HTML naar Markdown converteren met Python: een uitgebreid overzicht

pip install html2text

import html2text

# Maak converterinstantie
h = html2text.HTML2Text()

# Configureer opties
h.ignore_links = False
h.ignore_images = False
h.ignore_emphasis = False
h.body_width = 0  # Geen lijnen omsluiten

html_content = """
<h1>Welkom bij web scraping</h1>
<p>Dit is een <strong>uitgebreide gids</strong> voor het extraheren van inhoud.</p>
<ul>
    <li>Eenvoudig te gebruiken</li>
    <li>Bewezen in de praktijk</li>
    <li Breed aangenomen</li>
</ul>
<a href="https://example.com">Meer informatie</a>
"""

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

# Welkom bij web scraping

Dit is een **uitgebreide gids** voor het extraheren van inhoud.

  * Eenvoudig te gebruiken
  * Bewezen in de praktijk
  * Breed aangenomen

[Meer informatie](https://example.com)

import html2text

h = html2text.HTML2Text()

# Overslaan van specifieke elementen
h.ignore_links = True
h.ignore_images = True

# Beheer opmaak
h.body_width = 80  # Omsluiten bij 80 tekens
h.unicode_snob = True  # Gebruik Unicode-tekens
h.emphasis_mark = '*'  # Gebruik * voor nadruk in plaats van _
h.strong_mark = '**'

# Beheer tabellen
h.ignore_tables = False

# Bescherm vooraf opgemaakte tekst
h.protect_links = True

pip install markdownify

from markdownify import markdownify as md

html = """
<article>
    <h2>Moderne webontwikkeling</h2>
    <p>Bouwen met <code>Python</code> en <em>moderne frameworks</em>.</p>
    <blockquote>
        <p>Eenvoud is de uiteindelijke sofisticatie.</p>
    </blockquote>
</article>
"""

markdown = md(html)
print(markdown)

## Moderne webontwikkeling

Bouwen met `Python` en *moderne frameworks*.

> Eenvoud is de uiteindelijke sofisticatie.

from markdownify import MarkdownConverter

class CustomConverter(MarkdownConverter):
    """
    Maak een aangepaste converter met specifieke tagbehandeling
    """
    def convert_img(self, el, text, convert_as_inline):
        """Aangepaste beeldhandler met alternatieve tekst"""
        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):
        """Versterkte codeblokbehandeling met taaldetectie"""
        code = el.find('code')
        if code:
            # Haal taal op uit class-attribuut (bijv. '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'

# Gebruik aangepaste converter
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

# Verwijder specifieke tags volledig
markdown = md(html, strip=['script', 'style', 'nav'])

# Converteer alleen specifieke tags
markdown = md(
    html,
    heading_style="ATX",  # Gebruik # voor koppen
    bullets="-",  # Gebruik - voor lijstitems
    strong_em_symbol="*",  # Gebruik * voor nadruk
)

pip install html-to-markdown

from html_to_markdown import convert

html = """
<article>
    <h1>Tech-documentatie</h1>
    <table>
        <thead>
            <tr>
                <th>Kenmerk</th>
                <th>Ondersteuning</th>
            </tr>
        </thead>
        <tbody>
            <tr>
                <td>HTML5</td>
                <td>✓</td>
            </tr>
            <tr>
                <td>Tabellen</td>
                <td>✓</td>
            </tr>
        </tbody>
    </table>
</article>
"""

markdown = convert(html)
print(markdown)

from html_to_markdown import convert, Options

# Maak aangepaste opties
opties = Options(
    heading_style="ATX",
    bullet_style="-",
    code_language_default="python",
    strip_tags=["script", "style"],
    escape_special_chars=True,
    table_style="pipe",  # Gebruik | voor tabellen
    preserve_whitespace=False,
    extract_metadata=True,  # Metadata extraheren
)

markdown = convert(html, opties=opties)

