2026年杜书磊负责市场区域预决算分析报告

#!/usr/bin/env python3 """读取分析结果JSON，生成深色主题可视化HTML预算分析报告""" import json import os from collections import defaultdict BASE_DIR = "/data/www/files/2026-yjs-dsl" JSON_PATH = os.path.join(BASE_DIR, "analysis_results.json") HTML_OUTPUT = "/data/www/files/2026-yjs-dsl-2026-report.html" SUBDIR = "2026-yjs-dsl" # HTML与文件不在同目录，链接需加前缀 # 关键字颜色映射 KW_COLORS = { "网络培训": "#e74c3c", "培训": "#e67e22", "能力提升": "#f1c40f", "视频拍摄": "#2ecc71", "党员教育片": "#1abc9c", "课程制作": "#16a085", "直播": "#3498db", "视频": "#2980b9", "课件": "#9b59b6", "系统": "#8e44ad", "信息化": "#e84393", "网络": "#fd79a8", "数字": "#00cec9", "设备": "#6c5ce7", "平台": "#a29bfe", "维护": "#fdcb6e", "软件": "#ff7675", } # 关键字图标 KW_ICONS = { "网络培训": "🌐", "培训": "📚", "能力提升": "💪", "视频拍摄": "🎥", "党员教育片": "🎬", "课程制作": "📝", "直播": "📡", "视频": "📹", "课件": "📖", "系统": "⚙️", "信息化": "💻", "网络": "🔗", "数字": "🔢", "设备": "🖥️", "平台": "🏗️", "维护": "🔧", "软件": "💾", } def load_data(): with open(JSON_PATH, 'r', encoding='utf-8') as f: return json.load(f) def merge_matches(matches): """合并相同关键字：金额累加，位置全列出""" merged = defaultdict(lambda: {"keyword": "", "contents": [], "locations": [], "amount": 0.0, "count": 0}) for m in matches: kw = m["keyword"] merged[kw]["keyword"] = kw merged[kw]["contents"].append(m["content"]) merged[kw]["locations"].append(m["location"]) merged[kw]["amount"] += m["amount"] merged[kw]["count"] += 1 return list(merged.values()) def build_html(data): # 按市州→区县→单位类型分层 hierarchy = defaultdict(lambda: defaultdict(lambda: defaultdict(list))) for fname, info in data.items(): city = info["city"] district = info["district"] org_type = info["org_type"] for m in info["matches"]: m["source_file"] = fname hierarchy[city][district][org_type].append(m) # 汇总统计 total_files = len(data) total_matches = sum(len(info["matches"]) for info in data.values()) total_amount = sum(m["amount"] for info in data.values() for m in info["matches"]) cities = sorted(hierarchy.keys()) total_districts = sum(len(dists) for dists in hierarchy.values()) # 关键字统计 kw_stats = defaultdict(lambda: {"count": 0, "amount": 0.0}) for info in data.values(): for m in info["matches"]: kw_stats[m["keyword"]]["count"] += 1 kw_stats[m["keyword"]]["amount"] += m["amount"] kw_stats_sorted = sorted(kw_stats.items(), key=lambda x: x[1]["count"], reverse=True) kws_used = len(kw_stats) # 单位类型图标 org_icons = { "组织部": "📋", "党校": "🎓", "民政局": "🏥", "政府": "🏛️", } # 市州颜色 city_colors = { "青海省": "#e84393", "西宁市": "#0984e3", "海东市": "#00b894", } html_parts = [] # ===== HTML HEAD ===== html_parts.append(f''' 2026年杜书磊负责市场区域预决算分析报告

预算文件数

{total_files}个

匹配项总数

{total_matches}条

预算总金额

{total_amount:,.2f}万元

覆盖市州

{len(cities)}个

覆盖区县

{total_districts}个

命中关键字

{kws_used}/17

📈 关键字分布统计

''') max_count = max(v["count"] for _, v in kw_stats_sorted) if kw_stats_sorted else 1 for kw, stats in kw_stats_sorted: color = KW_COLORS.get(kw, "#636e72") icon = KW_ICONS.get(kw, "📌") pct = (stats["count"] / max_count * 100) if max_count > 0 else 0 html_parts.append(f'''

