MultiFactor 0.3.2__tar.gz → 0.3.4__tar.gz

{multifactor-0.3.2 → multifactor-0.3.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: MultiFactor
-Version: 0.3.2
+Version: 0.3.4
 Summary: 멀티팩터 기반 주식 데이터 수집 패키지
 Author-email: HANHO <hanhoman@gmail.com>
 Classifier: Programming Language :: Python :: 3

{multifactor-0.3.2 → multifactor-0.3.4}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta"
 [project]
 # 1. PyPI에 등록될 배포 이름 (pip install MultiFactor)
 name = "MultiFactor"
-version = "0.3.2"
+version = "0.3.4"
 authors = [
   { name="HANHO", email="hanhoman@gmail.com" },
 ]

{multifactor-0.3.2 → multifactor-0.3.4}/src/MultiFactor/__init__.py

@@ -14,6 +14,7 @@ os.environ['PYTHONWARNINGS'] = 'ignore'
 from .core import MultiFactorKR
 from .us_core import MultiFactorUS
 from .Visual import Visual
+from .daum_consensus import get_daum_finstate, get_daum_consensus
 
 # 패키지를 import할 때 노출할 항목을 명시합니다.
-__all__ = ['MultiFactorKR', 'MultiFactorUS', 'Visual']
+__all__ = ['MultiFactorKR', 'MultiFactorUS', 'Visual', 'get_daum_finstate', 'get_daum_consensus']

