improve financial fetch, bind financial KPIs to enum

pyproject.toml

@@ -48,6 +48,10 @@ seaborn = "^0.12.2"
 selenium = "^4.10.0"
 tqdm = "^4.65.0"
 
+# TODO Add dependent libraries (i.e., deutshcland, plotly, etc)
+[tool.poetry.extras]
+ingest = ["selenium"]
+
 [tool.poetry.group.develop.dependencies]
 black = {extras = ["jupyter"], version = "^23.3.0"}
 jupyterlab = "^4.0.0"
@@ -85,6 +89,10 @@ pytest-cov = "^4.1.0"
 pytest-mock = "^3.10.0"
 pytest-repeat = "^0.9.1"
 
+# TODO Add enrich_company_financials hinzufügen
+[tool.poetry.scripts]
+mein_test = "aki_prj23_transparenzregister.utils.postgres.connector:init_db"
+
 [tool.ruff]
 exclude = [
   ".bzr",

src/aki_prj23_transparenzregister/apps/enrich_company_financials.py

@@ -18,9 +18,9 @@ def work(company: typing.Any, company_service: CompanyMongoService) -> None:
         company (dict): _description_
         company_service (CompanyMongoService): _description_
     """
-    # print(company["name"])
-    yearly_results = Bundesanzeiger().get_information(company_name=company["name"])
-    # print(len(yearly_results))
+    yearly_results = Bundesanzeiger().get_information(
+        company["name"], company["location"]["city"]
+    )
     yearly_results_data = {}
     for _index, row in yearly_results.iterrows():
         yearly_results_data[row.jahr] = {

src/aki_prj23_transparenzregister/models/company.py

@@ -45,21 +45,54 @@ class CompanyRelationship(ABC):
     location: Location
 
 
+class FinancialKPIEnum(Enum):
+    """Financial KPI keys."""
+
+    # Umsatz || Erlöse
+    REVENUE = "revenue"
+    # Jahresüberschuss || Nettoeinkommen
+    NET_INCOME = "net_income"
+    # Ebit
+    EBIT = "ebit"
+    # Ebitda
+    EBITDA = "ebitda"
+    # Bruttogewinn
+    GROSS_PROFIT = "gross_profit"
+    # Betriebsgewinn
+    OPERATING_PROFIT = "operating_profit"
+    # Bilanzsumme
+    ASSETS = "assets"
+    # Gesamtverbindlichkeiten
+    LIABILITIES = "liabilities"
+    # Eigenkapital
+    EQUITY = "equity"
+    # Umlaufvermögen
+    CURRENT_ASSETS = "current_assets"
+    # Kurzfristige Verbindlichkeiten
+    CURRENT_LIABILITIES = "current_liabilities"
+    # Langfristige Verbindlichkeiten
+    LONG_TERM_DEBT = "long_term_debt"
+    # Kurzfristige Verbindlichkeiten
+    SHORT_TERM_DEBT = "short_term_debt"
+    # Barmittel
+    CASH_AND_CASH_EQUIVALENTS = "cash_and_cash_equivalents"
+    # Dividende
+    DIVIDENDS = "dividends"
+    # Cash Flow
+    CASH_FLOW = "cash_flow"
+
+
 @dataclass
-class FinancialResults:
-    """_summary_."""
+class YearlyResult:
+    """Company yearly result."""
 
     year: int
-    kpis: dict[str, float]
+    kpis: dict[FinancialKPIEnum, float]
 
 
 @dataclass
 class Company:
-    """_summary_.
-
-    Returns:
-        _type_: _description_
-    """
+    """Company dataclass."""
 
     id: CompanyID
     location: Location

src/aki_prj23_transparenzregister/utils/data_extraction/bundesanzeiger.py

@@ -6,23 +6,25 @@ from bs4 import BeautifulSoup
 from deutschland.bundesanzeiger import Bundesanzeiger as Ba
 
 from aki_prj23_transparenzregister.models.auditor import Auditor
+from aki_prj23_transparenzregister.models.company import FinancialKPIEnum
 
 
 class Bundesanzeiger:
     """Bundesanzeiger wrapper to export relevant information."""
 
-    def get_information(self, company_name: str) -> pd.DataFrame:
+    def get_information(self, company_name: str, city: str | None) -> pd.DataFrame:
         """Extract relevant information from all found yearly results for the given company.
 
