Dev version 0.2.10b3

When calibrating price repair, use weighted average to estimate stock split ratio, is more resilient

.github/ISSUE_TEMPLATE/bug_report.md

@@ -23,20 +23,20 @@ and comparing against [PIP](https://pypi.org/project/yfinance/#history).
 
 ### Does Yahoo actually have the data?
 
-Visit `finance.yahoo.com` and confim they have your data. Maybe your ticker was delisted.
+Are spelling ticker *exactly* same as Yahoo?
 
-Then check that you are spelling ticker *exactly* same as Yahoo.
+Visit `finance.yahoo.com` and confim they have your data. Maybe your ticker was delisted.
 
 ### Are you spamming Yahoo?
 
-Yahoo Finance free service has limit on query rate (roughly 100/s). Them delaying or blocking your spam is not a bug.
+Yahoo Finance free service has limit on query rate dependent on request - roughly 500/minute for prices, 10/minute for info. Them delaying or blocking your spam is not a bug.
 
 ### Still think it's a bug?
 
 Delete this default message and submit your bug report here, providing the following as best you can:
 
+- Simple code that reproduces your problem
+- Error message, with traceback if shown
 - Info about your system:
   - yfinance version
   - operating system
-- Simple code that reproduces your problem
-- The error message

CHANGELOG.rst

@@ -1,6 +1,24 @@
 Change Log
 ===========
 
+0.2.9
+-----
+- Fix fast_info bugs #1362
+
+0.2.7
+-----
+- Fix Yahoo decryption, smarter this time #1353
+- Rename basic_info -> fast_info #1354
+
+0.2.6
+-----
+- Fix Ticker.basic_info lazy-loading #1342
+
+0.2.5
+-----
+- Fix Yahoo data decryption again #1336
+- New: Ticker.basic_info - faster Ticker.info #1317
+
 0.2.4
 -----
 - Fix Yahoo data decryption #1297

README.md

@@ -42,12 +42,10 @@ Yahoo! finance API is intended for personal use only.**
 
 ---
 
-## What's new in version 0.2
+## News [2023-01-27]
+Since December 2022 Yahoo has been encrypting the web data that `yfinance` scrapes for non-market data. Fortunately the decryption keys are available, although Yahoo moved/changed them several times hence `yfinance` breaking several times. `yfinance` is now better prepared for any future changes by Yahoo.
 
-- Optimised web scraping
-- All 3 financials tables now match website so expect keys to change. If you really want old tables, use [`Ticker.get_[income_stmt|balance_sheet|cashflow](legacy=True, ...)`](https://github.com/ranaroussi/yfinance/blob/85783da515761a145411d742c2a8a3c1517264b0/yfinance/base.py#L968)
-- price data improvements: fix bug NaN rows with dividend; new repair feature for missing or 100x prices `download(repair=True)`; new attribute `Ticker.history_metadata`
-[See release notes for full list of changes](https://github.com/ranaroussi/yfinance/releases/tag/0.2.1)
+Why is Yahoo doing this? We don't know. Is it to stop scrapers? Maybe, so we've implemented changes to reduce load on Yahoo. In December we rolled out version 0.2 with optimised scraping. Then in 0.2.6 introduced `Ticker.fast_info`, providing much faster access to some `info` elements wherever possible e.g. price stats and forcing users to switch (sorry but we think necessary). `info` will continue to exist for as long as there are elements without a fast alternative.
 
 ## Quick Start
 
@@ -60,31 +58,28 @@ import yfinance as yf
 
 msft = yf.Ticker("MSFT")
 
-# get stock info
+# get all stock info (slow)
 msft.info
+# fast access to subset of stock info (opportunistic)
+msft.fast_info
 
 # get historical market data
-hist = msft.history(period="max")
+hist = msft.history(period="1mo")
 
 # show meta information about the history (requires history() to be called first)
 msft.history_metadata
 
 # show actions (dividends, splits, capital gains)
 msft.actions
-
-# show dividends
 msft.dividends
-
-# show splits
 msft.splits
-
-
-# show capital gains (for mutual funds & etfs)
-msft.capital_gains
+msft.capital_gains  # only for mutual funds & etfs
 
 # show share count
+# - yearly summary:
 msft.shares
-msft.get_shares_full()
+# - accurate time-series count:
+msft.get_shares_full(start="2022-01-01", end=None)
 
 # show financials:
 # - income statement
@@ -98,13 +93,9 @@ msft.cashflow
 msft.quarterly_cashflow
 # see `Ticker.get_income_stmt()` for more options
 
-# show major holders
+# show holders
 msft.major_holders
-
-# show institutional holders
 msft.institutional_holders
-
-# show mutualfund holders
 msft.mutualfund_holders
 
 # show earnings
@@ -225,7 +216,7 @@ data = yf.download(  # or pdr.get_data_yahoo(...
         # (optional, default is False)
         auto_adjust = True,
 
-        # attempt repair of missing data or currency mixups e.g. $/cents
+        # attempt repair of Yahoo data issues
         repair = False,
 
         # download pre/post regular market hours data

meta.yaml

@@ -1,5 +1,5 @@
 {% set name = "yfinance" %}
-{% set version = "0.2.4" %}
+{% set version = "0.2.9" %}
 
 package:
   name: "{{ name|lower }}"

tests/prices.py

@@ -24,9 +24,7 @@ class TestPriceHistory(unittest.TestCase):
 
     def test_daily_index(self):
         tkrs = ["BHP.AX", "IMP.JO", "BP.L", "PNL.L", "INTC"]
-
         intervals = ["1d", "1wk", "1mo"]
-
         for tkr in tkrs:
             dat = yf.Ticker(tkr, session=self.session)
 
@@ -44,8 +42,8 @@ class TestPriceHistory(unittest.TestCase):
 
             dt_utc = _tz.timezone("UTC").localize(_dt.datetime.utcnow())
             dt = dt_utc.astimezone(_tz.timezone(tz))
-
-            df = dat.history(start=dt.date() - _dt.timedelta(days=1), interval="1h")
+            start_d = dt.date() - _dt.timedelta(days=7)
+            df = dat.history(start=start_d, interval="1h")
 
             dt0 = df.index[-2]
             dt1 = df.index[-1]
@@ -55,7 +53,6 @@ class TestPriceHistory(unittest.TestCase):
                 print("Ticker = ", tkr)
                 raise
 
-
     def test_duplicatingDaily(self):
         tkrs = ["IMP.JO", "BHG.JO", "SSW.JO", "BP.L", "INTC"]
         test_run = False
@@ -110,22 +107,27 @@ class TestPriceHistory(unittest.TestCase):
     def test_intraDayWithEvents(self):
         # TASE dividend release pre-market, doesn't merge nicely with intra-day data so check still present
 
-        tkr = "ICL.TA"
-        # tkr = "ESLT.TA"
-        # tkr = "ONE.TA"
-        # tkr = "MGDL.TA"
-        start_d = _dt.date.today() - _dt.timedelta(days=60)
-        end_d = None
-        df_daily = yf.Ticker(tkr, session=self.session).history(start=start_d, end=end_d, interval="1d", actions=True)
-        df_daily_divs = df_daily["Dividends"][df_daily["Dividends"] != 0]
-        if df_daily_divs.shape[0] == 0:
-            self.skipTest("Skipping test_intraDayWithEvents() because 'ICL.TA' has no dividend in last 60 days")
+        tase_tkrs = ["ICL.TA", "ESLT.TA", "ONE.TA", "MGDL.TA"]
+        test_run = False
+        for tkr in tase_tkrs:
+            start_d = _dt.date.today() - _dt.timedelta(days=59)
+            end_d = None
+            df_daily = yf.Ticker(tkr, session=self.session).history(start=start_d, end=end_d, interval="1d", actions=True)
+            df_daily_divs = df_daily["Dividends"][df_daily["Dividends"] != 0]
+            if df_daily_divs.shape[0] == 0:
+                # self.skipTest("Skipping test_intraDayWithEvents() because 'ICL.TA' has no dividend in last 60 days")
+                continue
 
-        last_div_date = df_daily_divs.index[-1]
-        start_d = last_div_date.date()
-        end_d = last_div_date.date() + _dt.timedelta(days=1)
-        df = yf.Ticker(tkr, session=self.session).history(start=start_d, end=end_d, interval="15m", actions=True)
-        self.assertTrue((df["Dividends"] != 0.0).any())
+            last_div_date = df_daily_divs.index[-1]
+            start_d = last_div_date.date()
+            end_d = last_div_date.date() + _dt.timedelta(days=1)
+            df = yf.Ticker(tkr, session=self.session).history(start=start_d, end=end_d, interval="15m", actions=True)
+            self.assertTrue((df["Dividends"] != 0.0).any())
+            test_run = True
+            break
+
+        if not test_run:
+            self.skipTest("Skipping test_intraDayWithEvents() because no tickers had a dividend in last 60 days")
 
     def test_dailyWithEvents(self):
         # Reproduce issue #521
@@ -230,7 +232,6 @@ class TestPriceHistory(unittest.TestCase):
 
     def test_tz_dst_ambiguous(self):
         # Reproduce issue #1100
-
         try:
             yf.Ticker("ESLT.TA", session=self.session).history(start="2002-10-06", end="2002-10-09", interval="1d")
         except _tz.exceptions.AmbiguousTimeError:
@@ -261,6 +262,116 @@ class TestPriceHistory(unittest.TestCase):
             print("Weekly data not aligned to Monday")
             raise
 
