81 lines
2.8 KiB
Python
81 lines
2.8 KiB
Python
"""Fetch policy news from Chinese official sources RSS."""
|
||
import json, os, feedparser
|
||
from datetime import datetime, timezone, timedelta
|
||
|
||
OUTPUT = "/var/www/nav/data/policy.json"
|
||
tz = timezone(timedelta(hours=8))
|
||
|
||
FEEDS = [
|
||
# 新华社
|
||
{"name": "新华网·时政", "url": "http://www.xinhuanet.com/politics/news_politics.xml", "lang": "zh"},
|
||
{"name": "新华网·财经", "url": "http://www.xinhuanet.com/fortune/news_fortune.xml", "lang": "zh"},
|
||
{"name": "新华网·国际", "url": "http://www.xinhuanet.com/world/news_world.xml", "lang": "zh"},
|
||
# 人民网
|
||
{"name": "人民网·时政", "url": "http://www.people.com.cn/rss/politics.xml", "lang": "zh"},
|
||
# 中国政府网（国务院）
|
||
{"name": "中国政府网", "url": "http://www.gov.cn/xinwen/yaowen.htm", "lang": "zh"},
|
||
# 发改委（尝试 RSS，若无则用新华网发改委专题）
|
||
{"name": "新华网·财经政策", "url": "https://www.xinhuanet.com/fortune/policy.xml", "lang": "zh"},
|
||
# 财新（需确认 RSS 可用性）
|
||
{"name": "财新网", "url": "https://rss.caixin.com/conf/rss/valsart.xml", "lang": "zh"},
|
||
# 观察者网（政策解读强）
|
||
{"name": "观察者网", "url": "https://www.guancha.cn/index.rss", "lang": "zh"},
|
||
]
|
||
|
||
MAX_PER_FEED = 30
|
||
MAX_TOTAL = 200
|
||
|
||
|
||
def fetch_feed(feed_info):
|
||
try:
|
||
feed = feedparser.parse(feed_info["url"])
|
||
items = []
|
||
for entry in feed.entries[:MAX_PER_FEED]:
|
||
items.append({
|
||
"title": entry.get("title", ""),
|
||
"link": entry.get("link", ""),
|
||
"summary": entry.get("summary", "")[:300],
|
||
"published": entry.get("published", ""),
|
||
"source": feed_info["name"],
|
||
"lang": feed_info["lang"],
|
||
})
|
||
print(f" {feed_info['name']}: {len(items)} items")
|
||
return items
|
||
except Exception as e:
|
||
print(f" {feed_info['name']}: ERROR - {e}")
|
||
return []
|
||
|
||
|
||
def fetch_policy():
|
||
items = []
|
||
for feed_info in FEEDS:
|
||
items.extend(fetch_feed(feed_info))
|
||
|
||
# Deduplicate by title
|
||
seen = set()
|
||
unique = []
|
||
for item in items:
|
||
key = item["title"][:30]
|
||
if key not in seen:
|
||
seen.add(key)
|
||
unique.append(item)
|
||
|
||
result = {
|
||
"updated_at": datetime.now(tz).strftime("%Y-%m-%d %H:%M"),
|
||
"total": len(unique),
|
||
"items": unique[:MAX_TOTAL],
|
||
"sources": [f["name"] for f in FEEDS],
|
||
}
|
||
|
||
os.makedirs(os.path.dirname(OUTPUT), exist_ok=True)
|
||
with open(OUTPUT, "w", encoding="utf-8") as f:
|
||
json.dump(result, f, ensure_ascii=False, indent=2)
|
||
|
||
print(f"\nTotal: {len(unique)} unique items -> {OUTPUT}")
|
||
return result
|
||
|
||
|
||
if __name__ == "__main__":
|
||
print(f"Fetching policy news at {datetime.now(tz).strftime('%Y-%m-%d %H:%M')}")
|
||
fetch_policy()
|