yfinance-patches.diff

diff --git a/tmp/lima/python-pkg-lambda_quotes/python/yfinance/base.py b/./base.py
index 65a876b..67e1fff 100644
--- a/tmp/lima/python-pkg-lambda_quotes/python/yfinance/base.py
+++ b/./base.py
@@ -184,12 +184,16 @@ class TickerBase:
         # if the ticker is MUTUALFUND or ETF, then get capitalGains events
         params["events"] = "div,splits,capitalGains"
 
-        params_pretty = dict(params)
-        tz = self._get_ticker_tz(proxy, timeout)
-        for k in ["period1", "period2"]:
-            if k in params_pretty:
-                params_pretty[k] = str(pd.Timestamp(params[k], unit='s').tz_localize("UTC").tz_convert(tz))
-        logger.debug(f'{self.ticker}: Yahoo GET parameters: {str(params_pretty)}')
+        # Calling _get_ticker_tz() before downloading the data is wasteful,
+        # since it makes another HTTP request, that here is only used for a
+        # debug log.
+        if logger.isEnabledFor(logging.DEBUG):
+            params_pretty = dict(params)
+            tz = self._get_ticker_tz(proxy, timeout)
+            for k in ["period1", "period2"]:
+                if k in params_pretty:
+                    params_pretty[k] = str(pd.Timestamp(params[k], unit='s').tz_localize("UTC").tz_convert(tz))
+            logger.debug(f'{self.ticker}: Yahoo GET parameters: {str(params_pretty)}')
 
         # Getting data from json
         url = f"{self._base_url}/v8/finance/chart/{self.ticker}"
@@ -218,6 +222,8 @@ class TickerBase:
         except Exception:
             pass
 
+        tz = self._get_ticker_tz(proxy, timeout, data)
+
         # Store the meta data that gets retrieved simultaneously
         try:
             self._history_metadata = data["chart"]["result"][0]["meta"]
@@ -685,7 +691,7 @@ class TickerBase:
                 df_new.index = new_index
             logger.debug('df_new:' + '\n' + str(df_new))
 
-            # Calibrate! 
+            # Calibrate!
             common_index = np.intersect1d(df_block.index, df_new.index)
             if len(common_index) == 0:
                 # Can't calibrate so don't attempt repair
@@ -699,9 +705,9 @@ class TickerBase:
                 f_tag = df_block_calib['Adj Close'] == tag
                 if f_tag.any():
                     div_adjusts = df_block_calib['Adj Close'] / df_block_calib['Close']
-                    # The loop below assumes each 1d repair is isoloated, i.e. surrounded by 
-                    # good data. Which is case most of time. 
-                    # But in case are repairing a chunk of bad 1d data, back/forward-fill the 
+                    # The loop below assumes each 1d repair is isoloated, i.e. surrounded by
+                    # good data. Which is case most of time.
+                    # But in case are repairing a chunk of bad 1d data, back/forward-fill the
                     # good div-adjustments - not perfect, but a good backup.
                     div_adjusts[f_tag] = np.nan
                     div_adjusts = div_adjusts.fillna(method='bfill').fillna(method='ffill')
@@ -785,14 +791,14 @@ class TickerBase:
             no_fine_data_dts = []
             for idx in bad_dts:
                 if idx not in df_new.index:
-                    # Yahoo didn't return finer-grain data for this interval, 
+                    # Yahoo didn't return finer-grain data for this interval,
                     # so probably no trading happened.
                     no_fine_data_dts.append(idx)
             if len(no_fine_data_dts) > 0:
                 logger.debug(f"Yahoo didn't return finer-grain data for these intervals: " + str(no_fine_data_dts))
             for idx in bad_dts:
                 if idx not in df_new.index:
-                    # Yahoo didn't return finer-grain data for this interval, 
+                    # Yahoo didn't return finer-grain data for this interval,
                     # so probably no trading happened.
                     continue
                 df_new_row = df_new.loc[idx]
@@ -1125,7 +1131,7 @@ class TickerBase:
         div_indices = np.where(f_div)[0]
         last_div_idx = div_indices[-1]
         if last_div_idx == 0:
-            # Not enough data to recalculate the div-adjustment, 
+            # Not enough data to recalculate the div-adjustment,
             # because need close day before
             logger.debug('div-adjust-repair: Insufficient data to recalculate div-adjustment')
             return df
@@ -1169,8 +1175,8 @@ class TickerBase:
         # stock split to old price data.
         #
         # There is a slight complication, because Yahoo does another stupid thing.
-        # Sometimes the old data is adjusted twice. So cannot simply assume 
-        # which direction to reverse adjustment - have to analyse prices and detect. 
+        # Sometimes the old data is adjusted twice. So cannot simply assume
+        # which direction to reverse adjustment - have to analyse prices and detect.
         # Not difficult.
 
