使用 Python 将 HTML 转换为 Markdown：全面指南

pip install html2text

import html2text

# 创建转换器实例
h = html2text.HTML2Text()

# 配置选项
h.ignore_links = False
h.ignore_images = False
h.ignore_emphasis = False
h.body_width = 0  # 不换行

html_content = """
<h1>Welcome to Web Scraping</h1>
<p>This is a <strong>comprehensive guide</strong> to extracting content.</p>
<ul>
    <li>Easy to use</li>
    <li>Battle-tested</li>
    <li>Widely adopted</li>
</ul>
<a href="https://example.com">Learn more</a>
"""

markdown = h.handle(html_content)
print(markdown)

# Welcome to Web Scraping

This is a **comprehensive guide** to extracting content.

  * Easy to use
  * Battle-tested
  * Widely adopted

[Learn more](https://example.com)

import html2text

h = html2text.HTML2Text()

# 忽略特定元素
h.ignore_links = True
h.ignore_images = True

# 控制格式
h.body_width = 80  # 在80个字符处换行
h.unicode_snob = True  # 使用Unicode字符
h.emphasis_mark = '*'  # 使用*表示强调而不是_
h.strong_mark = '**'

# 处理表格
h.ignore_tables = False

# 保护预格式文本
h.protect_links = True

pip install markdownify

from markdownify import markdownify as md

html = """
<article>
    <h2>Modern Web Development</h2>
    <p>Building with <code>Python</code> and <em>modern frameworks</em>.</p>
    <blockquote>
        <p>Simplicity is the ultimate sophistication.</p>
    </blockquote>
</article>
"""

markdown = md(html)
print(markdown)

## Modern Web Development

Building with `Python` and *modern frameworks*.

> Simplicity is the ultimate sophistication.

from markdownify import MarkdownConverter

class CustomConverter(MarkdownConverter):
    """
    创建具有特定标签处理的自定义转换器
    """
    def convert_img(self, el, text, convert_as_inline):
        """自定义图像处理程序，带有替代文本"""
        alt = el.get('alt', '')
        src = el.get('src', '')
        title = el.get('title', '')

        if title:
            return f'![{alt}]({src} "{title}")'
        return f'![{alt}]({src})'

    def convert_pre(self, el, text, convert_as_inline):
        """增强代码块处理，带有语言检测"""
        code = el.find('code')
        if code:
            # 从类属性中提取语言（例如，'language-python'）
            classes = code.get('class', [''])
            language = classes[0].replace('language-', '') if classes else ''
            return f'\n```{language}\n{code.get_text()}\n```\n'
        return f'\n```\n{text}\n```\n'

# 使用自定义转换器
html = '<pre><code class="language-python">def hello():\n    print("world")</code></pre>'
markdown = CustomConverter().convert(html)
print(markdown)

from markdownify import markdownify as md

# 完全删除特定标签
markdown = md(html, strip=['script', 'style', 'nav'])

# 仅转换特定标签
markdown = md(
    html,
    heading_style="ATX",  # 使用#表示标题
    bullets="-",  # 使用-表示项目符号
    strong_em_symbol="*",  # 使用*表示强调
)

pip install html-to-markdown

from html_to_markdown import convert

html = """
<article>
    <h1>Technical Documentation</h1>
    <table>
        <thead>
            <tr>
                <th>Feature</th>
                <th>Support</th>
            </tr>
        </thead>
        <tbody>
            <tr>
                <td>HTML5</td>
                <td>✓</td>
            </tr>
            <tr>
                <td>Tables</td>
                <td>✓</td>
            </tr>
        </tbody>
    </table>
</article>
"""

markdown = convert(html)
print(markdown)

from html_to_markdown import convert, Options

# 创建自定义选项
options = Options(
    heading_style="ATX",
    bullet_style="-",
    code_language_default="python",
    strip_tags=["script", "style"],
    escape_special_chars=True,
    table_style="pipe",  # 使用|表示表格
    preserve_whitespace=False,
    extract_metadata=True,  # 提取元标签
)

markdown = convert(html, options=options)

