Taiwan Equity Research Coverage

import refrom pathlib import Path
def get_report(ticker: str, reports_dir: str = "Pilot_Reports") -> dict:    """Find and parse a ticker report."""    base = Path(reports_dir)    # Find the file across all sector subdirectories    matches = list(base.rglob(f"{ticker}_*.md"))    if not matches:        return {}        content = matches[0].read_text(encoding="utf-8")        # Extract all wikilinks    wikilinks = re.findall(r'\[\[([^\]]+)\]\]', content)        # Extract sector metadata    sector_match = re.search(r'\*\*產業:\*\*\s*(.+)', content)    board_match = re.search(r'\*\*板塊:\*\*\s*(.+)', content)        return {        "ticker": ticker,        "file": str(matches[0]),        "sector": sector_match.group(1).strip() if sector_match else None,        "board": board_match.group(1).strip() if board_match else None,        "wikilinks": list(set(wikilinks)),        "wikilink_count": len(set(wikilinks)),        "content": content    }
# Usagereport = get_report("2330")print(f"Sector: {report['sector']}")print(f"Wikilinks ({report['wikilink_count']}): {report['wikilinks'][:10]}")

import refrom pathlib import Pathfrom collections import defaultdict
def build_wikilink_index(reports_dir: str = "Pilot_Reports") -> dict:    """    Returns: {entity: [list of tickers that mention it]}    """    index = defaultdict(list)        for md_file in Path(reports_dir).rglob("*.md"):        # Extract ticker from filename (e.g. "2330_台積電.md" -> "2330")        ticker = md_file.stem.split("_")[0]        content = md_file.read_text(encoding="utf-8")        wikilinks = set(re.findall(r'\[\[([^\]]+)\]\]', content))                for link in wikilinks:            index[link].append(ticker)        # Sort by mention count    return dict(sorted(index.items(), key=lambda x: len(x[1]), reverse=True))
# Find all companies in Apple's supply chainindex = build_wikilink_index()apple_suppliers = index.get("Apple", [])print(f"Apple supply chain: {len(apple_suppliers)} companies")print(apple_suppliers[:20])
# Find companies involved in CoWoScowos_companies = index.get("CoWoS", [])print(f"\nCoWoS ecosystem: {len(cowos_companies)} companies: {cowos_companies}")

def supply_chain_overlap(entity_a: str, entity_b: str, reports_dir: str = "Pilot_Reports"):    """Find tickers that appear in both entities' supply chains."""    index = build_wikilink_index(reports_dir)        set_a = set(index.get(entity_a, []))    set_b = set(index.get(entity_b, []))    overlap = set_a & set_b        print(f"{entity_a}: {len(set_a)} companies")    print(f"{entity_b}: {len(set_b)} companies")    print(f"Overlap: {len(overlap)} companies — {sorted(overlap)}")    return overlap
# Companies in both NVIDIA and Apple supply chainssupply_chain_overlap("NVIDIA", "Apple")
# Companies in both AI server and EV supply chainssupply_chain_overlap("AI 伺服器", "電動車")

import subprocessimport sys
def update_sector_financials(sector: str, valuation_only: bool = False):    """Update financials for all tickers in a sector."""    script = "update_valuation.py" if valuation_only else "update_financials.py"    cmd = [sys.executable, f"scripts/{script}", "--sector", sector]        result = subprocess.run(cmd, capture_output=True, text=True)        if result.returncode != 0:        print(f"Error: {result.stderr}")    else:        print(result.stdout)        return result.returncode
# Update valuation multiples for semiconductors (fast)update_sector_financials("Semiconductors", valuation_only=True)
# Full financial update for a sectorupdate_sector_financials("Electronic Components", valuation_only=False)

import json
def build_enrichment_entry(ticker: str, company_name: str,                           description: str, upstream: list[str],                           midstream: str, downstream: list[str],                           customers: list[str], suppliers: list[str]) -> dict:    """    Build a properly formatted enrichment entry.    All entity names in lists will be wrapped in [[wikilinks]].    """    def wikify(items):        return "\n".join(f"- [[{item}]]" for item in items)        supply_chain = (        f"**上游:**\n{wikify(upstream)}\n"        f"**中游:**\n- **{company_name}** ({midstream})\n"        f"**下游:**\n{wikify(downstream)}"    )        cust_section = (        f"### 主要客戶\n{wikify(customers)}\n\n"        f"### 主要供應商\n{wikify(suppliers)}"    )        return {        "desc": description,        "supply_chain": supply_chain,        "cust": cust_section    }
# Build enrichment for multiple tickersenrichment = {    "2330": build_enrichment_entry(        ticker="2330",        company_name="台積電",        description="台積電為全球最大晶圓代工廠，專注於 [[CoWoS]]、[[3奈米]] 先進製程，為全球領先科技公司提供晶片製造服務。",        upstream=["ASML", "Applied Materials", "SUMCO", "Tokyo Electron"],        midstream="晶圓代工",        downstream=["Apple", "NVIDIA", "AMD", "Broadcom", "Qualcomm"],        customers=["Apple", "NVIDIA", "AMD", "Qualcomm", "MediaTek"],        suppliers=["ASML", "Tokyo Electron", "Shin-Etsu", "Applied Materials"]    )}
# Save to filewith open("enrichment.json", "w", encoding="utf-8") as f:    json.dump(enrichment, f, ensure_ascii=False, indent=2)
print("enrichment.json ready. Apply with:")print("python scripts/update_enrichment.py --data enrichment.json 2330")

import subprocessimport json
def audit_and_report(batch_id: int) -> dict:    """Run audit and parse results."""    result = subprocess.run(        ["python", "scripts/audit_batch.py", str(batch_id), "-v"],        capture_output=True, text=True    )        output = result.stdout        # Parse pass/fail counts from output    passed = output.count("✓")     failed = output.count("✗")        return {        "batch": batch_id,        "passed": passed,        "failed": failed,        "pass_rate": passed / (passed + failed) if (passed + failed) > 0 else 0,        "output": output    }
results = audit_and_report(101)print(f"Batch 101: {results['passed']} passed, {results['failed']} failed")print(f"Pass rate: {results['pass_rate']:.1%}")

# Find all Taiwan companies connected to a specific technologyfrom collections import defaultdictimport refrom pathlib import Path
def map_supply_chain(technology: str, reports_dir: str = "Pilot_Reports"):    results = {"upstream": [], "midstream": [], "downstream": []}        for md_file in Path(reports_dir).rglob("*.md"):        content = md_file.read_text(encoding="utf-8")                if f"[[{technology}]]" not in content:            continue                ticker = md_file.stem.split("_")[0]        company = md_file.stem.split("_", 1)[1] if "_" in md_file.stem else ""                # Detect position in supply chain        if f"**上游:**" in content and f"[[{technology}]]" in content.split("**上游:**")[1].split("**中游:**")[0]:            results["upstream"].append(f"{ticker} {company}")        elif f"[[{technology}]]" in content and "**中游:**" in content:            mid_section = content.split("**中游:**")[1].split("**下游:**")[0] if "**下游:**" in content else ""            if f"[[{technology}]]" in mid_section:                results["midstream"].append(f"{ticker} {company}")        else:            results["downstream"].append(f"{ticker} {company}")        return results
chain = map_supply_chain("CoWoS")print(f"Upstream: {chain['upstream']}")print(f"Midstream: {chain['midstream']}")print(f"Downstream: {chain['downstream']}")

import yfinance as yf# Taiwan tickers need .TW suffix for TWSE, .TWO for OTCtsmc = yf.Ticker("2330.TW")print(tsmc.info.get("marketCap"))