刷新今日的新闻数据

product/playwright-get-data.py

@@ -8,6 +8,7 @@ import asyncio
 from playwright.async_api import async_playwright
 from loguru import logger
 import sys
+from datetime import datetime
 
 # 配置日志
 logger.remove()
@@ -120,33 +121,74 @@ class ProductHuntScraper:
         try:
             product_info = {}
             
-            # 提取产品名称
+            # 提取产品名称（h1标签）
             name_element = await self.page.query_selector("h1")
             if name_element:
-                product_info["name"] = await name_element.text_content()
+                product_info["name"] = (await name_element.text_content()).strip()
                 logger.info(f"产品名称: {product_info['name']}")
             
-            # 提取产品描述
+            # 提取产品简介（class为"relative text-16 font-normal text-gray-700"的div）
-            desc_element = await self.page.query_selector("[data-testid='product-description']")
+            logger.info("正在提取产品简介...")
-            if not desc_element:
+            try:
-                desc_element = await self.page.query_selector(".styles_description__")
+                intro_div = await self.page.query_selector('div.relative.text-16.font-normal.text-gray-700')
+                if intro_div:
+                    product_info["introduction"] = (await intro_div.text_content()).strip()
+                    logger.info(f"产品简介: {product_info['introduction'][:200]}...")
+                else:
+                    logger.warning("未找到class为'relative text-16 font-normal text-gray-700'的div")
+            except Exception as e:
+                logger.error(f"提取产品简介失败: {e}")
             
-            if desc_element:
+            # 等待制作人发言动态加载（等待class="flex flex-col gap-2"的section标签出现）
-                product_info["description"] = await desc_element.text_content()
+            logger.info("等待制作人发言动态加载...")
-                logger.info(f"产品描述: {product_info['description'][:100]}...")
+            try:
+                # 等待section标签出现，最长等待60秒
+                section_element = await self.page.wait_for_selector(
+                    'section.flex.flex-col.gap-2', 
+                    timeout=60000
+                )
+                if section_element:
+                    logger.success("制作人发言区域已加载")
+                    
+                    # 提取制作人发言（class为"flex flex-col gap-1"的div里面的span标签）
+                    maker_div = await section_element.query_selector('div.flex.flex-col.gap-1')
+                    if maker_div:
+                        span_element = await maker_div.query_selector('span')
+                        if span_element:
+                            product_info["maker_statement"] = (await span_element.text_content()).strip()
+                            logger.info(f"制作人发言: {product_info['maker_statement'][:200]}...")
+                        else:
+                            logger.warning("在div中未找到span标签")
+                    else:
+                        logger.warning("未找到class为'flex flex-col gap-1'的div")
+                else:
+                    logger.warning("制作人发言区域未加载")
+            except Exception as e:
+                logger.error(f"等待制作人发言加载失败: {e}")
             
-            # 提取投票数
+            # 提取用户数（class="text-14 font-medium text-gray-700"的p标签）
-            votes_element = await self.page.query_selector("[data-testid='vote-button']")
+            logger.info("正在提取用户数...")
-            if votes_element:
+            try:
-                votes_text = await votes_element.text_content()
+                user_count_element = await self.page.query_selector('p.text-14.font-medium.text-gray-700')
-                product_info["votes"] = votes_text
+                if user_count_element:
-                logger.info(f"投票数: {votes_text}")
+                    product_info["user_count"] = (await user_count_element.text_content()).strip()
+                    logger.info(f"用户数: {product_info['user_count']}")
+                else:
+                    logger.warning("未找到class为'text-14 font-medium text-gray-700'的p标签")
+            except Exception as e:
+                logger.error(f"提取用户数失败: {e}")
             
-            # 提取产品链接
+            # 保存到临时文件
-            website_element = await self.page.query_selector("a[href*='://']")
+            temp_file_path = "temp_product_info.txt"
-            if website_element:
+            with open(temp_file_path, "w", encoding="utf-8") as f:
-                product_info["website"] = await website_element.get_attribute("href")
+                f.write("=== Product Hunt 产品信息 ===\n\n")
-                logger.info(f"产品网站: {product_info['website']}")
+                f.write(f"产品名称: {product_info.get('name', '未获取')}\n\n")
+                f.write(f"产品简介: {product_info.get('introduction', '未获取')}\n\n")
+                f.write(f"制作人发言: {product_info.get('maker_statement', '未获取')}\n\n")
+                f.write(f"用户数: {product_info.get('user_count', '未获取')}\n\n")
+                f.write(f"提取时间: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}\n")
+            
+            logger.info(f"产品信息已保存到临时文件: {temp_file_path}")
             
             # 截取页面截图
             screenshot_path = "product_screenshot.png"

temp_product_info.txt

@@ -0,0 +1,9 @@
+=== Product Hunt 产品信息 ===
+
+产品名称: Notion
+
+产品简介: Notion is an all-in-one workspace that combines note-taking, project management, and task organization. It allows users to create customized databases, documents, and calendars to streamline their personal and professional workflows.
+
+制作人发言: 未获取
+
+提取时间: 2025-11-17 22:51:58