# 转换单个文件
html-to-markdown input.html -o output.md

# 使用选项转换
html-to-markdown input.html \
    --heading-style atx \
    --strip-tags script,style \
    --extract-metadata

# 批量转换
find ./html_files -name "*.html" -exec html-to-markdown {} -o ./markdown_files/{}.md \;

pip install trafilatura

import trafilatura

# 从URL下载并提取
url = "https://example.com/article"
downloaded = trafilatura.fetch_url(url)
markdown = trafilatura.extract(downloaded, output_format='markdown')
print(markdown)

import trafilatura
from trafilatura.settings import use_config

# 创建自定义配置
config = use_config()
config.set("DEFAULT", "EXTRACTION_TIMEOUT", "30")

html = """
<html>
<head><title>Article Title</title></head>
<body>
    <nav>导航菜单</nav>
    <article>
        <h1>主文章</h1>
        <p>重要内容在这里。</p>
    </article>
    <aside>广告</aside>
    <footer>页脚内容</footer>
</body>
</html>
"""

# 仅提取主要内容
markdown = trafilatura.extract(
    html,
    output_format='markdown',
    include_comments=False,
    include_tables=True,
    include_images=True,
    include_links=True,
    config=config
)

# 带元数据提取
result = trafilatura.extract(
    html,
    output_format='markdown',
    with_metadata=True
)

if result:
    print(f"标题: {result.get('title', 'N/A')}")
    print(f"作者: {result.get('author', 'N/A')}")
    print(f"日期: {result.get('date', 'N/A')}")
    print(f"\n内容:\n{result.get('text', '')}")

import trafilatura
from concurrent.futures import ThreadPoolExecutor
from pathlib import Path

def process_url(url):
    """从URL提取Markdown"""
    downloaded = trafilatura.fetch_url(url)
    if downloaded:
        return trafilatura.extract(
            downloaded,
            output_format='markdown',
            include_links=True,
            include_images=True
        )
    return None

# 并行处理多个URL
urls = [
    "https://example.com/article1",
    "https://example.com/article2",
    "https://example.com/article3",
]

with ThreadPoolExecutor(max_workers=5) as executor:
    results = list(executor.map(process_url, urls))

for i, markdown in enumerate(results):
    if markdown:
        Path(f"article_{i}.md").write_text(markdown, encoding='utf-8')

pip install domscribe

from domscribe import html_to_markdown

html = """
<article>
    <header>
        <h1>理解语义HTML</h1>
        <time datetime="2024-10-24">2024年10月24日</time>
    </header>
    <section>
        <h2>简介</h2>
        <p>语义HTML为内容提供<mark>意义</mark>。</p>
    </section>
    <aside>
        <h3>相关主题</h3>
        <ul>
            <li>无障碍</li>
            <li>SEO</li>
        </ul>
    </aside>
</article>
"""

markdown = html_to_markdown(html)
print(markdown)

from domscribe import html_to_markdown, MarkdownOptions

options = MarkdownOptions(
    preserve_semantic_structure=True,
    include_aria_labels=True,
    strip_empty_elements=True
)

markdown = html_to_markdown(html, options=options)

pip install html2md

# 转换整个目录
m1f-html2md convert ./website -o ./docs

# 使用自定义设置
m1f-html2md convert ./website -o ./docs \
    --remove-tags nav,footer \
    --heading-offset 1 \
    --detect-language

# 转换单个文件
m1f-html2md convert index.html -o readme.md

import asyncio
from html2md import convert_html

async def convert_files():
    """异步批量转换"""
    html_files = [
        'page1.html',
        'page2.html',
        'page3.html'
    ]

    tasks = [convert_html(file) for file in html_files]
    results = await asyncio.gather(*tasks)
    return results

# 运行转换
results = asyncio.run(convert_files())

import time
import html2text
from markdownify import markdownify
from html_to_markdown import convert
import trafilatura

def benchmark(html_content, iterations=100):
    """基准测试转换速度"""

    # html2text
    start = time.time()
    h = html2text.HTML2Text()
    for _ in range(iterations):
        _ = h.handle(html_content)
    html2text_time = time.time() - start

