How to Scrape Data From Local HTML Files using Python?

# Necessary imports
import sys
import urllib.request

# Save a reference to the original
# standard output
original_stdout = sys.stdout

# as an example, taken my article list
# published link page and stored in local
with urllib.request.urlopen('https://auth.geeksforgeeks.org/user/priyarajtt/articles') as webPageResponse:
    outputHtml = webPageResponse.read()

# Scraped contents are placed in 
# samplehtml.html file and getting
# used for next set of examples
with open('samplehtml.html', 'w') as f:
    
    # Here the  standard output is 
    # written to the file that we 
    # used above
    sys.stdout = f
    print(outputHtml)
    
    # Reset the standard output to its 
    # original value
    sys.stdout = original_stdout

# Importing BeautifulSoup and 
# it is in the bs4 module
from bs4 import BeautifulSoup

# Opening the html file. If the file
# is present in different location, 
# exact location need to be mentioned
HTMLFileToBeOpened = open("samplehtml.html", "r")

# Reading the file and storing in a variable
contents = HTMLFileToBeOpened.read()

# Creating a BeautifulSoup object and
# specifying the parser 
beautifulSoupText = BeautifulSoup(contents, 'lxml')


# Using the prettify method to modify the code
#  Prettify() function in BeautifulSoup helps
# to view about the tag nature and their nesting
print(beautifulSoupText.body.prettify())

# Importing BeautifulSoup and it
# is in the bs4 module
from bs4 import BeautifulSoup

# Opening the html file. If the file
# is present in different location, 
# exact location need to be mentioned
HTMLFileToBeOpened = open("samplehtml.html", "r")

# Reading the file and storing in a variable
contents = HTMLFileToBeOpened.read()

# Creating a BeautifulSoup object and 
# specifying the parser
beautifulSoupText = BeautifulSoup(contents, 'lxml')

# To get all the tags present in the html 
# and getting their length
for tag in beautifulSoupText.findAll(True):
    print(tag.name, " : ", len(beautifulSoupText.find(tag.name).text))

# necessary import for getting
# directory and filenames
import os
from bs4 import BeautifulSoup

# Get current working directory
directory = os.getcwd()

# for all the files present in that
# directory
for filename in os.listdir(directory):
    
    # check whether the file is having
    # the extension as html and it can
    # be done with endswith function
    if filename.endswith('.html'):
        
        # os.path.join() method in Python join
        # one or more path components which helps
        # to exactly get the file
        fname = os.path.join(directory, filename)
        print("Current file name ..", os.path.abspath(fname))
        
        # open the file
        with open(fname, 'r') as file:
          
            beautifulSoupText = BeautifulSoup(file.read(), 'html.parser')
            
            # parse the html as you wish
            for tag in beautifulSoupText.findAll(True):
                print(tag.name, " : ", len(beautifulSoupText.find(tag.name).text))