
             # 获取第一页
+            try:
                 articles, total_pages, next_url = self.get_article_list_page(bz, page)
+                consecutive_failures = 0
+            except Exception as e:
+                result.error_message = str(e)
+                self.log(f"[API] 获取第1页列表失败: {str(e)}")
+                return result
 
             if not articles:
                 self.log(f"[API] '{browse_type}' 没有待处理内容")
@@ -396,6 +400,8 @@ class APIBrowser:
 
             if next_url:
                 base_url = next_url
+            elif total_pages > 1:
+                base_url = f"{BASE_URL}/admin/center.aspx?bz={bz}&page=2"
 
             total_records = int(getattr(self, "last_total_records", 0) or 0)
             last_report_ts = 0.0
@@ -416,22 +422,51 @@ class APIBrowser:
             report_progress(force=True)
 
             # 处理所有页面
-            while True:
+            while page <= total_pages:
                 if should_stop_callback and should_stop_callback():
                     self.log("[API] 收到停止信号")
                     break
 
+                # page==1 已取过，后续页在这里获取
+                if page > 1:
+                    try:
+                        articles, _, next_url = self.get_article_list_page(bz, page, base_url)
+                        consecutive_failures = 0
+                        if next_url:
+                            base_url = next_url
+                    except Exception as e:
+                        skipped_pages += 1
+                        consecutive_failures += 1
+                        self.log(
+                            f"[API] 获取第{page}页列表失败，跳过本页（连续失败{consecutive_failures}/{max_consecutive_failures}）: {str(e)}"
+                        )
+                        if consecutive_failures >= max_consecutive_failures:
+                            raise
+                        page += 1
+                        continue
+
                 for article in articles:
                     if should_stop_callback and should_stop_callback():
                         break
 
                     title = article['title'][:30]
+                    # 获取附件（文章详情页）
+                    try:
+                        attachments = self.get_article_attachments(article['href'])
+                        consecutive_failures = 0
+                    except Exception as e:
+                        skipped_items += 1
+                        consecutive_failures += 1
+                        self.log(
+                            f"[API] 获取文章失败，跳过（连续失败{consecutive_failures}/{max_consecutive_failures}）: {title} | {str(e)}"
+                        )
+                        if consecutive_failures >= max_consecutive_failures:
+                            raise
+                        continue
+
                     total_items += 1
                     report_progress()
 
-                    # 获取附件
-                    attachments = self.get_article_attachments(article['href'])
-
                     if attachments:
                         for attach in attachments:
                             if self.mark_read(attach['id'], attach['channel_id']):
@@ -441,21 +476,15 @@ class APIBrowser:
 
                     time.sleep(0.1)
 
-                # 下一页
                 page += 1
-                if page > total_pages:
-                    break
-
-                articles, _, next_url = self.get_article_list_page(bz, page, base_url)
-                if not articles:
-                    break
-
-                if next_url:
-                    base_url = next_url
-
                 time.sleep(0.2)
 
             report_progress(force=True)
+            if skipped_items or skipped_pages:
+                self.log(
+                    f"[API] 浏览完成: {total_items} 条内容，{total_attachments} 个附件（跳过 {skipped_items} 条内容，{skipped_pages} 页列表）"
+                )
+            else:
                 self.log(f"[API] 浏览完成: {total_items} 条内容，{total_attachments} 个附件")
 
             result.success = True