#!/usr/bin/env python3 # -*- coding: utf-8 -*- """ 全球中文新闻推送脚本 信源：BBC 中文、路透社中文、纽约时报中文、华尔街日报中文、金融时报中文、联合早报、日经中文等 涵盖：热点、财经、科技、国际、社会等各类新闻 特点：重大、及时、权威、全中文 """ import requests import json from datetime import datetime import re def get_bbc_chinese(): """获取 BBC 中文网新闻""" try: url = "https://feeds.bbci.co.uk/zhongwen/simp/rss.xml" headers = {"User-Agent": "Mozilla/5.0"} resp = requests.get(url, headers=headers, timeout=10) items = re.findall(r'(.*?)', resp.text, re.DOTALL)[:5] news = [] for item in items: title_match = re.search(r'<!\[CDATA\[(.*?)\]\]>', item) if title_match: title = title_match.group(1) news.append(f"• {title}") return "\n".join(news) if news else "暂无数据" except Exception as e: return f"获取失败：{str(e)}" def get_bbc_world_chinese(): """获取 BBC 中文网国际新闻""" try: url = "https://feeds.bbci.co.uk/zhongwen/simp/world/rss.xml" headers = {"User-Agent": "Mozilla/5.0"} resp = requests.get(url, headers=headers, timeout=10) items = re.findall(r'<item>(.*?)</item>', resp.text, re.DOTALL)[:3] news = [] for item in items: title_match = re.search(r'<title><!\[CDATA\[(.*?)\]\]>', item) if title_match: title = title_match.group(1) news.append(f"• {title}") return "\n".join(news) if news else "暂无数据" except Exception as e: return f"获取失败：{str(e)}" def get_reuters_chinese(): """获取路透社中文""" try: # 路透社中文首页抓取最新新闻 url = "https://www.reuters.com/world/china/" headers = {"User-Agent": "Mozilla/5.0"} resp = requests.get(url, headers=headers, timeout=10) # 尝试解析标题 titles = re.findall(r'<h2[^>]*class="[^"]*media__title[^"]*"[^>]*>([^<]+)</h2>', resp.text)[:5] if not titles: titles = re.findall(r'<span[^>]*class="[^"]*headline[^"]*"[^>]*>([^<]+)</span>', resp.text)[:5] if titles: return "\n".join([f"• {t.strip()}" for t in titles if len(t.strip()) > 5]) return "暂无数据" except Exception as e: return f"获取失败：{str(e)}" def get_nyt_chinese(): """获取纽约时报中文网""" try: url = "https://cn.nytimes.com/rss/" headers = {"User-Agent": "Mozilla/5.0"} resp = requests.get(url, headers=headers, timeout=10) items = re.findall(r'<item>(.*?)</item>', resp.text, re.DOTALL)[:5] news = [] for item in items: title_match = re.search(r'<title>(.*?)', item) if title_match: title = title_match.group(1).replace('', '').strip() if len(title) > 5: news.append(f"• {title}") return "\n".join(news) if news else "暂无数据" except Exception as e: return f"获取失败：{str(e)}" def get_wsj_chinese(): """获取华尔街日报中文网""" try: url = "https://cn.wsj.com/rss" headers = {"User-Agent": "Mozilla/5.0"} resp = requests.get(url, headers=headers, timeout=10) items = re.findall(r'(.*?)', resp.text, re.DOTALL)[:5] news = [] for item in items: title_match = re.search(r'(.*?)', item) if title_match: title = title_match.group(1).replace('', '').strip() if len(title) > 5: news.append(f"• {title}") return "\n".join(news) if news else "暂无数据" except Exception as e: return f"获取失败：{str(e)}" def get_ft_chinese(): """获取金融时报中文网""" try: url = "http://www.ftchinese.com/feed" headers = {"User-Agent": "Mozilla/5.0"} resp = requests.get(url, headers=headers, timeout=10) items = re.findall(r'(.*?)', resp.text, re.DOTALL)[:5] news = [] for item in items: title_match = re.search(r'(.*?)', item) if title_match: title = title_match.group(1).replace('', '').strip() if len(title) > 5: news.append(f"• {title}") return "\n".join(news) if news else "暂无数据" except Exception as e: return f"获取失败：{str(e)}" def get_zhnews_china(): """获取联合早报（中国新闻）""" try: url = "https://www.zaobao.com.sg/rss/realtime/china.xml" headers = {"User-Agent": "Mozilla/5.0"} resp = requests.get(url, headers=headers, timeout=10) items = re.findall(r'(.*?)', resp.text, re.DOTALL)[:5] news = [] for item in items: title_match = re.search(r'(.*?)', item) if title_match: title = title_match.group(1).replace('', '').strip() if len(title) > 5: news.append(f"• {title}") return "\n".join(news) if news else "暂无数据" except Exception as e: return f"获取失败：{str(e)}" def get_zhnews_world(): """获取联合早报（国际新闻）""" try: url = "https://www.zaobao.com.sg/rss/realtime/world.xml" headers = {"User-Agent": "Mozilla/5.0"} resp = requests.get(url, headers=headers, timeout=10) items = re.findall(r'(.