INNER CODE UNIT · Python

ReadmeHTMLTextExtractor

dedsec1121fk/DedSec · Scripts/DedSec Market.py:271

class ReadmeHTMLTextExtractor(HTMLParser):
    BLOCK_TAGS = {
        "p", "div", "section", "article", "details", "summary", "ul", "ol",
        "li", "br", "hr", "table", "tr", "td", "th", "h1", "h2", "h3",
        "h4", "h5", "h6", "blockquote"
    }

    def __init__(self):
        super().__init__(convert_charrefs=True)
        self.parts = []
        self.skip_tag = None

    def handle_starttag(self, tag, attrs):
        tag = tag.lower()
        if tag in {"script", "style"}:
            self.skip_tag = tag
            return
        if self.skip_tag:

View source record →