Bump version to 0.1.83

Fix cache error on read only system

.github/ISSUE_TEMPLATE/bug_report.md

@@ -14,4 +14,7 @@ Before posting an issue - please upgrade to the latest version and confirm the i
 Upgrade using:
 `$ pip install yfinance --upgrade --no-cache-dir`
 
-Bug still there? Delete this content and submit your bug report here...
+Bug still there? Delete this content and submit your bug report here and provide the following, as best you can:
+
+- Simple code that reproduces your problem
+- The error message

CHANGELOG.rst

@@ -1,9 +1,33 @@
 Change Log
 ===========
 
+0.1.83
+------
+- Reduce spam-effect of tz-fetch
+
+0.1.81
+------
+- Fix unhandled tz-cache exception #1107
+
+0.1.80
+------
+- Fix `download(ignore_tz=True)` for single ticker #1097
+- Fix rare case of error "Cannot infer DST time" #1100
+
+0.1.79
+------
+- Fix when Yahoo returns price=NaNs on dividend day
+
+0.1.78
+------
+- Fix download() when different timezones #1085
+
+0.1.77
+------
+- Fix user experience bug #1078
+
 0.1.75
 ------
-
 - Fixed datetime-related issues: #1048
 - Add 'keepna' argument #1032
 - Speedup Ticker() creation #1042

README.md

@@ -48,8 +48,6 @@ Yahoo! finance API is intended for personal use only.**
 
 The `Ticker` module, which allows you to access ticker data in a more Pythonic way:
 
-Note: yahoo finance datetimes are received as UTC.
-
 ```python
 import yfinance as yf
 
@@ -187,6 +185,11 @@ data = yf.download(  # or pdr.get_data_yahoo(...
         # (optional, default is '1d')
         interval = "1m",
 
+        # Whether to ignore timezone when aligning ticker data from 
+        # different timezones. Default is True. False may be useful for 
+        # minute/hourly data.
+        ignore_tz = False,
+
         # group by ticker (to access via data['SPY'])
         # (optional, default is 'column')
         group_by = 'ticker',
@@ -209,6 +212,18 @@ data = yf.download(  # or pdr.get_data_yahoo(...
     )
 ```
 
+### Timezone cache store
+
+When fetching price data, all dates are localized to stock exchange timezone. 
+But timezone retrieval is relatively slow, so yfinance attemps to cache them 
+in your users cache folder. 
+You can direct cache to use a different location with `set_tz_cache_location()`:
+```python
+import yfinance as yf
+yf.set_tz_cache_location("custom/cache/location")
+...
+```
+
 ### Managing Multi-Level Columns
 
 The following answer on Stack Overflow is for [How to deal with

yfinance/__init__.py

@@ -23,6 +23,7 @@ from . import version
 from .ticker import Ticker
 from .tickers import Tickers
 from .multi import download
+from .utils import set_tz_cache_location
 
 __version__ = version.version
 __author__ = "Ran Aroussi"
@@ -42,4 +43,4 @@ def pdr_override():
         pass
 
 
-__all__ = ['download', 'Ticker', 'Tickers', 'pdr_override']
+__all__ = ['download', 'Ticker', 'Tickers', 'pdr_override', 'set_tz_cache_location']

yfinance/base.py

@@ -151,7 +151,7 @@ class TickerBase():
         if start or period is None or period.lower() == "max":
             # Check can get TZ. Fail => probably delisted
             try:
-                tz = self._get_ticker_tz()
+                tz = self._get_ticker_tz(debug_mode, proxy, timeout)
             except KeyError as e:
                 if "exchangeTimezoneName" in str(e):
                     shared._DFS[self.ticker] = utils.empty_df()
@@ -293,9 +293,6 @@ class TickerBase():
                 "chart"]["result"][0]["meta"]["priceHint"])
         quotes['Volume'] = quotes['Volume'].fillna(0).astype(_np.int64)
 
-        if not keepna:
-            quotes.dropna(inplace=True)
-
         # actions
         dividends, splits = utils.parse_actions(data["chart"]["result"][0])
 
@@ -316,35 +313,83 @@ class TickerBase():
         elif params["interval"] == "1h":
             pass
         else:
-            df.index = _pd.to_datetime(df.index.date).tz_localize(tz_exchange)
+            # If a midnight is during DST transition hour when clocks roll back, 
+            # meaning clock hits midnight twice, then use the 2nd (ambiguous=True)
+            df.index = _pd.to_datetime(df.index.date).tz_localize(tz_exchange, ambiguous=True)
             df.index.name = "Date"
 
