import os
import json
import traceback
from scrapling import StealthyFetcher

def fetch_hn():
    print("Initiating scrapling StealthyFetcher request to Hacker News...")
    fetcher = StealthyFetcher()
    page = fetcher.fetch("https://news.ycombinator.com/")
    
    try:
        results = []
        # Each HN item is a <tr> with class athing
        posts = page.css("tr.athing")
        
        for post in posts[:15]:
            title_elem = post.css_first(".titleline > a")
            if not title_elem:
                continue
                
            title = title_elem.text
            url = title_elem.attrib.get('href', '')
            
            score = "Check HN for score"
            
            results.append({
                "title": title,
                "score": score,
                "url": url if url.startswith('http') else "https://news.ycombinator.com/" + url
            })
            
        print("\n=== 🚀 [Scrapling Crawler] Hacker News 抓取结果 ===")
        print(json.dumps(results[:5], indent=2, ensure_ascii=False))
        print("=========================================\n")
    except Exception as e:
        print("Failed to parse.")
        print(traceback.format_exc())

if __name__ == "__main__":
    fetch_hn()