import re import sys from pathlib import Path import pandas as pd # ------------------------------------------------------------ # Market_Wave 用：ツリー移転対応版 # この .py を C:\Users\machi\Market_Wave\05_ツール に置けば、 # 自動で C:\Users\machi\Market_Wave を基準にします。 # ------------------------------------------------------------ SCRIPT_DIR = Path(__file__).resolve().parent BASE = SCRIPT_DIR.parent TEXT_DIR = BASE / "00_波テキスト" OUT_DIR = BASE / "01_波Excel" OUT_DIR.mkdir(parents=True, exist_ok=True) ZEN2HAN = str.maketrans("０１２３４５６７８９", "0123456789") def normalize_text(s: str) -> str: return s.translate(ZEN2HAN) def extract_date(text: str): text = normalize_text(text) m = re.search(r"\d{4}-\d{2}-\d{2}", text) return m.group(0) if m else None def pick_txt_files(arg): """ 1) 引数なし -> inside_log_*.txt 全部 2) 日付指定 -> inside_log_日付.txt だけ 3) フルパス指定 -> その1ファイルだけ """ if not arg: return None, sorted(TEXT_DIR.glob("inside_log_*.txt")) arg_norm = normalize_text(arg) p = Path(arg) if p.exists() and p.is_file() and p.suffix.lower() == ".txt": target_date = extract_date(p.name) or p.stem return target_date, [p] target_date = extract_date(arg_norm) or arg_norm txt_files = sorted(TEXT_DIR.glob(f"inside_log_{target_date}.txt")) return target_date, txt_files def parse_30min_inside(txt_file: Path, text: str): rows = [] blocks = re.split(r"\n(?=\d{4}_.+?30分足の中身透視レーダー 開始)", text) for block in blocks: m = re.search(r"(\d{4}_.+?)\s*30分足の中身透視レーダー 開始", block) if not m: continue name = m.group(1).strip() for line in block.splitlines(): # 例: 1 09:00-09:30 2835.5 2855 ... if re.match(r"\s*\d+\s+\d{2}:\d{2}-\d{2}:\d{2}", line): parts = line.split() try: rows.append({ "元ファイル": txt_file.name, "銘柄": name, "区間": parts[1], "始値": float(parts[2]), "高値": float(parts[3]), "安値": float(parts[4]), "終値": float(parts[5]), "出来高": int(float(parts[6])), "30分方向": parts[7], "波の数": int(parts[8]), "中身判定": " ".join(parts[9:]), }) except Exception as e: print("30分読み取り失敗:", name, line, e) return rows def parse_1min_wave(txt_file: Path, text: str): rows = [] lines = text.splitlines() current_name = None current_date = None in_table = False for line in lines: raw = normalize_text(line).strip() if not raw: continue # 例: 464A_QPS　2026-06-29　1分波観測一覧 m = re.search(r"(\d{3,4}[A-Z]?_.+?)\s+(\d{4}-\d{2}-\d{2})\s+1分波観測一覧", raw.replace("　", " ")) if m: current_name = m.group(1).strip() current_date = m.group(2) in_table = True continue if "日別まとめ" in raw: in_table = False continue # 例: 09:00-09:01 1906.0 1883.0 92400 1.03 強い下落 第1波_下げ波 戻り売り確認 if in_table and current_name and re.match(r"^\d{2}:\d{2}-\d{2}:\d{2}\s+", raw): parts = raw.split() try: rows.append({ "元ファイル": txt_file.name, "日付": current_date, "銘柄": current_name, "区間": parts[0], "始値": float(parts[1]), "終値": float(parts[2]), "出来高": int(float(parts[3])), "出来高倍率": float(parts[4]), "方向": parts[5], "波判定": parts[6] if len(parts) >= 7 else "", "罠判定": " ".join(parts[7:]) if len(parts) >= 8 else "", }) except Exception as e: print("1分波読み取り失敗:", current_name, raw, e) return rows def autosize_excel(path: Path): try: from openpyxl import load_workbook from openpyxl.styles import Font, PatternFill, Alignment, Border, Side from openpyxl.utils import get_column_letter wb = load_workbook(path) header_fill = PatternFill("solid", fgColor="1F4E78") header_font = Font(color="FFFFFF", bold=True) thin = Side(style="thin", color="D9E2F3") border = Border(left=thin, right=thin, top=thin, bottom=thin) for ws in wb.worksheets: ws.freeze_panes = "A2" ws.auto_filter.ref = ws.dimensions for cell in ws[1]: cell.fill = header_fill cell.font = header_font cell.alignment = Alignment(horizontal="center", vertical="center") cell.border = border for row in ws.iter_rows(min_row=2): for cell in row: cell.border = border cell.alignment = Alignment(vertical="center") for col in ws.columns: col_letter = get_column_letter(col[0].column) max_len = max(len(str(c.value)) if c.value is not None else 0 for c in col) ws.column_dimensions[col_letter].width = min(max(max_len + 2, 10), 28) wb.save(path) except Exception as e: print("Excel整形はスキップしました:", e) def main(): arg = sys.argv[1] if len(sys.argv) >= 2 else None target_date, txt_files = pick_txt_files(arg) if not txt_files: print("対象ファイルが見つかりません") print(f"指定: {arg}") print(f"検索場所: {TEXT_DIR}") sys.exit(1) rows_30 = [] rows_wave = [] for txt_file in txt_files: text = txt_file.read_text(encoding="utf-8", errors="ignore") text = normalize_text(text) rows_30.extend(parse_30min_inside(txt_file, text)) rows_wave.extend(parse_1min_wave(txt_file, text)) df30 = pd.DataFrame(rows_30) dfwave = pd.DataFrame(rows_wave) if target_date: out_file = OUT_DIR / f"all_inside_radar_summary_{target_date}.xlsx" else: out_file = OUT_DIR / "all_inside_radar_summary.xlsx" with pd.ExcelWriter(out_file, engine="openpyxl") as writer: if not df30.empty: df30.to_excel(writer, index=False, sheet_name="全銘柄_30分中身") summary30 = ( df30.groupby("銘柄") .agg(総出来高=("出来高", "sum"), 総波数=("波の数", "sum"), 平均波数=("波の数", "mean"), 区間数=("区間", "count")) .reset_index() ) summary30.to_excel(writer, index=False, sheet_name="30分_銘柄別summary") if not dfwave.empty: dfwave.to_excel(writer, index=False, sheet_name="全銘柄_1分波") summary_wave = ( dfwave.groupby("銘柄") .agg( 日付=("日付", "first"), 総出来高=("出来高", "sum"), 最大出来高=("出来高", "max"), 最大出来高倍率=("出来高倍率", "max"), 記録行数=("区間", "count"), 上げ波回数=("波判定", lambda s: s.astype(str).str.contains("上げ波").sum()), 下げ波回数=("波判定", lambda s: s.astype(str).str.contains("下げ波").sum()), ) .reset_index() ) summary_wave.to_excel(writer, index=False, sheet_name="1分波_銘柄別summary") if df30.empty and dfwave.empty: pd.DataFrame([{ "メッセージ": "読み取れる行がありませんでした", "確認": "入力ログの形式が想定外か、表部分が貼り付けられていない可能性があります。", }]).to_excel(writer, index=False, sheet_name="読み取り結果") autosize_excel(out_file) print("保存完了") print(out_file) print(f"処理ファイル数: {len(txt_files)}") print(f"30分中身 行数: {len(df30)}") print(f"1分波 行数: {len(dfwave)}") for f in txt_files: print(f"処理: {f.name}") if __name__ == "__main__": main()