+    def test_prune_post_intraday_us(self):
+        # Half-day before USA Thanksgiving. Yahoo normally 
+        # returns an interval starting when regular trading closes, 
+        # even if prepost=False.
+
+        # Setup
+        tkr = "AMZN"
+        interval = "1h"
+        interval_td = _dt.timedelta(hours=1)
+        time_open = _dt.time(9, 30)
+        time_close = _dt.time(16)
+        special_day = _dt.date(2022, 11, 25)
+        time_early_close = _dt.time(13)
+        dat = yf.Ticker(tkr, session=self.session)
+
+        # Run
+        start_d = special_day - _dt.timedelta(days=7)
+        end_d = special_day + _dt.timedelta(days=7)
+        df = dat.history(start=start_d, end=end_d, interval=interval, prepost=False, keepna=True)
+        tg_last_dt = df.loc[str(special_day)].index[-1]
+        self.assertTrue(tg_last_dt.time() < time_early_close)
+
+        # Test no other afternoons (or mornings) were pruned
+        start_d = _dt.date(special_day.year, 1, 1)
+        end_d = _dt.date(special_day.year+1, 1, 1)
+        df = dat.history(start=start_d, end=end_d, interval="1h", prepost=False, keepna=True)
+        last_dts = _pd.Series(df.index).groupby(df.index.date).last()
+        f_early_close = (last_dts+interval_td).dt.time < time_close
+        early_close_dates = last_dts.index[f_early_close].values
+        self.assertEqual(len(early_close_dates), 1)
+        self.assertEqual(early_close_dates[0], special_day)
+
+        first_dts = _pd.Series(df.index).groupby(df.index.date).first()
+        f_late_open = first_dts.dt.time > time_open
+        late_open_dates = first_dts.index[f_late_open]
+        self.assertEqual(len(late_open_dates), 0)
+
+    def test_prune_post_intraday_omx(self):
+        # Half-day before Sweden Christmas. Yahoo normally 
+        # returns an interval starting when regular trading closes, 
+        # even if prepost=False.
+        # If prepost=False, test that yfinance is removing prepost intervals.
+
+        # Setup
+        tkr = "AEC.ST"
+        interval = "1h"
+        interval_td = _dt.timedelta(hours=1)
+        time_open = _dt.time(9)
+        time_close = _dt.time(17,30)
+        special_day = _dt.date(2022, 12, 23)
+        time_early_close = _dt.time(13, 2)
+        dat = yf.Ticker(tkr, session=self.session)
+
+        # Half trading day Jan 5, Apr 14, May 25, Jun 23, Nov 4, Dec 23, Dec 30
+        half_days = [_dt.date(special_day.year, x[0], x[1]) for x in [(1,5), (4,14), (5,25), (6,23), (11,4), (12,23), (12,30)]]
+
+        # Yahoo has incorrectly classified afternoon of 2022-04-13 as post-market.
+        # Nothing yfinance can do because Yahoo doesn't return data with prepost=False.
+        # But need to handle in this test.
+        expected_incorrect_half_days = [_dt.date(2022,4,13)]
+        half_days = sorted(half_days+expected_incorrect_half_days)
+
+        # Run
+        start_d = special_day - _dt.timedelta(days=7)
+        end_d = special_day + _dt.timedelta(days=7)
+        df = dat.history(start=start_d, end=end_d, interval=interval, prepost=False, keepna=True)
+        tg_last_dt = df.loc[str(special_day)].index[-1]
+        self.assertTrue(tg_last_dt.time() < time_early_close)
+
+        # Test no other afternoons (or mornings) were pruned
+        start_d = _dt.date(special_day.year, 1, 1)
+        end_d = _dt.date(special_day.year+1, 1, 1)
+        df = dat.history(start=start_d, end=end_d, interval="1h", prepost=False, keepna=True)
+        last_dts = _pd.Series(df.index).groupby(df.index.date).last()
+        f_early_close = (last_dts+interval_td).dt.time < time_close
+        early_close_dates = last_dts.index[f_early_close].values
+        unexpected_early_close_dates = [d for d in early_close_dates if not d in half_days]
+        self.assertEqual(len(unexpected_early_close_dates), 0)
+        self.assertEqual(len(early_close_dates), len(half_days))
+        self.assertTrue(_np.equal(early_close_dates, half_days).all())
+
+        first_dts = _pd.Series(df.index).groupby(df.index.date).first()
+        f_late_open = first_dts.dt.time > time_open
+        late_open_dates = first_dts.index[f_late_open]
+        self.assertEqual(len(late_open_dates), 0)
+
+    def test_prune_post_intraday_asx(self):
+        # Setup
+        tkr = "BHP.AX"
+        interval = "1h"
+        interval_td = _dt.timedelta(hours=1)
+        time_open = _dt.time(10)
+        time_close = _dt.time(16,12)
+        # No early closes in 2022
+        dat = yf.Ticker(tkr, session=self.session)
+
+        # Test no afternoons (or mornings) were pruned
+        start_d = _dt.date(2022, 1, 1)
+        end_d = _dt.date(2022+1, 1, 1)
+        df = dat.history(start=start_d, end=end_d, interval="1h", prepost=False, keepna=True)
+        last_dts = _pd.Series(df.index).groupby(df.index.date).last()
+        f_early_close = (last_dts+interval_td).dt.time < time_close
+        early_close_dates = last_dts.index[f_early_close].values
+        self.assertEqual(len(early_close_dates), 0)
+
+        first_dts = _pd.Series(df.index).groupby(df.index.date).first()
+        f_late_open = first_dts.dt.time > time_open
+        late_open_dates = first_dts.index[f_late_open]
+        self.assertEqual(len(late_open_dates), 0)
+
     def test_weekly_2rows_fix(self):
         tkr = "AMZN"
         start = _dt.date.today() - _dt.timedelta(days=14)
@@ -270,11 +381,43 @@ class TestPriceHistory(unittest.TestCase):
         df = dat.history(start=start, interval="1wk")
         self.assertTrue((df.index.weekday == 0).all())
 
+class TestPriceRepair(unittest.TestCase):
+    session = None
+
+    @classmethod
+    def setUpClass(cls):
+        cls.session = requests_cache.CachedSession(backend='memory')
+
+    @classmethod
+    def tearDownClass(cls):
+        if cls.session is not None:
+            cls.session.close()
+
+    def test_reconstruct_2m(self):
+        # 2m repair requires 1m data.
+        # Yahoo restricts 1m fetches to 7 days max within last 30 days.
+        # Need to test that '_reconstruct_intervals_batch()' can handle this.
+
+        tkrs = ["BHP.AX", "IMP.JO", "BP.L", "PNL.L", "INTC"]
+
+        dt_now = _pd.Timestamp.utcnow()
+        td_7d = _dt.timedelta(days=7)
+        td_60d = _dt.timedelta(days=60)
+
+        # Round time for 'requests_cache' reuse
+        dt_now = dt_now.ceil("1h")
+
+        for tkr in tkrs:
+            dat = yf.Ticker(tkr, session=self.session)
+            end_dt = dt_now
+            start_dt = end_dt - td_60d
+            df = dat.history(start=start_dt, end=end_dt, interval="2m", repair=True)
+
     def test_repair_100x_weekly(self):
         # Setup:
         tkr = "PNL.L"
         dat = yf.Ticker(tkr, session=self.session)
-        tz_exchange = dat.info["exchangeTimezoneName"]
+        tz_exchange = dat.fast_info["timezone"]
 
         data_cols = ["Low", "High", "Open", "Close", "Adj Close"]
         df = _pd.DataFrame(data={"Open":      [470.5, 473.5, 474.5, 470],
@@ -283,22 +426,22 @@ class TestPriceHistory(unittest.TestCase):
                                  "Close":     [475,   473.5, 472,   473.5],
                                  "Adj Close": [475,   473.5, 472,   473.5],
                                  "Volume": [2295613, 2245604, 3000287, 2635611]},
-                                index=_pd.to_datetime([_dt.date(2022, 10, 23),
-                                                       _dt.date(2022, 10, 16),
-                                                       _dt.date(2022, 10, 9),
-                                                       _dt.date(2022, 10, 2)]))
+                                index=_pd.to_datetime([_dt.date(2022, 10, 24),
+                                                       _dt.date(2022, 10, 17),
+                                                       _dt.date(2022, 10, 10),
+                                                       _dt.date(2022, 10, 3)]))
         df = df.sort_index()
         df.index.name = "Date"
         df_bad = df.copy()
-        df_bad.loc["2022-10-23", "Close"] *= 100
-        df_bad.loc["2022-10-16", "Low"] *= 100
-        df_bad.loc["2022-10-2", "Open"] *= 100
+        df_bad.loc["2022-10-24", "Close"] *= 100
+        df_bad.loc["2022-10-17", "Low"] *= 100
+        df_bad.loc["2022-10-03", "Open"] *= 100
         df.index = df.index.tz_localize(tz_exchange)
         df_bad.index = df_bad.index.tz_localize(tz_exchange)
 
         # Run test
 
-        df_repaired = dat._fix_unit_mixups(df_bad, "1wk", tz_exchange)
+        df_repaired = dat._fix_unit_mixups(df_bad, "1wk", tz_exchange, prepost=False)
 
         # First test - no errors left
         for c in data_cols:
@@ -326,7 +469,7 @@ class TestPriceHistory(unittest.TestCase):
 
         tkr = "PNL.L"
         dat = yf.Ticker(tkr, session=self.session)
-        tz_exchange = dat.info["exchangeTimezoneName"]
+        tz_exchange = dat.fast_info["timezone"]
 
         data_cols = ["Low", "High", "Open", "Close", "Adj Close"]
         df = _pd.DataFrame(data={"Open":      [400,   398,    392.5,   417],
@@ -353,7 +496,7 @@ class TestPriceHistory(unittest.TestCase):
         df.index = df.index.tz_localize(tz_exchange)
         df_bad.index = df_bad.index.tz_localize(tz_exchange)
 
-        df_repaired = dat._fix_unit_mixups(df_bad, "1wk", tz_exchange)
+        df_repaired = dat._fix_unit_mixups(df_bad, "1wk", tz_exchange, prepost=False)
 
         # First test - no errors left
         for c in data_cols:
@@ -381,7 +524,7 @@ class TestPriceHistory(unittest.TestCase):
     def test_repair_100x_daily(self):
         tkr = "PNL.L"
         dat = yf.Ticker(tkr, session=self.session)
-        tz_exchange = dat.info["exchangeTimezoneName"]
+        tz_exchange = dat.fast_info["timezone"]
 
         data_cols = ["Low", "High", "Open", "Close", "Adj Close"]
         df = _pd.DataFrame(data={"Open":      [478,    476,   476,   472],
@@ -403,7 +546,7 @@ class TestPriceHistory(unittest.TestCase):
         df.index = df.index.tz_localize(tz_exchange)
         df_bad.index = df_bad.index.tz_localize(tz_exchange)
 
-        df_repaired = dat._fix_unit_mixups(df_bad, "1d", tz_exchange)
+        df_repaired = dat._fix_unit_mixups(df_bad, "1d", tz_exchange, prepost=False)
 
         # First test - no errors left
         for c in data_cols:
@@ -423,7 +566,7 @@ class TestPriceHistory(unittest.TestCase):
     def test_repair_zeroes_daily(self):
         tkr = "BBIL.L"
         dat = yf.Ticker(tkr, session=self.session)
-        tz_exchange = dat.info["exchangeTimezoneName"]
+        tz_exchange = dat.fast_info["timezone"]
 
         df_bad = _pd.DataFrame(data={"Open":      [0,      102.04, 102.04],
                                      "High":      [0,      102.1,  102.11],
@@ -438,7 +581,7 @@ class TestPriceHistory(unittest.TestCase):
         df_bad.index.name = "Date"
         df_bad.index = df_bad.index.tz_localize(tz_exchange)
 
-        repaired_df = dat._fix_zeroes(df_bad, "1d", tz_exchange)
+        repaired_df = dat._fix_zeroes(df_bad, "1d", tz_exchange, prepost=False)
 
         correct_df = df_bad.copy()
         correct_df.loc["2022-11-01", "Open"] = 102.080002
@@ -450,40 +593,31 @@ class TestPriceHistory(unittest.TestCase):
     def test_repair_zeroes_hourly(self):
         tkr = "INTC"
         dat = yf.Ticker(tkr, session=self.session)
-        tz_exchange = dat.info["exchangeTimezoneName"]
+        tz_exchange = dat.fast_info["timezone"]
 
-        df_bad = _pd.DataFrame(data={"Open":      [29.68, 29.49, 29.545, _np.nan, 29.485],
-                                     "High":      [29.68, 29.625, 29.58, _np.nan, 29.49],
-                                     "Low":       [29.46, 29.4, 29.45, _np.nan, 29.31],
-                                     "Close":     [29.485, 29.545, 29.485, _np.nan, 29.325],
-                                     "Adj Close": [29.485, 29.545, 29.485, _np.nan, 29.325],
-                                     "Volume": [3258528, 2140195, 1621010, 0, 0]},
-                                index=_pd.to_datetime([_dt.datetime(2022,11,25, 9,30),
-                                                       _dt.datetime(2022,11,25, 10,30),
-                                                       _dt.datetime(2022,11,25, 11,30),
-                                                       _dt.datetime(2022,11,25, 12,30),
-                                                       _dt.datetime(2022,11,25, 13,00)]))
-        df_bad = df_bad.sort_index()
-        df_bad.index.name = "Date"
-        df_bad.index = df_bad.index.tz_localize(tz_exchange)
+        correct_df = dat.history(period="1wk", interval="1h", auto_adjust=False, repair=True)
 
-        repaired_df = dat._fix_zeroes(df_bad, "1h", tz_exchange)
+        df_bad = correct_df.copy()
+        bad_idx = correct_df.index[10]
+        df_bad.loc[bad_idx, "Open"] = _np.nan
+        df_bad.loc[bad_idx, "High"] = _np.nan
+        df_bad.loc[bad_idx, "Low"] = _np.nan
+        df_bad.loc[bad_idx, "Close"] = _np.nan
+        df_bad.loc[bad_idx, "Adj Close"] = _np.nan
+        df_bad.loc[bad_idx, "Volume"] = 0
+
+        repaired_df = dat._fix_zeroes(df_bad, "1h", tz_exchange, prepost=False)
 
-        correct_df = df_bad.copy()
-        idx = _pd.Timestamp(2022,11,25, 12,30).tz_localize(tz_exchange)
-        correct_df.loc[idx, "Open"] = 29.485001
-        correct_df.loc[idx, "High"] = 29.49
-        correct_df.loc[idx, "Low"] = 29.43
-        correct_df.loc[idx, "Close"] = 29.455
-        correct_df.loc[idx, "Adj Close"] = 29.455
-        correct_df.loc[idx, "Volume"] = 609164
         for c in ["Open", "Low", "High", "Close"]:
             try:
                 self.assertTrue(_np.isclose(repaired_df[c], correct_df[c], rtol=1e-7).all())
             except:
                 print("COLUMN", c)
+                print("- repaired_df")
                 print(repaired_df)
+                print("- correct_df[c]:")
                 print(correct_df[c])
+                print("- diff:")
                 print(repaired_df[c] - correct_df[c])
                 raise
 

tests/ticker.py

@@ -9,6 +9,7 @@ Specific test class:
 