multifactor-0.3.4/src/MultiFactor/daum_consensus.py

@@ -0,0 +1,131 @@
+"""다음증권 추정실적 컨센서스를 연간/분기 DataFrame으로 가져옵니다."""
+
+import json
+import re
+import time
+import ssl
+from urllib.parse import urlencode
+from urllib.request import Request, urlopen
+from urllib.error import URLError
+
+import pandas as pd
+import numpy as np
+
+CONSENSUS_URL = "https://wisefn.finance.daum.net/v1/company/cF1002.aspx"
+CONSENSUS_COLUMNS = [
+    "FY-end",
+    "주재무제표",
+    "매출액 (억원)",
+    "YoY (%)",
+    "영업이익 (억원)",
+    "당기순이익 (억원)",
+    "EPS (원)",
+    "PER (배)",
+    "PBR (배)",
+    "ROE (%)",
+    "EV/EBITDA (배)",
+    "순부채 비율 (%)",
+]
+DATA_BLOCK_PATTERN = re.compile(
+    r'\{\s*tid\s*:\s*"(?P<tab>TB_[01])"\s*,\s*'
+    r"dest\s*:\s*(?P<rows>\[\[.*?\]\])\s*\}",
+    re.DOTALL,
+)
+STOCK_CODE_PATTERN = re.compile(r"(?:A)?\d{6}")
+
+COLUMN_MAP = {
+    "매출액 (억원)": "매출액",
+    "영업이익 (억원)": "영업이익",
+    "당기순이익 (억원)": "당기순이익",
+    "PER (배)": "PER(배)",
+    "PBR (배)": "PBR(배)",
+    "ROE (%)": "ROE(%)",
+}
+
+
+def get_daum_consensus(
+    stock_code: str = "A005930",
+    timeout: float = 15,
+) -> tuple[pd.DataFrame, pd.DataFrame]:
+    """다음증권에서 종목의 연간·분기 컨센서스를 가져옵니다."""
+    clean_code = str(stock_code).strip()
+    if not STOCK_CODE_PATTERN.fullmatch(clean_code):
+        clean_code = clean_code.zfill(6)
+        if not STOCK_CODE_PATTERN.fullmatch(clean_code):
+            raise ValueError(f"올바르지 않은 종목코드 형식입니다: {stock_code}")
+
+    company_code = clean_code.removeprefix("A")
+    query = urlencode({"cmp_cd": company_code, "finGubun": "MAIN"})
+    request = Request(
+        f"{CONSENSUS_URL}?{query}",
+        headers={
+            "User-Agent": (
+                "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
+                "AppleWebKit/537.36 (KHTML, like Gecko) "
+                "Chrome/130.0.0.0 Safari/537.36"
+            ),
+            "Referer": f"https://finance.daum.net/quotes/A{company_code}",
+            "Accept": "text/html,application/xhtml+xml",
+        },
+    )
+    html = None
+    max_retries = 3
+    last_err = None
+
+    for attempt in range(max_retries):
+        try:
+            with urlopen(request, timeout=timeout) as response:
+                html = response.read().decode(
+                    response.headers.get_content_charset() or "utf-8"
+                )
+            break
+        except (URLError, ssl.SSLError, ConnectionError, OSError) as e:
+            last_err = e
+            if attempt < max_retries - 1:
+                time.sleep(1.0)
+            else:
+                raise last_err
+
+    rows_by_tab = {
+        match.group("tab"): json.loads(match.group("rows"))
+        for match in DATA_BLOCK_PATTERN.finditer(html)
+    }
+    if "TB_0" not in rows_by_tab or "TB_1" not in rows_by_tab:
+        raise ValueError(
+            "응답에서 연간/분기 컨센서스를 찾지 못했습니다. "
+            "다음증권 페이지의 데이터 형식이 변경되었을 수 있습니다."
+        )
+
+    def to_dataframe(rows: list[list[str]]) -> pd.DataFrame:
+        if any(len(row) != len(CONSENSUS_COLUMNS) for row in rows):
+            raise ValueError("컨센서스 데이터의 열 구성이 예상과 다릅니다.")
+        frame = pd.DataFrame(rows, columns=CONSENSUS_COLUMNS)
+        for column in CONSENSUS_COLUMNS[2:]:
+            values = frame[column].str.replace(",", "", regex=False)
+            frame[column] = pd.to_numeric(values, errors="coerce")
+        return frame
+
+    annual = to_dataframe(rows_by_tab["TB_0"])
+    quarterly = to_dataframe(rows_by_tab["TB_1"])
+    return annual, quarterly
+
+
+def get_daum_finstate(stock_code: str, freq: str = "Y", timeout: float = 15) -> pd.DataFrame:
+    """
+    다음증권 컨센서스를 수집하여 기존 SnapDataReader와 호환되는 컬럼 및 인덱스 구조로 반환합니다.
+    - freq: 'Y' (연간) 또는 'Q' (분기)
+    """
+    annual_df, quarterly_df = get_daum_consensus(stock_code=stock_code, timeout=timeout)
+    is_annual = freq.upper().endswith("Y") or freq.upper() == "Y"
+    df = annual_df.copy() if is_annual else quarterly_df.copy()
+
+    if "FY-end" in df.columns:
+        df.set_index("FY-end", inplace=True)
+        df.index.name = "날짜"
+
+    # 기존 SnapDataReader 컬럼명('매출액', '영업이익', 'PER(배)' 등) 매핑 추가
+    for orig_col, target_col in COLUMN_MAP.items():
+        if orig_col in df.columns:
+            df[target_col] = df[orig_col]
+
+    return df

{multifactor-0.3.2 → multifactor-0.3.4}/src/MultiFactor/quality.py

@@ -5,6 +5,11 @@ import numpy as np
 
 import time
 
+try:
+    from .daum_consensus import get_daum_finstate
+except ImportError:
+    from daum_consensus import get_daum_finstate
+
 
 def get_quality(stock_list):
     result_fin = []
@@ -18,10 +23,15 @@ def get_quality(stock_list):
             print(f"{i}/{len(stock_list)} 진행 중... ({sname})")
     
