scraper2-hj3415 1.0.1__py3-none-any.whl → 2.1.0__py3-none-any.whl

scraper2_hj3415/adapters/clients/http.py

@@ -1,51 +0,0 @@
-# src/scraper2_hj3415/adapters/clients/http.py
-
-import httpx
-from tenacity import retry, stop_after_attempt, wait_exponential, retry_if_exception_type
-
-# HTTPX 에러용 커스텀 예외
-class HttpClientError(Exception):
-    """기본 HTTP 클라이언트 예외."""
-
-# 재시도 데코레이터 (옵션)
-def retry_on_http_error():
-    return retry(
-        reraise=True,
-        stop=stop_after_attempt(3),
-        wait=wait_exponential(min=1, max=10),
-        retry=retry_if_exception_type((httpx.RequestError, httpx.HTTPStatusError)),
-    )
-
-# AsyncClient를 생성하는 팩토리 함수
-def create_http_client(
-    base_url: str | None = None,
-    timeout: float = 10.0,
-    headers: dict | None = None,
-) -> httpx.AsyncClient:
-    """
-    공통 설정을 가진 httpx.AsyncClient 인스턴스를 생성합니다.
-
-    Args:
-        base_url: 기본 URL (있으면 모든 요청이 상대경로로 가능)
-        timeout: 요청 타임아웃 (초)
-        headers: 기본 헤더 (없으면 User-Agent 자동 설정)
-    """
-    default_headers = {
-        "User-Agent": (
-        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) "
-        "AppleWebKit/537.36 (KHTML, like Gecko) "
-        "Chrome/127.0.0.0 Safari/537.36"
-        ),
-    }
-    if headers:
-        default_headers.update(headers)
-
-    client = httpx.AsyncClient(
-        base_url=base_url or "",
-        timeout=httpx.Timeout(timeout),
-        headers=default_headers,
-        follow_redirects=True,
-        verify=True,  # SSL 검증
-    )
-    return client
-

scraper2_hj3415/adapters/nfs/pipelines/c1034_pipeline.py

@@ -1,55 +0,0 @@
-# scraper2_hj3415/adapters/nfs/pipelines/c1034_pipeline.py
-
-import asyncio
-from typing import List, Callable
-from playwright.async_api import Browser
-from scraper2_hj3415.core import constants as C
-from scraper2_hj3415.core.types import NormalizedBundle
-from scraper2_hj3415.adapters.nfs.sources import c1034_fetch as fetch, c1034_session as session
-from scraper2_hj3415.adapters.nfs.pipelines.normalize_c1034 import normalize_dispatch
-from loguru import logger
-
-async def list_bundles(
-    page: C.PAGE,
-    cmp_cd: str,
-    rpt_enum: type[C.C103RPT | C.C104RPT],
-    get_data_func: Callable,
-    *,
-    browser: Browser | None = None,
-    concurrency: int = 2,
-) -> list[NormalizedBundle]:
-    sem = asyncio.Semaphore(max(1, concurrency))
-    session_info = await session.extract_session_info(browser=browser, cmp_cd=cmp_cd, page=page)
-
-    async def _one(rpt, frq):
-        async with sem:
-            meta = {"cmp_cd": cmp_cd, "page": page, "rpt": rpt, "frq": frq}
-            payload = await get_data_func(session_info=session_info, cmp_cd=cmp_cd, rpt=rpt, frq=frq)
-            return normalize_dispatch(payload, meta)
-
-    tasks = [_one(rpt, frq) for rpt in rpt_enum for frq in (C.FRQ.Q, C.FRQ.Y)]
-    results = await asyncio.gather(*tasks, return_exceptions=True)
-    bundles: list[NormalizedBundle] = []
-    for r in results:
-        if isinstance(r, Exception):
-            logger.warning(f"{C.PAGE_TO_LABEL[page]} partial failure: {r}")
-            continue
-        bundles.append(r)
-    return bundles
-
-async def list_c103_bundles(
-    cmp_cd: str,
-    *,
-    browser: Browser | None = None,
-    concurrency: int = 3,   # 분기/연간 총 6페이지 중 절반
-) -> List[NormalizedBundle]:
-    return await list_bundles(C.PAGE.c103, cmp_cd, C.C103RPT, fetch.get_c103_data, browser=browser, concurrency=concurrency)
-
-async def list_c104_bundles(
-    cmp_cd: str,
-    *,
-    browser: Browser | None = None,
-    concurrency: int = 5,   # 분기/연간 총 10페이지 중 절반
-) -> List[NormalizedBundle]:
-    return await list_bundles(C.PAGE.c104, cmp_cd, C.C104RPT, fetch.get_c104_data, browser=browser, concurrency=concurrency)
-