# Converteer enkel bestand
html-to-markdown input.html -o output.md

# Converteer met opties
html-to-markdown input.html \
    --heading-style atx \
    --strip-tags script,style \
    --extract-metadata

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

pip install trafilatura

import trafilatura

# Download en extraheren van URL
url = "https://example.com/artikel"
downloaded = trafilatura.fetch_url(url)
markdown = trafilatura.extract(downloaded, output_format='markdown')
print(markdown)

import trafilatura
from trafilatura.settings import use_config

# Maak aangepaste configuratie
config = use_config()
config.set("DEFAULT", "EXTRACTION_TIMEOUT", "30")

html = """
<html>
<head><title>Artikel Titel</title></head>
<body>
    <nav>Navigatiemenu</nav>
    <article>
        <h1>Hoofdartikel</h1>
        <p>Belangrijke inhoud hier.</p>
    </article>
    <aside>Reclame</aside>
    <footer>Voettekst</footer>
</body>
</html>
"""

# Extraheren van alleen hoofdinhoud
markdown = trafilatura.extract(
    html,
    output_format='markdown',
    include_comments=False,
    include_tables=True,
    include_images=True,
    include_links=True,
    config=config
)

# Extraheren met metadata
result = trafilatura.extract(
    html,
    output_format='markdown',
    with_metadata=True
)

if result:
    print(f"Titel: {result.get('title', 'N/A')}")
    print(f"Auteur: {result.get('author', 'N/A')}")
    print(f"Datum: {result.get('date', 'N/A')}")
    print(f"\nInhoud:\n{result.get('text', '')}")

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

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

# Verwerk meerdere URLs parallel
urls = [
    "https://example.com/artikel1",
    "https://example.com/artikel2",
    "https://example.com/artikel3",
]

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

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

pip install domscribe

from domscribe import html_to_markdown

html = """
<article>
    <header>
        <h1>Verstaan van semantische HTML</h1>
        <time datetime="2024-10-24">Oktober 24, 2024</time>
    </header>
    <section>
        <h2>Inleiding</h2>
        <p>Semantische HTML geeft <mark>betekenis</mark> aan inhoud.</p>
    </section>
    <aside>
        <h3>Gerelateerde onderwerpen</h3>
        <ul>
            <li>Toegankelijkheid</li>
            <li>SEO</li>
        </ul>
    </aside>
</article>
"""

markdown = html_to_markdown(html)
print(markdown)

from domscribe import html_to_markdown, MarkdownOptions

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

markdown = html_to_markdown(html, opties=opties)

pip install html2md

# Converteer hele map
m1f-html2md convert ./website -o ./docs

# Met aangepaste instellingen
m1f-html2md convert ./website -o ./docs \
    --remove-tags nav,footer \
    --heading-offset 1 \
    --detect-language

# Converteer enkel bestand
m1f-html2md convert index.html -o readme.md

import asyncio
from html2md import convert_html

async def convert_files():
    """Asynchrone batchconversie"""
    html_files = [
        'page1.html',
        'page2.html',
        'page3.html'
    ]

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

# Voer conversie uit
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):
    """Benchmark conversiesnelheid"""

    # 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': html2线时间,
        '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):
    """Converteer HTML-bestand naar markdown"""
    html = Path(html_path).read_text(encoding='utf-8')
    markdown = trafilatura.extract(
        html,
        output_format='markdown',
        include_links=False,  # Verwijderen voor schoner trainingdata
        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

# Verwerk 10.000 bestanden parallel
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"Verwerkt {len(html_files)} bestanden")
print(f"Totaal aantal tekens: {sum(token_counts):,}")

# Converteer alle berichten met frontmatter
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):
    """Converteer WordPress HTML naar Hugo markdown"""
    html = Path(html_file).read_text()

    # Extraheren van titel en datum uit HTML
    from bs4 import BeautifulSoup
    soup = BeautifulSoup(html, 'html.parser')
    title = soup.find('h1').get_text() if soup.find('h1') else 'Ongetiteld'

