122 lines
3.7 KiB
Python
122 lines
3.7 KiB
Python
"""Use DeepSeek to summarize policy news into categorized Chinese briefs."""
|
||
import json, os, requests, re
|
||
from datetime import datetime, timezone, timedelta
|
||
|
||
API_KEY = "sk-bbca4a0380d549389f0d27cdea0b5228"
|
||
API_URL = "https://api.deepseek.com/v1/chat/completions"
|
||
MODEL = "deepseek-v4-flash"
|
||
|
||
INPUT = "/var/www/nav/data/policy.json"
|
||
OUTPUT = "/var/www/nav/data/policy_summary.json"
|
||
tz = timezone(timedelta(hours=8))
|
||
|
||
|
||
def load_raw():
|
||
if not os.path.exists(INPUT):
|
||
return []
|
||
with open(INPUT) as f:
|
||
data = json.load(f)
|
||
return data.get("items", [])
|
||
|
||
|
||
def summarize(items):
|
||
news_text = ""
|
||
for i, item in enumerate(items[:100], 1):
|
||
title = item.get("title", "")
|
||
summary = item.get("summary", "")[:200].replace("<", "").replace(">", "")
|
||
source = item.get("source", "")
|
||
link = item.get("link", "")
|
||
news_text += f"{i}. [{source}] {title}\n {summary}\n url: {link}\n\n"
|
||
|
||
prompt = f"""你是一个政策分析助手。请从原始政策新闻中精选出**最重要的政策动态**，按优先级排序。
|
||
|
||
## 选稿标准
|
||
- 国务院/发改委/部委最新政策文件
|
||
- 习近平总书记重要讲话/活动
|
||
- 重大经济/产业政策（数字经济、AI、能源、金融）
|
||
- 重大改革举措
|
||
- 重要人事任免
|
||
|
||
## 输出
|
||
- 分类名：**政策速递**（只有一个分类）
|
||
- 每条：**15-30字完整标题**（subtitle），**300-500字政策解读摘要**（summary）
|
||
- 总计 **10-20 条**，按重要性排序
|
||
|
||
## 输出格式
|
||
每条输出到 items 数组，包含：rank, subtitle, title, source, link, summary
|
||
summary 用自然段落，关键信息用 **加粗**。
|
||
|
||
## 原始新闻
|
||
{news_text}
|
||
|
||
JSON格式: {{"categories": [{{"name":"政策速递","items":[{{"rank":1,"subtitle":"...","title":"...","source":"...","link":"...","summary":"..."}}]}}]}}"""
|
||
|
||
resp = requests.post(
|
||
API_URL,
|
||
headers={"Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json"},
|
||
json={
|
||
"model": MODEL,
|
||
"messages": [{"role": "user", "content": prompt}],
|
||
"temperature": 0.3,
|
||
"max_tokens": 16000,
|
||
},
|
||
timeout=180,
|
||
)
|
||
|
||
if resp.status_code != 200:
|
||
print(f"API error: {resp.status_code}")
|
||
return None
|
||
|
||
content = resp.json()["choices"][0]["message"]["content"].strip()
|
||
if content.startswith("```"):
|
||
lines = content.split("\n")
|
||
content = "\n".join(lines[1:-1]) if lines[-1].strip() == "```" else "\n".join(lines[1:])
|
||
|
||
try:
|
||
result = json.loads(content)
|
||
except:
|
||
import re as re_
|
||
content = re_.sub(r',\s*}', '}', content)
|
||
content = re_.sub(r',\s*]', ']', content)
|
||
try:
|
||
result = json.loads(content)
|
||
except:
|
||
print(f"JSON parse failed, len={len(content)}")
|
||
print(f"First 500: {content[:500]}")
|
||
return None
|
||
|
||
return result
|
||
|
||
|
||
def run():
|
||
now = datetime.now(tz).strftime("%Y-%m-%d %H:%M")
|
||
items = load_raw()
|
||
if not items:
|
||
print("No policy data")
|
||
exit(0)
|
||
|
||
print(f"Loaded {len(items)} policy items. AI summarizing...")
|
||
data = summarize(items)
|
||
|
||
if not data:
|
||
print("Summarization failed")
|
||
exit(1)
|
||
|
||
result = {
|
||
"updated_at": now,
|
||
"categories": data.get("categories", []),
|
||
}
|
||
|
||
total = sum(len(c["items"]) for c in result["categories"])
|
||
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"Written {total} policy briefs -> {OUTPUT}")
|
||
for c in result["categories"]:
|
||
print(f" {c['name']}: {len(c['items'])} items")
|
||
|
||
|
||
if __name__ == "__main__":
|
||
run()
|