covidproject webs.txt

url = "https://www.ndtv.com/coronavirus/india-covid-19-tracker"
import requests  #import requests library
page = requests.get(url)
page
page.text
from bs4 import BeautifulSoup
dir(BeautifulSoup)
soup = BeautifulSoup(page.text)
soup
soup.title
soup.table
soup = BeautifulSoup(page.text,'html.parser')
soup.table
table = soup.find_all('table')
table
rows = table[0].find_all('tr')
rows
[i.text for i in rows[0]]  # To get Headings
[i.text.replace('\n','') for i in rows[0]]  #Replace \n with empty string
[i.text.replace('\n','').strip() for i in rows[0]]  #Remove empty spaces
headings = [i.text.replace('\n','').strip() for i in rows[0]]  # Assigning a variable
rows = table[0].find_all('tr')
rows

for i in rows:
  print(i)

all_rows = []
for i in rows:
  td = i.find_all('td')
  row = [i.text for i in td]
  all_rows.append(row)              #get the rows in a list

all_rows
all_rows.pop(0)   #remove first element
all_rows

for i in all_rows:
  i[0] = i[0][:i[0].find("DistrictCases")]   #Remove the part of first element after 'DistrictCases'

for i in all_rows:
  i[1] = i[1][:i[1].find(" ")]
  i[2] = i[2][:i[2].find(" ")]
  i[3] = i[3][:i[3].find(" ")]
  i[4] = i[4][:i[4].find(" ")]  #remove inc/dec part after space

all_rows #data after cleansing

import pandas as pd
df = pd.DataFrame(all_rows,columns=headings) 

df