scraper2_hj3415/adapters/nfs/pipelines/normalize_c1034.py

@@ -1,109 +0,0 @@
-# scraper2_hj3415/adapters/nfs/pipeline/normalize_c1034.py
-
-import re
-import pandas as pd
-from scraper2_hj3415.core import constants as C
-from scraper2_hj3415.core.types import NormalizedBundle
-from scraper2_hj3415.adapters._shared.utils import log_df
-
-def _parse_yymm(lbl: str):
-    s = re.sub(r"<br\s*/?>", " ", lbl).strip()
-    # 날짜가 아닌 지표 라벨들(전년/전분기 비교 섹션) 필터링
-    if any(key in s for key in ["전년대비", "YoY", "QoQ", "전분기대비"]):
-        return {"label": s, "period": None, "basis": None, "is_estimate": False, "is_yoy_row": True}
-    est = "(E)" in s
-    m = re.search(r"(\d{4})/(\d{2})", s)
-    period = pd.Timestamp(f"{m.group(1)}-{m.group(2)}-01") if m else None
-    b = re.search(r"\(([^)]+)\)$", s.replace("(E)","").strip())
-    basis = b.group(1) if b else None
-    return {"label": s, "period": period, "basis": basis, "is_estimate": est, "is_yoy_row": False}
-
-def normalize_metric_rows(rows: list[dict], yymm: list[str], *, frq: C.FRQ, rate_fields: dict, meta: dict):
-    lab = pd.DataFrame([_parse_yymm(x) for x in yymm]).rename_axis("pos").reset_index()
-    lab_valid = lab[~lab["is_yoy_row"]].copy().reset_index(drop=True)
-    lab_valid["pos1"] = lab_valid.index + 1  # DATA1..K 매핑용
-    df = pd.DataFrame(rows)
-
-    # enum 값을 이해하기 쉬운 라벨로 변환
-    meta_lbl = {
-        "cmp_cd": meta["cmp_cd"],
-        "page": C.PAGE_TO_LABEL[meta["page"]],
-        "rpt": C.RPT_TO_LABEL[meta["rpt"]],
-        "frq": C.FRQ_TO_LABEL[meta["frq"]],
-    }
-
-    # fact 처리
-    k = len(lab_valid)
-    data_cols = [f"DATA{i}" for i in range(1, k+1) if f"DATA{i}" in df.columns]
-
-    long = df.melt(
-        id_vars=["ACCODE","ACC_NM","LVL","P_ACCODE","GRP_TYP","UNT_TYP","ACKIND","POINT_CNT"],
-        value_vars=data_cols, var_name="data_col", value_name="value"
-    )
-    long["pos1"] = long["data_col"].str.replace("DATA","",regex=False).astype(int)
-    long = long.merge(lab_valid[["pos1","period","basis","is_estimate"]], on="pos1", how="inner")
-    long = long.dropna(subset=["period", "value"])
-
-    for k in ["cmp_cd","page","rpt","frq"]:
-        long[k] = meta_lbl[k]
-    fact = (long
-        .drop(columns=["data_col","pos1"])
-        .rename(columns={
-            "ACCODE":"accode","ACC_NM":"account_name","LVL":"level",
-            "P_ACCODE":"parent_accode","GRP_TYP":"group_type","UNT_TYP":"unit_type",
-            "ACKIND":"acc_kind","POINT_CNT":"precision"
-        })
-        .reset_index(drop=True)
-    )
-
-    # dim_account 처리
-    dim_account = (fact[["accode","account_name","level","parent_accode","group_type","unit_type","acc_kind","precision"]]
-                   .drop_duplicates().reset_index(drop=True))
-
-    # dim_period 처리
-    dim_period = (lab_valid[["period","basis","is_estimate"]].dropna(subset=["period"]).drop_duplicates().reset_index(drop=True))
-    dim_period["frq"] = meta_lbl["frq"]
-
-    # delta 처리
-    rate_numeric = rate_fields.get("numeric", [])
-    rate_comments = rate_fields.get("comments", [])
-    use_cols = ["ACCODE"] + [c for c in rate_numeric+rate_comments if c in df.columns]
-    if len(use_cols) > 1:
-        delta = df[use_cols].copy().rename(columns={"ACCODE":"accode"})
-        for k in ["cmp_cd","page","rpt","frq"]:
-            delta[k] = meta_lbl[k]
-    else:
-        delta = pd.DataFrame(columns=["accode"] + rate_numeric + rate_comments + ["cmp_cd","page","rpt","frq"])
-
-    # 데이터프레임 로그출력
-    log_df(fact, "fact_df", 1000)
-    log_df(dim_account, "dim_account_df", 1000)
-    log_df(dim_period, "dim_period_df", 1000)
-    log_df(delta, "delta_df", 1000)
-
-    return fact, dim_account, dim_period, delta
-
-def normalize_quarter_payload(payload: dict, meta: dict):
-    return normalize_metric_rows(
-        payload["DATA"], payload["YYMM"], frq=C.FRQ.Q,
-        rate_fields={"numeric":["QOQ","QOQ_E"], "comments":["QOQ_COMMENT","QOQ_E_COMMENT"]},
-        meta=meta,
-    )
-
-def normalize_year_payload(payload: dict, meta: dict):
-    return normalize_metric_rows(
-        payload["DATA"], payload["YYMM"], frq=C.FRQ.Y,
-        rate_fields={"numeric":["YYOY","YEYOY"], "comments":[]},
-        meta=meta,
-    )
-
-def normalize_dispatch(payload: dict, meta: dict) -> NormalizedBundle:
-    """frq에 따라 분기/연간 정규화를 자동 선택."""
-    frq: C.FRQ = meta["frq"]
-    if frq == C.FRQ.Q:
-        fact, dim_account, dim_period, delta = normalize_quarter_payload(payload, meta)
-    elif frq == C.FRQ.Y:
-        fact, dim_account, dim_period, delta = normalize_year_payload(payload, meta)
-    else:
-        raise ValueError(f"Unsupported FRQ: {frq!r}")
-    return NormalizedBundle(fact, dim_account, dim_period, delta)

