ykxmz/_build/check_gitee_block.py

# -*- coding: utf-8 -*-
r'''查 Gitee 到底为什么判违规，以及 README 里哪些词可能触发。

== 已知 ==

    https://gitee.com/xmz7891/ykxmz/raw/main/README.md  -> HTTP 451
    Unavailable For Legal Reasons

451 是"应法律要求不可用"。在国内平台上，这个通常是**内容审核拦的**。

== 要分清两种情况 ==

    A. 整个仓库被限制（那 API 读仓库信息也会失败/受限）
    B. 只有 README 这个文件被拦（网页能开、raw 不行）

== 同时扫一下 README 里可能触发审核的词 ==

国内平台的关键词审核对这几类比较敏感：

    * 翻墙 / 代理 / VPN / 科学上网
    * 挖矿 / 矿机 / 算力 / 虚拟货币
    * 破解 / 破解版 / 盗版 / 激活工具
    * 外挂 / 作弊
    * 监控 / 偷拍 / 窃听 / 追踪（"监控"在教育场景容易误判）
    * 游戏相关的"封号""加速器"
    * 二维码 / 收款 / 打赏

这份 README 是"教室手表控电脑"，正常。但要确认没混进上面这些。
'''
from __future__ import annotations

import json
import re
import sys
import urllib.error
import urllib.request
from pathlib import Path

ROOT = Path(__file__).resolve().parent.parent
GITEE = "https://gitee.com/xmz7891/ykxmz"

RISKY = [
    "翻墙", "代理", "VPN", "vpn", "科学上网", "梯子", "加速器",
    "挖矿", "矿机", "算力", "比特币", "虚拟货币", "以太坊",
    "破解", "盗版", "激活工具", "注册机", "keygen", "crack",
    "外挂", "作弊", "开挂",
    "监控", "偷拍", "窃听", "追踪", "定位",
    "打赏", "收款", "二维码收款",
    "荷官", "博彩", "赌博",
]


def get(url: str, ua: str = "Mozilla/5.0") -> tuple:
    req = urllib.request.Request(url)
    req.add_header("User-Agent", ua)
    try:
        with urllib.request.urlopen(req, timeout=30) as r:
            return r.status, r.read().decode("utf-8", "replace")
    except urllib.error.HTTPError as exc:
        return exc.code, ""
    except Exception as exc:                              # noqa: BLE001
        return "失败", str(exc)[:60]


def main() -> int:
    print("=" * 62)
    print("  查 Gitee 为什么 451 + 扫 README 可疑词")
    print("=" * 62)

    print()
    print("  ── 1. 各入口的状态码 ──")
    for label, url in [
        ("仓库主页", GITEE),
        ("raw README", GITEE + "/raw/main/README.md"),
        ("raw LICENSE", GITEE + "/raw/main/LICENSE"),
        ("网页版 README", GITEE + "/blob/main/README.md"),
        ("发行版页", GITEE + "/releases"),
    ]:
        code, body = get(url)
        note = ""
        if isinstance(code, int):
            if code == 200:
                note = "正常"
            elif code == 451:
                note = "**被法律原因拦了**"
            elif code == 404:
                note = "不存在"
        print("    %-16s HTTP %-6s %s" % (label, code, note))

    print()
    print("  ── 2. 用 Gitee API 看仓库（API 走的是另一条路）──")
    token_file = ROOT / "_build" / ".gitee_token"
    if token_file.is_file():
        token = token_file.read_text(encoding="utf-8").strip()
        code, body = get(
            "https://gitee.com/api/v5/repos/xmz7891/ykxmz"
            "?access_token=%s" % token)
        print("    API 仓库信息 HTTP %s" % code)
        if code == 200:
            try:
                d = json.loads(body)
                print("      名称：%s" % d.get("name"))
                print("      是否私有：%s" % d.get("private"))
                print("      最近推送：%s" % d.get("pushed_at"))
            except Exception:                             # noqa: BLE001
                pass

    print()
    print("  ── 3. 扫 README 里的可疑词 ──")
    rm = ROOT / "README.md"
    text = rm.read_text(encoding="utf-8")
    lines = text.splitlines()
    hits = 0
    for word in RISKY:
        for i, line in enumerate(lines, 1):
            if word in line:
                hits += 1
                print("    %-10s 第 %d 行: %s"
                      % (word, i, line.strip()[:60]))
    if not hits:
        print("    ✅ 没扫到这些词")

    print()
    print("  ── 4. README 里的链接（外链也可能被拦）──")
    urls = re.findall(r"https?://[^\s\)\]\"'<>]+", text)
    seen = []
    for u in urls:
        host = re.sub(r"^https?://", "", u).split("/")[0]
        if host not in seen:
            seen.append(host)
    for h in seen:
        print("    %s" % h)

    print()
    print("  ── 5. 结论提示 ──")
    print("    如果只有 raw 是 451、主页 200，那就是**单个文件被拦**，")
    print("    通常改掉触发的措辞就能恢复。")
    print("    如果主页也 451，那是**整个仓库被限制**，得走 Gitee 申诉。")
    return 0


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