2026年王飞负责市场区域预决算分析报告

#!/usr/bin/env python3 """Generate HTML report from wf-2026-data.json with clickable source file links.""" import json import os import urllib.parse from collections import defaultdict # Load data with open("/data/www/files/wf-2026-data.json", "r", encoding="utf-8") as f: data = json.load(f) # Base URL prefix for file links - files are in 2026-yjs-wf/ subdirectory FILE_BASE = "2026-yjs-wf/" # Keywords KEYWORDS = [ "党员教育", "干部教育", "干部培训", "教育培训", "人才", "党建", "党员", "干部", "网络", "信息化", "智慧", "平台", "系统", "运维", "维护", "视频", "会议" ] # Aggregate stats total_files = len(set(m["source_file"] for m in data)) total_matches = len(data) total_amount = sum(m["amount"] for m in data if m["amount"]) amount_count = sum(1 for m in data if m["amount"]) cities_set = sorted(set(m["city"] for m in data)) counties_set = set() for m in data: counties_set.add((m["city"], m["county"])) total_counties = len(counties_set) # Keyword stats kw_stats = {} for kw in KEYWORDS: matches = [m for m in data if m["keyword"] == kw] if matches: amount = sum(m["amount"] for m in matches if m["amount"]) kw_stats[kw] = {"count": len(matches), "amount": amount} # City stats city_stats = {} for city in cities_set: matches = [m for m in data if m["city"] == city] amount = sum(m["amount"] for m in matches if m["amount"]) city_counties = set(m["county"] for m in matches) city_stats[city] = { "count": len(matches), "amount": amount, "counties": len(city_counties), "files": len(set(m["source_file"] for m in matches)) } # Group by city -> county -> unit_type -> keyword hierarchy = defaultdict(lambda: defaultdict(lambda: defaultdict(lambda: defaultdict(list)))) for m in data: hierarchy[m["city"]][m["county"]][m["unit_type"]][m["keyword"]].append(m) # Sort cities by match count descending sorted_cities = sorted(cities_set, key=lambda c: -city_stats[c]["count"]) # Max keyword count for bar chart scaling max_kw_count = max(v["count"] for v in kw_stats.values()) if kw_stats else 1 # Build keyword distribution bars kw_bars_html = "" for kw in KEYWORDS: if kw in kw_stats: s = kw_stats[kw] bar_width = int(s["count"] / max_kw_count * 100) kw_bars_html += f"""

{kw}

{s['count']}

{s['amount']:.2f}万元

""" # Build city cards city_cards_html = "" for city in sorted_cities: s = city_stats[city] card_id = city.replace(" ", "_") city_cards_html += f"""

{city}

{s['files']}个文件 {s['count']}条匹配 {s['amount']:.2f}万元 {s['counties']}个区县

▼

""" # Get counties for this city sorted by match count city_data = hierarchy[city] county_counts = {c: sum(len(ut) for ut in city_data[c].values()) for c in city_data} sorted_counties = sorted(city_data.keys(), key=lambda c: -county_counts[c]) for county in sorted_counties: county_data = city_data[county] county_matches = sum(sum(len(kw_list) for kw_list in ut.values()) for ut in county_data.values()) county_amount = sum(m["amount"] for ut in county_data.values() for kw_list in ut.values() for m in kw_list if m["amount"]) city_cards_html += f"""

📍 {county} {county_matches}条 {county_amount:.2f}万元 ▼

""" for unit_type, kw_data in sorted(county_data.items(), key=lambda x: -sum(len(v) for v in x[1].values())): unit_matches = sum(len(v) for v in kw_data.values()) unit_amount = sum(m["amount"] for kw_list in kw_data.values() for m in kw_list if m["amount"]) city_cards_html += f"""

🏛️ {unit_type} {unit_matches}条 {unit_amount:.2f}万元

""" for kw, match_list in sorted(kw_data.items(), key=lambda x: -len(x[1])): # Merge entries with same keyword kw_amount = sum(m["amount"] for m in match_list if m["amount"]) kw_locations = ", ".join(sorted(set(m["location"] for m in match_list))) # Get unique source files source_files = sorted(set(m["source_file"] for m in match_list)) # Build clickable file links file_links_html = "" for sf in source_files: encoded_path = urllib.parse.quote(FILE_BASE + sf) display_name = os.path.basename(sf) file_links_html += f'📎 {display_name}\n' city_cards_html += f"""

""" # Show up to 5 sample matches shown = 0 for m in match_list[:5]: content = m["content"][:200].replace("<", "<").replace(">", ">") amount_str = f"{m['amount']:.2f}万元" if m["amount"] else "—" sf_encoded = urllib.parse.quote(FILE_BASE + m["source_file"]) sf_display = os.path.basename(m["source_file"]) city_cards_html += f""" """ if len(match_list) > 5: city_cards_html += f""" """ city_cards_html += """

关键字	匹配内容	文件位置	预算金额	来源文件
{kw}	{content}	{m['location']}	{amount_str}	📎 {sf_display}
... 还有 {len(match_list)-5} 条匹配

""" city_cards_html += """

""" city_cards_html += """

""" city_cards_html += """

""" # Build city summary table rows city_summary_rows = "" for city in sorted_cities: s = city_stats[city] city_summary_rows += f""" {city} {s['files']} {s['count']} {s['amount']:.2f} {s['counties']} """ # Get unique file list for file index section all_files = sorted(set(m["source_file"] for m in data)) file_index_html = "" for i, sf in enumerate(all_files, 1): encoded = urllib.parse.quote(FILE_BASE + sf) display = os.path.basename(sf) file_index_html += f'{i}. {display}\n' html = f""" 2026年王飞负责市场区域预决算分析报告

{total_files}

预算文件

{total_matches}

关键字匹配

{total_amount:.2f}万元

预算金额合计

{len(cities_set)}

市州

{total_counties}

区县

{len(kw_stats)}

关键字

关键字分布

{kw_bars_html}

市州汇总

{city_summary_rows}

市州	文件数	匹配数	预算金额（万元）	区县数

市州详情（点击展开）

{city_cards_html}

来源文件索引（{len(all_files)}个文件）

{file_index_html}

""" output_path = "/data/www/files/wf-2026-report.html" with open(output_path, "w", encoding="utf-8") as f: f.write(html) print(f"HTML report generated: {output_path}") print(f"File size: {os.path.getsize(output_path) / 1024:.1f} KB") print(f"Total files: {total_files}") print(f"Total matches: {total_matches}") print(f"Total amount: {total_amount:.2f}万元") print(f"Cities: {len(cities_set)}") print(f"Counties: {total_counties}") print(f"Keywords matched: {len(kw_stats)}")