         try:
-            # 재무 데이터 추출 : 분기 K-IFRS 연결 기준
-            data = fdr.SnapDataReader(f'NAVER/FINSTATE-2Q/{scode}').dropna(subset='영업이익')  # 분기
+            # 재무 데이터 추출 : 1. SnapDataReader 먼저 시도 -> 에러 시 다음증권 컨센서스로 대체
+            try:
+                data = fdr.SnapDataReader(f'NAVER/FINSTATE-2Q/{scode}').dropna(subset='영업이익')  # 분기
+            except Exception:
+                data = get_daum_finstate(scode, freq='Q').dropna(subset='영업이익')
+
             fin = (data[['매출액','영업이익','당기순이익']].pct_change()*100).iloc[-1].to_list()
-            roe = data['ROE(%)'].iloc[-1]
+            roe_series = data['ROE(%)'].dropna()
+            roe = roe_series.iloc[-1] if not roe_series.empty else np.nan
             result_fin.append([scode] + fin + [roe])
     
         except:

multifactor-0.3.4/src/MultiFactor/quality_one.py

@@ -0,0 +1,31 @@
+import FinanceDataReader as fdr
+
+import pandas as pd
+import numpy as np
+
+try:
+    from .daum_consensus import get_daum_finstate
+except ImportError:
+    from daum_consensus import get_daum_finstate
+
+
+def get_quality_one(scode):
+    result_fin = []
+    try:
+        # 1. SnapDataReader 먼저 시도 -> 에러 시 다음증권 컨센서스로 대체
+        try:
+            data = fdr.SnapDataReader(f'NAVER/FINSTATE-2Q/{scode}').dropna(subset='영업이익')  # 분기
+        except Exception:
+            data = get_daum_finstate(scode, freq='Q').dropna(subset='영업이익')
+
+        fin = (data[['매출액','영업이익','당기순이익']].pct_change()*100).iloc[-1].to_list()
+        roe_series = data['ROE(%)'].dropna()
+        roe = roe_series.iloc[-1] if not roe_series.empty else np.nan
+        result_fin.append([scode] + fin + [roe])
+        data_fin = pd.DataFrame(result_fin, columns=['scode', 'revenue_rate', 'oper_income_rate', 'net_income_rate', 'ROE'])
+        return data_fin
+
+    except Exception as e:
+        print(f"에러가 발생했습니다. 상세 내용: {e}")
+        print("추출오류 : ", scode) # 에러 종목코드 출력
+        return None 

multifactor-0.3.4/src/MultiFactor/value.py

@@ -0,0 +1,46 @@
+import FinanceDataReader as fdr
+
+import pandas as pd
+import numpy as np
+
+import time
+
+try:
+    from .daum_consensus import get_daum_finstate
+except ImportError:
+    from daum_consensus import get_daum_finstate
+
+def get_value(stock_list):
+    
+    result = []
+    
+    for i, (scode, sname) in enumerate(stock_list.items()):
+    
+        # [중요] 데이터 수집 시 서버 차단 방지 (1초 대기)
+        time.sleep(1)
+    
+        # 진행 상황 모니터링 (50번째 순서마다 종목명 출력)
+        if i % 50 == 0:
+            print(f"{i}/{len(stock_list)} 진행 중... ({sname})")
+    
+        try:
+            # 재무제표 데이터 추출 : 1. SnapDataReader 먼저 시도 -> 에러 시 다음증권 컨센서스로 대체
+            try:
+                data = fdr.SnapDataReader(f'NAVER/FINSTATE-2Y/{scode}').dropna(subset='영업이익') # 연간
+            except Exception:
+                data = get_daum_finstate(scode, freq='Y').dropna(subset='영업이익')
+
+            per_series = data['PER(배)'].dropna()
+            pbr_series = data['PBR(배)'].dropna()
+            per = per_series.iloc[-1] if not per_series.empty else np.nan
+            pbr = pbr_series.iloc[-1] if not pbr_series.empty else np.nan
+            result.append([scode, per, pbr])
+    
+        except Exception as e:
+            print("추출오류 : ", sname, f"({type(e).__name__}: {e})") # 에러 종목코드 및 원인 출력
+            result.append([scode, None, None])
+
+    
+    data_val = pd.DataFrame(result, columns=['scode', 'PER', 'PBR'])
+
+    return data_val 