    # markdownify
    start = time.time()
    for _ in range(iterations):
        _ = markdownify(html_content)
    markdownify_time = time.time() - start

    # html-to-markdown
    start = time.time()
    for _ in range(iterations):
        _ = convert(html_content)
    html_to_markdown_time = time.time() - start

    # trafilatura
    start = time.time()
    for _ in range(iterations):
        _ = trafilatura.extract(html_content, output_format='markdown')
    trafilatura_time = time.time() - start

    return {
        'html2text': html2text_time,
        'markdownify': markdownify_time,
        'html-to-markdown': html_to_markdown_time,
        'trafilatura': trafilatura_time
    }

import trafilatura
from pathlib import Path
from concurrent.futures import ProcessPoolExecutor

def process_html_file(html_path):
    """将 HTML 文件转换为 markdown"""
    html = Path(html_path).read_text(encoding='utf-8')
    markdown = trafilatura.extract(
        html,
        output_format='markdown',
        include_links=False,  # 为更干净的训练数据移除
        include_images=False,
        include_comments=False
    )

    if markdown:
        output_path = html_path.replace('.html', '.md')
        Path(output_path).write_text(markdown, encoding='utf-8')
        return len(markdown)
    return 0

# 并行处理 10,000 个文件
html_files = list(Path('./docs').rglob('*.html'))

with ProcessPoolExecutor(max_workers=8) as executor:
    token_counts = list(executor.map(process_html_file, html_files))

print(f"已处理 {len(html_files)} 个文件")
print(f"总字符数: {sum(token_counts):,}")

# 转换所有包含 frontmatter 的文章
m1f-html2md convert ./wordpress-export \
    -o ./hugo/content/posts \
    --generate-frontmatter \
    --heading-offset 0 \
    --remove-tags script,style,nav,footer

from html_to_markdown import convert, Options
from pathlib import Path
import yaml

def migrate_post(html_file):
    """将 WordPress HTML 转换为 Hugo markdown"""
    html = Path(html_file).read_text()

    # 从 HTML 中提取标题和日期
    from bs4 import BeautifulSoup
    soup = BeautifulSoup(html, 'html.parser')
    title = soup.find('h1').get_text() if soup.find('h1') else 'Untitled'

    # 转换为 markdown
    options = Options(strip_tags=['script', 'style', 'nav', 'footer'])
    markdown = convert(html, options=options)

    # 添加 Hugo frontmatter
    frontmatter = {
        'title': title,
        'date': '2024-10-24',
        'draft': False,
        'tags': []
    }

    output = f"---\n{yaml.dump(frontmatter)}---\n\n{markdown}"

    # 保存
    output_file = html_file.replace('.html', '.md')
    Path(output_file).write_text(output, encoding='utf-8')

# 处理所有文章
for html_file in Path('./wordpress-export').glob('*.html'):
    migrate_post(html_file)

from markdownify import MarkdownConverter
import requests

class DocsConverter(MarkdownConverter):
    """用于技术文档的自定义转换器"""

    def convert_pre(self, el, text, convert_as_inline):
        """增强的代码块，带语法高亮"""
        code = el.find('code')
        if code:
            # 从类中提取语言
            classes = code.get('class', [])
            language = next(
                (c.replace('language-', '') for c in classes if c.startswith('language-')),
                'text'
            )
            return f'\n```{language}\n{code.get_text()}\n```\n'
        return super().convert_pre(el, text, convert_as_inline)

    def convert_div(self, el, text, convert_as_inline):
        """处理特殊文档块"""
        classes = el.get('class', [])

        # 警告块
        if 'warning' in classes:
            return f'\n> ⚠️ **警告**: {text}\n'

        # 信息块
        if 'info' in classes or 'note' in classes:
            return f'\n> 💡 **提示**: {text}\n'

        return text

def scrape_docs(url):
    """抓取并转换文档页面"""
    response = requests.get(url)
    markdown = DocsConverter().convert(response.text)
    return markdown

