GET RICH SLOW - Step by step value investing with Python

[Update 26/06/2021] I use beautiful soup to scrape morning star for EPS data. because of the way they have changed the way webpages are called it doesn't work anymore, however the data can be scraped with Selenium.  I haven't had a chance to update the whole lecture, but the below code works for me, hopefully that helps you

"""

New version using webdriver

NNB! - Make sure chromedriver is up to date if its not working.

"""

from selenium import webdriver

from time import time

from time import sleep

import pandas as pd

from os import chdir

#-------------------Create Function to Collect Data---------------------

def GetData(ticker,findf):

#chdir("C:\\Users\\nr453") # Point to where the Chrome driver is for now

#already in saved in the investment directory

driver = webdriver.Chrome() # Instance of Chrome WebDriver is created.

driver.get(r"htt p : // financials.morningstar.com/ratios/r. html?t=" #link adjusted to post -fix to use

+ ticker +

r"&region=usa&culture=en-US")

assert "Ratios" in driver.title # Confirm Ratios word in it.

sleep(2) # Wait for page to load

driver.find_element_by_class_name("large_button").click()

sleep(2) # Wait for download to start

assert "No results found." not in driver.page_source

driver.quit()

sleep(2) # Wait for Chrome window close (you can play with this time)

#--------------read CSV a dataframe----------------------

df = pd.read_csv(r'C:\\Users\\russe\Downloads\\'

+ ticker +

r' Key Ratios.csv', header = 2, index_col=False)

df.index = df['Unnamed: 0']

df = df.drop(['Unnamed: 0'], axis = 1)

df.index.names = ['Desc']

#-----------------Pull out the EPS data------------

dfeps = df.loc[['Earnings Per Share USD']].copy()

dfeps['name'] = ticker

dfeps.index = dfeps['name']

del dfeps['name']

#--------combine the two dataframes-------------------------

if j == 0: # If dataframe is empty

findf = dfeps # Save for the first time

else:

findf = findf.append(dfeps) # else just append

return findf

#-----------------------Import ticker data---------------------

chdir("C:\\Russell\\Investment\\Mkt_Val_Model")

splist = pd.read_csv("Inv201.02_List_All_US_Stocks_500m_INPY.csv",index_col=None) #, index_col=False

#--------------------Main dataframe to store data---------------

findf = pd.DataFrame() # Create empty data frame

FailedAttempt = [] # Store the names of stocks that have failed

t1 = time() # Start time

for j in range(0,len(splist)): #range(0,len(splist))

# Read in stock name (ticker)------------

ticker = splist['Symbol'][j].replace("-",".") # replace -'s with .'s

#-----Status Report---------------------

AveTime = round((time() - t1) / (j+1),2)

print ("Number %r of %r: %r Ave time: %r sec Time left: %r min/%r hr" %(j,len(splist),

ticker, AveTime, round(AveTime * (len(splist)-j)/60,2), round(AveTime * (len(splist)-j)/60/60,2)))

try:

findf = GetData(ticker, findf) # If not found, then it will skip to except to retry

except:

sleep(2)

FailedAttempt.append(ticker) # Save ticker

#----saving data to file ---

findf.to_csv("FinDat\\EpsSum01.csv")

FailedSeries = pd.Series(FailedAttempt) # convert from list

FailedSeries.to_csv("FinDat\\FailedTicker01.csv") # save failed ticker