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

@@ -0,0 +1,68 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+
+# Logs
+*.log
+integrated_product_system.log
+
+# Databases
+*.db
+*.sqlite
+
+# IDE
+.trae/
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Test files
+*test*.py
+*Test*.py
+pytest_cache/
+.tox/
+.coverage
+coverage.xml
+
+# Temporary files
+*.tmp
+*.temp
+temp*.txt
+*.bak
+*.swp
+*.swo
+*~
+temp_*.txt
+
+# Bug and debug files
+*debug*.png
+*bug*.txt
+
+# Batch files
+*.bat
+
+# Output files
+*.out
+*.output
+
+# Environment
+.env
+.env.local
+.env.*.local
+
+# Documentation build
+_build/
+build/
+dist/
+*.egg-info/
+
+# Other
+2025年12月*.txt
+*.png

temp_product_info.txt

@@ -1,13 +1,11 @@
 === Product Hunt 产品信息 ===
 
-产品名称: Croct
+产品名称: Greta
 
-产品简介: Croct is a conversion optimization platform that includes AI-powered audience segmentation, content personalization, AB testing, feature flag, real-time website analytics, and a component-based CMS for modern frameworks like Next.js and React.
+产品简介: 未获取
 
-It helps product and growth teams scale UI and website optimization, enabling faster growth without over-relying on developers.
+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...
 
-制作人发言: AI-powered website segmentation
+用户数: 664 followers
 
-用户数: 619 followers
+提取时间: 2026-03-08 20:40:13
-
-提取时间: 2025-12-17 18:36:11

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()