Python HTML to PDF Code Examples

Complete Python examples for common HTML to PDF tasks. See the Python SDK guide for installation and result handling.

You can run the examples below with the displayed API credentials. Update the input URLs and filenames as needed. Each Python example can be copied and run independently.

Basic examples

Choose file, in-memory, or output-stream handling for the result. Stream examples use a file stream as their destination.

Convert a URL

Save to a file

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setContentViewportWidth('balanced')
client.convertUrlToFile('https://example.com/', 'example.pdf')

Keep in memory

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setContentViewportWidth('balanced')
pdf = client.convertUrl('https://example.com/')  # bytes
print(len(pdf))

Write to a stream

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setContentViewportWidth('balanced')
with open('example.pdf', 'wb') as output_stream:
    client.convertUrlToStream('https://example.com/', output_stream)

Convert an HTML file

Upload an existing document.html file. For local images and stylesheets, see Local assets.

Save to a file

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setContentViewportWidth('balanced')
client.convertFileToFile('document.html', 'document.pdf')

Keep in memory

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setContentViewportWidth('balanced')
pdf = client.convertFile('document.html')  # bytes
print(len(pdf))

Write to a stream

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setContentViewportWidth('balanced')
with open('document.pdf', 'wb') as output_stream:
    client.convertFileToStream('document.html', output_stream)

Send HTML content

These examples read HTML text from document.html. In an application, pass the HTML produced by your template renderer instead.

Save to a file

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setContentViewportWidth('balanced')
with open('document.html', encoding='utf-8') as html_file:
    html = html_file.read()
client.convertStringToFile(html, 'html.pdf')

Keep in memory

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setContentViewportWidth('balanced')
with open('document.html', encoding='utf-8') as html_file:
    html = html_file.read()
pdf = client.convertString(html)  # bytes
print(len(pdf))

Write to a stream

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setContentViewportWidth('balanced')
with open('document.html', encoding='utf-8') as html_file:
    html = html_file.read()
with open('html.pdf', 'wb') as output_stream:
    client.convertStringToStream(html, output_stream)

Convert inline HTML

Define a small HTML document directly in your code.

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

html = """
    <!doctype html>
    <html><body><h1>Monthly report</h1></body></html>"""

client.setContentViewportWidth("balanced")
client.convertStringToFile(html, 'report.pdf')

Read from an input stream

Open document.html as a binary input stream and save the PDF to document.pdf.

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setContentViewportWidth('balanced')
with open('document.html', 'rb') as input_stream:
    client.convertStreamToFile(input_stream, 'document.pdf')

Local assets

Include HTML and its local images, stylesheets, and scripts in a ZIP archive, keeping their relative paths.

Convert a prepared archive

Upload an existing document.zip. Select the main HTML file explicitly when the archive contains multiple documents.

Detect the main HTML file

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setContentViewportWidth('balanced')
client.convertFileToFile('document.zip', 'output.pdf')

Select index.html

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setContentViewportWidth('balanced')
client.setZipMainFilename('index.html')
client.convertFileToFile('document.zip', 'document.pdf')

Convert a local directory

Create document.zip from the existing document directory, then convert it to PDF.

import shutil
import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

archive = shutil.make_archive("document", "zip", root_dir='document')
client.setContentViewportWidth("balanced")
client.convertFileToFile(archive, 'document.pdf')

Create an archive in memory

Package the existing document directory in memory. Its index.html file can refer to other files in the directory by relative path.

import io
from pathlib import Path
import zipfile
import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setContentViewportWidth("balanced")
client.setZipMainFilename("index.html")
directory = Path('document')

with io.BytesIO() as archive:
    with zipfile.ZipFile(archive, "w", zipfile.ZIP_DEFLATED) as zip_file:
        for path in sorted(directory.rglob("*")):
            if path.is_file():
                zip_file.write(path, path.relative_to(directory).as_posix())
    archive.seek(0)
    with open('document.pdf', "wb") as output_stream:
        client.convertStreamToStream(archive, output_stream)

Page rendering

Set page size and margins

Use landscape Letter pages with half-inch margins.

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setContentViewportWidth('balanced')
client.setMarginBottom('0.5in')
client.setMarginLeft('0.5in')
client.setMarginRight('0.5in')
client.setMarginTop('0.5in')
client.setOrientation('landscape')
client.setPageSize('Letter')
client.convertUrlToFile('https://example.com/', 'page-layout.pdf')

Add a header and page numbers

Show the source URL in the header and “Page N of M” in the footer.

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setFooterHeight('10mm')
client.setFooterHtml("""
    <center>
        Page <span class=\"pdfcrowd-page-number\"></span>
        of <span class=\"pdfcrowd-page-count\"></span>
    </center>""")
client.setHeaderHeight('15mm')
client.setHeaderHtml("""
    <a class=\"pdfcrowd-source-url\"
        data-pdfcrowd-placement=\"href-and-content\"></a>""")
client.setMarginBottom('0')
client.setMarginTop('0')
client.convertUrlToFile('https://example.com/', 'header_footer.pdf')

See the headers and footers guide for more layouts and placeholders.

Scale page content

Scale the HTML content to 300%.

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setScaleFactor(300)
client.convertUrlToFile('https://example.com/', 'zoom_300.pdf')

Choose a responsive layout

The browser viewport controls responsive breakpoints independently of the PDF paper size.

