From 09188b8765b67f31007a19485453b22cf13b7cc9 Mon Sep 17 00:00:00 2001
From: yuyx <237899745@qq.com>
Date: Wed, 14 Jan 2026 13:14:22 +0800
Subject: [PATCH] =?UTF-8?q?fix:=20=E9=98=B2=E6=AD=A2=E6=B5=8F=E8=A7=88?=
 =?UTF-8?q?=E6=97=B6=E6=97=A0=E9=99=90=E5=BE=AA=E7=8E=AF=E9=87=8D=E5=A4=8D?=
 =?UTF-8?q?=E5=A4=84=E7=90=86=E5=B7=B2=E5=A4=84=E7=90=86=E6=96=87=E7=AB=A0?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

- 添加 processed_hrefs 集合跟踪已处理的文章 href
- 处理文章前检查是否已处理过，避免重复处理
- 添加 new_articles_in_page 计数器，当前页无新文章时退出循环
- 解决 mark_read 未立即生效导致的无限循环问题

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---
 api_browser.py | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/api_browser.py b/api_browser.py
index 5eacf23..de96912 100755
--- a/api_browser.py
+++ b/api_browser.py
@@ -475,6 +475,7 @@ class APIBrowser:
             # 这样可以避免分页错位问题（标记已读后文章从列表消失导致后续页面上移）
             max_iterations = total_records + 10  # 防止无限循环
             iteration = 0
+            processed_hrefs = set()  # 跟踪已处理的文章，防止重复处理
 
             while articles and iteration < max_iterations:
                 iteration += 1
@@ -483,14 +484,24 @@ class APIBrowser:
                     self.log("[API] 收到停止信号")
                     break
 
+                new_articles_in_page = 0  # 本次迭代中新处理的文章数
+
                 for article in articles:
                     if should_stop_callback and should_stop_callback():
                         break
 
+                    article_href = article['href']
+                    # 跳过已处理的文章
+                    if article_href in processed_hrefs:
+                        continue
+
+                    processed_hrefs.add(article_href)
+                    new_articles_in_page += 1
                     title = article['title'][:30]
+
                     # 获取附件（文章详情页）
                     try:
-                        attachments = self.get_article_attachments(article['href'])
+                        attachments = self.get_article_attachments(article_href)
                         consecutive_failures = 0
                     except Exception as e:
                         skipped_items += 1
@@ -514,6 +525,11 @@ class APIBrowser:
 
                     time.sleep(0.1)
 
+                # 如果当前页没有新文章被处理，说明所有文章都已处理过，退出循环
+                if new_articles_in_page == 0:
+                    self.log(f"[API] 当前页所有文章均已处理，结束循环")
+                    break
+
                 time.sleep(0.2)
 
                 # 重新获取第1页，检查是否还有未处理的内容