Feature Proposal: Support Sector and Industry data from Markets Tab

README.md

@@ -223,6 +223,55 @@ data = yf.download("SPY AAPL", period="1mo")
 
 #### `yf.download()` and `Ticker.history()` have many options for configuring fetching and processing. [Review the Wiki](https://github.com/ranaroussi/yfinance/wiki) for more options and detail.
 
+### Sector and Industry
+
+The `Sector` and `Industry` modules allow you to access the US market information.
+
+To initialize, use the relevant sector or industry key as below. (Complete mapping of the keys is available in `const.py`.)
+
+```python
+import yfinance as yf
+
+tech = yf.Sector('technology')
+software = yf.Industry('software-infrastructure')
+
+# Common information
+tech.key
+tech.name
+tech.symbol
+tech.ticker
+tech.overview
+tech.top_companies
+tech.research_reports
+
+# Sector information
+tech.top_etfs
+tech.top_mutual_funds
+tech.industries
+
+# Industry information
+software.sector_key
+software.sector_name
+software.top_performing_companies
+software.top_growth_companies
+```
+
+The modules can be chained with Ticker as below.
+```python
+import yfinance as yf
+
+# Ticker to Sector and Industry
+msft = yf.Ticker('MSFT')
+tech = yf.Sector(msft.info.get('sectorKey'))
+software = yf.Industry(msft.info.get('industryKey'))
+
+# Sector and Industry to Ticker
+tech_ticker = tech.ticker
+tech_ticker.info
+software_ticker = software.ticker
+software_ticker.history()
+```
+
 ### Logging
 
 `yfinance` now uses the `logging` module to handle messages, default behaviour is only print errors. If debugging, use `yf.enable_debug_mode()` to switch logging to debug with custom formatting.

yfinance/__init__.py

@@ -25,11 +25,13 @@
 from .multi import download
 from .utils import enable_debug_mode
 from .cache import set_tz_cache_location
+from .domain.sector import Sector
+from .domain.industry import Industry
 
 __version__ = version.version
 __author__ = "Ran Aroussi"
 
 import warnings
 warnings.filterwarnings('default', category=DeprecationWarning, module='^yfinance')
 
-__all__ = ['download', 'Ticker', 'Tickers', 'enable_debug_mode', 'set_tz_cache_location']
+__all__ = ['download', 'Ticker', 'Tickers', 'enable_debug_mode', 'set_tz_cache_location', 'Sector', 'Industry']

yfinance/const.py

@@ -1,3 +1,4 @@
+_QUERY1_URL_ = 'https://query1.finance.yahoo.com'
 _BASE_URL_ = 'https://query2.finance.yahoo.com'
 _ROOT_URL_ = 'https://finance.yahoo.com'
 