Large viewport

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setContentViewportWidth('large')
client.setNoMargins(True)
client.convertUrlToFile('https://example.com/', 'bootstrap.pdf')

Small viewport

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setContentViewportWidth('small')
client.convertUrlToFile('https://example.com/', 'viewport_small.pdf')

Hide or restyle page elements

Replace the selectors with elements from your page.

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setContentViewportWidth('balanced')
client.setCustomCss("""
    /* Hide navigation, ads, and sidebar */
    nav, .advertisement, .sidebar, footer {
        display: none !important;
    }
    /* Adjust layout for print */
    .content {
        width: 100% !important;
        max-width: none !important;
    }""")
client.convertUrlToFile('https://example.com/', 'custom_css.pdf')

Modify the page with JavaScript

Adjust the selectors and class names for your page.

Remove widgets and expand sections

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setContentViewportWidth('balanced')
client.setCustomJavascript("""
    // Remove dynamic content before conversion
    document.querySelectorAll('.video-player, .chat-widget').forEach(el => {
        el.remove();
    });
    // Expand collapsed sections
    document.querySelectorAll('.collapsed').forEach(el => {
        el.classList.remove('collapsed');
    });""")
client.convertUrlToFile('https://example.com/', 'custom_js.pdf')

Add content to the page

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setCustomJavascript("""
    el = document.createElement('h2');
    el.textContent = 'Hello from PDFCrowd API';
    el.style.color = 'red';
    el_before = document.getElementsByTagName('h1')[0];
    el_before.parentNode.insertBefore(el, el_before.nextSibling);""")
client.convertUrlToFile('https://example.com/', 'html_inject.pdf')

Convert a specific element

Convert only #main in an existing document.html file. Adjust the filename and selector for your document.

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setElementToConvert('#main')
client.convertFileToFile('document.html', 'html_part.pdf')

Wait for a page element

Wait for #content-loaded to appear in an existing document.html file. Choose an element that appears when your content is ready.

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setContentViewportWidth('balanced')
client.setWaitForElement('#content-loaded')
client.convertFileToFile('document.html', 'wait_element.pdf')

Allow extra time for JavaScript

Add a delay of 2000 milliseconds. When the page has a reliable readiness marker, use Wait for a page element.

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setContentViewportWidth('balanced')
client.setJavascriptDelay(2000)
client.convertUrlToFile('https://example.com/', 'with_delay.pdf')

Apply the page’s @media print rules. The page must provide print styles for this to change its appearance.

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setContentViewportWidth('balanced')
client.setUsePrintMedia(True)
client.convertUrlToFile('https://example.com/', 'print_media.pdf')

Inspect element boundaries

Highlight element boxes to investigate spacing and layout.

Highlight backgrounds

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setCustomJavascript("""
    libPdfcrowd.highlightHtmlElements({
        backgroundColor: 'rgba(255, 191, 0, 0.1)',
        borderColor: null
    });""")
client.convertUrlToFile('https://example.com/', 'highlight_background.pdf')

Add borders and spacing

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setCustomJavascript("""
    libPdfcrowd.highlightHtmlElements({
        borderColor: 'orange',
        backgroundColor: null,
        padding: '4px',
        margin: '4px'
    });""")
client.convertUrlToFile('https://example.com/', 'highlight_borders.pdf')

HTML and CSS

Add these fragments to HTML you control.

Remove or hide elements

<nav class="pdfcrowd-remove">This won't appear in the PDF</nav>
<div class="pdfcrowd-hide">This is invisible but takes up space</div>

pdfcrowd-remove removes the element from the layout. pdfcrowd-hide preserves its space.

Control page breaks

<!-- Force a page break before the following section -->
<div style="page-break-before: always"></div>

<!-- Avoid breaking tables across pages -->
<style>
  table, tr, td { page-break-inside: avoid; }
</style>

Content taller than a page still needs to break.

Apply styles only during conversion

<style>
  /* These styles only apply during PDF conversion */
  .pdfcrowd-body h1 { font-size: 48px; }
  .pdfcrowd-body footer { display: none; }
  .pdfcrowd-body .main-content { width: 100%; }
</style>

The .pdfcrowd-body prefix limits these rules to conversion; it does not change the page in a visitor’s browser.

Templates

Render a template with JSON data

Upload existing template.html and data.json files. See the template rendering guide for template syntax, data mapping, and other supported data formats.

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setContentViewportWidth('balanced')
client.setDataFormat('json')
client.setDataFile('data.json')
client.convertFileToFile('template.html', 'output.pdf')

PDF features

Create a fillable PDF

Use an existing form.html file containing HTML form controls.

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setContentViewportWidth('balanced')
client.setEnablePdfForms(True)
client.convertFileToFile('form.html', 'form.pdf')

See fillable PDF forms for supported controls and attributes.

Set PDF metadata

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setAuthor('PDFCrowd')
client.setKeywords('PDFCrowd,demo')
client.setSubject('Demo')
client.setTitle('Hello World')
client.convertUrlToFile('https://example.com/', 'with_metadata.pdf')

Set a presentation view

import pdfcrowd

client = pdfcrowd.HtmlToPdfClient('demo', 'demo')

client.setInitialZoomType('fit-page')
client.setNoMargins(True)
client.setOrientation('landscape')
client.setPageLayout('single-page')
client.setPageMode('full-screen')
client.convertUrlToFile('https://example.com/', 'slide_show.pdf')

These settings request a full-screen initial view with landscape pages. The PDF viewer controls whether it honors those preferences.