import json, csv, sqlite3 MASTER_V2_PATH = '/workspace/ecommerce_research_sources/benchmark_master_v2.json' TIMELINE_DATA_PATH = '/workspace/ecommerce_research_sources/timeline_deep_dataset.json' DB_PATH = '/workspace/ecommerce_research_sources/ecommerce_brands_research.db' with open(MASTER_V2_PATH, 'r', encoding='utf-8') as f: master = json.load(f) with open(TIMELINE_DATA_PATH, 'r', encoding='utf-8') as f: timeline = json.load(f) # 1. commissions_and_contracts.csv commissions = master.get('commissions_data', []) if commissions: keys = list(commissions[0].keys()) with open('/workspace/ecommerce_research_sources/commissions_and_contracts.csv', 'w', encoding='utf-8-sig', newline='') as f: writer = csv.DictWriter(f, fieldnames=keys, extrasaction='ignore') writer.writeheader() for row in commissions: row_copy = row.copy() if isinstance(row_copy.get('top_brands'), list): row_copy['top_brands'] = ' | '.join(row_copy['top_brands']) writer.writerow(row_copy) # 2. growth_levers_analysis.csv growth_levers = master.get('growth_levers_data', []) if growth_levers: keys = list(growth_levers[0].keys()) with open('/workspace/ecommerce_research_sources/growth_levers_analysis.csv', 'w', encoding='utf-8-sig', newline='') as f: writer = csv.DictWriter(f, fieldnames=keys, extrasaction='ignore') writer.writeheader() for row in growth_levers: writer.writerow(row) # 3. revenue_models_roadmap.csv revenue_models = master.get('revenue_models_data', []) if revenue_models: keys = list(revenue_models[0].keys()) with open('/workspace/ecommerce_research_sources/revenue_models_roadmap.csv', 'w', encoding='utf-8-sig', newline='') as f: writer = csv.DictWriter(f, fieldnames=keys, extrasaction='ignore') writer.writeheader() for row in revenue_models: writer.writerow(row) # 4. yearly_metrics_timeline.csv years = timeline.get('yearly_metrics', []) with open('/workspace/ecommerce_research_sources/yearly_metrics_timeline.csv', 'w', encoding='utf-8-sig', newline='') as f: writer = csv.writer(f) writer.writerow(['سال شمسی', 'سال میلادی', 'فاز توسعه', 'تنوع کالا (SKU)', 'فروشندگان فعال', 'سفارش روزانه', 'پرسنل', 'سهم برند ایرانی (٪)', 'سهم برند خارجی (٪)', 'نفوذ ایکامرس (٪)', 'برندهای برتر', 'دستاوردها', 'پیوت‌ها و شکست‌ها', 'رگولاتوری']) for y in years: writer.writerow([ y.get('year_shamsi'), y.get('year_gregorian'), y.get('phase'), y.get('sku_count'), y.get('active_sellers'), y.get('daily_orders'), y.get('workforce'), y.get('domestic_brand_share'), y.get('foreign_brand_share'), y.get('ecom_penetration_iran'), ' | '.join(y.get('top_brands', [])), ' | '.join(y.get('milestones', [])), ' | '.join(y.get('pivots_and_failures', [])), ' | '.join(y.get('regulatory_and_macro', [])) ]) # 5. executives_and_interviews.csv execs = master.get('executives_directory', []) with open('/workspace/ecommerce_research_sources/executives_and_interviews.csv', 'w', encoding='utf-8-sig', newline='') as f: writer = csv.writer(f) writer.writerow(['نام مدیر', 'سمت و جایگاه سازمانی', 'دسته سازمانی', 'دوره فعالیت', 'موضع و دیدگاه کلیدی پیرامون برندها', 'مصاحبه‌ها و لینک‌ها']) for e in execs: invs_str = ' || '.join([f"{inv['title']} ({inv['platform']} {inv['year']}): {inv['url']}" for inv in e.get('key_interviews', [])]) writer.writerow([ e.get('name'), e.get('title'), e.get('role_category'), e.get('tenure'), e.get('key_stance'), invs_str ]) # 6. industry_market_channels.csv markets = master.get('market_channel_breakdown', []) if markets: keys = list(markets[0].keys()) with open('/workspace/ecommerce_research_sources/industry_market_channels.csv', 'w', encoding='utf-8-sig', newline='') as f: writer = csv.DictWriter(f, fieldnames=keys, extrasaction='ignore') writer.writeheader() for row in markets: writer.writerow(row) # 7. failures_and_pivots.csv failures = master.get('failures_and_pivots_dossier', []) if failures: keys = list(failures[0].keys()) with open('/workspace/ecommerce_research_sources/failures_and_pivots.csv', 'w', encoding='utf-8-sig', newline='') as f: writer = csv.DictWriter(f, fieldnames=keys, extrasaction='ignore') writer.writeheader() for row in failures: writer.writerow(row) # 8. Update DB export to CSV conn = sqlite3.connect(DB_PATH) c = conn.cursor() c.execute('SELECT * FROM sources') rows = c.fetchall() cols = [desc[0] for desc in c.description] conn.close() with open('/workspace/ecommerce_research_sources/ecommerce_brands_research.csv', 'w', encoding='utf-8-sig', newline='') as f: writer = csv.writer(f) writer.writerow(cols) writer.writerows(rows) print("All CSV exports generated successfully with full headers.")