Python将Markdown批量转为HTML的两大实现方案

pip install Spire.Doc

from spire.doc import *

doc = Document()
doc.LoadFromFile("example.md", FileFormat.Markdown)
doc.SaveToFile("example.html", FileFormat.Html)
doc.Close()

import os
from spire.doc import *

input_folder = "markdown_files"
output_folder = "html_files"

os.makedirs(output_folder, exist_ok=True)

for filename in os.listdir(input_folder):
    if filename.endswith(".md"):
        doc = Document()
        doc.LoadFromFile(os.path.join(input_folder, filename), FileFormat.Markdown)
        output_path = os.path.join(output_folder, filename.replace(".md", ".html"))
        doc.SaveToFile(output_path, FileFormat.Html)
        doc.Close()

from pathlib import Path
import markdown
src_dir = Path("docs_md")
out_dir = Path("docs_html")
out_dir.mkdir(exist_ok=True)
for md_file in src_dir.glob("*.md"):
    md_text = md_file.read_text(encoding="utf-8")
    html_body = markdown.markdown(md_text)
    (out_dir / f"{md_file.stem}.html").write_text(html_body, encoding="utf-8")

from pathlib import Path
import markdown
SRC = Path("docs_md")
OUT = Path("docs_html")
TEMPLATE = """<!DOCTYPE html>
<html lang="zh-CN">
<head>
<meta charset="UTF-8">
<title>{title}</title>
<style>
body {{ max-width: 860px; margin: 2rem auto; padding: 0 1rem;
       font-family: system-ui, sans-serif; line-height: 1.7; }}
pre {{ background: #f5f5f5; padding: 1rem; overflow-x: auto; }}
table {{ border-collapse: collapse; width: 100%; }}
th, td {{ border: 1px solid #ddd; padding: 6px 10px; }}
</style>
</head>
<body>{body}</body>
</html>"""
def convert_one(md_path: Path) -> None:
    md_text = md_path.read_text(encoding="utf-8")
    html_body = markdown.markdown(
        md_text,
        extensions=["tables", "fenced_code", "codehilite", "toc", "sane_lists"],
        extension_configs={
            "codehilite": {"guess_lang": False, "css_class": "codehilite"}
        },
    )
    html = TEMPLATE.format(title=md_path.stem, body=html_body)
    (OUT / f"{md_path.stem}.html").write_text(html, encoding="utf-8")
OUT.mkdir(exist_ok=True)
for f in SRC.rglob("*.md"):          # rglob 递归子目录
    convert_one(f)

from pathlib import Path
import markdown
SRC = Path("docs_md")
OUT = Path("docs_html")
def convert_tree(src: Path, out: Path):
    for md_file in src.rglob("*.md"):
        rel = md_file.relative_to(src)              # 保留相对路径
        target = (out / rel).with_suffix(".html")
        target.parent.mkdir(parents=True, exist_ok=True)
        md_text = md_file.read_text(encoding="utf-8")
        html_body = markdown.markdown(
            md_text,
            extensions=["tables", "fenced_code", "toc", "sane_lists"],
        )
        full = f"<!DOCTYPE html><html><head><meta charset='UTF-8'>" \
               f"<title>{md_file.stem}</title></head><body>{html_body}</body></html>"
        target.write_text(full, encoding="utf-8")
        print(f"✓ {md_file} -> {target}")
convert_tree(SRC, OUT)

from concurrent.futures import ProcessPoolExecutor
from pathlib import Path
import markdown
SRC, OUT = Path("docs_md"), Path("docs_html")
def convert(md_file: Path):
    rel = md_file.relative_to(SRC).with_suffix(".html")
    target = OUT / rel
    target.parent.mkdir(parents=True, exist_ok=True)
    md_text = md_file.read_text(encoding="utf-8")
    html = markdown.markdown(md_text, extensions=["tables", "fenced_code", "toc"])
    target.write_text(html, encoding="utf-8")
    return str(target)
if __name__ == "__main__":          # 多进程必须放在 main 保护下
    files = list(SRC.rglob("*.md"))
    with ProcessPoolExecutor() as pool:
        for result in pool.map(convert, files):
            print("done:", result)