 """
 import pandas as pd
+import numpy as np
 
 from .context import yfinance as yf
 
@@ -660,16 +661,140 @@ class TestTickerMiscFinancials(unittest.TestCase):
         self.assertIsInstance(data, pd.Series, "data has wrong type")
         self.assertFalse(data.empty, "data is empty")
 
-    def test_info(self):
-        data = self.ticker.info
-        self.assertIsInstance(data, dict, "data has wrong type")
-        self.assertIn("symbol", data.keys(), "Did not find expected key in info dict")
-        self.assertEqual("GOOGL", data["symbol"], "Wrong symbol value in info dict")
-
     def test_bad_freq_value_raises_exception(self):
         self.assertRaises(ValueError, lambda: self.ticker.get_cashflow(freq="badarg"))
 
 
+class TestTickerInfo(unittest.TestCase):
+    session = None
+
+    @classmethod
+    def setUpClass(cls):
+        cls.session = requests_cache.CachedSession(backend='memory')
+
+    @classmethod
+    def tearDownClass(cls):
+        if cls.session is not None:
+            cls.session.close()
+
+    def setUp(self):
+        self.symbols = []
+        self.symbols += ["ESLT.TA", "BP.L", "GOOGL"]
+        self.symbols.append("QCSTIX")  # good for testing, doesn't trade
+        self.symbols += ["BTC-USD", "IWO", "VFINX", "^GSPC"]
+        self.symbols += ["SOKE.IS", "ADS.DE"]  # detected bugs
+        self.tickers = [yf.Ticker(s, session=self.session) for s in self.symbols]
+
+    def tearDown(self):
+        self.ticker = None
+
+    def test_info(self):
+        data = self.tickers[0].info
+        self.assertIsInstance(data, dict, "data has wrong type")
+        self.assertIn("symbol", data.keys(), "Did not find expected key in info dict")
+        self.assertEqual(self.symbols[0], data["symbol"], "Wrong symbol value in info dict")
+
+    def test_fast_info(self):
+        yf.scrapers.quote.PRUNE_INFO = False
+
+        fast_info_keys = set()
+        for ticker in self.tickers:
+            fast_info_keys.update(set(ticker.fast_info.keys()))
+        fast_info_keys = sorted(list(fast_info_keys))
+
+        key_rename_map = {}
+        key_rename_map["currency"] = "currency"
+        key_rename_map["quote_type"] = "quoteType"
+        key_rename_map["timezone"] = "exchangeTimezoneName"
+
+        key_rename_map["last_price"] = ["currentPrice", "regularMarketPrice"]
+        key_rename_map["open"] = ["open", "regularMarketOpen"]
+        key_rename_map["day_high"] = ["dayHigh", "regularMarketDayHigh"]
+        key_rename_map["day_low"] = ["dayLow", "regularMarketDayLow"]
+        key_rename_map["previous_close"] = ["previousClose"]
+        key_rename_map["regular_market_previous_close"] = ["regularMarketPreviousClose"]
+
+        key_rename_map["fifty_day_average"] = "fiftyDayAverage"
+        key_rename_map["two_hundred_day_average"] = "twoHundredDayAverage"
+        key_rename_map["year_change"] = ["52WeekChange", "fiftyTwoWeekChange"]
+        key_rename_map["year_high"] = "fiftyTwoWeekHigh"
+        key_rename_map["year_low"] = "fiftyTwoWeekLow"
+
+        key_rename_map["last_volume"] = ["volume", "regularMarketVolume"]
+        key_rename_map["ten_day_average_volume"] = ["averageVolume10days", "averageDailyVolume10Day"]
+        key_rename_map["three_month_average_volume"] = "averageVolume"
+
+        key_rename_map["market_cap"] = "marketCap"
+        key_rename_map["shares"] = "sharesOutstanding"
+
+        for k in list(key_rename_map.keys()):
+            if '_' in k:
+                key_rename_map[yf.utils.snake_case_2_camelCase(k)] = key_rename_map[k]
+
+        # Note: share count items in info[] are bad. Sometimes the float > outstanding!
+        # So often fast_info["shares"] does not match. 
+        # Why isn't fast_info["shares"] wrong? Because using it to calculate market cap always correct.
+        bad_keys = {"shares"}
+
+        # Loose tolerance for averages, no idea why don't match info[]. Is info wrong?
+        custom_tolerances = {}
+        custom_tolerances["year_change"] = 1.0
+        # custom_tolerances["ten_day_average_volume"] = 1e-3
+        custom_tolerances["ten_day_average_volume"] = 1e-1
+        # custom_tolerances["three_month_average_volume"] = 1e-2
+        custom_tolerances["three_month_average_volume"] = 5e-1
+        custom_tolerances["fifty_day_average"] = 1e-2
+        custom_tolerances["two_hundred_day_average"] = 1e-2
+        for k in list(custom_tolerances.keys()):
+            if '_' in k:
+                custom_tolerances[yf.utils.snake_case_2_camelCase(k)] = custom_tolerances[k]
+
+        for k in fast_info_keys:
+            if k in key_rename_map:
+                k2 = key_rename_map[k]
+            else:
+                k2 = k
+
+            if not isinstance(k2, list):
+                k2 = [k2]
+
+            for m in k2:
+                for ticker in self.tickers:
+                    if not m in ticker.info:
+                        # print(f"symbol={ticker.ticker}: fast_info key '{k}' mapped to info key '{m}' but not present in info")
+                        continue
+
+                    if k in bad_keys:
+                        continue
+
+                    if k in custom_tolerances:
+                        rtol = custom_tolerances[k]
+                    else:
+                        rtol = 5e-3
+                        # rtol = 1e-4
+
+                    correct = ticker.info[m]
+                    test = ticker.fast_info[k]
+                    # print(f"Testing: symbol={ticker.ticker} m={m} k={k}: test={test} vs correct={correct}")
+                    if k in ["market_cap","marketCap"] and ticker.fast_info["currency"] in ["GBp", "ILA"]:
+                        # Adjust for currency to match Yahoo:
+                        test *= 0.01
+                    try:
+                        if correct is None:
+                            self.assertTrue(test is None or (not np.isnan(test)), f"{k}: {test} must be None or real value because correct={correct}")
+                        elif isinstance(test, float) or isinstance(correct, int):
+                            self.assertTrue(np.isclose(test, correct, rtol=rtol), f"{ticker.ticker} {k}: {test} != {correct}")
+                        else:
+                            self.assertEqual(test, correct, f"{k}: {test} != {correct}")
+                    except:
+                        if k in ["regularMarketPreviousClose"] and ticker.ticker in ["ADS.DE"]:
+                            # Yahoo is wrong, is returning post-market close not regular
+                            continue
+                        else:
+                            raise
+
+
+
 def suite():
     suite = unittest.TestSuite()
     suite.addTest(TestTicker('Test ticker'))
@@ -677,6 +802,7 @@ def suite():
     suite.addTest(TestTickerHolders('Test holders'))
     suite.addTest(TestTickerHistory('Test Ticker history'))
     suite.addTest(TestTickerMiscFinancials('Test misc financials'))
+    suite.addTest(TestTickerInfo('Test info & fast_info'))
     return suite
 
 

yfinance/base.py

@@ -23,6 +23,7 @@ from __future__ import print_function
 
 import time as _time
 import datetime as _datetime
+import dateutil as _dateutil
 from typing import Optional
 
 import pandas as _pd
@@ -47,6 +48,448 @@ _SCRAPE_URL_ = 'https://finance.yahoo.com/quote'
 _ROOT_URL_ = 'https://finance.yahoo.com'
 
 
+class FastInfo:
+    # Contain small subset of info[] items that can be fetched faster elsewhere.
+    # Imitates a dict.
+    def __init__(self, tickerBaseObject):
+        self._tkr = tickerBaseObject
+
+        self._prices_1y = None
+        self._prices_1wk_1h_prepost = None
+        self._prices_1wk_1h_reg = None
+        self._md = None
+
+        self._currency = None
+        self._quote_type = None
+        self._exchange = None
+        self._timezone = None
+
+        self._shares = None
+        self._mcap = None
+
+        self._open = None
+        self._day_high = None
+        self._day_low = None
+        self._last_price = None
+        self._last_volume = None
+
+        self._prev_close = None
+
+        self._reg_prev_close = None
+
+        self._50d_day_average = None
+        self._200d_day_average = None
+        self._year_high = None
+        self._year_low = None
+        self._year_change = None
+
+        self._10d_avg_vol = None
+        self._3mo_avg_vol = None
+
+        # attrs = utils.attributes(self)
+        # self.keys = attrs.keys()
+        # utils.attributes is calling each method, bad! Have to hardcode
+        _properties = ["currency", "quote_type", "exchange", "timezone"]
+        _properties += ["shares", "market_cap"]
+        _properties += ["last_price", "previous_close", "open", "day_high", "day_low"]
+        _properties += ["regular_market_previous_close"]
+        _properties += ["last_volume"]
+        _properties += ["fifty_day_average", "two_hundred_day_average", "ten_day_average_volume", "three_month_average_volume"]
+        _properties += ["year_high", "year_low", "year_change"]
+
+        # Because released before fixing key case, need to officially support 
+        # camel-case but also secretly support snake-case
+        base_keys = [k for k in _properties if not '_' in k]
+
+        sc_keys = [k for k in _properties if '_' in k]
+
+        self._sc_to_cc_key = {k:utils.snake_case_2_camelCase(k) for k in sc_keys}
+        self._cc_to_sc_key = {v:k for k,v in self._sc_to_cc_key.items()}
+ 
+        self._public_keys = sorted(base_keys + list(self._sc_to_cc_key.values()))
+        self._keys = sorted(self._public_keys + sc_keys)
+
+    # dict imitation:
+    def keys(self):
+        return self._public_keys
+    def items(self):
+        return [(k,self[k]) for k in self._public_keys]
+    def values(self):
+        return [self[k] for k in self._public_keys]
+    def get(self, key, default=None):
+        if key in self.keys():
+            if key in self._cc_to_sc_key:
+                key = self._cc_to_sc_key[key]
+            return self[key]
+        return default
+    def __getitem__(self, k):
+        if not isinstance(k, str):
+            raise KeyError(f"key must be a string")
+        if not k in self._keys:
+            raise KeyError(f"'{k}' not valid key. Examine 'FastInfo.keys()'")
+        if k in self._cc_to_sc_key:
+            k = self._cc_to_sc_key[k]
+        return getattr(self, k)
+    def __contains__(self, k):
+        return k in self.keys()
+    def __iter__(self):
+        return iter(self.keys())
+
+    def __str__(self):
+        return "lazy-loading dict with keys = " + str(self.keys())
+    def __repr__(self):
+        return self.__str__()
+
+    def toJSON(self, indent=4):
+        d = {k:self[k] for k in self.keys()}
+        return _json.dumps({k:self[k] for k in self.keys()}, indent=indent)
+
+    def _get_1y_prices(self, fullDaysOnly=False):
+        if self._prices_1y is None:
+            self._prices_1y = self._tkr.history(period="380d", auto_adjust=False, debug=False, keepna=True)
+            self._md = self._tkr.get_history_metadata()
+            try:
+                ctp = self._md["currentTradingPeriod"]
+                self._today_open = pd.to_datetime(ctp["regular"]["start"], unit='s', utc=True).tz_convert(self.timezone)
+                self._today_close = pd.to_datetime(ctp["regular"]["end"], unit='s', utc=True).tz_convert(self.timezone)
+                self._today_midnight = self._today_close.ceil("D")
+            except:
+                self._today_open = None
+                self._today_close = None
+                self._today_midnight = None
+                raise
+
+        if self._prices_1y.empty:
+            return self._prices_1y
+
+        dnow = pd.Timestamp.utcnow().tz_convert(self.timezone).date()
+        d1 = dnow
+        d0 = (d1 + _datetime.timedelta(days=1)) - utils._interval_to_timedelta("1y")
+        if fullDaysOnly and self._exchange_open_now():
+            # Exclude today
+            d1 -= utils._interval_to_timedelta("1d")
+        return self._prices_1y.loc[str(d0):str(d1)]
+
+    def _get_1wk_1h_prepost_prices(self):
+        if self._prices_1wk_1h_prepost is None:
+            self._prices_1wk_1h_prepost = self._tkr.history(period="1wk", interval="1h", auto_adjust=False, prepost=True, debug=False)
+        return self._prices_1wk_1h_prepost
+
+    def _get_1wk_1h_reg_prices(self):
+        if self._prices_1wk_1h_reg is None:
+            self._prices_1wk_1h_reg = self._tkr.history(period="1wk", interval="1h", auto_adjust=False, prepost=False, debug=False)
+        return self._prices_1wk_1h_reg
+
+    def _get_exchange_metadata(self):
+        if self._md is not None:
+            return self._md
+
+        self._get_1y_prices()
+        self._md = self._tkr.get_history_metadata()
+        return self._md
+
+    def _exchange_open_now(self):
+        t = pd.Timestamp.utcnow()
+        self._get_exchange_metadata()
+
+        # if self._today_open is None and self._today_close is None:
+        #     r = False
+        # else:
+        #     r = self._today_open <= t and t < self._today_close
+
+        # if self._today_midnight is None:
+        #     r = False
+        # elif self._today_midnight.date() > t.tz_convert(self.timezone).date():
+        #     r = False
+        # else:
+        #     r = t < self._today_midnight
+
+        last_day_cutoff = self._get_1y_prices().index[-1] + _datetime.timedelta(days=1)
+        last_day_cutoff += _datetime.timedelta(minutes=20)
+        r = t < last_day_cutoff
+
+        # print("_exchange_open_now() returning", r)
+        return r
+
+    @property
+    def currency(self):
+        if self._currency is not None:
+            return self._currency
+
+        if self._tkr._history_metadata is None:
+            self._get_1y_prices()
+        md = self._tkr.get_history_metadata()
+        self._currency = md["currency"]
+        return self._currency
+
+    @property
+    def quote_type(self):
+        if self._quote_type is not None:
+            return self._quote_type
+
+        if self._tkr._history_metadata is None:
+            self._get_1y_prices()
+        md = self._tkr.get_history_metadata()
+        self._quote_type = md["instrumentType"]
+        return self._quote_type
+
+    @property
+    def exchange(self):
+        if self._exchange is not None:
+            return self._exchange
+
+        self._exchange = self._get_exchange_metadata()["exchangeName"]
+        return self._exchange
+
+    @property
+    def timezone(self):
+        if self._timezone is not None:
+            return self._timezone
+
+        self._timezone = self._get_exchange_metadata()["exchangeTimezoneName"]
+        return self._timezone
+
+    @property
+    def shares(self):
+        if self._shares is not None:
+            return self._shares
+
+        shares = self._tkr.get_shares_full(start=pd.Timestamp.utcnow().date()-pd.Timedelta(days=548))
+        if shares is None:
+            # Requesting 18 months failed, so fallback to shares which should include last year
+            shares = self._tkr.get_shares()
+        if shares is not None:
+            if isinstance(shares, pd.DataFrame):
+                shares = shares[shares.columns[0]]
+            self._shares = int(shares.iloc[-1])
+        return self._shares
+
+    @property
+    def last_price(self):
+        if self._last_price is not None:
+            return self._last_price
+        prices = self._get_1y_prices()
+        if prices.empty:
+            self._last_price = self._get_exchange_metadata()["regularMarketPrice"]
+        else:
+            self._last_price = float(prices["Close"].iloc[-1])
+            if _np.isnan(self._last_price):
+                self._last_price = self._get_exchange_metadata()["regularMarketPrice"]
+        return self._last_price
+
+    @property
+    def previous_close(self):
+        if self._prev_close is not None:
+            return self._prev_close
+        prices = self._get_1wk_1h_prepost_prices()
+        prices = prices[["Close"]].groupby(prices.index.date).last()
+        if prices.shape[0] < 2:
+            # Very few symbols have previousClose despite no 
+            # no trading data. E.g. 'QCSTIX'.
+            # So fallback to original info[] if available.
+            self._tkr.info  # trigger fetch
+            if "previousClose" in self._tkr._quote._retired_info:
+                self._prev_close = self._tkr._quote._retired_info["previousClose"]
+        else:
+            self._prev_close = float(prices["Close"].iloc[-2])
+        return self._prev_close
+
+    @property
+    def regular_market_previous_close(self):
+        if self._reg_prev_close is not None:
+            return self._reg_prev_close
+        prices = self._get_1y_prices()
+        if prices.shape[0] == 1:
+            # Tiny % of tickers don't return daily history before last trading day, 
+            # so backup option is hourly history:
+            prices = self._get_1wk_1h_reg_prices()
+            prices = prices[["Close"]].groupby(prices.index.date).last()
+        if prices.shape[0] < 2:
+            # Very few symbols have regularMarketPreviousClose despite no 
+            # no trading data. E.g. 'QCSTIX'.
+            # So fallback to original info[] if available.
+            self._tkr.info  # trigger fetch
+            if "regularMarketPreviousClose" in self._tkr._quote._retired_info:
+                self._reg_prev_close = self._tkr._quote._retired_info["regularMarketPreviousClose"]
+        else:
+            self._reg_prev_close = float(prices["Close"].iloc[-2])
+        return self._reg_prev_close
+
+    @property
+    def open(self):
+        if self._open is not None:
+            return self._open
+        prices = self._get_1y_prices()
+        if prices.empty:
+            self._open = None
+        else:
+            self._open = float(prices["Open"].iloc[-1])
+            if _np.isnan(self._open):
+                self._open = None
+        return self._open
+
+    @property
+    def day_high(self):
+        if self._day_high is not None:
+            return self._day_high
+        prices = self._get_1y_prices()
+        if prices.empty:
+            self._day_high = None
+        else:
+            self._day_high = float(prices["High"].iloc[-1])
+            if _np.isnan(self._day_high):
+                self._day_high = None
+        return self._day_high
+
+    @property
+    def day_low(self):
+        if self._day_low is not None:
+            return self._day_low
+        prices = self._get_1y_prices()
+        if prices.empty:
+            self._day_low = None
+        else:
+            self._day_low = float(prices["Low"].iloc[-1])
+            if _np.isnan(self._day_low):
+                self._day_low = None
+        return self._day_low
+
+    @property
+    def last_volume(self):
+        if self._last_volume is not None:
+            return self._last_volume
+        prices = self._get_1y_prices()
+        self._last_volume = None if prices.empty else int(prices["Volume"].iloc[-1])
+        return self._last_volume
+
+    @property
+    def fifty_day_average(self):
+        if self._50d_day_average is not None:
+            return self._50d_day_average
+
+        prices = self._get_1y_prices(fullDaysOnly=True)
+        if prices.empty:
+            self._50d_day_average = None
+        else:
+            n = prices.shape[0]
+            a = n-50
+            b = n
+            if a < 0:
+                a = 0
+            self._50d_day_average = float(prices["Close"].iloc[a:b].mean())
+
+        return self._50d_day_average
+
+    @property
+    def two_hundred_day_average(self):
+        if self._200d_day_average is not None:
+            return self._200d_day_average
+
+        prices = self._get_1y_prices(fullDaysOnly=True)
+        if prices.empty:
+            self._200d_day_average = None
+        else:
+            n = prices.shape[0]
+            a = n-200
+            b = n
+            if a < 0:
+                a = 0
+
+            self._200d_day_average = float(prices["Close"].iloc[a:b].mean())
+
+        return self._200d_day_average
+
+    @property
+    def ten_day_average_volume(self):
+        if self._10d_avg_vol is not None:
+            return self._10d_avg_vol
+
+        prices = self._get_1y_prices(fullDaysOnly=True)
+        if prices.empty:
+            self._10d_avg_vol = None
+        else:
+            n = prices.shape[0]
+            a = n-10
+            b = n
+            if a < 0:
+                a = 0
+            self._10d_avg_vol = int(prices["Volume"].iloc[a:b].mean())
+
+        return self._10d_avg_vol
+
+    @property
+    def three_month_average_volume(self):
+        if self._3mo_avg_vol is not None:
+            return self._3mo_avg_vol
+
+        prices = self._get_1y_prices(fullDaysOnly=True)
+        if prices.empty:
+            self._3mo_avg_vol = None
+        else:
+            dt1 = prices.index[-1]
+            dt0 = dt1 - utils._interval_to_timedelta("3mo") + utils._interval_to_timedelta("1d")
+            self._3mo_avg_vol = int(prices.loc[dt0:dt1, "Volume"].mean())
+
+        return self._3mo_avg_vol
+
+    @property
+    def year_high(self):
+        if self._year_high is not None:
+            return self._year_high
+
+        prices = self._get_1y_prices(fullDaysOnly=True)
+        if prices.empty:
+            prices = self._get_1y_prices(fullDaysOnly=False)
+        self._year_high = float(prices["High"].max())
+        return self._year_high
+
+    @property
+    def year_low(self):
+        if self._year_low is not None:
+            return self._year_low
+
+        prices = self._get_1y_prices(fullDaysOnly=True)
+        if prices.empty:
+            prices = self._get_1y_prices(fullDaysOnly=False)
+        self._year_low = float(prices["Low"].min())
+        return self._year_low
+
+    @property
+    def year_change(self):
+        if self._year_change is not None:
+            return self._year_change
+
+        prices = self._get_1y_prices(fullDaysOnly=True)
+        if prices.shape[0] >= 2:
+            self._year_change = (prices["Close"].iloc[-1] - prices["Close"].iloc[0]) / prices["Close"].iloc[0]
+            self._year_change = float(self._year_change)
+        return self._year_change
+
+    @property
+    def market_cap(self):
+        if self._mcap is not None:
+            return self._mcap
+
+        try:
+            shares = self.shares
+        except Exception as e:
+            if "Cannot retrieve share count" in str(e):
+                shares = None
+            else:
+                raise
+
+        if shares is None:
+            # Very few symbols have marketCap despite no share count.
+            # E.g. 'BTC-USD'
+            # So fallback to original info[] if available.
+            self._tkr.info
+            if "marketCap" in self._tkr._quote._retired_info:
+                self._mcap = self._tkr._quote._retired_info["marketCap"]
+        else:
+            self._mcap = float(shares * self.last_price)
+        return self._mcap
+
+
 class TickerBase:
     def __init__(self, ticker, session=None):
         self.ticker = ticker.upper()
@@ -77,6 +520,8 @@ class TickerBase:
         self._quote = Quote(self._data)
         self._fundamentals = Fundamentals(self._data)
 
+        self._fast_info = FastInfo(self)
+
     def stats(self, proxy=None):
         ticker_url = "{}/{}".format(self._scrape_url, self.ticker)
 
@@ -110,8 +555,9 @@ class TickerBase:
                 Adjust all OHLC automatically? Default is True
             back_adjust: bool
                 Back-adjusted data to mimic true historical prices
-            repair: bool
-                Detect currency unit 100x mixups and attempt repair
+            repair: bool or "silent"
+                Detect currency unit 100x mixups and attempt repair.
+                If True, fix & print summary. If "silent", just fix.
                 Default is False
             keepna: bool
                 Keep NaN rows returned by Yahoo?
@@ -214,6 +660,7 @@ class TickerBase:
             self._history_metadata = data["chart"]["result"][0]["meta"]
         except Exception:
             self._history_metadata = {}
+        self._history_metadata = utils.format_history_metadata(self._history_metadata)
 
         err_msg = "No data found for this date range, symbol may be delisted"
         fail = False
@@ -290,6 +737,9 @@ class TickerBase:
         quotes = utils.set_df_tz(quotes, params["interval"], tz_exchange)
         quotes = utils.fix_Yahoo_dst_issue(quotes, params["interval"])
         quotes = utils.fix_Yahoo_returning_live_separate(quotes, params["interval"], tz_exchange)
+        intraday = params["interval"][-1] in ("m", 'h')
+        if not prepost and intraday and "tradingPeriods" in self._history_metadata:
+            quotes = utils.fix_Yahoo_returning_prepost_unrequested(quotes, params["interval"], self._history_metadata)
 
         # actions
         dividends, splits, capital_gains = utils.parse_actions(data["chart"]["result"][0])
@@ -354,10 +804,10 @@ class TickerBase:
             else:
                 df["Capital Gains"] = 0.0
 