scraper2_hj3415/adapters/nfs/sinks/c1034_sink.py

@@ -1,51 +0,0 @@
-# scraper2_hj3415/adapters/nfs/sinks/c1034_sink.py
-
-import pandas as pd
-
-from .df_to_dto_mappers import (
-    rows_to_dim_account, rows_to_dim_period,
-    rows_to_fact_finance, rows_to_delta_finance,
-)
-from scraper2_hj3415.adapters._shared.utils import chunked
-from scraper2_hj3415.core.ports.sink_port import C1034SinkPort
-from contracts_hj3415.ports.c1034_write_repo import C1034WriteRepoPort
-
-DEFAULT_CHUNK = 1_000
-
-class C1034Sink(C1034SinkPort):
-    def __init__(self, repo: C1034WriteRepoPort, chunk: int = DEFAULT_CHUNK):
-        self.repo = repo
-        self.chunk = chunk
-
-    async def save_dim_account(self, df: pd.DataFrame) -> None:
-        for batch in chunked(rows_to_dim_account(df), self.chunk):
-            await self.repo.upsert_dim_account(batch)
-
-    async def save_dim_period(self, df: pd.DataFrame) -> None:
-        for batch in chunked(rows_to_dim_period(df), self.chunk):
-            await self.repo.upsert_dim_period(batch)
-
-    async def save_fact_finance(self, df: pd.DataFrame) -> None:
-        for batch in chunked(rows_to_fact_finance(df), self.chunk):
-            await self.repo.upsert_fact_finance(batch)
-
-    async def save_delta_finance(self, df: pd.DataFrame) -> None:
-        for batch in chunked(rows_to_delta_finance(df), self.chunk):
-            await self.repo.upsert_delta_finance(batch)
-
-    async def save_all(
-        self,
-        *,
-        dim_account_df: pd.DataFrame,
-        dim_period_df: pd.DataFrame,
-        fact_df: pd.DataFrame,
-        delta_df: pd.DataFrame,
-    ) -> None:
-        if dim_account_df is not None:
-            await self.save_dim_account(dim_account_df)
-        if dim_period_df is not None:
-            await self.save_dim_period(dim_period_df)
-        if fact_df is not None:
-            await self.save_fact_finance(fact_df)
-        if delta_df is not None:
-            await self.save_delta_finance(delta_df)

