Parse all text content from an HTML document using BeautifulSoup.

parse_html_bsoup.py

from bs4 import BeautifulSoup

# path to the local file
doc = "C:\\Users\\Ryland\\Desktop\\index.html"

# open the file in read mode
with open(doc, 'r') as f:
    content = f.read()

# Initialize the object with the document
soup = BeautifulSoup(content, "html.parser")

# Get the whole body tag
tag = soup.body

# Open a file for writing
with open("C:\\Users\\Ryland\\Desktop\\index.txt", "w") as file:
	# Write each string recursively to the file
	for string in tag.strings:
		file.write(string + "\n")