         logger = utils.get_yf_logger()
@@ -1218,7 +1224,7 @@ class TickerBase:
         OHLC = ['Open', 'High', 'Low', 'Close']
         OHLCA = OHLC + ['Adj Close']
 
-        # Do not attempt repair of the split is small, 
+        # Do not attempt repair of the split is small,
         # could be mistaken for normal price variance
         if 0.8 < split < 1.25:
             logger.info("price-repair-split: Split ratio too close to 1. Won't repair")
@@ -1256,10 +1262,10 @@ class TickerBase:
         else:
             debug_cols = []
 
-        # Calculate daily price % change. To reduce effect of price volatility, 
+        # Calculate daily price % change. To reduce effect of price volatility,
         # calculate change for each OHLC column.
         if interday and interval != '1d' and split not in [100.0, 100, 0.001]:
-            # Avoid using 'Low' and 'High'. For multiday intervals, these can be 
+            # Avoid using 'Low' and 'High'. For multiday intervals, these can be
             # very volatile so reduce ability to detect genuine stock split errors
             _1d_change_x = np.full((n, 2), 1.0)
             price_data = df2[['Open','Close']].replace(0.0, 1.0).to_numpy()
@@ -1407,9 +1413,9 @@ class TickerBase:
         if correct_columns_individually:
             f_corrected = np.full(n, False)
             if correct_volume:
-                # If Open or Close is repaired but not both, 
+                # If Open or Close is repaired but not both,
                 # then this means the interval has a mix of correct
-                # and errors. A problem for correcting Volume, 
+                # and errors. A problem for correcting Volume,
                 # so use a heuristic:
                 # - if both Open & Close were Nx bad => Volume is Nx bad
                 # - if only one of Open & Close are Nx bad => Volume is 0.5*Nx bad
@@ -1423,7 +1429,7 @@ class TickerBase:
                 if appears_suspended and (idx_latest_active is not None and idx_latest_active >= idx_first_f):
                     # Suspended midway during data date range.
                     # 1: process data before suspension in index-ascending (date-descending) order.
-                    # 2: process data after suspension in index-descending order. Requires signals to be reversed, 
+                    # 2: process data after suspension in index-descending order. Requires signals to be reversed,
                     #    then returned ranges to also be reversed, because this logic was originally written for
                     #    index-ascending (date-descending) order.
                     fj = f[:, j]
@@ -1513,7 +1519,7 @@ class TickerBase:
             if appears_suspended and (idx_latest_active is not None and idx_latest_active >= idx_first_f):
                 # Suspended midway during data date range.
                 # 1: process data before suspension in index-ascending (date-descending) order.
-                # 2: process data after suspension in index-descending order. Requires signals to be reversed, 
+                # 2: process data after suspension in index-descending order. Requires signals to be reversed,
                 #    then returned ranges to also be reversed, because this logic was originally written for
                 #    index-ascending (date-descending) order.
                 ranges_before = map_signals_to_ranges(f[idx_latest_active:], f_up[idx_latest_active:], f_down[idx_latest_active:])
@@ -1580,7 +1586,7 @@ class TickerBase:
 
         return df2
 
-    def _get_ticker_tz(self, proxy, timeout):
+    def _get_ticker_tz(self, proxy, timeout, data=None):
         if self._tz is not None:
             return self._tz
         cache = utils.get_tz_cache()
@@ -1592,7 +1598,7 @@ class TickerBase:
             tz = None
 
         if tz is None:
-            tz = self._fetch_ticker_tz(proxy, timeout)
+            tz = self._fetch_ticker_tz(proxy, timeout, data)
 
             if utils.is_valid_timezone(tz):
                 # info fetch is relatively slow so cache timezone
@@ -1604,8 +1610,10 @@ class TickerBase:
         return tz
 
