# -*- coding: utf-8 -*-
r'''抓 Gitee 在 README 页面上挂的违规公告原文。

== 为什么要抓原文 ==

    网页版 README 页里出现了：
        「违规信息」2 次
        「内容可能」2 次
        「违规」2 次
        「举报」10 次

但 raw 接口是 451。光看关键词猜没用 —— 要把 Gitee 的**原话**读出来，
才知道它到底判的是哪一条，才能对症改。

== 抓什么 ==

把「违规信息」「内容可能」附近的 HTML 片段剥掉标签打出来。
'''
from __future__ import annotations

import html
import re
import sys
import urllib.error
import urllib.request

URL = "https://gitee.com/xmz7891/ykxmz/blob/main/README.md"


def main() -> int:
    req = urllib.request.Request(URL)
    req.add_header("User-Agent",
                   "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
                   "AppleWebKit/537.36 Chrome/120 Safari/537.36")
    try:
        with urllib.request.urlopen(req, timeout=30) as r:
            page = r.read().decode("utf-8", "replace")
    except urllib.error.HTTPError as exc:
        print("  ✗ HTTP %s" % exc.code)
        return 1

    print("  页面 %d 字节" % len(page))

    # 去掉 script/style
    body = re.sub(r"<script.*?</script>", " ", page, flags=re.S | re.I)
    body = re.sub(r"<style.*?</style>", " ", body, flags=re.S | re.I)

    print()
    print("=" * 62)
    print("  「违规」/「内容可能」附近的原文")
    print("=" * 62)
    for kw in ("违规信息", "内容可能", "违规"):
        for m in re.finditer(kw, body):
            start = max(0, m.start() - 500)
            end = min(len(body), m.end() + 500)
            chunk = body[start:end]
            chunk = re.sub(r"<[^>]+>", " ", chunk)
            chunk = html.unescape(chunk)
            chunk = re.sub(r"\s+", " ", chunk).strip()
            if len(chunk) > 30:
                print()
                print("  【%s】" % kw)
                print("    ...%s..." % chunk)
                break   # 每个词只看第一条，免得太长

    print()
    print("=" * 62)
    print("  页面里所有提到「审核 / 举报 / 法律」的短句")
    print("=" * 62)
    for kw in ("审核", "举报", "法律", "不可用"):
        seen = set()
        for m in re.finditer(kw, body):
            start = max(0, m.start() - 120)
            end = min(len(body), m.end() + 120)
            chunk = re.sub(r"<[^>]+>", " ", body[start:end])
            chunk = html.unescape(chunk)
            chunk = re.sub(r"\s+", " ", chunk).strip()
            # 只留信息量够、而且不是重复的
            key = chunk[:40]
            if len(chunk) > 25 and key not in seen:
                seen.add(key)
                print("  【%s】%s" % (kw, chunk[:180]))
                if len(seen) >= 2:
                    break
    return 0


if __name__ == "__main__":
    sys.exit(main())