# 使用它
docs_url = "https://docs.example.com/api-reference"
markdown = scrape_docs(docs_url)
Path('api-reference.md').write_text(markdown)

import html2text
import email
from pathlib import Path

def convert_newsletter(email_file):
    """将 HTML 电子邮件转换为 markdown"""
    # 解析电子邮件
    with open(email_file, 'r') as f:
        msg = email.message_from_file(f)

    # 获取 HTML 部分
    html_content = None
    for part in msg.walk():
        if part.get_content_type() == 'text/html':
            html_content = part.get_payload(decode=True).decode('utf-8')
            break

    if not html_content:
        return None

    # 配置转换器
    h = html2text.HTML2Text()
    h.ignore_images = False
    h.images_to_alt = True
    h.body_width = 0
    h.protect_links = True
    h.unicode_snob = True

    # 转换
    markdown = h.handle(html_content)

    # 添加元数据
    subject = msg.get('Subject', '无标题')
    date = msg.get('Date', '')

    output = f"# {subject}\n\n*日期: {date}*\n\n---\n\n{markdown}"

    return output

# 处理新闻通讯归档
for email_file in Path('./newsletters').glob('*.eml'):
    markdown = convert_newsletter(email_file)
    if markdown:
        output_file = email_file.with_suffix('.md')
        output_file.write_text(markdown, encoding='utf-8')

from bs4 import BeautifulSoup
import trafilatura

def clean_and_convert(html):
    """在转换前移除不需要的元素"""
    soup = BeautifulSoup(html, 'html.parser')

    # 移除不需要的元素
    for element in soup(['script', 'style', 'nav', 'footer', 'header', 'aside']):
        element.decompose()

    # 移除广告和跟踪
    for element in soup.find_all(class_=['ad', 'advertisement', 'tracking']):
        element.decompose()

    # 转换清理后的 HTML
    markdown = trafilatura.extract(
        str(soup),
        output_format='markdown'
    )

    return markdown

import re

def normalize_markdown(markdown):
    """清理 markdown 空格"""
    # 移除多个空行
    markdown = re.sub(r'\n{3,}', '\n\n', markdown)

    # 移除尾随空格
    markdown = '\n'.join(line.rstrip() for line in markdown.split('\n'))

    # 确保结尾只有一个换行
    markdown = markdown.rstrip() + '\n'

    return markdown

def validate_markdown(markdown):
    """验证 markdown 质量"""
    issues = []

    # 检查是否有 HTML 残留
    if '<' in markdown and '>' in markdown:
        issues.append("检测到 HTML 标签")

    # 检查是否有损坏的链接
    if '[' in markdown and ']()' in markdown:
        issues.append("检测到空链接")

    # 检查是否有过多的代码块
    code_block_count = markdown.count('```')
    if code_block_count % 2 != 0:
        issues.append("未闭合的代码块")

    return len(issues) == 0, issues

from pathlib import Path
from concurrent.futures import ProcessPoolExecutor
import trafilatura
import logging

logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

def process_file(html_path):
    """处理单个 HTML 文件"""
    try:
        html = Path(html_path).read_text(encoding='utf-8')
        markdown = trafilatura.extract(
            html,
            output_format='markdown',
            include_links=True,
            include_images=False
        )

        if markdown:
            # 规范化
            markdown = normalize_markdown(markdown)

            # 验证
            is_valid, issues = validate_markdown(markdown)
            if not is_valid:
                logger.warning(f"{html_path}: {', '.join(issues)}")

            # 保存
            output_path = Path(str(html_path).replace('.html', '.md'))
            output_path.write_text(markdown, encoding='utf-8')

            return True

        return False

    except Exception as e:
        logger.error(f"处理 {html_path} 时出错: {e}")
        return False

def batch_convert(input_dir, max_workers=4):
    """转换目录中的所有 HTML 文件"""
    html_files = list(Path(input_dir).rglob('*.html'))
    logger.info(f"找到 {len(html_files)} 个 HTML 文件")

    with ProcessPoolExecutor(max_workers=max_workers) as executor:
        results = list(executor.map(process_file, html_files))

    success_count = sum(results)
    logger.info(f"成功转换了 {success_count}/{len(html_files)} 个文件")

# 使用
batch_convert('./html_docs', max_workers=8)