         Args:
             company_name (str): Name of the company to search for
+            city (Optional[str]): City where the company is registered
 
         Returns:
             pd.DataFrame: Result
         """
         ba = Ba()
         # Get Bundesanzeiger entries for company
-        reports = ba.get_reports(company_name)
+        reports = ba.get_reports(f"{company_name} {city}")
         # Transform to list of data
         report_contents = []
         for key in reports:
@@ -113,22 +115,22 @@ class Bundesanzeiger:
 
         # Define KPI patterns to search for
         kpi_patterns = {
-            "revenue": r"(?:revenue|umsatz|erlöse)[:\s]*([\d,.]+[mmb]?)",
-            "net_income": r"(?:net income|jahresüberschuss|nettoeinkommen|Ergebnis nach Steuern)[:\s]*([\d,.]+[mmb]?)",
-            "ebit": r"(?:ebit|operating income)[:\s]*([\d,.]+[mmb]?)",
-            "ebitda": r"(?:ebitda)[:\s]*([\d,.]+[mmb]?)",
-            "gross_profit": r"(?:gross profit|bruttogewinn)[:\s]*([\d,.]+[mmb]?)",
-            "operating_profit": r"(?:operating profit|betriebsgewinn)[:\s]*([\d,.]+[mmb]?)",
-            "assets": r"(?:total assets|bilanzsumme)[:\s]*([\d,.]+[mmb]?)",
-            "liabilities": r"(?:total liabilities|gesamtverbindlichkeiten)[:\s]*([\d,.]+[mmb]?)",
-            "equity": r"(?:shareholders'? equity|eigenkapital)[:\s]*([\d,.]+[mmb]?)",
-            "current_assets": r"(?:current assets|umlaufvermögen)[:\s]*([\d,.]+[mmb]?)",
-            "current_liabilities": r"(?:current liabilities|kurzfristige verbindlichkeiten)[:\s]*([\d,.]+[mmb]?)",
-            "long_term_debt": r"(?:long[-\s]?term debt|langfristige verbindlichkeiten)[:\s]*([\d,.]+[mmb]?)",
-            "short_term_debt": r"(?:short[-\s]?term debt|kurzfristige verbindlichkeiten)[:\s]*([\d,.]+[mmb]?)",
-            "cash_and_cash_equivalents": r"(?:cash (?:and cash equivalents)?|barmittel)[:\s]*([\d,.]+[mmb]?)",
-            "dividends": r"(?:dividends?|dividende)[:\s]*([\d,.]+[mmb]?)",
-            "cash_flow": r"(?:cash flow|cashflow|cash flow from operating activities)[:\s]*([\d,.]+[mmb]?)",
+            FinancialKPIEnum.REVENUE: r"(?:revenue|umsatz|erlöse)[:\s]*([\d,.]+[mmb]?)",
+            FinancialKPIEnum.NET_INCOME: r"(?:net income|jahresüberschuss|nettoeinkommen|Ergebnis nach Steuern)[:\s]*([\d,.]+[mmb]?)",
+            FinancialKPIEnum.EBIT: r"(?:ebit|operating income)[:\s]*([\d,.]+[mmb]?)",
+            FinancialKPIEnum.EBITDA: r"(?:ebitda)[:\s]*([\d,.]+[mmb]?)",
+            FinancialKPIEnum.GROSS_PROFIT: r"(?:gross profit|bruttogewinn)[:\s]*([\d,.]+[mmb]?)",
+            FinancialKPIEnum.OPERATING_PROFIT: r"(?:operating profit|betriebsgewinn)[:\s]*([\d,.]+[mmb]?)",
+            FinancialKPIEnum.ASSETS: r"(?:total assets|bilanzsumme)[:\s]*([\d,.]+[mmb]?)",
+            FinancialKPIEnum.LIABILITIES: r"(?:total liabilities|gesamtverbindlichkeiten)[:\s]*([\d,.]+[mmb]?)",
+            FinancialKPIEnum.EQUITY: r"(?:shareholders'? equity|eigenkapital)[:\s]*([\d,.]+[mmb]?)",
+            FinancialKPIEnum.CURRENT_ASSETS: r"(?:current assets|umlaufvermögen)[:\s]*([\d,.]+[mmb]?)",
+            FinancialKPIEnum.CURRENT_LIABILITIES: r"(?:current liabilities|kurzfristige verbindlichkeiten)[:\s]*([\d,.]+[mmb]?)",
+            FinancialKPIEnum.LONG_TERM_DEBT: r"(?:long[-\s]?term debt|langfristige verbindlichkeiten)[:\s]*([\d,.]+[mmb]?)",
+            FinancialKPIEnum.SHORT_TERM_DEBT: r"(?:short[-\s]?term debt|kurzfristige verbindlichkeiten)[:\s]*([\d,.]+[mmb]?)",
+            FinancialKPIEnum.CASH_AND_CASH_EQUIVALENTS: r"(?:cash (?:and cash equivalents)?|barmittel)[:\s]*([\d,.]+[mmb]?)",
+            FinancialKPIEnum.DIVIDENDS: r"(?:dividends?|dividende)[:\s]*([\d,.]+[mmb]?)",
+            FinancialKPIEnum.CASH_FLOW: r"(?:cash flow|cashflow|cash flow from operating activities)[:\s]*([\d,.]+[mmb]?)",
         }
 
         for kpi, pattern in kpi_patterns.items():
@@ -176,4 +178,4 @@ class Bundesanzeiger:
 
 if __name__ == "__main__":
     ba_wrapper = Bundesanzeiger()
-    ba_wrapper.get_information("Atos IT-Dienstleistung und Beratung GmbH")
+    ba_wrapper.get_information("Atos IT-Dienstleistung und Beratung GmbH", None)