abs51295
/ html_to_text.py
Last active
July 31, 2024 07:07
— forked from racitup/html_to_text.py
Extract text from html in python using BeautifulSoup4
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
| from bs4 import BeautifulSoup, NavigableString, Tag | |
| import urllib.request | |
| def html_to_text(html): | |
| "Creates a formatted text email message as a string from a rendered html template (page)" | |
| soup = BeautifulSoup(html, 'html.parser') | |
| # Ignore anything in head | |
| body, text = soup.body, [] | |
| for element in body.descendants: | |
| # We use type and not isinstance since comments, cdata, etc are subclasses that we don't want |