scraper2_hj3415/adapters/nfs/sinks/df_to_dto_mappers.py

@@ -1,106 +0,0 @@
-# scraper2_hj3415/adapters/nfs/sinks/mappers.py
-# DF → DTO 변환 유틸
-
-from typing import Iterator
-import math
-import pandas as pd
-from pydantic import ValidationError
-from contracts_hj3415.nfs.dto import FactC1034DTO, DimAccountDTO, DimPeriodDTO, DeltaC1034DTO
-
-def _none_if_nan(v):
-    # pandas NaN/NaT → None
-    if v is None:
-        return None
-    if isinstance(v, float) and math.isnan(v):
-        return None
-    if pd.isna(v):
-        return None
-    return v
-
-def rows_to_dim_account(df: pd.DataFrame) -> Iterator[DimAccountDTO]:
-    # 기대 컬럼: ['accode','account_name','level','parent_accode','group_type','unit_type','acc_kind','precision']
-    for row in df.itertuples(index=False):
-        try:
-            yield DimAccountDTO(
-                accode=row.accode,
-                account_name=row.account_name,
-                level=_none_if_nan(getattr(row, "level", None)),
-                parent_accode=_none_if_nan(getattr(row, "parent_accode", None)),
-                group_type=_none_if_nan(getattr(row, "group_type", None)),
-                unit_type=_none_if_nan(getattr(row, "unit_type", None)),
-                acc_kind=_none_if_nan(getattr(row, "acc_kind", None)),
-                precision=_none_if_nan(getattr(row, "precision", None)),
-            )
-        except ValidationError:
-            # 필요시 로깅/수집
-            continue
-
-def _sanitize_basis(v):
-    return "" if v is None or (isinstance(v, float) and pd.isna(v)) else v
-
-def rows_to_dim_period(df: pd.DataFrame) -> Iterator[DimPeriodDTO]:
-    # 기대 컬럼: ['period','basis','is_estimate','frq']
-    # period는 반드시 date로 변환되어 있어야 안전
-    if df["period"].dtype != "datetime64[ns]":
-        df = df.copy()
-        df["period"] = pd.to_datetime(df["period"], errors="coerce").dt.date
-
-    for row in df.itertuples(index=False):
-        try:
-            yield DimPeriodDTO(
-                period=row.period,
-                basis=_sanitize_basis(getattr(row, "basis", None)),
-                is_estimate=bool(getattr(row, "is_estimate", False)),
-                frq=row.frq,
-            )
-        except ValidationError:
-            continue
-
-def rows_to_fact_finance(df: pd.DataFrame) -> Iterator[FactC1034DTO]:
-    # 기대 컬럼: ['cmp_cd','page','rpt','frq','accode','account_name','period','value', ...옵션들]
-    if df["period"].dtype != "datetime64[ns]":
-        df = df.copy()
-        df["period"] = pd.to_datetime(df["period"], errors="coerce").dt.date
-
-    for row in df.itertuples(index=False):
-        try:
-            yield FactC1034DTO(
-                cmp_cd=row.cmp_cd,
-                page=row.page,
-                rpt=row.rpt,
-                frq=row.frq,
-                accode=row.accode,
-                account_name=row.account_name,
-                period=row.period,
-                value=float(row.value),
-                basis=_none_if_nan(getattr(row, "basis", None)),
-                is_estimate=bool(getattr(row, "is_estimate", False)),
-                unit_type=_none_if_nan(getattr(row, "unit_type", None)),
-                level=_none_if_nan(getattr(row, "level", None)),
-                parent_accode=_none_if_nan(getattr(row, "parent_accode", None)),
-                group_type=_none_if_nan(getattr(row, "group_type", None)),
-                acc_kind=_none_if_nan(getattr(row, "acc_kind", None)),
-                precision=_none_if_nan(getattr(row, "precision", None)),
-            )
-        except (ValidationError, TypeError, ValueError):
-            continue
-
-def rows_to_delta_finance(df: pd.DataFrame) -> Iterator[DeltaC1034DTO]:
-    # 기대 컬럼: ['cmp_cd','page','rpt','frq','accode','qoq','yoy','qoq_e','yoy_e','qoq_comment','yoy_comment']
-    for row in df.itertuples(index=False):
-        try:
-            yield DeltaC1034DTO(
-                cmp_cd=row.cmp_cd,
-                page=row.page,
-                rpt=row.rpt,
-                frq=row.frq,
-                accode=row.accode,
-                qoq=_none_if_nan(getattr(row, "qoq", None)),
-                yoy=_none_if_nan(getattr(row, "yoy", None)),
-                qoq_e=_none_if_nan(getattr(row, "qoq_e", None)),
-                yoy_e=_none_if_nan(getattr(row, "yoy_e", None)),
-                qoq_comment=_none_if_nan(getattr(row, "qoq_comment", None)),
-                yoy_comment=_none_if_nan(getattr(row, "yoy_comment", None)),
-            )
-        except ValidationError:
-            continue

