sync dev -> main

.github/workflows/ruff.yml

@@ -0,0 +1,13 @@
+name: Ruff
+on:
+  pull_request:
+    branches:
+      - master
+      - main
+      - dev
+jobs:
+  ruff:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: chartboost/ruff-action@v1

README.md

@@ -42,6 +42,26 @@ Yahoo! finance API is intended for personal use only.**
 
 ---
 
+## Installation
+
+Install `yfinance` using `pip`:
+
+``` {.sourceCode .bash}
+$ pip install yfinance --upgrade --no-cache-dir
+```
+
+[With Conda](https://anaconda.org/ranaroussi/yfinance).
+
+To install with optional dependencies, replace `optional` with: `nospam` for [caching-requests](#smarter-scraping), `repair` for [price repair](https://github.com/ranaroussi/yfinance/wiki/Price-repair), or `nospam,repair` for both:
+
+``` {.sourceCode .bash}
+$ pip install yfinance[optional]
+```
+
+[Required dependencies](./requirements.txt) , [all dependencies](./setup.py#L62).
+
+---
+
 ## Quick Start
 
 ### The Ticker module
@@ -87,6 +107,9 @@ msft.quarterly_cashflow
 msft.major_holders
 msft.institutional_holders
 msft.mutualfund_holders
+msft.insider_transactions
+msft.insider_purchases
+msft.insider_roster_holders
 
 # Show future and historic earnings dates, returns at most next 4 quarters and last 8 quarters by default. 
 # Note: If more are needed use msft.get_earnings_dates(limit=XX) with increased limit argument.
@@ -155,9 +178,10 @@ data = yf.download("SPY AAPL", period="1mo")
 
 ### Smarter scraping
 
-To use a custom `requests` session (for example to cache calls to the
-API or customize the `User-agent` header), pass a `session=` argument to
-the Ticker constructor.
+Install the `nospam` packages for smarter scraping using `pip` (see [Installation](#installation)). These packages help cache calls such that Yahoo is not spammed with requests. 
+
+To use a custom `requests` session, pass a `session=` argument to
+the Ticker constructor. This allows for caching calls to the API as well as a custom way to modify requests via  the `User-agent` header.
 
 ```python
 import requests_cache
@@ -168,7 +192,7 @@ ticker = yf.Ticker('msft', session=session)
 ticker.actions
 ```
 
