Add dividends, splits, and currencies

Dividends and splits are now returned along with prices in a dict of DataFrames. Only one call needed per ticker. Currency pairs (e.g. CADUSD) can now be accessed with YahooFXReader.

Author: Noah Stoffman

docs/source/whatsnew/v0.7.0.txt

@@ -50,9 +50,10 @@ Bug Fixes
 
 - Added support for passing the API KEY to QuandlReader either directly or by
   setting the environmental variable QUANDL_API_KEY (:issue:`485`).
-- Added back support for Yahoo! price data
 - Handle Morningstar index volume data properly (:issue:`486`).
 - Added support for optionally passing a custom base_url to the EnigmaReader  (:issue:`499`).
 - Fixed Morningstar 'retry' incrementation (:issue:`513`)
 - Updated Google Daily Price API to functional url (:issue:`502`)
 - Fix Yahoo! price data (:issue:`498`)
+- Added back support for Yahoo! price, dividends, and splits data for stocks
+	and currency pairs (:issue:`487`).

pandas_datareader/data.py

@@ -32,7 +32,6 @@
     RobinhoodQuoteReader
 from pandas_datareader.stooq import StooqDailyReader
 from pandas_datareader.tiingo import TiingoDailyReader, TiingoQuoteReader
-from pandas_datareader.yahoo.actions import (YahooActionReader, YahooDivReader)
 from pandas_datareader.yahoo.components import _get_data as \
     get_components_yahoo
 from pandas_datareader.yahoo.daily import YahooDailyReader
@@ -81,7 +80,6 @@ def get_quote_av(*args, **kwargs):
 
 def get_data_yahoo_actions(*args, **kwargs):
     raise ImmediateDeprecationError(DEP_ERROR_MSG.format('Yahoo Actions'))
-    return YahooActionReader(*args, **kwargs).read()
 
 
 def get_quote_yahoo(*args, **kwargs):
@@ -313,67 +311,6 @@ def DataReader(name, data_source=None, start=None, end=None,
                                 retry_count=retry_count, pause=pause,
                                 session=session).read()
 
-    elif data_source == "yahoo-actions":
-        raise ImmediateDeprecationError(DEP_ERROR_MSG.format('Yahoo Actions'))
-        return YahooActionReader(symbols=name, start=start, end=end,
-                                 retry_count=retry_count, pause=pause,
-                                 session=session).read()
-
-    elif data_source == "yahoo-dividends":
-        comp = 'Yahoo Dividends'
-        raise ImmediateDeprecationError(DEP_ERROR_MSG.format(comp))
-        return YahooDivReader(symbols=name, start=start, end=end,
-                              adjust_price=False, chunksize=25,
-                              retry_count=retry_count, pause=pause,
-                              session=session, interval='d').read()
-
-    elif data_source == "av-forex":
-        return AVForexReader(symbols=name, retry_count=retry_count,
-                             pause=pause, session=session,
-                             api_key=access_key).read()
-
-    elif data_source == "av-daily":
-        return AVTimeSeriesReader(symbols=name,
-                                  function="TIME_SERIES_DAILY", start=start,
-                                  end=end, retry_count=retry_count,
-                                  pause=pause, session=session,
-                                  api_key=access_key).read()
-
-    elif data_source == "av-daily-adjusted":
-        return AVTimeSeriesReader(symbols=name,
-                                  function="TIME_SERIES_DAILY_ADJUSTED",
-                                  start=start, end=end,
-                                  retry_count=retry_count, pause=pause,
-                                  session=session, api_key=access_key).read()
-
-    elif data_source == "av-weekly":
-        return AVTimeSeriesReader(symbols=name,
-                                  function="TIME_SERIES_WEEKLY", start=start,
-                                  end=end, retry_count=retry_count,
-                                  pause=pause, session=session,
-                                  api_key=access_key).read()
-
-    elif data_source == "av-weekly-adjusted":
-        return AVTimeSeriesReader(symbols=name,
-                                  function="TIME_SERIES_WEEKLY_ADJUSTED",
-                                  start=start, end=end,
-                                  retry_count=retry_count, pause=pause,
-                                  session=session, api_key=access_key).read()
-
-    elif data_source == "av-monthly":
-        return AVTimeSeriesReader(symbols=name,
-                                  function="TIME_SERIES_MONTHLY", start=start,
-                                  end=end, retry_count=retry_count,
-                                  pause=pause, session=session,
-                                  api_key=access_key).read()
-
-    elif data_source == "av-monthly-adjusted":
-        return AVTimeSeriesReader(symbols=name,
-                                  function="TIME_SERIES_MONTHLY_ADJUSTED",
-                                  start=start, end=end,
-                                  retry_count=retry_count, pause=pause,
-                                  session=session, api_key=access_key).read()
-
     elif data_source == "google":
         return GoogleDailyReader(symbols=name, start=start, end=end,
                                  chunksize=25,