scraper2_hj3415/adapters/nfs/sources/bundle_source.py

@@ -1,24 +0,0 @@
-# scraper2_hj3415/adapters/nfs/sources/bundle_source.py
-
-from typing import List, Literal
-from scraper2_hj3415.core.types import NormalizedBundle
-from scraper2_hj3415.core.ports.source_port import C1034BundleSourcePort
-from scraper2_hj3415.adapters.nfs.pipelines.c1034_pipeline import list_c103_bundles, list_c104_bundles
-from scraper2_hj3415.adapters.clients.browser import PlaywrightSession  # 세션은 Adapter에서 관리
-
-class NfsBundleSource(C1034BundleSourcePort):
-    def __init__(self, session: PlaywrightSession):
-        self.session = session
-        self.browser = session.browser
-
-    async def list_bundles(
-        self,
-        cmp_cd: str,
-        page: Literal["c103", "c104"],
-        *,
-        concurrency: int = 2,
-    ) -> List[NormalizedBundle]:
-        if page == "c103":
-            return await list_c103_bundles(cmp_cd, browser=self.browser, concurrency=concurrency)
-        else:
-            return await list_c104_bundles(cmp_cd, browser=self.browser, concurrency=concurrency)

scraper2_hj3415/adapters/nfs/sources/c1034_fetch.py

@@ -1,117 +0,0 @@
-# scraper2-hj3415/adapters/nfs/sources/c1034_fetch.py
-
-import httpx
-from loguru import logger
-from scraper2_hj3415.core.constants import ASPXInner, FRQ, C103RPT, C104RPT
-from scraper2_hj3415.adapters.clients.http import create_http_client
-
-async def fetch_financial_json(
-    *,
-    cmp_cd: str = "005930",
-    aspx_inner: ASPXInner = ASPXInner.c103,
-    rpt: C103RPT | C104RPT = C103RPT.손익계산서,
-    frq: FRQ = FRQ.Y,
-    encparam: str,
-    cookies: str,
-    referer: str,
-    user_agent: str,
-) -> dict | list:
-    if not encparam:
-        raise ValueError("encparam is missing")
-
-    request_url = f"https://navercomp.wisereport.co.kr/v2/company/{aspx_inner}?cmp_cd={cmp_cd}"
-
-    params = {
-        "cmp_cd": cmp_cd,
-        "frq": frq,
-        "rpt": rpt,
-        "finGubun": "MAIN",
-        "frqTyp": frq,  # 연간
-        "encparam": encparam,
-    }
-    
-    headers = {
-        "Cookie": cookies,
-        "Referer": referer,
-        "User-Agent": user_agent,
-        "Accept": "application/json, text/javascript, */*; q=0.01",
-        "X-Requested-With": "XMLHttpRequest",  # 일부 서버가 AJAX 헤더 선호
-    }
-
-    async with create_http_client(timeout=10.0) as client:
-        r = await client.get(request_url, params=params, headers=headers)
-        r.raise_for_status()
-        try:
-            import json
-            payload = r.json()
-            for i, row in enumerate(payload["DATA"]):
-                logger.debug(
-                    "row {}/{} ACC_NM={}, ACCODE={}",
-                    i + 1,
-                    len(payload["DATA"]),
-                    row.get("ACC_NM"),
-                    row.get("ACCODE"),
-                )
-                logger.debug(
-                    "row raw:\n{}", json.dumps(row, indent=2, ensure_ascii=False)
-                )
-            return payload
-        except Exception:
-            # text/html이더라도 JSON 형태면 그대로 파싱 시도
-            text = r.text.strip()
-            if text.startswith("{") or text.startswith("["):
-                import json
-                return json.loads(text)
-            # 진짜 HTML일 경우만 예외 발생
-            ctype = r.headers.get("Content-Type", "")
-            snippet = text[:2000]
-            raise httpx.HTTPStatusError(
-                f"Unexpected content-type: {ctype}. Snippet:\n{snippet}",
-                request=r.request,
-                response=r,
-            )
-
-async def get_c103_data(
-    *,
-    session_info : dict,
-    cmp_cd: str = "005930",
-    rpt: C103RPT = C103RPT.손익계산서,
-    frq: FRQ = FRQ.Y,
-) -> dict | list:
-
-    aspx_inner = ASPXInner.c103
-
-    resp = await fetch_financial_json(
-        cmp_cd=cmp_cd,
-        aspx_inner=aspx_inner,
-        rpt=rpt,
-        frq=frq,
-        encparam=session_info["encparam"],
-        cookies=session_info["cookies"],
-        referer=session_info["referer"],
-        user_agent=session_info["user_agent"],
-    )
-
-    return resp
-
-async def get_c104_data(
-        *,
-        session_info : dict,
-        cmp_cd: str = "005930",
-        rpt: C104RPT = C104RPT.수익성,
-        frq: FRQ = FRQ.Y,
-) -> dict | list:
-
-    aspx_inner = ASPXInner.c104
-
-    resp = await fetch_financial_json(
-        cmp_cd=cmp_cd,
-        aspx_inner=aspx_inner,
-        rpt=rpt,
-        frq=frq,
-        encparam=session_info["encparam"],
-        cookies=session_info["cookies"],
-        referer=session_info["referer"],
-        user_agent=session_info["user_agent"],
-    )
-    return resp