*?)', resp.text, re.DOTALL)[:5] news = [] for item in items: title_match = re.search(r'(.*?)', item) if title_match: title = title_match.group(1).replace('', '').strip() if len(title) > 5: news.append(f"• {title}") return "\n".join(news) if news else "暂无数据" except Exception as e: return f"获取失败：{str(e)}" def get_nikkei_chinese(): """获取日经中文网""" try: url = "https://cn.nikkei.com/rssfeed.xml" headers = {"User-Agent": "Mozilla/5.0"} resp = requests.get(url, headers=headers, timeout=10) items = re.findall(r'(.*?)', resp.text, re.DOTALL)[:5] news = [] for item in items: title_match = re.search(r'(.*?)', item) if title_match: title = title_match.group(1).replace('', '').strip() if len(title) > 5: news.append(f"• {title}") return "\n".join(news) if news else "暂无数据" except Exception as e: return f"获取失败：{str(e)}" def get_chinadialogue(): """获取对话地球（环境新闻）""" try: url = "https://chinadialogue.net/zh/feed/" headers = {"User-Agent": "Mozilla/5.0"} resp = requests.get(url, headers=headers, timeout=10) items = re.findall(r'(.*?)', resp.text, re.DOTALL)[:3] news = [] for item in items: title_match = re.search(r'(.*?)', item) if title_match: title = title_match.group(1).replace('', '').strip() if len(title) > 5: news.append(f"• {title}") return "\n".join(news) if news else "暂无数据" except Exception as e: return f"获取失败：{str(e)}" def get_tech_chinese(): """获取科技新闻（中文源）""" try: # 36 氪 url = "https://36kr.com/feed" headers = {"User-Agent": "Mozilla/5.0"} resp = requests.get(url, headers=headers, timeout=10) items = re.findall(r'(.*?)', resp.text, re.DOTALL)[:3] news = [] for item in items: title_match = re.search(r'(.*?)', item) if title_match: title = title_match.group(1).replace('', '').strip() if len(title) > 5: news.append(f"• {title[:50]}...") return "\n".join(news) if news else "暂无数据" except Exception as e: return f"获取失败：{str(e)}" def get_finance_chinese(): """获取财经新闻（中文源）""" try: # 财新网 url = "https://www.caixin.com/rss/finance.xml" headers = {"User-Agent": "Mozilla/5.0"} resp = requests.get(url, headers=headers, timeout=10) items = re.findall(r'(.*?)', resp.text, re.DOTALL)[:5] news = [] for item in items: title_match = re.search(r'(.*?)', item) if title_match: title = title_match.group(1).replace('', '').strip() if len(title) > 5: news.append(f"• {title[:60]}...") return "\n".join(news) if news else "暂无数据" except Exception as e: return f"获取失败：{str(e)}" def get_breaking_chinese(): """获取突发/重大新闻（中文）""" try: sources = [ ("BBC", "https://feeds.bbci.co.uk/zhongwen/simp/rss.xml"), ("联合早报", "https://www.zaobao.com.sg/rss/realtime/china.xml"), ("日经", "https://cn.nikkei.com/rssfeed.xml"), ] breaking = [] for name, url in sources: try: headers = {"User-Agent": "Mozilla/5.0"} resp = requests.get(url, headers=headers, timeout=5) items = re.findall(r'(.*?)', resp.text, re.DOTALL)[:2] for item in items: title_match = re.search(r'(.*?)', item) if title_match: title = title_match.group(1).replace('', '').strip() if len(title) > 5: breaking.append(f"• [{name}] {title}") except: continue return "\n".join(breaking[:5]) if breaking else "暂无重大新闻" except Exception as e: return f"获取失败：{str(e)}" def generate_newsletter(morning=True): """生成新闻简报""" today = datetime.now().strftime("%Y 年 %m 月 %d 日") weekday = datetime.now().strftime("%A") time_str = "早报" if morning else "晚报" newsletter = f"""📰 全球中文新闻{time_str} | {today} 🌍 国际焦点 {get_bbc_chinese()} 💰 财经动态 {get_finance_chinese()} 🤖 科技前沿 {get_tech_chinese()} 📊 市场观察 {get_wsj_chinese()} 🇸🇬 亚洲视角 {get_zhnews_china()} --- 信源：BBC 中文 | 路透社中文 | 纽约时报中文 | 华尔街日报中文 | 金融时报中文 | 联合早报 | 日经中文网 | 财新 | 36 氪 祝您{ '一天工作顺利' if morning else '晚安好梦'}！🤖 """ return newsletter if __name__ == "__main__": # 根据当前时间判断是早报还是晚报 hour = datetime.now().hour is_morning = hour < 17 print(generate_newsletter(morning=is_morning))