guanlan-src/_修复记录_20260911/scan_portal_links.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""全量核查 portal.html 里指向本机静态件的引用 (含相对写法), 找出同类"交付件没随包"的坏链。"""
import pathlib
import re
import urllib.error
import urllib.parse
import urllib.request

REL = pathlib.Path(r"F:\temp\guanlan-rudong-v2_0.2.0\release")
html = (REL / "portal.html").read_text(encoding="utf-8", errors="replace")

# 所有 href/src 里含 如东 或 release 的
cand = set()
for m in re.finditer(r'(?:href|src)="([^"]+)"', html):
    u = m.group(1)
    if ("如东" in u or "/release" in u or "release/" in u) and not u.startswith(("mailto:", "javascript:")):
        cand.add(u)
print(f"候选引用 {len(cand)} 个\n")


def check(u: str):
    if u.startswith("http"):
        full = u
    else:
        base = "http://127.0.0.1:28084/" if u.startswith("/") else "http://127.0.0.1:28084/"
        full = base + u.lstrip("/")
    p = urllib.parse.urlsplit(full)
    full = urllib.parse.urlunsplit((p.scheme, p.netloc, urllib.parse.quote(p.path), p.query, ""))
    try:
        with urllib.request.urlopen(full, timeout=30) as r:
            r.read(1)
            return r.status
    except urllib.error.HTTPError as e:
        return e.code
    except Exception as e:
        return f"{e.__class__.__name__}"


bad = []
for u in sorted(cand):
    s = check(u)
    tag = "ok  " if s == 200 else "BAD "
    if s != 200:
        bad.append(u)
    print(f"  [{s}] {tag} {u}")

print(f"\n坏链 {len(bad)} 个")
for u in bad:
    print("   - " + u)