INNER CODE UNIT · Python

get_text

dedsec1121fk/DedSec · Scripts/DedSec Market.py:315

    def get_text(self):
        return "".join(self.parts)


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)

View source record →