BrunoGaoandClaude
4da23af857
- Add RSS news crawler with 5 international medical tech news sources - Configure GitHub Actions for automated bi-daily news updates - Implement smart data loading with fallback mechanism - Clean up mock data (reduced from 55+ items to 1 fallback item) - Add comprehensive documentation and troubleshooting guide - Create verification and testing scripts Key Features: - Real-time news from MedTech Dive, Medical Device Network, etc. - Automated crawling via GitHub Actions (8:00 & 20:00 Beijing time) - Graceful degradation when crawler data unavailable - Date parsing fixes and User-Agent configuration - 20 real news articles successfully crawled Documentation: - NEWS_CRAWLER_USAGE.md - User guide - NEWS_CRAWLER_IMPROVEMENTS.md - Implementation details - REAL_NEWS_CRAWLER_DESIGN.md - Architecture design - TROUBLESHOOTING.md - Debug guide - test-news-data.html - Browser testing tool 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <[email protected]>
49 lines
1.4 KiB
Bash
Executable File
49 lines
1.4 KiB
Bash
Executable File
#!/bin/bash
|
|
|
|
# 验证新闻爬虫数据
|
|
|
|
echo "🔍 验证新闻爬虫系统..."
|
|
echo ""
|
|
|
|
# 1. 检查数据文件
|
|
if [ -f "public/data/news.json" ]; then
|
|
echo "✅ 数据文件存在: public/data/news.json"
|
|
|
|
# 2. 统计新闻数量
|
|
NEWS_COUNT=$(cat public/data/news.json | jq 'length')
|
|
echo "📊 总新闻数: $NEWS_COUNT 条"
|
|
|
|
# 3. 按来源统计
|
|
echo ""
|
|
echo "📰 新闻来源分布:"
|
|
cat public/data/news.json | jq -r 'group_by(.source) | .[] | " \(.[0].source): \(length)条"'
|
|
|
|
# 4. 按分类统计
|
|
echo ""
|
|
echo "📂 分类分布:"
|
|
cat public/data/news.json | jq -r 'group_by(.category) | .[] | " \(.[0].category): \(length)条"'
|
|
|
|
# 5. 最新3条新闻
|
|
echo ""
|
|
echo "🆕 最新3条新闻:"
|
|
cat public/data/news.json | jq -r '.[:3] | .[] | " 📌 \(.title | .[0:60])... (\(.source))"'
|
|
|
|
# 6. 热门新闻
|
|
echo ""
|
|
HOT_COUNT=$(cat public/data/news.json | jq '[.[] | select(.isHot == true)] | length')
|
|
echo "🔥 热门新闻: $HOT_COUNT 条"
|
|
|
|
# 7. 最新抓取时间
|
|
echo ""
|
|
LATEST_CRAWL=$(cat public/data/news.json | jq -r '.[0].crawledAt')
|
|
echo "⏰ 最新抓取时间: $LATEST_CRAWL"
|
|
|
|
echo ""
|
|
echo "✅ 新闻数据验证完成！"
|
|
echo "🌐 访问 http://192.168.1.83:5175/website/industry-news 查看效果"
|
|
else
|
|
echo "❌ 数据文件不存在"
|
|
echo "💡 请先运行: cd scripts && npm run crawl"
|
|
exit 1
|
|
fi
|