chore: 更新二进制数据库文件 tophub_data.db

更新 temp_product_info.txt 文件中的产品名称、制作人发言和用户数等信息，反映最新的产品数据

.gitignore

@@ -34,7 +34,7 @@ coverage.xml
 # Temporary files
 *.tmp
 *.temp
-temp*.*
+temp*.txt
 *.bak
 *.swp
 *.swo

temp_product_info.txt

@@ -1,11 +1,11 @@
 === Product Hunt 产品信息 ===
 
-产品名称: Mujo AI
+产品名称: Greta
 
-产品简介: Generate ecom product images and copy in minutes. The AI design agent thinks, recommends, and builds tailored visuals and text for you. Fully editable, personalized, and ready to boost sales. It's a conversion-focused system built around ecom best practices.
+产品简介: 未获取
 
-制作人发言: 
+制作人发言: This is first first proposed project. If you want to support Santiago getting his project built, here are the details.https://onemillionlines.com/proj...
 
-用户数: 369 followers
+用户数: 664 followers
 
-提取时间: 2025-12-19 19:02:18
+提取时间: 2026-03-08 20:40:13

tophub_add_data_to_db.py

@@ -205,9 +205,13 @@ def process_temp_files():
             continue
         
         # 处理每篇文章
-        for article in tqdm(articles, desc=f"处理 {file_path}"):
+        for i, article in tqdm(enumerate(articles), desc=f"处理 {file_path}", total=len(articles)):
             total_processed += 1
             
+            # 每处理10篇文章记录一次进度
+            if i % 10 == 0 and i > 0:
+                logger.info(f"已处理 {i}/{len(articles)} 篇文章，完成 {i/len(articles)*100:.1f}%")
+            
             # 检查重复
             if check_duplicate(article['title'], source_date):
                 logger.info(f"跳过重复文章(最近三天已存在): {article['title']}")

tophub_scraper.py

@@ -262,7 +262,7 @@ class TopHubScraper:
             
             # 实时读取输出以避免编码问题
             try:
-                stdout, stderr = process.communicate(timeout=300)  # 5分钟超时
+                stdout, stderr = process.communicate(timeout=3600)  # 1小时超时
             except subprocess.TimeoutExpired:
                 process.kill()
                 logger.error("tophub_add_data_to_db.py执行超时")
@@ -287,6 +287,8 @@ class TopHubScraper:
             
 if __name__ == "__main__":
     scraper = TopHubScraper()
+
+    
     try:
         # 抓取数据
         scraped_data = scraper.scrape_by_node_ids()