{icon} {kw}

{stats["count"]}次

{stats["amount"]:,.2f}万元

''') html_parts.append('''

''') for city in cities: color = city_colors.get(city, "#636e72") city_amount = sum(m["amount"] for d in hierarchy[city].values() for ot in d.values() for m in ot) city_count = sum(len(ot) for d in hierarchy[city].values() for ot in d.values()) html_parts.append(f' {city} · {city_count}条 · {city_amount:,.2f}万元\n') html_parts.append('

\n\n') # ===== City Sections ===== for city in cities: color = city_colors.get(city, "#636e72") city_amount = sum(m["amount"] for d in hierarchy[city].values() for ot in d.values() for m in ot) city_count = sum(len(ot) for d in hierarchy[city].values() for ot in d.values()) html_parts.append(f'''

📍 {city}

{city_amount:,.2f}万元 {city_count}条匹配 ▼

''') for district in sorted(hierarchy[city].keys()): html_parts.append(f'

\n') html_parts.append(f'

📍 {district}

\n') for org_type in sorted(hierarchy[city][district].keys()): matches = hierarchy[city][district][org_type] merged = merge_matches(matches) org_total = sum(m["amount"] for m in merged) org_icon = org_icons.get(org_type, "📄") html_parts.append(f'''

{org_icon} {org_type} 汇总：{org_total:,.2f}万元

''') for m in merged: kw = m["keyword"] color = KW_COLORS.get(kw, "#636e72") icon = KW_ICONS.get(kw, "📌") count_badge = f'×{m["count"]}' if m["count"] > 1 else "" # 合并内容（取前3条，每条截断） contents = m["contents"][:3] content_str = "; ".join(c[:80] for c in contents) if m["count"] > 3: content_str += f" ...等{m['count']}条" locations = ", ".join(m["locations"][:5]) if len(m["locations"]) > 5: locations += f" ...等{len(m['locations'])}处" # 来源文件链接 source_files = list(set(mm.get("source_file", "") for mm in matches if mm["keyword"] == kw)) file_links = [] for sf in source_files: href = f"{SUBDIR}/{sf}" file_links.append(f'📄 {sf}') file_links_html = '|'.join(file_links) amount = m["amount"] amount_str = f'{amount:,.2f}' if amount > 0 else '0.00' amount_color = "#fdcb6e" if amount > 0 else "#636e72" html_parts.append(f''' ''') html_parts.append('''

关键字	匹配内容	位置	预算金额	来源文件
{icon} {kw}{count_badge}	{content_str}	{locations}	{amount_str}万元	{file_links_html}

''') html_parts.append('

\n') html_parts.append('''

''') # ===== Footer ===== html_parts.append(f'''

''') return '\n'.join(html_parts) def main(): data = load_data() html = build_html(data) with open(HTML_OUTPUT, 'w', encoding='utf-8') as f: f.write(html) print(f"HTML report generated: {HTML_OUTPUT}") print(f"File size: {os.path.getsize(HTML_OUTPUT) / 1024:.1f} KB") # 验证链接 print("\n=== Link Verification ===") all_links = [] for fname in data.keys(): href = f"{SUBDIR}/{fname}" all_links.append((href, os.path.join(BASE_DIR, fname))) all_ok = True for href, fpath in all_links: exists = os.path.exists(fpath) status = "✅" if exists else "❌" if not exists: all_ok = False print(f" {status} {href} → {fpath}") if all_ok: print(f"\n✅ All {len(all_links)} file links verified!") else: print(f"\n❌ Some links are broken!") print(f"\n📊 Report Summary:") total_matches = sum(len(info["matches"]) for info in data.values()) total_amount = sum(m["amount"] for info in data.values() for m in info["matches"]) print(f" Files: {len(data)}") print(f" Matches: {total_matches}") print(f" Total amount: {total_amount:,.2f}万元") print(f"\n🔗 Internal: http://192.168.99.133:5678/2026-yjs-dsl-2026-report.html") print(f"🔗 External: https://ziyuan.cdlhyj.com/2026-yjs-dsl-2026-report.html") if __name__ == "__main__": main()