ENH: Add support for Nasdaq symbol list

docs/source/remote_data.rst

@@ -33,6 +33,7 @@ Currently the following sources are supported:
     - :ref:`Eurostat<remote_data.eurostat>`
     - :ref:`Thrift Savings Plan<remote_data.tsp>`
     - :ref:`Oanda currency historical rate<remote_data.oanda_curr_hist>`
+    - :ref:`Nasdaq Trader symbol definitions<remote_data.nasdaq_symbols`
 
 It should be noted, that various sources support different kinds of data, so not all sources implement the same methods and the data elements returned might also differ.
 
@@ -540,3 +541,33 @@ Download currency historical rate from `Oanda <https://www.oanda.com/>`__.
       2016-06-01  1.115170  1.445410  0.009095
 
       [153 rows x 3 columns]
+
+.. _remote_data.nasdaq_symbols
+
+Nasdaq Trader Symbol Definitions
+==============================
+
+Download the latest symbols from `Nasdaq<ftp://ftp.nasdaqtrader.com/SymbolDirectory/nasdaqtraded.txt/>`__.
+
+Note that Nasdaq updates this file daily, and historical versions are not
+available. More information on the `field<http://www.nasdaqtrader.com/trader.aspx?id=symboldirdefs/>` definitions.
+
+.. code-block:: python
+
+    In [12]: from pandas_datareader.nasdaq_trader import get_nasdaq_symbols
+    In [13]: symbols = get_nasdaq_symbols()
+    In [14]: print(symbols.ix['IBM'])
+        Nasdaq Traded                                                    True
+        Security Name       International Business Machines Corporation Co...
+        Listing Exchange                                                    N
+        Market Category
+        ETF                                                             False
+        Round Lot Size                                                    100
+        Test Issue                                                      False
+        Financial Status                                                  NaN
+        CQS Symbol                                                        IBM
+        NASDAQ Symbol                                                     IBM
+        NextShares                                                      False
+        Name: IBM, dtype: object
+
+

pandas_datareader/data.py

@@ -21,6 +21,7 @@
 from pandas_datareader.edgar import EdgarIndexReader
 from pandas_datareader.enigma import EnigmaReader
 from pandas_datareader.oanda import get_oanda_currency_historical_rates
+from pandas_datareader.nasdaq_trader import get_nasdaq_symbols
 
 
 def get_data_fred(*args, **kwargs):
@@ -161,6 +162,11 @@ def DataReader(name, data_source=None, start=None, end=None,
             quote_currency="USD", base_currency=name,
             reversed=True, session=session
         )
+    elif data_source == 'nasdaq':
+        if name != 'symbols':
+            raise ValueError("Only the string 'symbols' is supported for "
+                             "Nasdaq, not %r" % (name,))
+        return get_nasdaq_symbols(retry_count=retry_count, pause=pause)
     else:
         msg = "data_source=%r is not implemented" % data_source
         raise NotImplementedError(msg)

pandas_datareader/nasdaq_trader.py

@@ -0,0 +1,102 @@
+from ftplib import FTP, all_errors
+from pandas import read_csv
+from pandas_datareader._utils import RemoteDataError
+from pandas.compat import StringIO
+import time
+
+_NASDAQ_TICKER_LOC = '/SymbolDirectory/nasdaqtraded.txt'
+_NASDAQ_FTP_SERVER = 'ftp.nasdaqtrader.com'
+_TICKER_DTYPE = [('Nasdaq Traded', bool),
+                 ('Symbol', str),
+                 ('Security Name', str),
+                 ('Listing Exchange', str),
+                 ('Market Category', str),
+                 ('ETF', bool),
+                 ('Round Lot Size', float),
+                 ('Test Issue', bool),
+                 ('Financial Status', str),
+                 ('CQS Symbol', str),
+                 ('NASDAQ Symbol', str),
+                 ('NextShares', bool)]
+_CATEGORICAL = ('Listing Exchange', 'Financial Status')
+
+_DELIMITER = '|'
+_ticker_cache = None
+
+
+def _bool_converter(item):
+    return item == 'Y'
+
+
+def _download_nasdaq_symbols(timeout):
+    """
+    @param timeout: the time to wait for the FTP connection
+    """
+    try:
+        ftp_session = FTP(_NASDAQ_FTP_SERVER, timeout=timeout)
+        ftp_session.login()
+    except all_errors as err:
+        raise RemoteDataError('Error connecting to %r: $s' %
+                              (_NASDAQ_FTP_SERVER, err))
+
+    lines = []
+    try:
+        ftp_session.retrlines('RETR ' + _NASDAQ_TICKER_LOC, lines.append)
+    except all_errors as err:
+        raise RemoteDataError('Error downloading from %r: $s' %
+                              (_NASDAQ_FTP_SERVER, err))
+    finally:
+        ftp_session.close()
+
+    # Sanity Checking
+    if not lines[-1].startswith('File Creation Time:'):
+        raise RemoteDataError('Missing expected footer. Found %r' % lines[-1])
+
+    # Convert Y/N to True/False.
+    converter_map = dict((col, _bool_converter) for col, t in _TICKER_DTYPE
+                         if t is bool)
+
+    data = read_csv(StringIO('\n'.join(lines[:-1])), '|',
+                    dtype=_TICKER_DTYPE, converters=converter_map,
+                    index_col=1)
+
+    # Properly cast enumerations
+    for cat in _CATEGORICAL:
+        data[cat] = data[cat].astype('category')
+
+    return data
+
+
+def get_nasdaq_symbols(retry_count=3, timeout=30, pause=None):
+    """
+    Get the list of all available equity symbols from Nasdaq.
+
+    Returns
+    -------
+    nasdaq_tickers : pandas.DataFrame
+        DataFrame with company tickers, names, and other properties.
+    """
+    global _ticker_cache
+
+    if timeout < 0:
+        raise ValueError('timeout must be >= 0, not %r' % (timeout,))
+
+    if pause is None:
+        pause = timeout / 3
+    elif pause < 0:
+        raise ValueError('pause must be >= 0, not %r' % (pause,))
+
+    if _ticker_cache is None:
+        while retry_count > 0:
+            try:
+                _ticker_cache = _download_nasdaq_symbols(timeout=timeout)
+                retry_count = -1
+            except RemoteDataError:
+                # retry on any exception
+                if retry_count <= 0:
+                    raise
+                else:
+                    retry_count -= 1
+                    time.sleep(pause)
+
+    return _ticker_cache

pandas_datareader/tests/test_nasdaq.py

@@ -0,0 +1,22 @@
+import nose
+
+import pandas.util.testing as tm
+
+import pandas_datareader.data as web
+from pandas_datareader._utils import RemoteDataError
+
+
+class TestNasdaqSymbols(tm.TestCase):
+
+    def test_get_symbols(self):
+        try:
+            symbols = web.DataReader('symbols', 'nasdaq')
+        except RemoteDataError as e:
+            raise nose.SkipTest(e)
+
+        assert 'IBM' in symbols.index
+
+
+if __name__ == '__main__':
+    nose.runmodule(argv=[__file__, '-vvs', '-x', '--pdb', '--pdb-failure'],
+                   exit=False)