@@ -155,3 +156,152 @@
     "recommendationTrend",
     "futuresChain",
 )
+
+# map last updated as of 2024.09.18
+SECTOR_INDUSTY_MAPPING = {
+    'basic-materials': {'specialty-chemicals',
+                        'gold',
+                        'building-materials',
+                        'copper',
+                        'steel',
+                        'agricultural-inputs',
+                        'chemicals',
+                        'other-industrial-metals-mining',
+                        'lumber-wood-production',
+                        'aluminum',
+                        'other-precious-metals-mining',
+                        'coking-coal',
+                        'paper-paper-products',
+                        'silver'},
+    'communication-services': {'internet-content-information',
+                                'telecom-services',
+                                'entertainment',
+                                'electronic-gaming-multimedia',
+                                'advertising-agencies',
+                                'broadcasting',
+                                'publishing'},
+    'consumer-cyclical': {'internet-retail',
+                            'auto-manufacturers',
+                            'restaurants',
+                            'home-improvement-retail',
+                            'travel-services',
+                            'specialty-retail',
+                            'apparel-retail',
+                            'residential-construction',
+                            'footwear-accessories',
+                            'packaging-containers',
+                            'lodging',
+                            'auto-parts',
+                            'auto-truck-dealerships',
+                            'gambling',
+                            'resorts-casinos',
+                            'leisure',
+                            'apparel-manufacturing',
+                            'personal-services',
+                            'furnishings-fixtures-appliances',
+                            'recreational-vehicles',
+                            'luxury-goods',
+                            'department-stores',
+                            'textile-manufacturing'},
+    'consumer-defensive': {'discount-stores',
+                            'beverages-non-alcoholic',
+                            'household-personal-products',
+                            'packaged-foods',
+                            'tobacco',
+                            'confectioners',
+                            'farm-products',
+                            'food-distribution',
+                            'grocery-stores',
+                            'beverages-brewers',
+                            'education-training-services',
+                            'beverages-wineries-distilleries'},
+    'energy': {'oil-gas-integrated',
+                'oil-gas-midstream',
+                'oil-gas-e-p',
+                'oil-gas-equipment-services',
+                'oil-gas-refining-marketing',
+                'uranium',
+                'oil-gas-drilling',
+                'thermal-coal'},
+    'financial-services': {'banks-diversified',
+                            'credit-services',
+                            'asset-management',
+                            'insurance-diversified',
+                            'banks-regional',
+                            'capital-markets',
+                            'financial-data-stock-exchanges',
+                            'insurance-property-casualty',
+                            'insurance-brokers',
+                            'insurance-life',
+                            'insurance-specialty',
+                            'mortgage-finance',
+                            'insurance-reinsurance',
+                            'shell-companies',
+                            'financial-conglomerates'},
+    'healthcare': {'drug-manufacturers-general',
+                    'healthcare-plans',
+                    'biotechnology',
+                    'medical-devices',
+                    'diagnostics-research',
+                    'medical-instruments-supplies',
+                    'medical-care-facilities',
+                    'drug-manufacturers-specialty-generic',
+                    'health-information-services',
+                    'medical-distribution',
+                    'pharmaceutical-retailers'},
+    'industrials': {'aerospace-defense',
+                    'specialty-industrial-machinery',
+                    'railroads',
+                    'building-products-equipment',
+                    'farm-heavy-construction-machinery',
+                    'specialty-business-services',
+                    'integrated-freight-logistics',
+                    'waste-management',
+                    'conglomerates',
+                    'industrial-distribution',
+                    'engineering-construction',
+                    'rental-leasing-services',
+                    'consulting-services',
+                    'trucking',
+                    'electrical-equipment-parts',
+                    'airlines',
+                    'tools-accessories',
+                    'pollution-treatment-controls',
+                    'security-protection-services',
+                    'marine-shipping',
+                    'metal-fabrication',
+                    'infrastructure-operations',
+                    'staffing-employment-services',
+                    'airports-air-services',
+                    'business-equipment-supplies'},
+    'real-estate': {'reit-specialty',
+                    'reit-industrial',
+                    'reit-retail',
+                    'reit-residential',
+                    'reit-healthcare-facilities',
+                    'real-estate-services',
+                    'reit-office',
+                    'reit-diversified',
+                    'reit-mortgage',
+                    'reit-hotel-motel',
+                    'real-estate-development',
+                    'real-estate-diversified'},
+    'technology': {'software-infrastructure',
+                    'semiconductors',
+                    'consumer-electronics',
+                    'software-application',
+                    'information-technology-services',
+                    'semiconductor-equipment-materials',
+                    'communication-equipment',
+                    'computer-hardware',
+                    'electronic-components',
+                    'scientific-technical-instruments',
+                    'solar',
+                    'electronics-computer-distribution'},
+    'utilities': {'utilities-regulated-electric',
+                    'utilities-renewable',
+                    'utilities-diversified',
+                    'utilities-regulated-gas',
+                    'utilities-independent-power-producers',
+                    'utilities-regulated-water'}
+}

