INNER CODE UNIT · Python
html_to_text
dedsec1121fk/DedSec · Scripts/DedSec Market.py:319
def html_to_text(text):
parser = ReadmeHTMLTextExtractor()
parser.feed(text)
parser.close()
return parser.get_text()
def strip_markdown(text):
text = re.sub(r"```[^\n]*\n(.*?)```", lambda m: "\n" + m.group(1).strip() + "\n", text, flags=re.DOTALL)
text = re.sub(r"~~~[^\n]*\n(.*?)~~~", lambda m: "\n" + m.group(1).strip() + "\n", text, flags=re.DOTALL)
text = re.sub(r"<!--.*?-->", "", text, flags=re.DOTALL)
text = re.sub(r"<style.*?>.*?</style>", "", text, flags=re.DOTALL | re.IGNORECASE)
text = re.sub(r"<script.*?>.*?</script>", "", text, flags=re.DOTALL | re.IGNORECASE)
text = re.sub(r"!\[[^\]]*\]\([^)]*\)", "", text)
text = re.sub(r"\[([^\]]+)\]\([^)]*\)", r"\1", text)
if "<" in text and ">" in text:
text = html_to_text(text)
text = re.sub(r"`([^`]+)`", r"\1", text)