Created
February 17, 2018 16:56
-
-
Save stoffprof/719ae8d876d3a5539112e74d292339c9 to your computer and use it in GitHub Desktop.
Read Yahoo price data
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
class YahooDailyReader(): | |
def __init__(self, symbol=None, start=None, end=None): | |
import datetime, time | |
self.symbol = symbol | |
# initialize start/end dates if not provided | |
if end is None: | |
end = datetime.datetime.today() | |
if start is None: | |
start = datetime.datetime(2010,1,1) | |
self.start = start | |
self.end = end | |
# convert dates to unix time strings | |
unix_start = int(time.mktime(self.start.timetuple())) | |
day_end = self.end.replace(hour=23, minute=59, second=59) | |
unix_end = int(time.mktime(day_end.timetuple())) | |
url = 'https://finance.yahoo.com/quote/{}/history?' | |
url += 'period1={}&period2={}' | |
url += '&filter=history' | |
url += '&interval=1d' | |
url += '&frequency=1d' | |
self.url = url.format(self.symbol, unix_start, unix_end) | |
def read(self): | |
import requests, re, json | |
r = requests.get(self.url) | |
ptrn = r'root\.App\.main = (.*?);\n}\(this\)\);' | |
txt = re.search(ptrn, r.text, re.DOTALL).group(1) | |
jsn = json.loads(txt) | |
df = pd.DataFrame( | |
jsn['context']['dispatcher']['stores'] | |
['HistoricalPriceStore']['prices'] | |
) | |
df.insert(0, 'symbol', self.symbol) | |
df['date'] = pd.to_datetime(df['date'], unit='s').dt.date | |
# drop rows that aren't prices | |
df = df.dropna(subset=['close']) | |
df = df[['symbol', 'date', 'high', 'low', 'open', 'close', | |
'volume', 'adjclose']] | |
df = df.set_index('symbol') | |
return df | |
ydr = YahooDailyReader('IBM') | |
df = ydr.read() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment