Created
May 7, 2023 15:37
-
-
Save archatas/b8320a9230ec5d28633488964b5f8cfa to your computer and use it in GitHub Desktop.
Converting HTML to plain text
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import re | |
from html.parser import HTMLParser | |
class HTMLStripper(HTMLParser): | |
# stackoverflow.com/questions/753052/strip-html-from-strings-in-python | |
def __init__(self): | |
super().__init__() | |
self.reset() | |
self.strict = False | |
self.convert_charrefs = True | |
self.text = [] | |
def handle_starttag(self, tag: str, attrs): | |
if tag.lower() == "br": | |
self.text.append("\n") | |
def handle_endtag(self, tag): | |
if tag.lower() in ["p", "ul", "h1", "h2", "h3", "h4", "h5", "h6"]: | |
self.text.append("\n\n") | |
def handle_data(self, data): | |
# Replace any consecutive whitespace characters with just one space | |
data = re.sub("\s+", " ", data) | |
self.text.append(data) | |
def get_data(self): | |
return "".join(self.text).strip() | |
def strip_html_tags(html): | |
""" | |
Strip tags from a text that contains HTML tags and return a text. | |
""" | |
s = HTMLStripper() | |
s.feed(html) | |
return s.get_data() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment