"""极简 HTML→纯文本提取（纯标准库，零第三方依赖，避免引入许可不明的解析库）。

不追求完美排版，目标是从网页中抽取可读正文供模型摘要。会丢弃 script/style/
noscript 等非正文标签，折叠多余空白。
"""

from html.parser import HTMLParser

_SKIP_TAGS = {"script", "style", "noscript", "template", "svg", "head"}
_BLOCK_TAGS = {
    "p", "div", "br", "li", "ul", "ol", "tr", "table",
    "h1", "h2", "h3", "h4", "h5", "h6", "section", "article", "header", "footer",
}


class _Extractor(HTMLParser):
    def __init__(self):
        super().__init__(convert_charrefs=True)
        self._parts: list[str] = []
        self._skip_depth = 0

    def handle_starttag(self, tag, attrs):
        if tag in _SKIP_TAGS:
            self._skip_depth += 1
        elif tag in _BLOCK_TAGS:
            self._parts.append("\n")

    def handle_endtag(self, tag):
        if tag in _SKIP_TAGS and self._skip_depth > 0:
            self._skip_depth -= 1
        elif tag in _BLOCK_TAGS:
            self._parts.append("\n")

    def handle_data(self, data):
        if self._skip_depth == 0 and data:
            self._parts.append(data)

    def text(self) -> str:
        raw = "".join(self._parts)
        # 折叠空白：去掉行内多余空格，压缩连续空行
        lines = [ " ".join(line.split()) for line in raw.splitlines() ]
        out: list[str] = []
        blank = False
        for line in lines:
            if line:
                out.append(line)
                blank = False
            elif not blank:
                out.append("")
                blank = True
        return "\n".join(out).strip()


def html_to_text(html: str, max_chars: int = 6000) -> str:
    """把 HTML 转为纯文本并截断到 max_chars。解析失败时退化为原文截断。"""
    if not html:
        return ""
    try:
        parser = _Extractor()
        parser.feed(html)
        text = parser.text()
    except Exception:
        text = html
    if len(text) > max_chars:
        text = text[:max_chars] + "…"
    return text