multifactor-0.3.4/src/MultiFactor/value_one.py

@@ -0,0 +1,34 @@
+import FinanceDataReader as fdr
+
+import pandas as pd
+import numpy as np
+
+try:
+    from .daum_consensus import get_daum_finstate
+except ImportError:
+    from daum_consensus import get_daum_finstate
+
+
+def get_value_one(scode):
+    
+    result = []
+    
+    try:
+        # 1. SnapDataReader 먼저 시도 -> 에러 시 다음증권 컨센서스로 대체
+        try:
+            data = fdr.SnapDataReader(f'NAVER/FINSTATE-2Y/{scode}').dropna(subset='영업이익') # 연간
+        except Exception:
+            data = get_daum_finstate(scode, freq='Y').dropna(subset='영업이익')
+
+        per_series = data['PER(배)'].dropna()
+        pbr_series = data['PBR(배)'].dropna()
+        per = per_series.iloc[-1] if not per_series.empty else np.nan
+        pbr = pbr_series.iloc[-1] if not pbr_series.empty else np.nan
+        result.append([scode, per, pbr])
+        data_val = pd.DataFrame(result, columns=['scode', 'PER', 'PBR'])
+        return data_val 
+
+    except Exception as e:
+        print(f"에러가 발생했습니다. 상세 내용: {e}")
+        print("추출오류 : ", scode) # 에러 종목코드 출력
+        return None   

{multifactor-0.3.2 → multifactor-0.3.4}/src/MultiFactor/vfinance_kr.py

@@ -10,6 +10,10 @@ import concurrent.futures
 # 데이터 수집 라이브러리
 import FinanceDataReader as fdr
 import yfinance as yf
+try:
+	from .daum_consensus import get_daum_finstate
+except ImportError:
+	from daum_consensus import get_daum_finstate
 
 # 시각화 라이브러리
 import matplotlib.pyplot as plt
@@ -57,13 +61,17 @@ def finance_kr():
 
 		# --- [2] 밸류 & 퀄리티 지표: 재무 데이터 막대그래프 ---
 		try:
-			# 연간(Y) 또는 분기(Q) 재무제표 동적 수집
-			fs = fdr.SnapDataReader(f'NAVER/FINSTATE-{YQ}/{stock_code}')
+			# 연간(Y) 또는 분기(Q) 재무제표 동적 수집 (SnapDataReader 먼저 시도 -> 에러 시 다음증권 대체)
+			try:
+				fs = fdr.SnapDataReader(f'NAVER/FINSTATE-{YQ}/{stock_code}')
+			except Exception:
+				fs = get_daum_finstate(stock_code, freq=YQ)
+
 			period_text = "연간" if YQ == 'Y' else "분기"
 
 			cols = ['PER(배)', 'PBR(배)', 'ROE(%)', '매출액', '영업이익', '당기순이익']
 			res = fs[cols].T.dropna(axis=1, how='all')
-			res.columns = [x.strftime('%y-%m') for x in res.columns]
+			res.columns = [x.strftime('%y-%m') if hasattr(x, 'strftime') else str(x) for x in res.columns]
 
 			fig_vq, axes = plt.subplots(2, 3, figsize=(14, 8), tight_layout=True)
 			fig_vq.suptitle(f"[{stock_name}] 밸류 & 퀄리티 지표 ({period_text} 재무제표)", fontsize=15, fontweight='bold', y=1.02)

{multifactor-0.3.2 → multifactor-0.3.4}/src/MultiFactor.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: MultiFactor
-Version: 0.3.2
+Version: 0.3.4
 Summary: 멀티팩터 기반 주식 데이터 수집 패키지
 Author-email: HANHO <hanhoman@gmail.com>
 Classifier: Programming Language :: Python :: 3

