Merge pull request #2160 from dhruvan2006/feature/search

Feature: Add search feature

README.md

@@ -39,6 +39,7 @@ Yahoo! finance API is intended for personal use only.**
 - `Ticker`: single ticker data
 - `Tickers`: multiple tickers' data
 - `download`: download market data for multiple tickers
+- `Search`: quotes and news from search
 - `Sector` and `Industry`: sector and industry information
 - `EquityQuery` and `Screener`: build query to screen market
 

doc/source/reference/examples/search.py

@@ -0,0 +1,7 @@
+import yfinance as yf
+
+# get list of quotes
+quotes = yf.Search("AAPL", max_results=10).quotes
+
+# get list of news
+news = yf.Search("Google", news_count=10).news

doc/source/reference/index.rst

@@ -15,6 +15,7 @@ The following are the publicly available classes, and functions exposed by the `
 
 - :attr:`Ticker <yfinance.Ticker>`: Class for accessing single ticker data.
 - :attr:`Tickers <yfinance.Tickers>`: Class for handling multiple tickers.
+- :attr:`Search <yfinance.Search>`: Class for accessing search results.
 - :attr:`Sector <yfinance.Sector>`: Domain class for accessing sector information.
 - :attr:`Industry <yfinance.Industry>`: Domain class for accessing industry information.
 - :attr:`download <yfinance.download>`: Function to download market data for multiple tickers.
@@ -32,6 +33,7 @@ The following are the publicly available classes, and functions exposed by the `
    yfinance.stock
    yfinance.financials
    yfinance.analysis
+   yfinance.search
    yfinance.sector_industry
    yfinance.functions
 

doc/source/reference/yfinance.search.rst

@@ -0,0 +1,22 @@
+=====================
+Search & News
+=====================
+
+.. currentmodule:: yfinance
+
+
+Class
+------------
+The `Search` module, allows you to access search data in a Pythonic way.
+
+.. autosummary::
+   :toctree: api/
+
+   Search
+
+Search Sample Code
+------------------
+The `Search` module, allows you to access search data in a Pythonic way.
+
+.. literalinclude:: examples/search.py
+   :language: python

tests/test_search.py

@@ -0,0 +1,31 @@
+import unittest
+
+from tests.context import yfinance as yf
+
+
+class TestSearch(unittest.TestCase):
+    def test_valid_query(self):
+        search = yf.Search(query="AAPL", max_results=5, news_count=3)
+
+        self.assertEqual(len(search.quotes), 5)
+        self.assertEqual(len(search.news), 3)
+        self.assertIn("AAPL", search.quotes[0]['symbol'])
+
+    def test_invalid_query(self):
+        search = yf.Search(query="XYZXYZ")
+
+        self.assertEqual(len(search.quotes), 0)
+        self.assertEqual(len(search.news), 0)
+
+    def test_empty_query(self):
+        search = yf.Search(query="")
+
+        self.assertEqual(len(search.quotes), 0)
+        self.assertEqual(len(search.news), 0)
+
+    def test_fuzzy_query(self):
+        search = yf.Search(query="Appel", enable_fuzzy_query=True)
+
+        # Check if the fuzzy search retrieves relevant results despite the typo
+        self.assertGreater(len(search.quotes), 0)
+        self.assertIn("AAPL", search.quotes[0]['symbol'])

yfinance/__init__.py

@@ -20,6 +20,7 @@
 #
 
 from . import version
+from .search import Search
 from .ticker import Ticker
 from .tickers import Tickers
 from .multi import download
@@ -36,5 +37,5 @@
 import warnings
 warnings.filterwarnings('default', category=DeprecationWarning, module='^yfinance')
 
-__all__ = ['download', 'Ticker', 'Tickers', 'enable_debug_mode', 'set_tz_cache_location', 'Sector', 'Industry',
-           'EquityQuery','Screener']
+__all__ = ['download', 'Search', 'Ticker', 'Tickers', 'enable_debug_mode', 'set_tz_cache_location', 'Sector',
+           'Industry', 'EquityQuery', 'Screener']

yfinance/base.py

@@ -30,7 +30,7 @@
 import pandas as pd
 import requests
 
-from . import utils, cache
+from . import utils, cache, Search
 from .data import YfData
 from .exceptions import YFEarningsDateMissing
 from .scrapers.analysis import Analysis
@@ -538,22 +538,15 @@ def get_news(self, proxy=None) -> list:
         if self._news:
             return self._news
 
-        # Getting data from json
-        url = f"{_BASE_URL_}/v1/finance/search?q={self.ticker}"
-        data = self._data.cache_get(url=url, proxy=proxy)
-        if data is None or "Will be right back" in data.text:
-            raise RuntimeError("*** YAHOO! FINANCE IS CURRENTLY DOWN! ***\n"
-                               "Our engineers are working quickly to resolve "
-                               "the issue. Thank you for your patience.")
-        try:
-            data = data.json()
-        except (_json.JSONDecodeError): 
-            logger = utils.get_yf_logger()
-            logger.error(f"{self.ticker}: Failed to retrieve the news and received faulty response instead.")
-            data = {}
+        search = Search(
+            query=self.ticker,
+            news_count=10,
+            session=self.session,
+            proxy=proxy,
+            raise_errors=True
+        )
+        self._news = search.news
 
