Get additional PegRations using yfinance (package) and yahoo scraping api

get_pegs.py

# 
# To resolve issue #903 in yfinance
# https://github.com/ranaroussi/yfinance/issues/903
#----------------------------------------------------------
# Date:			2021-12-19
# 
# The PEG Ratio Yahoo Finance Paths:
#
# The working curl:
#	curl -s https://finance.yahoo.com/quote/{FE}/key-statistics?p={FE} | grep "root.App.main = " | sed -e "s/root.App.main = //" |sed 's/.$//'> dafuck_ok.json
#	curl -s https://finance.yahoo.com/quote/{FE}/key-statistics?p={FE} | grep "root.App.main = " | sed -e "s/root.App.main = //" |sed 's/.$//' |grep -ioE "[a-zA-Z_\"]*pegRatio.{120}"
#
# 	For: quarterlyPegRatio,trailingPegRatio
#	curl -s 'https://query1.finance.yahoo.com/ws/fundamentals-timeseries/v1/finance/timeseries/FE?symbol=FE&type={quarterlyPegRatio,trailingPegRatio}&period1=493590046&period2=1913180947'
#
# Optional curl headers (user_agent & headers): 
#	-A "curl/7.55.1" 
#	-H "x-api-key: xxxxxx" 
#	-H "accept: application/json" 
#	-H "content-type: application/json"
#
#	accept:	application/json;charset=utf-8		#text/html
#	referer: https://finance.yahoo.com/
#	cache-control: no-cache
#	connection: close
#
#	Default requests (sessions) settings:
#  		"User-Agent": "python-requests/2.26.0",
# 		"Accept-Encoding": "gzip, deflate",
#  		"Accept": "*/*",
#  		"Connection": "keep-alive"
# 
# References:
#	[1] https://github.com/Mtaylert/Stock_Evaluation/blob/dd5873ceb0c8b614b491a246aa3949960816ad92/src_code/StockEvaluations.ipynb
#	[2] https://stackoverflow.com/questions/44030983/yahoo-finance-url-not-working
# 	[3] https://www.nylas.com/blog/use-python-requests-module-rest-apis/
#	[4] https://docs.python-requests.org/en/master/user/advanced/#session-objects
#----------------------------------------------------------
import requests, re, json #, pprint
import numpy as np

debug = 1
showline = '\n'+'-'*60+'\n'

# The RegEx to grab only the JSON part of the request
p = re.compile(r'root\.App\.main = (.*);')

#tickers = list(np.unique(TopShifts_up['ticker']))
tickers = ['FE']
q_results = {}

# QuoteTimeSeriesStore: ['trailingPsRatio','quarterlyPbRatio', 'quarterlyForwardPeRatio', 'quarterlyMarketCap', 'quarterlyPeRatio', 'trailingMarketCap', 'trailingEnterprisesValueEBITDARatio', 'quarterlyEnterprisesValueEBITDARatio', 'trailingForwardPeRatio', 'trailingEnterpriseValue', 'trailingPeRatio', 'quarterlyEnterprisesValueRevenueRatio', 'quarterlyPsRatio', 'trailingEnterprisesValueRevenueRatio', 'quarterlyPegRatio', 'trailingPbRatio', 'quarterlyEnterpriseValue', 'trailingPegRatio', 'timestamp']
my_qs_keys = ['pegRatio']                               # QuoteSummaryStore
my_ts_keys = ['trailingPegRatio', 'quarterlyPegRatio']  # QuoteTimeSeriesStore

my_headers = {'user-agent': 'curl/7.55.1','accept': 'application/json', 'content-type': 'application/json', 'referer': 'https://finance.yahoo.com/', 'cache-control': 'no-cache', 'connection': 'close'}


with requests.Session() as s:

	for ticker in tickers:
		try:
			#r = session.get(url=url, proxies=proxy, headers=user_agent_headers)
			#r = s.get('https://finance.yahoo.com/quote/{}/key-statistics?p={}'.format(ticker,ticker), proxies=none, headers=my_headers)
			r = s.get('https://finance.yahoo.com/quote/{}/key-statistics?p={}'.format(ticker,ticker), headers=my_headers)
			
			if (debug): 
				
				print(showline,'  Request Headers:', showline)
				reqh = dict(r.request.headers) #.replace('"', '')
				#json_str = json_str.replace('"', '')
				print(json.dumps(reqh, indent=2))
				#------------------------------------------------------------
				print(showline,'  Response Headers:', r.status_code, showline)
				resh = dict(r.headers)
				print(json.dumps(resh, indent=2))
				
				#pprint.pprint(r.headers, indent=4, depth=1, width=120)
				print(showline)
				#if (debug == 2): print(r.text)
				
			regex_data = p.findall(r.text)
			if not regex_data:
				print(showline,'  No JSON block found in Response!', showline)
				break
			
			data = json.loads(p.findall(r.text)[0])
			
			#key_stats = data['context']['dispatcher']['stores']['QuoteSummaryStore']
			key_stats = data['context']['dispatcher']['stores']['QuoteTimeSeriesStore']

			q_results.setdefault(ticker,[])
			for i in my_ts_keys:
				#j=0
				try:
					#res = {i: key_stats['timeSeries'][i][1]['reportedValue']['raw']}
					# We need to loop over multiple items, if they exist: 0,1,2,..
					zzz = key_stats['timeSeries'][i]
					for j in range(len(zzz)):
						if key_stats['timeSeries'][i][j]:
							res = {i: key_stats['timeSeries'][i][j]['reportedValue']['raw']}
							q_results[ticker].append(res)
				
					#print(res)
					#q_results[ticker].append(res)
				except:
					q_results[ticker].append({i:np.nan})

			res = {'Company' : ticker}
			q_results[ticker].append(res)  
		except:
			pass

if (q_results):
	print(q_results)

#----------------------------------------------------------
#  EOF
#----------------------------------------------------------

Awesome! Will integrate into yfinance and provide full credit!