-        if repair:
+        if repair==True or repair=="silent":
             # Do this before auto/back adjust
-            df = self._fix_zeroes(df, interval, tz_exchange)
-            df = self._fix_unit_mixups(df, interval, tz_exchange)
+            df = self._fix_zeroes(df, interval, tz_exchange, prepost, silent=(repair=="silent"))
+            df = self._fix_unit_mixups(df, interval, tz_exchange, prepost, silent=(repair=="silent"))
 
         # Auto/back adjust
         try:
@@ -401,31 +851,40 @@ class TickerBase:
 
     # ------------------------
 
-    def _reconstruct_intervals_batch(self, df, interval, tag=-1):
+    def _reconstruct_intervals_batch(self, df, interval, prepost, tag=-1, silent=False):
         if not isinstance(df, _pd.DataFrame):
             raise Exception("'df' must be a Pandas DataFrame not", type(df))
+        if interval == "1m":
+            # Can't go smaller than 1m so can't reconstruct
+            return df
 
         # Reconstruct values in df using finer-grained price data. Delimiter marks what to reconstruct
 
+        debug = False
+        # debug = True
+
+        if interval[1:] in ['d', 'wk', 'mo']:
+            # Interday data always includes pre & post
+            prepost = True
+            intraday = False
+        else:
+            intraday = True
+
         price_cols = [c for c in ["Open", "High", "Low", "Close", "Adj Close"] if c in df]
         data_cols = price_cols + ["Volume"]
 
         # If interval is weekly then can construct with daily. But if smaller intervals then
         # restricted to recent times:
-        # - daily = hourly restricted to last 730 days
-        sub_interval = None
-        td_range = None
-        if interval == "1wk":
-            # Correct by fetching week of daily data
-            sub_interval = "1d"
-            td_range = _datetime.timedelta(days=7)
-        elif interval == "1d":
-            # Correct by fetching day of hourly data
-            sub_interval = "1h"
-            td_range = _datetime.timedelta(days=1)
-        elif interval == "1h":
-            sub_interval = "30m"
-            td_range = _datetime.timedelta(hours=1)
+        intervals = ["1wk", "1d", "1h", "30m", "15m", "5m", "2m", "1m"]
+        itds = {i:utils._interval_to_timedelta(interval) for i in intervals}
+        nexts = {intervals[i]:intervals[i+1] for i in range(len(intervals)-1)}
+        min_lookbacks = {"1wk":None, "1d":None, "1h":_datetime.timedelta(days=730)}
+        for i in ["30m", "15m", "5m", "2m"]:
+            min_lookbacks[i] = _datetime.timedelta(days=60)
+        min_lookbacks["1m"] = _datetime.timedelta(days=30)
+        if interval in nexts:
+            sub_interval = nexts[interval]
+            td_range = itds[interval]
         else:
             print("WARNING: Have not implemented repair for '{}' interval. Contact developers".format(interval))
             raise Exception("why here")
@@ -437,76 +896,107 @@ class TickerBase:
         f_repair_rows = f_repair.any(axis=1)
 
         # Ignore old intervals for which Yahoo won't return finer data:
-        if sub_interval == "1h":
-            f_recent = _datetime.date.today() - df.index.date < _datetime.timedelta(days=730)
+        m = min_lookbacks[sub_interval]
+        if m is None:
+            min_dt = None
+        else:
+            m -= _datetime.timedelta(days=1)  # allow space for 1-day padding
+            min_dt = _pd.Timestamp.utcnow() - m
+            min_dt = min_dt.tz_convert(df.index.tz).ceil("D")
+        if debug:
+            print(f"- min_dt={min_dt} interval={interval} sub_interval={sub_interval}")
+        if min_dt is not None:
+            f_recent = df.index >= min_dt
             f_repair_rows = f_repair_rows & f_recent
-        elif sub_interval in ["30m", "15m"]:
-            f_recent = _datetime.date.today() - df.index.date < _datetime.timedelta(days=60)
-            f_repair_rows = f_repair_rows & f_recent
-        if not f_repair_rows.any():
-            print("data too old to fix")
-            return df
+            if not f_repair_rows.any():
+                if debug:
+                    print("data too old to repair")
+                return df
 
         dts_to_repair = df.index[f_repair_rows]
         indices_to_repair = _np.where(f_repair_rows)[0]
 
         if len(dts_to_repair) == 0:
+            if debug:
+                print("dts_to_repair[] is empty")
             return df
 
         df_v2 = df.copy()
-        df_noNa = df[~df[price_cols].isna().any(axis=1)]
+        f_good = ~(df[price_cols].isna().any(axis=1))
+        f_good = f_good & (df[price_cols].to_numpy()!=tag).all(axis=1)
+        df_good = df[f_good]
 
         # Group nearby NaN-intervals together to reduce number of Yahoo fetches
         dts_groups = [[dts_to_repair[0]]]
         last_dt = dts_to_repair[0]
         last_ind = indices_to_repair[0]
         td = utils._interval_to_timedelta(interval)
-        if interval == "1mo":
-            grp_td_threshold = _datetime.timedelta(days=28)
-        elif interval == "1wk":
-            grp_td_threshold = _datetime.timedelta(days=28)
-        elif interval == "1d":
-            grp_td_threshold = _datetime.timedelta(days=14)
-        elif interval == "1h":
-            grp_td_threshold = _datetime.timedelta(days=7)
+        # Note on setting max size: have to allow space for adding good data
+        if sub_interval == "1mo":
+            grp_max_size = _dateutil.relativedelta.relativedelta(years=2)
+        elif sub_interval == "1wk":
+            grp_max_size = _dateutil.relativedelta.relativedelta(years=2)
+        elif sub_interval == "1d":
+            grp_max_size = _dateutil.relativedelta.relativedelta(years=2)
+        elif sub_interval == "1h":
+            grp_max_size = _dateutil.relativedelta.relativedelta(years=1)
+        elif sub_interval == "1m":
+            grp_max_size = _datetime.timedelta(days=5)  # allow 2 days for buffer below
         else:
-            grp_td_threshold = _datetime.timedelta(days=2)
-            # grp_td_threshold = _datetime.timedelta(days=7)
+            grp_max_size = _datetime.timedelta(days=30)
+        if debug:
+            print("- grp_max_size =", grp_max_size)
         for i in range(1, len(dts_to_repair)):
             ind = indices_to_repair[i]
             dt = dts_to_repair[i]
-            if (dt-dts_groups[-1][-1]) < grp_td_threshold:
-                dts_groups[-1].append(dt)
-            elif ind - last_ind <= 3:
+            if dt.date() < dts_groups[-1][0].date()+grp_max_size:
                 dts_groups[-1].append(dt)
             else:
                 dts_groups.append([dt])
             last_dt = dt
             last_ind = ind
 
+        if debug:
+            print("Repair groups:")
+            for g in dts_groups:
+                print(f"- {g[0]} -> {g[-1]}")
+
         # Add some good data to each group, so can calibrate later:
         for i in range(len(dts_groups)):
             g = dts_groups[i]
             g0 = g[0]
-            i0 = df_noNa.index.get_loc(g0)
+            i0 = df_good.index.get_indexer([g0], method="nearest")[0]
             if i0 > 0:
-                dts_groups[i].insert(0, df_noNa.index[i0-1])
+                if (min_dt is None or df_good.index[i0-1] >= min_dt) and \
+                    ((not intraday) or df_good.index[i0-1].date()==g0.date()):
+                    i0 -= 1
             gl = g[-1]
-            il = df_noNa.index.get_loc(gl)
-            if il < len(df_noNa)-1:
-                dts_groups[i].append(df_noNa.index[il+1])
+            il = df_good.index.get_indexer([gl], method="nearest")[0]
+            if il < len(df_good)-1:
+                if (not intraday) or df_good.index[il+1].date()==gl.date():
+                    il += 1
+            good_dts = df_good.index[i0:il+1]
+            dts_groups[i] += good_dts.to_list()
+            dts_groups[i].sort()
 
         n_fixed = 0
         for g in dts_groups:
             df_block = df[df.index.isin(g)]
+            if debug:
+                print("- df_block:")
+                print(df_block)
 
             start_dt = g[0]
             start_d = start_dt.date()
             if sub_interval == "1h" and (_datetime.date.today() - start_d) > _datetime.timedelta(days=729):
                 # Don't bother requesting more price data, Yahoo will reject
+                if debug:
+                    print(f"- Don't bother requesting {sub_interval} price data, Yahoo will reject")
                 continue
             elif sub_interval in ["30m", "15m"] and (_datetime.date.today() - start_d) > _datetime.timedelta(days=59):
                 # Don't bother requesting more price data, Yahoo will reject
+                if debug:
+                    print(f"- Don't bother requesting {sub_interval} price data, Yahoo will reject")
                 continue
 
             td_1d = _datetime.timedelta(days=1)
@@ -520,15 +1010,25 @@ class TickerBase:
                 fetch_start = g[0]
                 fetch_end = g[-1] + td_range
 
-            prepost = interval == "1d"
-            df_fine = self.history(start=fetch_start, end=fetch_end, interval=sub_interval, auto_adjust=False, prepost=prepost, repair=False, keepna=True)
+            # The first and last day returned by Yahoo can be slightly wrong, so add buffer:
+            fetch_start -= td_1d
+            fetch_end += td_1d
+            if intraday:
+                fetch_start = fetch_start.date()
+                fetch_end = fetch_end.date()+td_1d
+            if debug:
+                print(f"- fetching {sub_interval} prepost={prepost} {fetch_start}->{fetch_end}")
+            r = "silent" if silent else True
+            df_fine = self.history(start=fetch_start, end=fetch_end, interval=sub_interval, auto_adjust=False, actions=False, prepost=prepost, repair=r, keepna=True)
             if df_fine is None or df_fine.empty:
-                print("YF: WARNING: Cannot reconstruct because Yahoo not returning data in interval")
+                if not silent:
+                    print("YF: WARNING: Cannot reconstruct because Yahoo not returning data in interval")
                 continue
+            # Discard the buffer
+            df_fine = df_fine.loc[g[0] : g[-1]+itds[sub_interval]-_datetime.timedelta(milliseconds=1)]
 
             df_fine["ctr"] = 0
             if interval == "1wk":
-                # df_fine["Week Start"] = df_fine.index.tz_localize(None).to_period("W-SUN").start_time
                 weekdays = ["MON", "TUE", "WED", "THU", "FRI", "SAT", "SUN"]
                 week_end_day = weekdays[(df_block.index[0].weekday()+7-1)%7]
                 df_fine["Week Start"] = df_fine.index.tz_localize(None).to_period("W-"+week_end_day).start_time
@@ -543,7 +1043,8 @@ class TickerBase:
                 grp_col = "intervalID"
             df_fine = df_fine[~df_fine[price_cols].isna().all(axis=1)]
 
-            df_new = df_fine.groupby(grp_col).agg(
+            df_fine_grp = df_fine.groupby(grp_col)
+            df_new = df_fine_grp.agg(
                 Open=("Open", "first"),
                 Close=("Close", "last"),
                 AdjClose=("Adj Close", "last"),
@@ -557,31 +1058,42 @@ class TickerBase:
                 new_index = _np.append([df_fine.index[0]], df_fine.index[df_fine["intervalID"].diff()>0])
                 df_new.index = new_index
 
+            if debug:
+                print("- df_new:")
+                print(df_new)
+
             # Calibrate! Check whether 'df_fine' has different split-adjustment.
             # If different, then adjust to match 'df'
-            df_block_calib = df_block[price_cols]
-            common_index = df_block_calib.index[df_block_calib.index.isin(df_new.index)]
+            common_index = _np.intersect1d(df_block.index, df_new.index)
             if len(common_index) == 0:
                 # Can't calibrate so don't attempt repair
+                if debug:
+                    print("Can't calibrate so don't attempt repair")
                 continue
-            df_new_calib = df_new[df_new.index.isin(common_index)][price_cols]
-            df_block_calib = df_block_calib[df_block_calib.index.isin(common_index)]
-            calib_filter = (df_block_calib != tag).to_numpy()
+            df_new_calib = df_new[df_new.index.isin(common_index)][price_cols].to_numpy()
+            df_block_calib = df_block[df_block.index.isin(common_index)][price_cols].to_numpy()
+            calib_filter = (df_block_calib != tag)
             if not calib_filter.any():
                 # Can't calibrate so don't attempt repair
+                if debug:
+                    print("Can't calibrate so don't attempt repair")
                 continue
-            # Avoid divide-by-zero warnings printing:
-            df_new_calib = df_new_calib.to_numpy()
-            df_block_calib = df_block_calib.to_numpy()
+            # Avoid divide-by-zero warnings:
             for j in range(len(price_cols)):
-                c = price_cols[j]
                 f = ~calib_filter[:,j]
                 if f.any():
                     df_block_calib[f,j] = 1
                     df_new_calib[f,j] = 1
-            ratios = (df_block_calib / df_new_calib)[calib_filter]
-            ratio = _np.mean(ratios)
-            #
+            ratios = df_block_calib[calib_filter] / df_new_calib[calib_filter]
+            weights = df_fine_grp.size()
+            weights.index = df_new.index
+            weights = weights[weights.index.isin(common_index)].to_numpy().astype(float)
+            weights = weights[:,None]  # transpose
+            weights = _np.tile(weights, len(price_cols))  # 1D -> 2D
+            weights = weights[calib_filter]  # flatten
+            ratio = _np.average(ratios, weights=weights)
+            if debug:
+                print(f"- price calibration ratio (raw) = {ratio}")
             ratio_rcp = round(1.0 / ratio, 1)
             ratio = round(ratio, 1)
             if ratio == 1 and ratio_rcp == 1:
@@ -600,13 +1112,22 @@ class TickerBase:
                     df_new["Volume"] *= ratio_rcp
 
             # Repair!
-            bad_dts = df_block.index[(df_block[price_cols]==tag).any(axis=1)]
+            bad_dts = df_block.index[(df_block[price_cols+["Volume"]]==tag).any(axis=1)]
 
+            if debug:
+                no_fine_data_dts = []
+                for idx in bad_dts:
+                    if not idx in df_new.index:
+                        # 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:
+                    print(f"Yahoo didn't return finer-grain data for these intervals:")
+                    print(no_fine_data_dts)
             for idx in bad_dts:
                 if not idx in df_new.index:
                     # Yahoo didn't return finer-grain data for this interval, 
                     # so probably no trading happened.
-                    # print("no fine data")
                     continue
                 df_new_row = df_new.loc[idx]
 
@@ -635,9 +1156,12 @@ class TickerBase:
                     df_v2.loc[idx, "Volume"] = df_new_row["Volume"]
                 n_fixed += 1
 
+        if debug:
+            print("df_v2:") ; print(df_v2)
+
         return df_v2
 
-    def _fix_unit_mixups(self, df, interval, tz_exchange):
+    def _fix_unit_mixups(self, df, interval, tz_exchange, prepost, silent=False):
         # Sometimes Yahoo returns few prices in cents/pence instead of $/£
         # I.e. 100x bigger
         # Easy to detect and fix, just look for outliers = ~100x local median
@@ -659,7 +1183,7 @@ class TickerBase:
         # adding it to dependencies.
         from scipy import ndimage as _ndimage
 
-        data_cols = ["High", "Open", "Low", "Close"]  # Order important, separate High from Low
+        data_cols = ["High", "Open", "Low", "Close", "Adj Close"]  # Order important, separate High from Low
         data_cols = [c for c in data_cols if c in df2.columns]
         f_zeroes = (df2[data_cols]==0).any(axis=1)
         if f_zeroes.any():
@@ -684,7 +1208,7 @@ class TickerBase:
             df2.loc[fi, c] = tag
 
         n_before = (df2[data_cols].to_numpy()==tag).sum()
-        df2 = self._reconstruct_intervals_batch(df2, interval, tag=tag)
+        df2 = self._reconstruct_intervals_batch(df2, interval, prepost, tag, silent)
         n_after = (df2[data_cols].to_numpy()==tag).sum()
 
         if n_after > 0:
@@ -707,6 +1231,11 @@ class TickerBase:
                 if fi[j]:
                     df2.loc[idx, c] = df.loc[idx, c] * 0.01
                 #
+                c = "Adj Close"
+                j = data_cols.index(c)
+                if fi[j]:
+                    df2.loc[idx, c] = df.loc[idx, c] * 0.01
+                #
                 c = "High"
                 j = data_cols.index(c)
                 if fi[j]:
@@ -721,7 +1250,7 @@ class TickerBase:
 
         n_fixed = n_before - n_after_crude
         n_fixed_crudely = n_after - n_after_crude
-        if n_fixed > 0:
+        if not silent and n_fixed > 0:
             report_msg = f"{self.ticker}: fixed {n_fixed}/{n_before} currency unit mixups "
             if n_fixed_crudely > 0:
                 report_msg += f"({n_fixed_crudely} crudely) "
@@ -741,7 +1270,7 @@ class TickerBase:
 
         return df2
 
-    def _fix_zeroes(self, df, interval, tz_exchange):
+    def _fix_zeroes(self, df, interval, tz_exchange, prepost, silent=False):
         # Sometimes Yahoo returns prices=0 or NaN when trades occurred.
         # But most times when prices=0 or NaN returned is because no trades.
         # Impossible to distinguish, so only attempt repair if few or rare.
@@ -749,6 +1278,12 @@ class TickerBase:
         if df.shape[0] == 0:
             return df
 
+        debug = False
+        # debug = True
+
+        intraday = interval[-1] in ("m", 'h')
+
+        df = df.sort_index()  # important!
         df2 = df.copy()
 
         if df2.index.tz is None:
@@ -757,16 +1292,34 @@ class TickerBase:
             df2.index = df2.index.tz_convert(tz_exchange)
 
         price_cols = [c for c in ["Open", "High", "Low", "Close", "Adj Close"] if c in df2.columns]
-        f_zero_or_nan = (df2[price_cols] == 0.0).values | df2[price_cols].isna().values
+        f_prices_bad = (df2[price_cols] == 0.0) | df2[price_cols].isna()
+        df2_reserve = None
+        if intraday:
+            # Ignore days with >50% intervals containing NaNs
+            df_nans = pd.DataFrame(f_prices_bad.any(axis=1), columns=["nan"])
+            df_nans["_date"] = df_nans.index.date
+            grp = df_nans.groupby("_date")
+            nan_pct = grp.sum() / grp.count()
+            dts = nan_pct.index[nan_pct["nan"]>0.5]
+            f_zero_or_nan_ignore = _np.isin(f_prices_bad.index.date, dts)
+            df2_reserve = df2[f_zero_or_nan_ignore]
+            df2 = df2[~f_zero_or_nan_ignore]
+            f_prices_bad = (df2[price_cols] == 0.0) | df2[price_cols].isna()
+
+        f_high_low_good = (~df2["High"].isna()) & (~df2["Low"].isna())
+        f_vol_bad = (df2["Volume"]==0).to_numpy() & f_high_low_good & (df2["High"]!=df2["Low"]).to_numpy()
+
         # Check whether worth attempting repair
-        if f_zero_or_nan.any(axis=1).sum() == 0:
+        f_prices_bad = f_prices_bad.to_numpy()
+        f_bad_rows = f_prices_bad.any(axis=1) | f_vol_bad
+        if not f_bad_rows.any():
+            if debug:
+                print("no bad data to repair")
             return df
-        if f_zero_or_nan.sum() == len(price_cols)*len(df2):
+        if f_prices_bad.sum() == len(price_cols)*len(df2):
             # Need some good data to calibrate
-            return df
-        # - avoid repair if many zeroes/NaNs
-        pct_zero_or_nan = f_zero_or_nan.sum() / (len(price_cols)*len(df2))
-        if f_zero_or_nan.any(axis=1).sum()>2 and pct_zero_or_nan > 0.05:
+            if debug:
+                print("no good data to calibrate")
             return df
 
         data_cols = price_cols + ["Volume"]
@@ -775,17 +1328,31 @@ class TickerBase:
         tag = -1.0
         for i in range(len(price_cols)):
             c = price_cols[i]
-            df2.loc[f_zero_or_nan[:,i], c] = tag
+            df2.loc[f_prices_bad[:,i], c] = tag
+        df2.loc[f_vol_bad, "Volume"] = tag
         # If volume=0 or NaN for bad prices, then tag volume for repair
-        df2.loc[f_zero_or_nan.any(axis=1) & (df2["Volume"]==0), "Volume"] = tag
-        df2.loc[f_zero_or_nan.any(axis=1) & (df2["Volume"].isna()), "Volume"] = tag
+        f_vol_zero_or_nan = (df2["Volume"].to_numpy()==0) | (df2["Volume"].isna().to_numpy())
+        df2.loc[f_prices_bad.any(axis=1) & f_vol_zero_or_nan, "Volume"] = tag
+        # If volume=0 or NaN but price moved in interval, then tag volume for repair
+        f_change = df2["High"].to_numpy() != df2["Low"].to_numpy()
+        df2.loc[f_change & f_vol_zero_or_nan, "Volume"] = tag
 
         n_before = (df2[data_cols].to_numpy()==tag).sum()
-        df2 = self._reconstruct_intervals_batch(df2, interval, tag=tag)
+        dts_tagged = df2.index[(df2[data_cols].to_numpy()==tag).any(axis=1)]
+        df2 = self._reconstruct_intervals_batch(df2, interval, prepost, tag, silent)
         n_after = (df2[data_cols].to_numpy()==tag).sum()
+        dts_not_repaired = df2.index[(df2[data_cols].to_numpy()==tag).any(axis=1)]
         n_fixed = n_before - n_after
-        if n_fixed > 0:
-            print("{}: fixed {} price=0.0 errors in {} price data".format(self.ticker, n_fixed, interval))
+        if not silent and n_fixed > 0:
+            msg = f"{self.ticker}: fixed {n_fixed}/{n_before} value=0 errors in {interval} price data"
+            if n_fixed < 4:
+                dts_repaired = sorted(list(set(dts_tagged).difference(dts_not_repaired)))
+                msg += f": {dts_repaired}"
+            print(msg)
+
+        if df2_reserve is not None:
+            df2 = _pd.concat([df2, df2_reserve])
+        df2 = df2.sort_index()
 
         # Restore original values where repair failed (i.e. remove tag values)
         f = df2[data_cols].values==tag
@@ -821,7 +1388,7 @@ class TickerBase:
         return tz
 
     def _fetch_ticker_tz(self, debug_mode, proxy, timeout):
-        # Query Yahoo for basic price data just to get returned timezone
+        # Query Yahoo for fast price data just to get returned timezone
 
         params = {"range": "1d", "interval": "1d"}
 
@@ -895,6 +1462,15 @@ class TickerBase:
         data = self._quote.info
         return data
 
+    @property
+    def fast_info(self):
+        return self._fast_info
+
+    @property
+    def basic_info(self):
+        print("WARNING: 'Ticker.basic_info' is renamed to 'Ticker.fast_info', hopefully purpose is clearer")
+        return self.fast_info
+
     def get_sustainability(self, proxy=None, as_dict=False):
         self._quote.proxy = proxy
         data = self._quote.sustainability
@@ -1160,7 +1736,6 @@ class TickerBase:
 
         shares_data = json_data["timeseries"]["result"]
         if not "shares_out" in shares_data[0]:
-            print(f"{self.ticker}: Yahoo did not return share count in date range {start} -> {end}")
             return None
         try:
             df = _pd.Series(shares_data[0]["shares_out"], index=_pd.to_datetime(shares_data[0]["timestamp"], unit="s"))
@@ -1319,6 +1894,6 @@ class TickerBase:
 
     def get_history_metadata(self) -> dict:
         if self._history_metadata is None:
-            raise RuntimeError("Metadata was never retrieved so far, "
-                               "call history() to retrieve it")
+            # Request intraday data, because then Yahoo returns exchange schedule.
+            self.history(period="1wk", interval="1h", prepost=True)
         return self._history_metadata

yfinance/data.py

@@ -14,6 +14,7 @@ else:
 
 import requests as requests
 import re
+from bs4 import BeautifulSoup
 
 from frozendict import frozendict
 
@@ -46,40 +47,45 @@ def lru_cache_freezeargs(func):
     return wrapped
 
 
-def decrypt_cryptojs_aes_stores(data):
+def _extract_extra_keys_from_stores(data):
+    new_keys = [k for k in data.keys() if k not in ["context", "plugins"]]
+    new_keys_values = set([data[k] for k in new_keys])
+
+    # Maybe multiple keys have same value - keep one of each
+    new_keys_uniq = []
+    new_keys_uniq_values = set()
+    for k in new_keys:
+        v = data[k]
+        if not v in new_keys_uniq_values:
+            new_keys_uniq.append(k)
+            new_keys_uniq_values.add(v)
+
+    return [data[k] for k in new_keys_uniq]
+
+
+def decrypt_cryptojs_aes_stores(data, keys=None):
     encrypted_stores = data['context']['dispatcher']['stores']
 