{multifactor-0.3.2 → multifactor-0.3.4}/src/MultiFactor.egg-info/SOURCES.txt

@@ -3,6 +3,7 @@ pyproject.toml
 src/MultiFactor/Visual.py
 src/MultiFactor/__init__.py
 src/MultiFactor/core.py
+src/MultiFactor/daum_consensus.py
 src/MultiFactor/momentum.py
 src/MultiFactor/momentum_one.py
 src/MultiFactor/quality.py

multifactor-0.3.2/src/MultiFactor/quality_one.py

@@ -1,21 +0,0 @@
-import FinanceDataReader as fdr
-
-import pandas as pd
-import numpy as np
-
-
-def get_quality_one(scode):
-    result_fin = []
-    try:
-        # 재무 데이터 추출 : 분기 K-IFRS 연결 기준
-        data = fdr.SnapDataReader(f'NAVER/FINSTATE-2Q/{scode}').dropna(subset='영업이익')  # 분기
-        fin = (data[['매출액','영업이익','당기순이익']].pct_change()*100).iloc[-1].to_list()
-        roe = data['ROE(%)'].iloc[-1]
-        result_fin.append([scode] + fin + [roe])
-        data_fin = pd.DataFrame(result_fin, columns=['scode', 'revenue_rate', 'oper_income_rate', 'net_income_rate', 'ROE'])
-        return data_fin
-
-    except Exception as e:
-        print(f"에러가 발생했습니다. 상세 내용: {e}")
-        print("추출오류 : ", sname) # 에러 종목코드 출력
-        return None 

multifactor-0.3.2/src/MultiFactor/value.py

@@ -1,34 +0,0 @@
-import FinanceDataReader as fdr
-
-import pandas as pd
-import numpy as np
-
-import time
-
-def get_value(stock_list):
-    
-    result = []
-    
-    for i, (scode, sname) in enumerate(stock_list.items()):
-    
-        # [중요] 데이터 수집 시 서버 차단 방지 (1초 대기)
-        time.sleep(1)
-    
-        # 진행 상황 모니터링 (50번째 순서마다 종목명 출력)
-        if i % 50 == 0:
-            print(f"{i}/{len(stock_list)} 진행 중... ({sname})")
-    
-        try:
-            # 재무제표 데이터 추출 (연간 K-IFRS 연결 기준)
-            data = fdr.SnapDataReader(f'NAVER/FINSTATE-2Y/{scode}').dropna(subset='영업이익') # 연간
-            per, pbr = data['PER(배)'].iloc[-1], data['PBR(배)'].iloc[-1]
-            result.append([scode, per, pbr])
-    
-        except:
-            print("추출오류 : ", sname) # 에러 종목코드 출력
-            result.append([scode, None, None])
-
-    
-    data_val = pd.DataFrame(result, columns=['scode', 'PER', 'PBR'])
-
-    return data_val 

multifactor-0.3.2/src/MultiFactor/value_one.py

@@ -1,22 +0,0 @@
-import FinanceDataReader as fdr
-
-import pandas as pd
-import numpy as np
-
-
-def get_value_one(scode):
-    
-    result = []
-    
-    try:
-        # 재무제표 데이터 추출 (연간 K-IFRS 연결 기준)
-        data = fdr.SnapDataReader(f'NAVER/FINSTATE-2Y/{scode}').dropna(subset='영업이익') # 연간
-        per, pbr = data['PER(배)'].iloc[-1], data['PBR(배)'].iloc[-1]
-        result.append([scode, per, pbr])
-        data_val = pd.DataFrame(result, columns=['scode', 'PER', 'PBR'])
-        return data_val 
-
-    except Exception as e:
-        print(f"에러가 발생했습니다. 상세 내용: {e}")
-        print("추출오류 : ", sname) # 에러 종목코드 출력
-        return None