-Combine a `requests_cache` with rate-limiting to avoid triggering Yahoo's rate-limiter/blocker that can corrupt data.
+Combine `requests_cache` with rate-limiting to avoid triggering Yahoo's rate-limiter/blocker that can corrupt data.
 ```python
 from requests import Session
 from requests_cache import CacheMixin, SQLiteCache
@@ -230,41 +254,6 @@ yf.set_tz_cache_location("custom/cache/location")
 
 ---
 
-## Installation
-
-Install `yfinance` using `pip`:
-
-``` {.sourceCode .bash}
-$ pip install yfinance --upgrade --no-cache-dir
-```
-
-Test new features by installing betas, provide feedback in [corresponding Discussion](https://github.com/ranaroussi/yfinance/discussions):
-``` {.sourceCode .bash}
-$ pip install yfinance --upgrade --no-cache-dir --pre
-```
-
-To install `yfinance` using `conda`, see
-[this](https://anaconda.org/ranaroussi/yfinance).
-
-### Requirements
-
--   [Python](https://www.python.org) \>= 2.7, 3.4+
--   [Pandas](https://github.com/pydata/pandas) \>= 1.3.0
--   [Numpy](http://www.numpy.org) \>= 1.16.5
--   [requests](http://docs.python-requests.org/en/master) \>= 2.31
--   [lxml](https://pypi.org/project/lxml) \>= 4.9.1
--   [appdirs](https://pypi.org/project/appdirs) \>= 1.4.4
--   [pytz](https://pypi.org/project/pytz) \>=2022.5
--   [frozendict](https://pypi.org/project/frozendict) \>= 2.3.4
--   [beautifulsoup4](https://pypi.org/project/beautifulsoup4) \>= 4.11.1
--   [html5lib](https://pypi.org/project/html5lib) \>= 1.1
--   [peewee](https://pypi.org/project/peewee)  \>= 3.16.2
-
-#### Optional (if you want to use `pandas_datareader`)
-
--   [pandas\_datareader](https://github.com/pydata/pandas-datareader)
-    \>= 0.4.0
-
 ## Developers: want to contribute?
 
 `yfinance` relies on community to investigate bugs and contribute code. Developer guide: https://github.com/ranaroussi/yfinance/discussions/1084

setup.py

@@ -64,6 +64,10 @@
                       'lxml>=4.9.1', 'appdirs>=1.4.4', 'pytz>=2022.5',
                       'frozendict>=2.3.4', 'peewee>=3.16.2',
                       'beautifulsoup4>=4.11.1', 'html5lib>=1.1'],
+    extras_require={
+        'nospam': ['requests_cache>=1.0', 'requests_ratelimiter>=0.3.1'],
+        'repair': ['scipy>=1.6.3'],
+    },
     # Note: Pandas.read_html() needs html5lib & beautifulsoup4
     entry_points={
         'console_scripts': [

tests/context.py

@@ -4,18 +4,20 @@
 import datetime as _dt
 import sys
 import os
+import yfinance
+from requests import Session
+from requests_cache import CacheMixin, SQLiteCache
+from requests_ratelimiter import LimiterMixin, MemoryQueueBucket
+from pyrate_limiter import Duration, RequestRate, Limiter
+
 _parent_dp = os.path.abspath(os.path.join(os.path.dirname(__file__), '..'))
 _src_dp = _parent_dp
 sys.path.insert(0, _src_dp)
 
-import yfinance
-
-
 # Optional: see the exact requests that are made during tests:
 # import logging
 # logging.basicConfig(level=logging.DEBUG)
 
-
 # Use adjacent cache folder for testing, delete if already exists and older than today
 testing_cache_dirpath = os.path.join(_ad.user_cache_dir(), "py-yfinance-testing")
 yfinance.set_tz_cache_location(testing_cache_dirpath)
@@ -27,12 +29,8 @@
 
 
 # Setup a session to rate-limit and cache persistently:
-from requests import Session
-from requests_cache import CacheMixin, SQLiteCache
-from requests_ratelimiter import LimiterMixin, MemoryQueueBucket
 class CachedLimiterSession(CacheMixin, LimiterMixin, Session):
     pass
-from pyrate_limiter import Duration, RequestRate, Limiter
 history_rate = RequestRate(1, Duration.SECOND*2)
 limiter = Limiter(history_rate)
 cache_fp = os.path.join(testing_cache_dirpath, "unittests-cache")

tests/data/CNE-L-1d-bad-stock-split-fixed.csv

@@ -2,10 +2,10 @@ Date,Open,High,Low,Close,Adj Close,Volume,Dividends,Stock Splits
 2023-05-18 00:00:00+01:00,193.220001220703,200.839996337891,193.220001220703,196.839996337891,196.839996337891,653125,0,0
 2023-05-17 00:00:00+01:00,199.740005493164,207.738006591797,190.121994018555,197.860000610352,197.860000610352,822268,0,0
 2023-05-16 00:00:00+01:00,215.600006103516,215.600006103516,201.149993896484,205.100006103516,205.100006103516,451009,243.93939,0.471428571428571
-2023-05-15 00:00:00+01:00,215.399955531529,219.19995640346,210.599967302595,217.399987792969,102.39998147147,1761679.3939394,0,0
-2023-05-12 00:00:00+01:00,214.599988664899,216.199965558733,209.599965558733,211.399977329799,99.573855808803,1522298.48484849,0,0
-2023-05-11 00:00:00+01:00,219.999966430664,219.999966430664,212.199987357003,215.000000871931,101.269541277204,3568042.12121213,0,0
-2023-05-10 00:00:00+01:00,218.199954659598,223.000000435965,212.59995640346,215.399955531529,101.457929992676,5599908.78787879,0,0
-2023-05-09 00:00:00+01:00,224,227.688003540039,218.199996948242,218.399993896484,102.87100982666,1906090,0,0
-2023-05-05 00:00:00+01:00,220.999968174526,225.19996686663,220.799976457868,224.4,105.697140066964,964523.636363637,0,0
-2023-05-04 00:00:00+01:00,216.999989972796,222.799965558733,216.881988961356,221.399965994698,104.284055655343,880983.93939394,0,0
+2023-05-15 00:00:00+01:00,456.9090,464.9696,446.7272,461.1515,217.2121,830506.0000,0,0
+2023-05-12 00:00:00+01:00,455.2121,458.6060,444.6060,448.4242,211.2173,717655.0000,0,0
+2023-05-11 00:00:00+01:00,466.6666,466.6666,450.1212,456.0606,214.8142,1682077.0000,0,0
+2023-05-10 00:00:00+01:00,462.8484,473.0303,450.9696,456.9090,215.2138,2639957.0000,0,0
+2023-05-09 00:00:00+01:00,475.1515,482.9746,462.8485,463.2727,218.2112,898585.2857,0,0
+2023-05-05 00:00:00+01:00,468.7878,477.6969,468.3636,476.0000,224.2061,454704.0000,0,0
+2023-05-04 00:00:00+01:00,460.3030,472.6060,460.0527,469.6363,221.2086,415321.0000,0,0

tests/prices.py

@@ -132,7 +132,6 @@ def test_pricesEventsMerge(self):
 
     def test_pricesEventsMerge_bug(self):
         # Reproduce exception when merging intraday prices with future dividend
-        tkr = 'S32.AX'
         interval = '30m'
         df_index = []
         d = 13
@@ -148,7 +147,7 @@ def test_pricesEventsMerge_bug(self):
         future_div_dt = _dt.datetime(2023, 9, 14, 10)
         divs = _pd.DataFrame(data={"Dividends":[div]}, index=[future_div_dt])
 
-        df2 = yf.utils.safe_merge_dfs(df, divs, interval)
+        yf.utils.safe_merge_dfs(df, divs, interval)
         # No exception = test pass
 
     def test_intraDayWithEvents(self):
@@ -223,8 +222,10 @@ def test_dailyWithEvents(self):
                 self.assertTrue((df_divs.index.date == dates).all())
             except AssertionError:
                 print(f'- ticker = {tkr}')
-                print('- response:') ; print(df_divs.index.date)
-                print('- answer:') ; print(dates)
+                print('- response:')
+                print(df_divs.index.date)
+                print('- answer:')
+                print(dates)
                 raise
 
     def test_dailyWithEvents_bugs(self):
@@ -270,60 +271,6 @@ def test_dailyWithEvents_bugs(self):
         self.assertTrue(df_merged[df_prices.columns].iloc[1:].equals(df_prices))
         self.assertEqual(df_merged.index[0], div_dt)
 
-    def test_intraDayWithEvents(self):
-        tkrs = ["BHP.AX", "IMP.JO", "BP.L", "PNL.L", "INTC"]
-        test_run = False
-        for tkr in 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:
-                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_intraday = yf.Ticker(tkr, session=self.session).history(start=start_d, end=end_d, interval="15m", actions=True)
-            self.assertTrue((df_intraday["Dividends"] != 0.0).any())
-
-            df_intraday_divs = df_intraday["Dividends"][df_intraday["Dividends"] != 0]
-            df_intraday_divs.index = df_intraday_divs.index.floor('D')
-            self.assertTrue(df_daily_divs.equals(df_intraday_divs))
-
-            test_run = True
-
-        if not test_run:
-            self.skipTest("Skipping test_intraDayWithEvents() because no tickers had a dividend in last 60 days")
-
-    def test_intraDayWithEvents_tase(self):
-        # TASE dividend release pre-market, doesn't merge nicely with intra-day data so check still present
-
-        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:
-                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_intraday = yf.Ticker(tkr, session=self.session).history(start=start_d, end=end_d, interval="15m", actions=True)
-            self.assertTrue((df_intraday["Dividends"] != 0.0).any())
-
-            df_intraday_divs = df_intraday["Dividends"][df_intraday["Dividends"] != 0]