+    password = None
+    if keys is not None:
+        if not isinstance(keys, list):
+            raise TypeError("'keys' must be list")
+        candidate_passwords = keys
+    else:
+        candidate_passwords = []
+
     if "_cs" in data and "_cr" in data:
         _cs = data["_cs"]
         _cr = data["_cr"]
         _cr = b"".join(int.to_bytes(i, length=4, byteorder="big", signed=True) for i in json.loads(_cr)["words"])
         password = hashlib.pbkdf2_hmac("sha1", _cs.encode("utf8"), _cr, 1, dklen=32).hex()
-    else:
-        # Currently assume one extra key in dict, which is password. Print error if 
-        # more extra keys detected.
-        new_keys = [k for k in data.keys() if k not in ["context", "plugins"]]
-        l = len(new_keys)
-        if l == 0:
-            return None
-        elif l == 1 and isinstance(data[new_keys[0]], str):
-            password_key = new_keys[0]
-        else:
-            msg = "Yahoo has again changed data format, yfinance now unsure which key(s) is for decryption:"
-            k = new_keys[0]
-            k_str = k if len(k) < 32 else k[:32-3]+"..."
-            msg += f" '{k_str}'->{type(data[k])}"
-            for i in range(1, len(new_keys)):
-                msg += f" , '{k_str}'->{type(data[k])}"
-            raise Exception(msg)
-        password_key = new_keys[0]
-        password = data[password_key]
 
     encrypted_stores = b64decode(encrypted_stores)
     assert encrypted_stores[0:8] == b"Salted__"
     salt = encrypted_stores[8:16]
     encrypted_stores = encrypted_stores[16:]
 
-    def EVPKDF(password, salt, keySize=32, ivSize=16, iterations=1, hashAlgorithm="md5") -> tuple:
+    def _EVPKDF(password, salt, keySize=32, ivSize=16, iterations=1, hashAlgorithm="md5") -> tuple:
         """OpenSSL EVP Key Derivation Function
         Args:
             password (Union[str, bytes, bytearray]): Password to generate key from.
@@ -118,22 +124,42 @@ def decrypt_cryptojs_aes_stores(data):
         key, iv = key_iv[:keySize], key_iv[keySize:final_length]
         return key, iv
 
-    try:
-        key, iv = EVPKDF(password, salt, keySize=32, ivSize=16, iterations=1, hashAlgorithm="md5")
-    except:
-        raise Exception("yfinance failed to decrypt Yahoo data response")
+    def _decrypt(encrypted_stores, password, key, iv):
+        if usePycryptodome:
+            cipher = AES.new(key, AES.MODE_CBC, iv=iv)
+            plaintext = cipher.decrypt(encrypted_stores)
+            plaintext = unpad(plaintext, 16, style="pkcs7")
+        else:
+            cipher = Cipher(algorithms.AES(key), modes.CBC(iv))
+            decryptor = cipher.decryptor()
+            plaintext = decryptor.update(encrypted_stores) + decryptor.finalize()
+            unpadder = padding.PKCS7(128).unpadder()
+            plaintext = unpadder.update(plaintext) + unpadder.finalize()
+            plaintext = plaintext.decode("utf-8")
+        return plaintext
 
-    if usePycryptodome:
-        cipher = AES.new(key, AES.MODE_CBC, iv=iv)
-        plaintext = cipher.decrypt(encrypted_stores)
-        plaintext = unpad(plaintext, 16, style="pkcs7")
+    if not password is None:
+        try:
+            key, iv = _EVPKDF(password, salt, keySize=32, ivSize=16, iterations=1, hashAlgorithm="md5")
+        except:
+            raise Exception("yfinance failed to decrypt Yahoo data response")
+        plaintext = _decrypt(encrypted_stores, password, key, iv)
     else:
-        cipher = Cipher(algorithms.AES(key), modes.CBC(iv))
-        decryptor = cipher.decryptor()
-        plaintext = decryptor.update(encrypted_stores) + decryptor.finalize()
-        unpadder = padding.PKCS7(128).unpadder()
-        plaintext = unpadder.update(plaintext) + unpadder.finalize()
-        plaintext = plaintext.decode("utf-8")
+        success = False
+        for i in range(len(candidate_passwords)):
+            # print(f"Trying candiate pw {i+1}/{len(candidate_passwords)}")
+            password = candidate_passwords[i]
+            try:
+                key, iv = _EVPKDF(password, salt, keySize=32, ivSize=16, iterations=1, hashAlgorithm="md5")
+
+                plaintext = _decrypt(encrypted_stores, password, key, iv)
+
+                success = True
+                break
+            except:
+                pass
+        if not success:
+            raise Exception("yfinance failed to decrypt Yahoo data response")
 
     decoded_stores = json.loads(plaintext)
     return decoded_stores
@@ -176,6 +202,66 @@ class TickerData:
             proxy = {"https": proxy}
         return proxy
 
+    def _get_decryption_keys_from_yahoo_js(self, soup):
+        result = None
+
+        key_count = 4
+        re_script = soup.find("script", string=re.compile("root.App.main")).text
+        re_data = json.loads(re.search("root.App.main\s+=\s+(\{.*\})", re_script).group(1))
+        re_data.pop("context", None)
+        key_list = list(re_data.keys())
+        if re_data.get("plugins"):  # 1) attempt to get last 4 keys after plugins
+            ind = key_list.index("plugins")
+            if len(key_list) > ind+1:
+                sub_keys = key_list[ind+1:]
+                if len(sub_keys) == key_count:
+                    re_obj = {}
+                    missing_val = False
+                    for k in sub_keys:
+                        if not re_data.get(k):
+                            missing_val = True
+                            break
+                        re_obj.update({k: re_data.get(k)})
+                    if not missing_val:
+                        result = re_obj
+
+        if not result is None:
+            return [''.join(result.values())]
+
+        re_keys = []    # 2) attempt scan main.js file approach to get keys
+        prefix = "https://s.yimg.com/uc/finance/dd-site/js/main."
+        tags = [tag['src'] for tag in soup.find_all('script') if prefix in tag.get('src', '')]
+        for t in tags:
+            response_js = self.cache_get(t)
+            #
+            if response_js.status_code != 200:
+                time.sleep(random.randrange(10, 20))
+                response_js.close()
+            else:
+                r_data = response_js.content.decode("utf8")
+                re_list = [
+                    x.group() for x in re.finditer(r"context.dispatcher.stores=JSON.parse((?:.*?\r?\n?)*)toString", r_data)
+                ]
+                for rl in re_list:
+                    re_sublist = [x.group() for x in re.finditer(r"t\[\"((?:.*?\r?\n?)*)\"\]", rl)]
+                    if len(re_sublist) == key_count:
+                        re_keys = [sl.replace('t["', '').replace('"]', '') for sl in re_sublist]
+                        break
+                response_js.close()
+            if len(re_keys) == key_count:
+                break
+        re_obj = {}
+        missing_val = False
+        for k in re_keys:
+            if not re_data.get(k):
+                missing_val = True
+                break
+            re_obj.update({k: re_data.get(k)})
+        if not missing_val:
+            return [''.join(re_obj.values())]
+
+        return []
+
     @lru_cache_freezeargs
     @lru_cache(maxsize=cache_maxsize)
     def get_json_data_stores(self, sub_page: str = None, proxy=None) -> dict:
@@ -187,7 +273,8 @@ class TickerData:
         else:
             ticker_url = "{}/{}".format(_SCRAPE_URL_, self.ticker)
 
-        html = self.get(url=ticker_url, proxy=proxy).text
+        response = self.get(url=ticker_url, proxy=proxy)
+        html = response.text
 
         # The actual json-data for stores is in a javascript assignment in the webpage
         try:
@@ -199,7 +286,28 @@ class TickerData:
 
         data = json.loads(json_str)
 
-        stores = decrypt_cryptojs_aes_stores(data)
+        # Gather decryption keys:
+        soup = BeautifulSoup(response.content, "html.parser")
+        keys = self._get_decryption_keys_from_yahoo_js(soup)
+        if len(keys) == 0:
+            msg = "No decryption keys could be extracted from JS file."
+            if "requests_cache" in str(type(response)):
+                msg += " Try flushing your 'requests_cache', probably parsing old JS."
+            print("WARNING: " + msg + " Falling back to backup decrypt methods.")
+        if len(keys) == 0:
+            keys = []
+            try:
+                extra_keys = _extract_extra_keys_from_stores(data)
+                keys = [''.join(extra_keys[-4:])]
+            except:
+                pass
+            #
+            keys_url = "https://github.com/ranaroussi/yfinance/raw/main/yfinance/scrapers/yahoo-keys.txt"
+            response_gh = self.cache_get(keys_url)
+            keys += response_gh.text.splitlines()
+
+        # Decrypt!
+        stores = decrypt_cryptojs_aes_stores(data, keys)
         if stores is None:
             # Maybe Yahoo returned old format, not encrypted
             if "context" in data and "dispatcher" in data["context"]:

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, ignore_tz=False,
+def download(tickers, start=None, end=None, actions=False, threads=True, ignore_tz=None,
              group_by='column', auto_adjust=False, back_adjust=False, repair=False, keepna=False,
              progress=True, period="max", show_errors=True, interval="1d", prepost=False,
              proxy=None, rounding=False, timeout=10):
@@ -68,7 +68,7 @@ def download(tickers, start=None, end=None, actions=False, threads=True, ignore_
             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 False
+            Default depends on interval. Intraday = False. Day+ = True.
         proxy: str
             Optional. Proxy server URL scheme. Default is None
         rounding: bool
@@ -80,6 +80,14 @@ def download(tickers, start=None, end=None, actions=False, threads=True, ignore_
             seconds. (Can also be a fraction of a second e.g. 0.01)
     """
 
+    if ignore_tz is None:
+        # Set default value depending on interval
+        if interval[1:] in ['m', 'h']:
+            # Intraday
+            ignore_tz = False
+        else:
+            ignore_tz = True
+
     # create ticker list
     tickers = tickers if isinstance(
         tickers, (list, set, tuple)) else tickers.replace(',', ' ').split()

yfinance/scrapers/quote.py

@@ -7,6 +7,73 @@ from yfinance import utils
 from yfinance.data import TickerData
 
 
+info_retired_keys_price = {"currentPrice", "dayHigh", "dayLow", "open", "previousClose", "volume", "volume24Hr"}
+info_retired_keys_price.update({"regularMarket"+s for s in ["DayHigh", "DayLow", "Open", "PreviousClose", "Price", "Volume"]})
+info_retired_keys_price.update({"fiftyTwoWeekLow", "fiftyTwoWeekHigh", "fiftyTwoWeekChange", "52WeekChange", "fiftyDayAverage", "twoHundredDayAverage"})
+info_retired_keys_price.update({"averageDailyVolume10Day", "averageVolume10days", "averageVolume"})
+info_retired_keys_exchange = {"currency", "exchange", "exchangeTimezoneName", "exchangeTimezoneShortName", "quoteType"}
+info_retired_keys_marketCap = {"marketCap"}
+info_retired_keys_symbol = {"symbol"}
+info_retired_keys = info_retired_keys_price | info_retired_keys_exchange | info_retired_keys_marketCap | info_retired_keys_symbol
+
+
+PRUNE_INFO = True
+# PRUNE_INFO = False
+
+
+from collections.abc import MutableMapping
+class InfoDictWrapper(MutableMapping):
+    """ Simple wrapper around info dict, intercepting 'gets' to 
+    print how-to-migrate messages for specific keys. Requires
+    override dict API"""
+
+    def __init__(self, info):
+        self.info = info
+
+    def keys(self):
+        return self.info.keys()
+
+    def __str__(self):
+        return self.info.__str__()
+
+    def __repr__(self):
+        return self.info.__repr__()
+
+    def __contains__(self, k):
+        return k in self.info.keys()
+
+    def __getitem__(self, k):
+        if k in info_retired_keys_price:
+            print(f"Price data removed from info (key='{k}'). Use Ticker.fast_info or history() instead")
+            return None
+        elif k in info_retired_keys_exchange:
+            print(f"Exchange data removed from info (key='{k}'). Use Ticker.fast_info or Ticker.get_history_metadata() instead")
+            return None
+        elif k in info_retired_keys_marketCap:
+            print(f"Market cap removed from info (key='{k}'). Use Ticker.fast_info instead")
+            return None
+        elif k in info_retired_keys_symbol:
+            print(f"Symbol removed from info (key='{k}'). You know this already")
+            return None
+        return self.info[self._keytransform(k)]
+
+    def __setitem__(self, k, value):
+        self.info[self._keytransform(k)] = value
+
+    def __delitem__(self, k):
+        del self.info[self._keytransform(k)]
+
+    def __iter__(self):
+        return iter(self.info)
+    
+    def __len__(self):
+        return len(self.info)
+
+    def _keytransform(self, k):
+        return k
+
+
+
 class Quote:
 
     def __init__(self, data: TickerData, proxy=None):
@@ -14,6 +81,7 @@ class Quote:
         self.proxy = proxy
 
         self._info = None
+        self._retired_info = None
         self._sustainability = None
         self._recommendations = None
         self._calendar = None
@@ -130,6 +198,19 @@ class Quote:
         except Exception:
             pass
 