-        # parse news
-        self._news = data.get("news", [])
         return self._news
 
     @utils.log_indent_decorator

yfinance/search.py

@@ -0,0 +1,95 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+#
+# yfinance - market data downloader
+# https://github.com/ranaroussi/yfinance
+#
+# Copyright 2017-2019 Ran Aroussi
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import json as _json
+
+from . import utils
+from .const import _BASE_URL_
+from .data import YfData
+
+
+class Search:
+    def __init__(self, query, max_results=8, news_count=8, enable_fuzzy_query=False,
+                 session=None, proxy=None, timeout=30, raise_errors=True):
+        """
+        Fetches and organizes search results from Yahoo Finance, including stock quotes and news articles.
+
+        Args:
+            query: The search query (ticker symbol or company name).
+            max_results: Maximum number of stock quotes to return (default 8).
+            news_count: Number of news articles to include (default 8).
+            enable_fuzzy_query: Enable fuzzy search for typos (default False).
+            session: Custom HTTP session for requests (default None).
+            proxy: Proxy settings for requests (default None).
+            timeout: Request timeout in seconds (default 30).
+            raise_errors: Raise exceptions on error (default True).
+        """
+        self.query = query
+        self.max_results = max_results
+        self.enable_fuzzy_query = enable_fuzzy_query
+        self.news_count = news_count
+        self.session = session
+        self.proxy = proxy
+        self.timeout = timeout
+        self.raise_errors = raise_errors
+
+        self._data = YfData(session=self.session)
+        self._logger = utils.get_yf_logger()
+
+        self._response = self._fetch_results()
+        self._quotes = self._response.get("quotes", [])
+        self._news = self._response.get("news", [])
+
+    def _fetch_results(self):
+        url = f"{_BASE_URL_}/v1/finance/search"
+        params = {
+            "q": self.query,
+            "quotesCount": self.max_results,
+            "enableFuzzyQuery": self.enable_fuzzy_query,
+            "newsCount": self.news_count,
+            "quotesQueryId": "tss_match_phrase_query",
+            "newsQueryId": "news_cie_vespa"
+        }
+
+        self._logger.debug(f'{self.query}: Yahoo GET parameters: {str(dict(params))}')
+
+        data = self._data.cache_get(url=url, params=params, proxy=self.proxy, timeout=self.timeout)
+        if data is None or "Will be right back" in data.text:
+            raise RuntimeError("*** YAHOO! FINANCE IS CURRENTLY DOWN! ***\n"
+                               "Our engineers are working quickly to resolve "
+                               "the issue. Thank you for your patience.")
+        try:
+            data = data.json()
+        except _json.JSONDecodeError:
+            self._logger.error(f"{self.query}: Failed to retrieve the news and received faulty response instead.")
+            data = {}
+
+        return data
+
+    @property
+    def quotes(self):
+        """Get the quotes from the search results."""
+        return self._quotes
+
+    @property
+    def news(self):
+        """Get the news from the search results."""
+        return self._news

yfinance/utils.py

@@ -39,7 +39,6 @@
 from pytz import UnknownTimeZoneError
 
 from yfinance import const
-from .const import _BASE_URL_
 
 user_agent_headers = {
     'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'}
@@ -189,24 +188,27 @@ def is_isin(string):
 def get_all_by_isin(isin, proxy=None, session=None):
     if not (is_isin(isin)):
         raise ValueError("Invalid ISIN number")
+
+    # Deferred this to prevent circular imports
+    from .search import Search
+
     session = session or _requests
-    url = f"{_BASE_URL_}/v1/finance/search?q={isin}"
-    data = session.get(url=url, proxies=proxy, headers=user_agent_headers)
-    try:
-        data = data.json()
-        ticker = data.get('quotes', [{}])[0]
-        return {
-            'ticker': {
-                'symbol': ticker['symbol'],
-                'shortname': ticker['shortname'],
-                'longname': ticker.get('longname',''),
-                'type': ticker['quoteType'],
-                'exchange': ticker['exchDisp'],
-            },
-            'news': data.get('news', [])
-        }
-    except Exception:
-        return {}
+    search = Search(query=isin, max_results=1, session=session, proxy=proxy)
+
+    # Extract the first quote and news
+    ticker = search.quotes[0] if search.quotes else {}
+    news = search.news
+
+    return {
+        'ticker': {
+            'symbol': ticker.get('symbol', ''),
+            'shortname': ticker.get('shortname', ''),
+            'longname': ticker.get('longname', ''),
+            'type': ticker.get('quoteType', ''),
+            'exchange': ticker.get('exchDisp', ''),
+        },
+        'news': news
+    }
 
 
 def get_ticker_by_isin(isin, proxy=None, session=None):