         # duplicates and missing rows cleanup
-        df.dropna(how='all', inplace=True)
         df = df[~df.index.duplicated(keep='first')]
-
         self._history = df.copy()
-
         if not actions:
-            df.drop(columns=["Dividends", "Stock Splits"], inplace=True)
+            df = df.drop(columns=["Dividends", "Stock Splits"])
+        if not keepna:
+            mask_nan_or_zero = (df.isna()|(df==0)).all(axis=1)
+            df = df.drop(mask_nan_or_zero.index[mask_nan_or_zero])
 
         return df
 
     # ------------------------
 
-    def _get_ticker_tz(self):
+    def _get_ticker_tz(self, debug_mode, proxy, timeout):
         if not self._tz is None:
             return self._tz
 
         tkr_tz = utils.cache_lookup_tkr_tz(self.ticker)
         if tkr_tz is None:
-            tkr_tz = self.info["exchangeTimezoneName"]
-            # info fetch is relatively slow so cache timezone
-            utils.cache_store_tkr_tz(self.ticker, tkr_tz)
+            tkr_tz = self._fetch_ticker_tz(debug_mode, proxy, timeout)
+
+            try:
+                utils.cache_store_tkr_tz(self.ticker, tkr_tz)
+            except PermissionError:
+                # System probably read-only, so cannot cache
+                pass
 
         self._tz = tkr_tz
         return tkr_tz
 
+
+    def _fetch_ticker_tz(self, debug_mode, proxy, timeout):
+        # Query Yahoo for basic price data just to get returned timezone
+
+        params = {"range":"1d", "interval":"1d"}
+
+        # setup proxy in requests format
+        if proxy is not None:
+            if isinstance(proxy, dict) and "https" in proxy:
+                proxy = proxy["https"]
+            proxy = {"https": proxy}
+
+        # Getting data from json
+        url = "{}/v8/finance/chart/{}".format(self._base_url, self.ticker)
+
+        session = self.session or _requests
+        try:
+            data = session.get(url=url, params=params, proxies=proxy, headers=utils.user_agent_headers, timeout=timeout)
+            data = data.json()
+        except Exception as e:
+            if debug_mode:
+                print("Failed to get ticker '{}' reason: {}".format(self.ticker, e))
+            return None
+        else:
+            error = data.get('chart', {}).get('error', None)
+            if error:
+                # explicit error from yahoo API
+                if debug_mode:
+                    print("Got error from yahoo api for ticker {}, Error: {}".format(self.ticker, error))
+            else:
+                try:
+                    return data["chart"]["result"][0]["meta"]["exchangeTimezoneName"]
+                except Exception as err:
+                    if debug_mode:
+                        print("Could not get exchangeTimezoneName for ticker '{}' reason: {}".format(self.ticker, err))
+                        print("Got response: ")
+                        print("-------------")
+                        print(" {}".format(data))
+                        print("-------------")
+        return None
+
+
     def _get_info(self, proxy=None):
         # setup proxy in requests format
         if proxy is not None:

yfinance/multi.py

@@ -29,7 +29,7 @@ from . import Ticker, utils
 from . import shared
 
 
-def download(tickers, start=None, end=None, actions=False, threads=True,
+def download(tickers, start=None, end=None, actions=False, threads=True, ignore_tz=True, 
              group_by='column', auto_adjust=False, back_adjust=False, keepna=False,
              progress=True, period="max", show_errors=True, interval="1d", prepost=False,
              proxy=None, rounding=False, timeout=None, **kwargs):
@@ -63,6 +63,9 @@ def download(tickers, start=None, end=None, actions=False, threads=True,
             Download dividend + stock splits data. Default is False
         threads: bool / int
             How many threads to use for mass downloading. Default is True
+        ignore_tz: bool
+            When combining from different timezones, ignore that part of datetime.
+            Default is True
         proxy: str
             Optional. Proxy server URL scheme. Default is None
         rounding: bool
@@ -136,16 +139,21 @@ def download(tickers, start=None, end=None, actions=False, threads=True,
         print("\n".join(['- %s: %s' %
                          v for v in list(shared._ERRORS.items())]))
 
+    if ignore_tz:
+        for tkr in shared._DFS.keys():
+            if (shared._DFS[tkr] is not None) and (shared._DFS[tkr].shape[0]>0):
+                shared._DFS[tkr].index = shared._DFS[tkr].index.tz_localize(None)
+
     if len(tickers) == 1:
         ticker = tickers[0]
         return shared._DFS[shared._ISINS.get(ticker, ticker)]
 
     try:
-        data = _pd.concat(shared._DFS.values(), axis=1,
+        data = _pd.concat(shared._DFS.values(), axis=1, sort=True,
                           keys=shared._DFS.keys())
     except Exception:
         _realign_dfs()
-        data = _pd.concat(shared._DFS.values(), axis=1,
+        data = _pd.concat(shared._DFS.values(), axis=1, sort=True,
                           keys=shared._DFS.keys())
 
     # switch names back to isins if applicable

yfinance/utils.py

@@ -316,8 +316,17 @@ class ProgressBar:
 
 
 # Simple file cache of ticker->timezone:
+_cache_dp = None
 def get_cache_dirpath():
-    return _os.path.join(_ad.user_cache_dir(), "py-yfinance")
+    if _cache_dp is None:
+        dp = _os.path.join(_ad.user_cache_dir(), "py-yfinance")
+    else:
+        dp = _os.path.join(_cache_dp, "py-yfinance")
+    return dp
+def set_tz_cache_location(dp):
+    global _cache_dp
+    _cache_dp = dp
+
 def cache_lookup_tkr_tz(tkr):
     fp = _os.path.join(get_cache_dirpath(), "tkr-tz.csv")
     if not _os.path.isfile(fp):

yfinance/version.py

@@ -1 +1 @@
-version = "0.1.75"
+version = "0.1.83"