⚙️

Python project - Web Scraping

!pip install yfinance
!pip install bs4
!pip install nbformat
!pip install --upgrade plotly
!pip install lxml


import yfinance as yf
import pandas as pd
import requests
from bs4 import BeautifulSoup
import plotly.graph_objects as go
from plotly.subplots import make_subplots
import lxml
import plotly.io as pio
pio.renderers.default = "iframe"
import warnings
# Ignore all warnings
warnings.filterwarnings("ignore", category=FutureWarning)

TESLA = yf.Ticker("TSLA")
tesla_data = TESLA.history("max")

tesla_data.reset_index()
tesla_data.head()

url =  " https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-PY0220EN-SkillsNetwork/labs/project/revenue.htm"
html_data = requests.get(url).text
html_parse = BeautifulSoup(html_data,"html.parser")

pandas_tables= pd.read_html("https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-PY0220EN-SkillsNetwork/labs/project/revenue.htm")
tesla_revenue = pandas_tables[0]
tesla_revenue.columns = ['Year','Revenue']

tesla_revenue["Revenue"] = tesla_revenue['Revenue'].str.replace(',|\$',"",regex = True)

tesla_revenue.dropna(inplace=True)
tesla_revenue = tesla_revenue[tesla_revenue['Revenue'] != ""]

tesla_revenue.tail()

GME Analysis

GME = yf.Ticker("GME")
gme_data = GME.history("max")
html_data_2 = requests.get(url).text
html_parse = BeautifulSoup(html_data_2,"html.parser")

gme_revenue_data = pd.read_html(" https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-PY0220EN-SkillsNetwork/labs/project/stock.html")
gme_revenue = gme_revenue_data[0]
gme_revenue.columns = ['Date', 'Revenue']
gme_revenue["Revenue"] = gme_revenue['Revenue'].str.replace(',|\$',"",regex=True)

print(gme_revenue.dtypes)

gme_revenue['Date'] = pd.to_datetime(gme_revenue['Date'])
gme_data['Date'] = pd.to_datetime(gme_data['Date'])

tesla_revenue['Date'] = pd.to_datetime(tesla_revenue['Date'])
tesla_data['Date'] = pd.to_datetime(tesla_data['Date']).dt.normalize()

gme_revenue['Date'] = pd.to_datetime(gme_revenue['Date'])
gme_data['Date'] = pd.to_datetime(gme_data['Date'])

#make_graph: IBM Course, function(not made by me)
make_graph(tesla_data,tesla_revenue,'Tesla')