-            df_intraday_divs.index = df_intraday_divs.index.floor('D')
-            self.assertTrue(df_daily_divs.equals(df_intraday_divs))
-
-            test_run = True
-
-        if not test_run:
-            self.skipTest("Skipping test_intraDayWithEvents_tase() because no tickers had a dividend in last 60 days")
-
     def test_weeklyWithEvents(self):
         # Reproduce issue #521
         tkr1 = "QQQ"
@@ -415,9 +362,9 @@ def test_tz_dst_ambiguous(self):
             raise Exception("Ambiguous DST issue not resolved")
 
     def test_dst_fix(self):
-        # Daily intervals should start at time 00:00. But for some combinations of date and timezone, 
+        # Daily intervals should start at time 00:00. But for some combinations of date and timezone,
         # Yahoo has time off by few hours (e.g. Brazil 23:00 around Jan-2022). Suspect DST problem.
-        # The clue is (a) minutes=0 and (b) hour near 0. 
+        # The clue is (a) minutes=0 and (b) hour near 0.
         # Obviously Yahoo meant 00:00, so ensure this doesn't affect date conversion.
 
         # The correction is successful if no days are weekend, and weekly data begins Monday
@@ -440,8 +387,8 @@ def test_dst_fix(self):
             raise
 
     def test_prune_post_intraday_us(self):
-        # Half-day before USA Thanksgiving. Yahoo normally 
-        # returns an interval starting when regular trading closes, 
+        # Half-day before USA Thanksgiving. Yahoo normally
+        # returns an interval starting when regular trading closes,
         # even if prepost=False.
 
         # Setup
@@ -477,8 +424,8 @@ def test_prune_post_intraday_us(self):
         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, 
+        # 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.
 
@@ -528,7 +475,6 @@ def test_prune_post_intraday_omx(self):
     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)
@@ -566,7 +512,7 @@ def test_aggregate_capital_gains(self):
         end = "2019-12-31"
         interval = "3mo"
 
-        df = dat.history(start=start, end=end, interval=interval)
+        dat.history(start=start, end=end, interval=interval)
 
 
 class TestPriceRepair(unittest.TestCase):
@@ -589,7 +535,6 @@ def test_reconstruct_2m(self):
         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
@@ -599,7 +544,7 @@ def test_reconstruct_2m(self):
             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)
+            dat.history(start=start_dt, end=end_dt, interval="2m", repair=True)
 
     def test_repair_100x_random_weekly(self):
         # Setup:
@@ -844,7 +789,7 @@ def test_repair_zeroes_daily(self):
         self.assertFalse(repaired_df["Repaired?"].isna().any())
 
     def test_repair_zeroes_daily_adjClose(self):
-        # Test that 'Adj Close' is reconstructed correctly, 
+        # Test that 'Adj Close' is reconstructed correctly,
         # particularly when a dividend occurred within 1 day.
 
         tkr = "INTC"
@@ -914,10 +859,10 @@ def test_repair_zeroes_hourly(self):
         self.assertFalse(repaired_df["Repaired?"].isna().any())
 
     def test_repair_bad_stock_split(self):
-        # Stocks that split in 2022 but no problems in Yahoo data, 
+        # Stocks that split in 2022 but no problems in Yahoo data,
         # so repair should change nothing
         good_tkrs = ['AMZN', 'DXCM', 'FTNT', 'GOOG', 'GME', 'PANW', 'SHOP', 'TSLA']
-        good_tkrs += ['AEI', 'CHRA', 'GHI', 'IRON', 'LXU', 'NUZE', 'RSLS', 'TISI']
+        good_tkrs += ['AEI', 'GHI', 'IRON', 'LXU', 'NUZE', 'RSLS', 'TISI']
         good_tkrs += ['BOL.ST', 'TUI1.DE']
         intervals = ['1d', '1wk', '1mo', '3mo']
         for tkr in good_tkrs:
@@ -979,8 +924,8 @@ def test_repair_bad_stock_split(self):
                     # print(repaired_df[c] - correct_df[c])
                     raise
 
-        # Had very high price volatility in Jan-2021 around split date that could 
-        # be mistaken for missing stock split adjustment. And old logic did think 
+        # Had very high price volatility in Jan-2021 around split date that could
+        # be mistaken for missing stock split adjustment. And old logic did think
         # column 'High' required fixing - wrong!
         sketchy_tkrs = ['FIZZ']
         intervals = ['1wk']