yfinance/domain/__init__.py

@@ -0,0 +1,5 @@
+# domain/__init__.py
+from .sector import Sector
+from .industry import Industry
+
+__all__ = ['Sector', 'Industry']

yfinance/domain/domain.py

@@ -0,0 +1,97 @@
+from ..ticker import Ticker
+from ..const import _QUERY1_URL_
+from ..data import YfData
+from typing import Dict, List, Optional
+
+import pandas as _pd
+
+_QUERY_URL_ = f'{_QUERY1_URL_}/v1/finance'
+
+class Domain:
+    def __init__(self, key: str, session=None, proxy=None):
+        self._key: str = key
+        self.proxy = proxy
+        self.session = session
+        self._data: YfData = YfData(session=session)
+
+        self._name: Optional[str] = None
+        self._symbol: Optional[str] = None
+        self._overview: Optional[Dict] = None
+        self._top_companies: Optional[_pd.DataFrame] = None
+        self._research_reports: Optional[List[Dict[str, str]]] = None
+
+    @property
+    def key(self) -> str:
+        return self._key
+
+    @property
+    def name(self) -> str:
+        self._ensure_fetched(self._name)
+        return self._name
+
+    @property
+    def symbol(self) -> str:
+        self._ensure_fetched(self._symbol)
+        return self._symbol
+
+    @property
+    def ticker(self) -> Ticker:
+        self._ensure_fetched(self._symbol)
+        return Ticker(self._symbol)
+
+    @property
+    def overview(self) -> Dict:
+        self._ensure_fetched(self._overview)
+        return self._overview
+
+    @property
+    def top_companies(self) -> Optional[_pd.DataFrame]:
+        self._ensure_fetched(self._top_companies)
+        return self._top_companies 
+
+    @property
+    def research_reports(self) -> List[Dict[str, str]]:
+        self._ensure_fetched(self._research_reports)
+        return self._research_reports
+
+    def _fetch(self, query_url, proxy) -> Dict:
+        params_dict = {"formatted": "true", "withReturns": "true", "lang": "en-US", "region": "US"}
+        result = self._data.get_raw_json(query_url, user_agent_headers=self._data.user_agent_headers, params=params_dict, proxy=proxy)
+        return result
+
+    def _parse_and_assign_common(self, data) -> None:
+        self._name = data.get('name')
+        self._symbol = data.get('symbol')
+        self._overview = self._parse_overview(data.get('overview', {}))
+        self._top_companies = self._parse_top_companies(data.get('topCompanies', {}))
+        self._research_reports = data.get('researchReports')
+
+    def _parse_overview(self, overview) -> Dict:
+        return {
+            "companies_count": overview.get('companiesCount', None),
+            "market_cap": overview.get('marketCap', {}).get('raw', None),
+            "message_board_id": overview.get('messageBoardId', None),
+            "description": overview.get('description', None),
+            "industries_count": overview.get('industriesCount', None),
+            "market_weight": overview.get('marketWeight', {}).get('raw', None),
+            "employee_count": overview.get('employeeCount', {}).get('raw', None)
+        }
+
+    def _parse_top_companies(self, top_companies) -> Optional[_pd.DataFrame]:
+        top_companies_column = ['symbol', 'name', 'rating', 'market weight']
+        top_companies_values = [(c.get('symbol'), 
+                                c.get('name'), 
+                                c.get('rating'), 
+                                c.get('marketWeight',{}).get('raw',None)) for c in top_companies]
+
+        if not top_companies_values: 
+            return None
+
+        return _pd.DataFrame(top_companies_values, columns = top_companies_column).set_index('symbol')
+
+    def _fetch_and_parse(self) -> None:
+        raise NotImplementedError("_fetch_and_parse() needs to be implemented by children classes")
+
+    def _ensure_fetched(self, attribute) -> None:
+        if attribute is None:
+            self._fetch_and_parse()