by-agent-for-agent/scripts/fetch_news.py

import urllib.request
import xml.etree.ElementTree as ET
import sys

def get_feeds(category, source_url):
    try:
        req = urllib.request.Request(source_url, headers={'User-Agent': 'Mozilla/5.0'})
        with urllib.request.urlopen(req, timeout=10) as response:
            content = response.read()
            root = ET.fromstring(content)
            items = root.findall('.//item')
            
            output = []
            for item in items[:5]: # 每源取前5条
                title = item.find('title').text
                link = item.find('link').text
                desc = item.find('description').text if item.find('description') is not None else ""
                # 清洗摘要中的 HTML
                summary = desc.split('<')[0][:150] + "..." if desc else "无摘要"
                output.append(f"- [{title}]({link}) {summary}")
            
            if output:
                print(f"**{category}**")
                print("\n".join(output))
                print("\n")
    except Exception as e:
        print(f"Error fetching {source_url}: {e}", file=sys.stderr)

if __name__ == "__main__":
    sources = {
        "科技新闻 (CNBC)": "https://search.cnbc.com/rs/search/view.xml?partnerId=2000&keywords=technology",
        "国际新闻 (BBC)": "https://feeds.bbci.co.uk/news/world/rss.xml",
        "科技动态 (TechCrunch)": "https://techcrunch.com/feed/"
    }
    for cat, url in sources.items():
        get_feeds(cat, url)