    # Converteer naar markdown
    opties = Options(strip_tags=['script', 'style', 'nav', 'footer'])
    markdown = convert(html, opties=opties)

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

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

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

# Verwerk alle berichten
for html_file in Path('./wordpress-export').glob('*.html'):
    migrate_post(html_file)

from markdownify import MarkdownConverter
import requests

class DocsConverter(MarkdownConverter):
    """Aangepaste converter voor technische documentatie"""

    def convert_pre(self, el, text, convert_as_inline):
        """Versterkte codeblok met syntaxismarkering"""
        code = el.find('code')
        if code:
            # Haal taal op uit class
            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):
        """Beheer speciale documentatieblokken"""
        classes = el.get('class', [])

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

        # Info-blokken
        if 'info' in classes or 'note' in classes:
            return f'\n> 💡 **Opmerking**: {text}\n'

        return text

def scrape_docs(url):
    """Scrapen en converteren van documentatiepagina"""
    response = requests.get(url)
    markdown = DocsConverter().convert(response.text)
    return markdown

# Gebruik
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):
    """Converteer HTML-e-mail naar markdown"""
    # Parse e-mail
    with open(email_file, 'r') as f:
        msg = email.message_from_file(f)

    # Haal HTML-deel op
    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

    # Configureer converter
    h = html2text.HTML2Text()
    h.ignore_images = False
    h.images_to_alt = True
    h.body_width = 0
    h.protect_links = True
    h.unicode_snob = True

    # Converteer
    markdown = h.handle(html_content)

    # Voeg metadata toe
    subject = msg.get('Subject', 'Geen onderwerp')
    date = msg.get('Date', '')

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

    return output

# Verwerk nieuwsbriefarchief
for email_file in Path('./nieuwsbrieven').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):
    """Verwijder ongewenste elementen voor het converteren"""
    soup = BeautifulSoup(html, 'html.parser')

    # Verwijder ongewenste elementen
    for element in soup(['script', 'style', 'nav', 'footer', 'header', 'aside']):
        element.decompose()

    # Verwijder advertenties en tracking
    for element in soup.find_all(class_=['ad', 'advertisement', 'tracking']):
        element.decompose()

    # Converteer de gereinigde HTML
    markdown = trafilatura.extract(
        str(soup),
        output_format='markdown'
    )

    return markdown

import re

def normalize_markdown(markdown):
    """Reinig de markdown-ruimte"""
    # Verwijder meerdere lege regels
    markdown = re.sub(r'\n{3,}', '\n\n', markdown)

    # Verwijder achterliggende witruimte
    markdown = '\n'.join(line.rstrip() for line in markdown.split('\n'))

    # Zorg voor één nieuwe regel aan het einde
    markdown = markdown.rstrip() + '\n'

    return markdown

def validate_markdown(markdown):
    """Valideer de kwaliteit van de markdown"""
    issues = []

    # Controleer op resterende HTML
    if '<' in markdown and '>' in markdown:
        issues.append("HTML-tags gedetecteerd")

    # Controleer op gebroken links
    if '[' in markdown and ']()' in markdown:
        issues.append("Lege link gedetecteerd")

    # Controleer op te veel codeblokken
    code_block_count = markdown.count('```')
    if code_block_count % 2 != 0:
        issues.append("Niet gesloten codeblok")

    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):
    """Verwerk een enkel HTML-bestand"""
    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:
            # Normaliseer
            markdown = normalize_markdown(markdown)

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

            # Sla op
            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"Fout bij het verwerken van {html_path}: {e}")
        return False

def batch_convert(input_dir, max_workers=4):
    """Converteer alle HTML-bestanden in een map"""
    html_files = list(Path(input_dir).rglob('*.html'))
    logger.info(f"Gevonden {len(html_files)} HTML-bestanden")

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

    success_count = sum(results)
    logger.info(f"Met succes geconverteerd {success_count}/{len(html_files)} bestanden")

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