scraper2_hj3415/adapters/nfs/sources/c1034_session.py

@@ -1,90 +0,0 @@
-# scraper2_hj3415/adapters/nfs/sources/c1034_session.py
-
-import re
-from loguru import logger
-
-from scraper2_hj3415.adapters.clients.browser import browser_context
-from scraper2_hj3415.core.constants import PAGE
-from playwright.async_api import Browser
-
-async def extract_session_info(
-    *,
-    browser: Browser | None = None,
-    cmp_cd: str = "005930",
-    page: PAGE = PAGE.c103,
-) -> dict:
-    """
-    Playwright로 referer/UA/쿠키/encparam만 추출.
-    - 외부 browser가 있으면 재사용, 없으면 내부에서 열고 닫음.
-    - 데이터 호출은 httpx로 하는 하이브리드 구성 전제를 만족하도록 세션 구성만 담당.
-    """
-    is_external = browser is not None
-
-    if not is_external:
-        # 내부 생성
-        browser_cm = browser_context(headless=True)  # 기존에 갖고있는 @asynccontextmanager
-        browser = await browser_cm.__aenter__()
-
-    context = None
-    page_ = None
-    try:
-        # 1) 격리된 Context 생성 (쿠키/스토리지 분리)
-        context = await browser.new_context()
-
-        # 2) 리소스 차단: 불필요한 렌더링 비용 제거
-        await context.route("**/*", lambda route: (
-            route.abort()
-            if route.request.resource_type in {"image", "font", "stylesheet", "media"}
-            else route.continue_()
-        ))
-
-        # 3) 페이지 오픈
-        page_ = await context.new_page()
-        # StrEnum이라도 안전하게 .value 로 명시
-        url = f"https://navercomp.wisereport.co.kr/v2/company/{page.value}?cmp_cd={cmp_cd}"
-
-        # UA는 context 생성 이후 읽어도 같지만, page 쪽이 더 직관적
-        await page_.goto(url, wait_until="domcontentloaded")
-
-        # 4) 'encparam'이 들어있는 스크립트가 로드될 시간을 짧게 확보
-        #    가능하면 안정적인 셀렉터를 쓰세요(예: 표/탭 등). 없으면 폴백 타임아웃.
-        try:
-            # 스크립트 내 텍스트 매칭 (Playwright의 has-text 선택자를 활용)
-            await page_.wait_for_selector("script:has-text('encparam')", timeout=3000)
-        except Exception:
-            # 폴백: 짧은 대기
-            await page_.wait_for_timeout(300)
-
-        html = await page_.content()
-        m = re.search(
-            r"""encparam\s*(?:[:=])\s*['"]([^'"]+)['"]""", html, re.IGNORECASE
-        )
-        encparam = m.group(1) if m else None
-        if not encparam:
-            logger.warning("encparam not found in page HTML")
-
-        # 5) UA / 쿠키 수집(컨텍스트 기준)
-        ua = await page_.evaluate("navigator.userAgent")
-        cookies = await context.cookies()
-        cookie_header = "; ".join(f"{c['name']}={c['value']}" for c in cookies)
-
-        logger.debug(f"encparam={encparam!r}")
-        logger.debug(f"cookies={cookie_header!r}")
-
-        return {
-            "encparam": encparam,
-            "cookies": cookie_header,
-            "referer": url,
-            "user_agent": ua,
-        }
-
-    finally:
-        # 열린 순서의 반대로 정리
-        try:
-            if page_:
-                await page_.close()
-        finally:
-            if context:
-                await context.close()
-            if not is_external:
-                await browser_cm.__aexit__(None, None, None)

scraper2_hj3415/core/constants.py

@@ -1,47 +0,0 @@
-# scraper2_hj3415/core/constants.py
-
-from enum import StrEnum
-
-class PAGE(StrEnum):
-    c101 = "c1010001.aspx"
-    c103 = "c1030001.aspx"
-    c104 = "c1040001.aspx"
-
-PAGE_TO_LABEL = {
-    PAGE.c101: "c101",
-    PAGE.c103: "c103",
-    PAGE.c104: "c104"
-}
-
-class ASPXInner(StrEnum):
-    c103 = "cF3002.aspx"
-    c104 = "cF4002.aspx"
-
-class FRQ(StrEnum):
-    Y = "0"   # 연간
-    Q = "1"   # 분기
-
-FRQ_TO_LABEL = {FRQ.Y: "y", FRQ.Q: "q"}   # 저장·로그용 라벨
-
-class C103RPT(StrEnum):
-    손익계산서 = "0"
-    재무상태표 = "1"
-    현금흐름표 = "2"
-
-class C104RPT(StrEnum):
-    수익성 = "1"
-    성장성 = "2"
-    안정성 = "3"
-    활동성 = "4"
-    가치분석 = "5"
-
-RPT_TO_LABEL = {
-    C103RPT.손익계산서: "손익계산서",
-    C103RPT.재무상태표: "재무상태표",
-    C103RPT.현금흐름표: "현금흐름표",
-    C104RPT.수익성: "수익성",
-    C104RPT.성장성: "성장성",
-    C104RPT.안정성: "안정성",
-    C104RPT.활동성: "활동성",
-    C104RPT.가치분석: "가치분석",
-}

scraper2_hj3415/core/ports/sink_port.py

@@ -1,16 +0,0 @@
-# scraper2_hj3415/core/ports/sink_port.py
-
-from typing import Protocol
-import pandas as pd
-
-class C1034SinkPort(Protocol):
-    async def save_all(
-        self,
-        *,
-        dim_account_df: pd.DataFrame,
-        dim_period_df: pd.DataFrame,
-        fact_df: pd.DataFrame,
-        delta_df: pd.DataFrame,
-    ) -> None: ...
-
-