INNER CODE UNIT · Python

_extract_urls

ermaozi/get_subscribe · main.py:41

def _extract_urls(summary):
    decoded = html.unescape(summary)
    urls = []
    for raw_url in re.findall(r"https?://[^\s\"'<>]+", decoded):
        url = raw_url.strip().rstrip('.,;)')
        if url not in urls:
            urls.append(url)
    return urls, decoded


_NODE_SCHEME_RE = re.compile(r"(?:vmess|vless|trojan|ss|ssr|hysteria2?|hy2|tuic|anytls|mieru|https?|socks[45]?)://")


def _b64decode(text):
    compact = re.sub(r"\s+", "", text)
    if not compact:
        return ""
    try:

View source record →