# -*- coding: utf-8 -*- """校验 Markdown 内部链接:目标文件是否存在、锚点是否命中。 Gitea 规则(实测): 标题 id = "user-content-" + anchor(标题原文) anchor = 小写,保留字母数字汉字与下划线,空格变 -,其余字符全删 同文件链接写 #anchor —— Gitea 渲染时自动补 user-content- 跨文件链接写 file.md#user-content-anchor —— Gitea 不补,必须手写 用法: python check_md_links.py <目录或文件> [更多...] """ import os import re import sys def anchor(title): out = [] for ch in title.lower(): if ch.isalnum() or ch == '_': out.append(ch) elif ch in ' \t': out.append('-') return ''.join(out) def read(p): with open(p, encoding='utf-8', newline='') as f: return f.read().replace('\r\n', '\n') def headings(txt): return [m.group(1).strip() for m in re.finditer(r'^#{1,6}\s+(.*)$', txt, re.M)] def collect(paths): files = [] for p in paths: if os.path.isdir(p): for fn in sorted(os.listdir(p)): if fn.endswith('.md'): files.append(os.path.join(p, fn)) else: files.append(p) return files LINK = re.compile(r'\[([^\]]*)\]\(([^)\s]+)\)') def main(paths): files = collect(paths) ids = {} for p in files: ids[os.path.abspath(p)] = {anchor(t) for t in headings(read(p))} bad = 0 total = 0 for p in files: base = os.path.dirname(p) txt = read(p) # 跳过围栏代码块中的链接 txt = re.sub(r'^```.*?^```', '', txt, flags=re.M | re.S) for text, target in LINK.findall(txt): if target.startswith(('http://', 'https://', 'mailto:')): continue total += 1 if '#' in target: tfile, frag = target.split('#', 1) else: tfile, frag = target, None tgt = os.path.abspath(os.path.join(base, tfile)) if tfile else os.path.abspath(p) tag = '%s -> %s' % (os.path.basename(p), target) if not os.path.exists(tgt): print(' ✗ 文件不存在 %s' % tag) bad += 1 continue if frag is None: continue pure = frag[len('user-content-'):] if frag.startswith('user-content-') else frag if pure not in ids.get(tgt, set()): print(' ✗ 锚点未命中 %s' % tag) bad += 1 print('检查 %d 个文件、%d 条内部链接,异常 %d 条' % (len(files), total, bad)) return 0 if bad == 0 else 1 if __name__ == '__main__': if len(sys.argv) < 2: raise SystemExit(__doc__) raise SystemExit(main(sys.argv[1:]))