+        # Delete redundant info[] keys, because values can be accessed faster
+        # elsewhere - e.g. price keys. Hope is reduces Yahoo spam effect.
+        # But record the dropped keys, because in rare cases they are needed.
+        self._retired_info = {}
+        for k in info_retired_keys:
+            if k in self._info:
+                self._retired_info[k] = self._info[k]
+                if PRUNE_INFO:
+                    del self._info[k]
+        if PRUNE_INFO:
+            # InfoDictWrapper will explain how to access above data elsewhere
+            self._info = InfoDictWrapper(self._info)
+
         # events
         try:
             cal = pd.DataFrame(quote_summary_store['calendarEvents']['earnings'])
@@ -202,11 +283,14 @@ class Quote:
 
             json_str = self._data.cache_get(url=url, proxy=proxy).text
             json_data = json.loads(json_str)
-            key_stats = json_data["timeseries"]["result"][0]
-            if k not in key_stats:
-                # Yahoo website prints N/A, indicates Yahoo lacks necessary data to calculate
+            try:
+                key_stats = json_data["timeseries"]["result"][0]
+                if k not in key_stats:
+                    # Yahoo website prints N/A, indicates Yahoo lacks necessary data to calculate
+                    v = None
+                else:
+                    # Select most recent (last) raw value in list:
+                    v = key_stats[k][-1]["reportedValue"]["raw"]
+            except Exception:
                 v = None
-            else:
-                # Select most recent (last) raw value in list:
-                v = key_stats[k][-1]["reportedValue"]["raw"]
             self._info[k] = v

yfinance/scrapers/yahoo-keys.txt

@@ -0,0 +1,5 @@
+daf93e37cbf219cd4c1f3f74ec4551265ec5565b99e8c9322dccd6872941cf13c818cbb88cba6f530e643b4e2329b17ec7161f4502ce6a02bb0dbbe5fc0d0474
+ad4d90b3c9f2e1d156ef98eadfa0ff93e4042f6960e54aa2a13f06f528e6b50ba4265a26a1fd5b9cd3db0d268a9c34e1d080592424309429a58bce4adc893c87
+e9a8ab8e5620b712ebc2fb4f33d5c8b9c80c0d07e8c371911c785cf674789f1747d76a909510158a7b7419e86857f2d7abbd777813ff64840e4cbc514d12bcae
+6ae2523aeafa283dad746556540145bf603f44edbf37ad404d3766a8420bb5eb1d3738f52a227b88283cca9cae44060d5f0bba84b6a495082589f5fe7acbdc9e
+3365117c2a368ffa5df7313a4a84988f73926a86358e8eea9497c5ff799ce27d104b68e5f2fbffa6f8f92c1fef41765a7066fa6bcf050810a9c4c7872fd3ebf0

yfinance/tickers.py

@@ -34,12 +34,8 @@ class Tickers:
         tickers = tickers if isinstance(
             tickers, list) else tickers.replace(',', ' ').split()
         self.symbols = [ticker.upper() for ticker in tickers]
-        ticker_objects = {}
+        self.tickers = {ticker:Ticker(ticker, session=session) for ticker in self.symbols}
 
-        for ticker in self.symbols:
-            ticker_objects[ticker] = Ticker(ticker, session=session)
-
-        self.tickers = ticker_objects
         # self.tickers = _namedtuple(
         #     "Tickers", ticker_objects.keys(), rename=True
         # )(*ticker_objects.values())

yfinance/utils.py

@@ -49,6 +49,18 @@ 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'}
 
 
+# From https://stackoverflow.com/a/59128615
+from types import FunctionType
+from inspect import getmembers
+def attributes(obj):
+    disallowed_names = {
+      name for name, value in getmembers(type(obj)) 
+        if isinstance(value, FunctionType)}
+    return {
+      name: getattr(obj, name) for name in dir(obj) 
+        if name[0] != '_' and name not in disallowed_names and hasattr(obj, name)}
+
+
 def is_isin(string):
     return bool(_re.match("^([A-Z]{2})([A-Z0-9]{9})([0-9]{1})$", string))
 
@@ -288,6 +300,11 @@ def camel2title(strings: List[str], sep: str = ' ', acronyms: Optional[List[str]
     return strings
 
 
+def snake_case_2_camelCase(s):
+    sc = s.split('_')[0] + ''.join(x.title() for x in s.split('_')[1:])
+    return sc
+
+
 def _parse_user_dt(dt, exchange_tz):
     if isinstance(dt, int):
         # Should already be epoch, test with conversion:
@@ -307,7 +324,11 @@ def _parse_user_dt(dt, exchange_tz):
 
 def _interval_to_timedelta(interval):
     if interval == "1mo":
-        return _dateutil.relativedelta(months=1)
+        return _dateutil.relativedelta.relativedelta(months=1)
+    elif interval == "3mo":
+        return _dateutil.relativedelta.relativedelta(months=3)
+    elif interval == "1y":
+        return _dateutil.relativedelta.relativedelta(years=1)
     elif interval == "1wk":
         return _pd.Timedelta(days=7, unit='d')
     else: 
@@ -427,6 +448,35 @@ def set_df_tz(df, interval, tz):
     return df
 
 
+def fix_Yahoo_returning_prepost_unrequested(quotes, interval, metadata):
+    # Sometimes Yahoo returns post-market data despite not requesting it.
+    # Normally happens on half-day early closes.
+    #
+    # And sometimes returns pre-market data despite not requesting it.
+    # E.g. some London tickers.
+    tps_df = metadata["tradingPeriods"]
+    tps_df["_date"] = tps_df.index.date
+    quotes["_date"] = quotes.index.date
+    idx = quotes.index.copy()
+    quotes = quotes.merge(tps_df, how="left", validate="many_to_one")
+    quotes.index = idx
+    # "end" = end of regular trading hours (including any auction)
+    f_drop = quotes.index >= quotes["end"]
+    f_drop = f_drop | (quotes.index < quotes["start"])
+    if f_drop.any():
+        # When printing report, ignore rows that were already NaNs:
+        f_na = quotes[["Open","Close"]].isna().all(axis=1)
+        n_nna = quotes.shape[0] - _np.sum(f_na)
+        n_drop_nna = _np.sum(f_drop & ~f_na)
+        quotes_dropped = quotes[f_drop]
+        # if debug and n_drop_nna > 0:
+        #     print(f"Dropping {n_drop_nna}/{n_nna} intervals for falling outside regular trading hours")
+        quotes = quotes[~f_drop]
+    metadata["tradingPeriods"] = tps_df.drop(["_date"], axis=1)
+    quotes = quotes.drop(["_date", "start", "end"], axis=1)
+    return quotes
+
+
 def fix_Yahoo_returning_live_separate(quotes, interval, tz_exchange):
     # Yahoo bug fix. If market is open today then Yahoo normally returns 
     # todays data as a separate row from rest-of week/month interval in above row. 
@@ -640,6 +690,71 @@ def is_valid_timezone(tz: str) -> bool:
     return True
 
 
+def format_history_metadata(md):
+    if not isinstance(md, dict):
+        return md
+    if len(md) == 0:
+        return md
+
+    tz = md["exchangeTimezoneName"]
+
+    for k in ["firstTradeDate", "regularMarketTime"]:
+        if k in md:
+            md[k] = _pd.to_datetime(md[k], unit='s', utc=True).tz_convert(tz)
+
+    if "currentTradingPeriod" in md:
+        for m in ["regular", "pre", "post"]:
+            if m in md["currentTradingPeriod"]:
+                for t in ["start", "end"]:
+                    md["currentTradingPeriod"][m][t] = \
+                        _pd.to_datetime(md["currentTradingPeriod"][m][t], unit='s', utc=True).tz_convert(tz)
+                del md["currentTradingPeriod"][m]["gmtoffset"]
+                del md["currentTradingPeriod"][m]["timezone"]
+
+    if "tradingPeriods" in md:
+        if md["tradingPeriods"] == {"pre":[], "post":[]}:
+            del md["tradingPeriods"]
+
+    if "tradingPeriods" in md:
+        tps = md["tradingPeriods"]
+        if isinstance(tps, list):
+            # Only regular times
+            regs_dict = [tps[i][0] for i in range(len(tps))]
+            pres_dict = None
+            posts_dict = None
+        elif isinstance(tps, dict):
+            # Includes pre- and post-market
+            pres_dict = [tps["pre"][i][0] for i in range(len(tps["pre"]))]
+            posts_dict = [tps["post"][i][0] for i in range(len(tps["post"]))]
+            regs_dict = [tps["regular"][i][0] for i in range(len(tps["regular"]))]
+        else:
+            raise Exception()
+
+        def _dict_to_table(d):
+            df = _pd.DataFrame.from_dict(d).drop(["timezone", "gmtoffset"], axis=1)
+            df["end"] = _pd.to_datetime(df["end"], unit='s', utc=True).dt.tz_convert(tz)
+            df["start"] = _pd.to_datetime(df["start"], unit='s', utc=True).dt.tz_convert(tz)
+            df.index = _pd.to_datetime(df["start"].dt.date)
+            df.index = df.index.tz_localize(tz)
+            return df
+
+        df = _dict_to_table(regs_dict)
+        df_cols = ["start", "end"]
+        if pres_dict is not None:
+            pre_df = _dict_to_table(pres_dict)
+            df = df.merge(pre_df.rename(columns={"start":"pre_start", "end":"pre_end"}), left_index=True, right_index=True)
+            df_cols = ["pre_start", "pre_end"]+df_cols
+        if posts_dict is not None:
+            post_df = _dict_to_table(posts_dict)
+            df = df.merge(post_df.rename(columns={"start":"post_start", "end":"post_end"}), left_index=True, right_index=True)
+            df_cols = df_cols+["post_start", "post_end"]
+        df = df[df_cols]
+        df.index.name = "Date"
+
+        md["tradingPeriods"] = df
+
+    return md
+
 class ProgressBar:
     def __init__(self, iterations, text='completed'):
         self.text = text
@@ -702,7 +817,14 @@ class _KVStore:
         with self._cache_mutex:
             self.conn = _sqlite3.connect(filename, timeout=10, check_same_thread=False)
             self.conn.execute('pragma journal_mode=wal')
-            self.conn.execute('create table if not exists "kv" (key TEXT primary key, value TEXT) without rowid')
+            try:
+                self.conn.execute('create table if not exists "kv" (key TEXT primary key, value TEXT) without rowid')
+            except Exception as e:
+                if 'near "without": syntax error' in str(e):
+                    # "without rowid" requires sqlite 3.8.2. Older versions will raise exception
+                    self.conn.execute('create table if not exists "kv" (key TEXT primary key, value TEXT)')
+                else:
+                    raise
             self.conn.commit()
         _atexit.register(self.close)
 

yfinance/version.py

@@ -1 +1 @@
-version = "0.2.4"
+version = "0.2.10b3"