#!/usr/bin/env python3 # -*- coding: utf-8 -*- """生成HTML报告""" import json, os BASE = "/data/www/files/scQxYjs" with open(f"{BASE}/_complete_results.json", "r") as f: data = json.load(f) # 统计 total_items = 0 total_amount = 0.0 kw_stats = {} city_stats = {} total_org = 0 total_dx = 0 for city in data: city_total = 0 city_items = 0 for ut in data[city]: for county in data[city][ut]: for item in data[city][ut][county]: total_items += 1 total_amount += item['amount'] city_total += item['amount'] city_items += 1 kw = item['keyword'] if kw not in kw_stats: kw_stats[kw] = {'count': 0, 'amount': 0} kw_stats[kw]['count'] += item.get('count', 1) kw_stats[kw]['amount'] += item['amount'] if ut == '组织部': total_org += sum(len(data[city][ut][c]) for c in data[city][ut]) elif ut == '党校': total_dx += sum(len(data[city][ut][c]) for c in data[city][ut]) city_stats[city] = {'items': city_items, 'amount': round(city_total, 2)} total_amount = round(total_amount, 2) # 关键字排序 kw_sorted = sorted(kw_stats.keys(), key=lambda k: kw_stats[k]['amount'], reverse=True) # 市州排序 city_sorted = sorted(city_stats.keys(), key=lambda c: city_stats[c]['amount'], reverse=True) # 生成关键字分布条形图数据 max_kw_amount = max(kw_stats[k]['amount'] for k in kw_stats) if kw_stats else 1 # 生成HTML html = f''' 四川区县预算关键字分析报告

📊 四川省区县预算关键字分析报告

2026年度部门预算公开 · 17项关键字匹配 · 21个市州 · 组织部/党校分类分析

覆盖市州
{len(data)}
预算文件
483
匹配项
{total_items}
总预算金额
{total_amount:,.2f}万元
组织部匹配
{total_org}
党校匹配
{total_dx}

🔑 关键字匹配分布

''' for kw in kw_sorted: s = kw_stats[kw] pct = (s['amount'] / max_kw_amount * 100) if max_kw_amount > 0 else 0 html += f'''
{kw}
{s['count']}次
{s['amount']:,.2f}万元
''' html += '''

🗺️ 市州快速导航

''' for city in city_sorted: s = city_stats[city] html += f'{city} ({s["items"]}项)\n' html += '''
''' for city in city_sorted: s = city_stats[city] city_data = data[city] html += f'''

📍 {city}

{s["items"]}项匹配 · 预算{s["amount"]:,.2f}万元
''' # 收集该市州所有区县 all_counties = set() for ut in ['组织部', '党校', '其他']: if ut in city_data: all_counties.update(city_data[ut].keys()) for county in sorted(all_counties): html += f'
\n' html += f'
📂 {county}
\n' for ut_key, ut_label, ut_class in [('组织部', '📋 组织部', 'org'), ('党校', '🎓 党校', 'dx'), ('其他', '📄 其他', 'org')]: if ut_key not in city_data or county not in city_data[ut_key]: continue items = city_data[ut_key][county] if not items: continue unit_total = sum(item['amount'] for item in items) html += f'
\n' html += f'
{ut_label} 汇总: {unit_total:,.2f}万元
\n' html += f'\n' html += f'\n\n' for item in sorted(items, key=lambda x: x['amount'], reverse=True): kw = item['keyword'] content = item.get('contents_str', item.get('content', ''))[:80] location = item.get('locations_str', item.get('location', ''))[:60] amount = item['amount'] count = item.get('count', 1) file_url = item.get('file_urls_str', item.get('file_url', '')).split('；')[0] if item.get('file_urls_str') else item.get('file_url', '') file_name = item.get('files_str', item.get('file', '')).split('；')[0] if item.get('files_str') else item.get('file', '') # 如果file_url为空，用file_name构建 if not file_url and file_name: file_url = f"/scQxYjs/{city}/{file_name}" count_str = f' ({count}项合并)' if count > 1 else '' amount_str = f'{amount:,.2f}万元' if amount > 0 else '—' html += f'' html += f'' html += f'' html += f'' html += f'' html += f'' html += f'\n' html += '
关键字匹配内容文件位置预算金额打开文件
{kw}{content}{count_str}{location}{amount_str}📂 {file_name[:20]}{"..." if len(file_name)>20 else ""}
\n
\n' html += '
\n' # county-block end html += '
\n
\n' # city-body, city-section end html += '''

四川省区县预算关键字分析报告 · 2026年度

数据来源：各市州区县部门预算公开文件 · 共483个文件 · 17项关键字匹配

''' output_path = f"{BASE}/report.html" with open(output_path, 'w', encoding='utf-8') as f: f.write(html) print(f"报告已生成: {output_path}") print(f"文件大小: {os.path.getsize(output_path)/1024:.1f}KB")