     @utils.log_indent_decorator
-    def _fetch_ticker_tz(self, proxy, timeout):
-        # Query Yahoo for fast price data just to get returned timezone
+    def _fetch_ticker_tz(self, proxy, timeout, data=None):
+        # Query Yahoo for fast price data just to get returned timezone.
+        # If data is provided, get the timezone from it instead of reaching
+        # out to Yahoo.
 
         logger = utils.get_yf_logger()
 
@@ -1614,26 +1622,27 @@ class TickerBase:
         # Getting data from json
         url = f"{self._base_url}/v8/finance/chart/{self.ticker}"
 
-        try:
-            data = self._data.cache_get(url=url, params=params, proxy=proxy, timeout=timeout)
-            data = data.json()
-        except Exception as e:
-            logger.error(f"Failed to get ticker '{self.ticker}' reason: {e}")
-            return None
+        if not data:
+            try:
+                data = self._data.cache_get(url=url, params=params, proxy=proxy, timeout=timeout)
+                data = data.json()
+            except Exception as e:
+                logger.error(f"Failed to get ticker '{self.ticker}' reason: {e}")
+                return None
+
+        error = data.get('chart', {}).get('error', None)
+        if error:
+            # explicit error from yahoo API
+            logger.debug(f"Got error from yahoo api for ticker {self.ticker}, Error: {error}")
         else:
-            error = data.get('chart', {}).get('error', None)
-            if error:
-                # explicit error from yahoo API
-                logger.debug(f"Got error from yahoo api for ticker {self.ticker}, Error: {error}")
-            else:
-                try:
-                    return data["chart"]["result"][0]["meta"]["exchangeTimezoneName"]
-                except Exception as err:
-                    logger.error(f"Could not get exchangeTimezoneName for ticker '{self.ticker}' reason: {err}")
-                    logger.debug("Got response: ")
-                    logger.debug("-------------")
-                    logger.debug(f" {data}")
-                    logger.debug("-------------")
+            try:
+                return data["chart"]["result"][0]["meta"]["exchangeTimezoneName"]
+            except Exception as err:
+                logger.error(f"Could not get exchangeTimezoneName for ticker '{self.ticker}' reason: {err}")
+                logger.debug("Got response: ")
+                logger.debug("-------------")
+                logger.debug(f" {data}")
+                logger.debug("-------------")
         return None
 
     def get_recommendations(self, proxy=None, as_dict=False):
diff --git a/tmp/lima/python-pkg-lambda_quotes/python/yfinance/data.py b/./data.py
index 442c747..eafc7f9 100644
--- a/tmp/lima/python-pkg-lambda_quotes/python/yfinance/data.py
+++ b/./data.py
@@ -49,12 +49,16 @@ class TickerData:
 
     def get(self, url, user_agent_headers=None, params=None, proxy=None, timeout=30):
         proxy = self._get_proxy(proxy)
+        logger = utils.get_yf_logger()
+        start_time = time.time()
+        logger.info(f"> URL GET {self.ticker} start")
         response = self._session.get(
             url=url,
             params=params,
             proxies=proxy,
             timeout=timeout,
             headers=user_agent_headers or self.user_agent_headers)
+        logger.info(f"< URL GET {self.ticker} took {round(time.time() - start_time, 2)}s")
         return response
 
     @lru_cache_freezeargs
diff --git a/tmp/lima/python-pkg-lambda_quotes/python/yfinance/multi.py b/./multi.py
index d51791f..0446b3b 100644
--- a/tmp/lima/python-pkg-lambda_quotes/python/yfinance/multi.py
+++ b/./multi.py
@@ -31,6 +31,10 @@ import pandas as _pd
 from . import Ticker, utils
 from . import shared
 
+# This needs to be done at top level, not inside a function, since the thread
+# pool config gets decided by the multitasking lib when evaluating the "@task"
+# decorator, and it cannot be changed at a later point.
+_multitasking.set_max_threads(32)
 
 @utils.log_indent_decorator
 def download(tickers, start=None, end=None, actions=False, threads=True, ignore_tz=None,
@@ -145,9 +149,6 @@ def download(tickers, start=None, end=None, actions=False, threads=True, ignore_
 
     # download using threads
     if threads:
-        if threads is True:
-            threads = min([len(tickers), _multitasking.cpu_count() * 2])
-        _multitasking.set_max_threads(threads)
         for i, ticker in enumerate(tickers):
             _download_one_threaded(ticker, period=period, interval=interval,
                                    start=start, end=end, prepost=prepost,