pandas_datareader/yahoo/FX.py

@@ -0,0 +1,113 @@
+import time
+import json
+import warnings
+from pandas import (DataFrame, Series, to_datetime, concat)
+from pandas_datareader.yahoo.daily import YahooDailyReader
+import pandas.compat as compat
+from pandas_datareader._utils import (RemoteDataError, SymbolWarning)
+from pandas.core.indexes.numeric import Int64Index
+
+
+class YahooFXReader(YahooDailyReader):
+    """
+    Returns DataFrame of historical prices for currencies
+
+    Parameters
+    ----------
+    symbols : string, array-like object (list, tuple, Series), or DataFrame
+        Single stock symbol (ticker), array-like object of symbols or
+        DataFrame with index containing stock symbols.
+    start : string, (defaults to '1/1/2010')
+        Starting date, timestamp. Parses many different kind of date
+        representations (e.g., 'JAN-01-2010', '1/1/10', 'Jan, 1, 1980')
+    end : string, (defaults to today)
+        Ending date, timestamp. Same format as starting date.
+    retry_count : int, default 3
+        Number of times to retry query request.
+    pause : int, default 0
+        Time, in seconds, to pause between consecutive queries of chunks. If
+        single value given for symbol, represents the pause between retries.
+    session : Session, default None
+        requests.sessions.Session instance to be used
+    chunksize : int, default 25 (NOT IMPLEMENTED)
+        Number of symbols to download consecutively before intiating pause.
+    interval : string, default '1d'
+        Valid values are '1d', '5d', '1mo', '3mo', '6mo', '1y', '2y', '5y',
+            '10y', 'ytd', 'max'
+    """
+
+    def _get_params(self, symbol):
+        unix_start = int(time.mktime(self.start.timetuple()))
+        day_end = self.end.replace(hour=23, minute=59, second=59)
+        unix_end = int(time.mktime(day_end.timetuple()))
+
+        params = {
+            'symbol': symbol + '=X',
+            'period1': unix_start,
+            'period2': unix_end,
+            'interval': self.interval,    # deal with this
+            'includePrePost': 'true',
+            'events': 'div|split|earn',
+            'corsDomain': 'finance.yahoo.com'
+        }
+        return params
+
+    def read(self):
+        """Read data"""
+        try:
+            # If a single symbol, (e.g., 'GOOG')
+            if isinstance(self.symbols, (compat.string_types, int)):
+                df = self._read_one_data(self.symbols)
+
+            # Or multiple symbols, (e.g., ['GOOG', 'AAPL', 'MSFT'])
+            elif isinstance(self.symbols, DataFrame):
+                df = self._dl_mult_symbols(self.symbols.index)
+            else:
+                df = self._dl_mult_symbols(self.symbols)
+
+            if isinstance(df.index, Int64Index):
+                df = df.set_index('Date')
+
+            if 'Volume' in df:
+                df = df.drop('Volume', axis=1)
+
+            return df.sort_index().dropna(how='all')
+        finally:
+            self.close()
+
+    def _read_one_data(self, symbol):
+        """ read one data from specified URL """
+        url = 'https://query1.finance.yahoo.com/v8/finance/chart/{}=X'\
+            .format(symbol)
+        params = self._get_params(symbol)
+
+        resp = self._get_response(url, params=params)
+        jsn = json.loads(resp.text)
+
+        data = jsn['chart']['result'][0]
+        df = DataFrame(data['indicators']['quote'][0])
+        df.insert(0, 'date', to_datetime(Series(data['timestamp']),
+                                         unit='s').dt.date)
+        df.columns = map(str.capitalize, df.columns)
+        return df
+
+    def _dl_mult_symbols(self, symbols):
+        stocks = {}
+        failed = []
+        passed = []
+        for sym in symbols:
+            try:
+                df = self._read_one_data(sym)
+                df['PairCode'] = sym
+                stocks[sym] = df
+                passed.append(sym)
+            except IOError:
+                msg = 'Failed to read symbol: {0!r}, replacing with NaN.'
+                warnings.warn(msg.format(sym), SymbolWarning)
+                failed.append(sym)
+
+        if len(passed) == 0:
+            msg = "No data fetched using {0!r}"
+            raise RemoteDataError(msg.format(self.__class__.__name__))
+        else:
+            return concat(stocks).set_index(['PairCode', 'Date'])