""" 将 v2/main.md 转成 main.html。 特点： - 嵌套目录（可折叠/展开） - 主题切换（浅色/深色/护眼） - 字体缩放 - 响应式布局 - 百度统计 - 锚点跳转 """ import html import re from pathlib import Path ROOT = Path(r"E:\GitHub3\article\艺术理论\v2") SOURCE_MD = ROOT / "main.md" TARGET_HTML = ROOT / "main.html" def load_markdown(file_path: Path) -> list[str]: """读取 Markdown 文件并返回逐行文本。""" return file_path.read_text(encoding="utf-8").splitlines() def escape_html(text: str) -> str: """HTML 转义。""" return html.escape(text, quote=True) def format_inline(text: str) -> str: """处理行内链接、代码和加粗，避免正文中的特殊字符破坏 HTML。""" # 先用占位符保护代码块和图片 placeholders = {} def protect(pattern, key_prefix, text): def repl(m): key = f"@@{key_prefix}_{len(placeholders)}@@" placeholders[key] = m.group(0) return key return re.sub(pattern, repl, text) # 必须先保护图片（包含 ! 前缀），再保护链接（避免 LINK 误吞 IMG 的 [...]） # 保护图片 text = protect(r"!\[([^\]]*)\]\(([^)]+)\)", "IMG", text) # 保护链接 text = protect(r"\[([^\]]+)\]\(([^)]+)\)", "LINK", text) # 保护行内代码 text = protect(r"`([^`]+)`", "CODE", text) # 转义剩余 HTML 字符 text = escape_html(text) # 处理加粗（**xxx**） text = re.sub(r"\*\*([^*]+)\*\*", r"\1", text) # 处理斜体（*xxx* 或 _xxx_） text = re.sub(r"(?\1", text) # 还原占位符 def restore(m): key = m.group(0) original = placeholders.get(key, key) if original.startswith("[") and "](" in original: # 还原链接 link_match = re.match(r"\[([^\]]+)\]\(([^)]+)\)", original) if link_match: return f'{escape_html(link_match.group(1))}' elif original.startswith("`"): # 还原代码 code_match = re.match(r"`([^`]+)`", original) if code_match: return f"{escape_html(code_match.group(1))}" elif original.startswith("!["): # 还原图片 img_match = re.match(r"!\[([^\]]*)\]\(([^)]+)\)", original) if img_match: alt = escape_html(img_match.group(1)) src = escape_html(img_match.group(2)) # SVG 自动用 figure 包装 if src.lower().endswith(".svg"): return f'
{alt}{f"
{alt}
" if alt else ""}
' return f'{alt}' return escape_html(original) text = re.sub(r"@@[A-Z]+_\d+@@", restore, text) return text def heading_id(index: int) -> str: """生成稳定的标题锚点，便于页面内跳转。""" return f"heading-{index}" def is_table_separator(line: str) -> bool: """判断一行是否为 Markdown 表格的分隔线。""" compact = line.replace(" ", "") return bool(re.fullmatch(r"\|?[:\-|]+\|?", compact)) and "-" in compact def parse_table(lines: list[str], start: int) -> tuple[str, int]: """把连续的 Markdown 表格转换为 HTML。""" header_line = lines[start].strip() if start + 1 >= len(lines): return "", start separator_line = lines[start + 1].strip() if "|" not in header_line or not is_table_separator(separator_line): return "", start rows: list[list[str]] = [] index = start while index < len(lines): line = lines[index].strip() if "|" not in line or not line: break cells = [format_inline(cell.strip()) for cell in line.strip("|").split("|")] rows.append(cells) index += 1 if len(rows) < 2: return "", start header_cells = "".join(f"{cell}" for cell in rows[0]) body_rows = [] for row in rows[2:]: body_rows.append("" + "".join(f"{cell}" for cell in row) + "") table_html = ( "
" f"{header_cells}" f"{''.join(body_rows)}" "
" ) return table_html, index - 1 def build_article(lines: list[str]) -> tuple[str, list[dict], str]: """把 Markdown 正文转换为 HTML，并抽取页面标题和提纲。""" blocks: list[str] = [] outline: list[dict] = [] title = "艺术理论 v2" heading_count = 0 in_ul = False in_ol = False blockquote_lines: list[str] = [] def close_lists() -> None: nonlocal in_ul, in_ol if in_ul: blocks.append("") in_ul = False if in_ol: blocks.append("") in_ol = False def close_blockquote() -> None: nonlocal blockquote_lines if blockquote_lines: blocks.append("
" + "
".join(blockquote_lines) + "
") blockquote_lines = [] index = 0 while index < len(lines): raw = lines[index] line = raw.strip() if not line: close_lists() close_blockquote() index += 1 continue if line.startswith("> "): close_lists() blockquote_lines.append(format_inline(line[2:].strip())) index += 1 continue close_blockquote() # 表格 if index + 1 < len(lines): table_html, table_end = parse_table(lines, index) if table_html: close_lists() blocks.append(table_html) index = table_end + 1 continue # 标题 if line.startswith("# "): close_lists() heading_count += 1 anchor = heading_id(heading_count) heading = line[2:].strip() title = heading blocks.append(f"

{format_inline(heading)}

") outline.append({"level": 1, "title": heading, "id": anchor}) index += 1 continue if line.startswith("## "): close_lists() heading_count += 1 anchor = heading_id(heading_count) heading = line[3:].strip() blocks.append(f"

{format_inline(heading)}

") outline.append({"level": 2, "title": heading, "id": anchor}) index += 1 continue if line.startswith("### "): close_lists() heading_count += 1 anchor = heading_id(heading_count) heading = line[4:].strip() blocks.append(f"

{format_inline(heading)}

") outline.append({"level": 3, "title": heading, "id": anchor}) index += 1 continue if line.startswith("#### "): close_lists() heading_count += 1 anchor = heading_id(heading_count) heading = line[5:].strip() blocks.append(f"

{format_inline(heading)}

") outline.append({"level": 4, "title": heading, "id": anchor}) index += 1 continue # 任务列表或无序列表 if line.startswith("- ") or line.startswith("* "): if not in_ul: close_lists() blocks.append("