HTML to PDF / Python Examples

This page contains various examples of using the HTML to PDF API in Python. The examples are complete and fully functional. Read more about how to convert HTML to PDF in Python.

Basic examples
Advanced examples
Template rendering examples
Django examples
Flask examples

Basic examples

Webpage to PDF file

import pdfcrowd
import sys

try:
    # Create an API client instance.
    client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # Specify the mapping of HTML content width to the PDF page width.
    # To fine-tune the layout, you can specify an exact viewport width, such as '960px'.
    client.setContentViewportWidth('balanced')

    # Run the conversion and save the result to a file.
    client.convertUrlToFile('http://www.example.com', 'example.pdf')
    
except pdfcrowd.Error as why:
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))
    raise

Webpage to in-memory PDF

import pdfcrowd
import sys

try:
    # Create an API client instance.
    client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # Run the conversion and store the result in the `pdf` variable.
    pdf = client.convertUrl('http://www.example.com')

    # at this point the "pdf" variable contains PDF raw data and
    # can be sent in an HTTP response, saved to a file, etc.
    
except pdfcrowd.Error as why:
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))
    raise

Webpage to PDF stream

import pdfcrowd
import sys

try:
    # Create an API client instance.
    client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # Create an output stream for the conversion result
    output_stream = open('example.pdf', 'wb')

    # run the conversion and write the result to the output stream.
    client.convertUrlToStream('http://www.example.com', output_stream)

    # Close the output stream.
    output_stream.close()
    
except pdfcrowd.Error as why:
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))
    raise

HTML file to PDF file

import pdfcrowd
import sys

try:
    # Create an API client instance.
    client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # Specify the mapping of HTML content width to the PDF page width.
    # To fine-tune the layout, you can specify an exact viewport width, such as '960px'.
    client.setContentViewportWidth('balanced')

    # Run the conversion and save the result to a file.
    client.convertFileToFile('/path/to/MyLayout.html', 'MyLayout.pdf')
    
except pdfcrowd.Error as why:
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))
    raise

HTML file to in-memory PDF

import pdfcrowd
import sys

try:
    # Create an API client instance.
    client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # Run the conversion and store the result in the `pdf` variable.
    pdf = client.convertFile('/path/to/MyLayout.html')

    # at this point the "pdf" variable contains PDF raw data and
    # can be sent in an HTTP response, saved to a file, etc.
    
except pdfcrowd.Error as why:
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))
    raise

HTML file to PDF stream

import pdfcrowd
import sys

try:
    # Create an API client instance.
    client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # Create an output stream for the conversion result
    output_stream = open('MyLayout.pdf', 'wb')

    # run the conversion and write the result to the output stream.
    client.convertFileToStream('/path/to/MyLayout.html', output_stream)

    # Close the output stream.
    output_stream.close()
    
except pdfcrowd.Error as why:
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))
    raise

HTML string to PDF file

import pdfcrowd
import sys

try:
    # Create an API client instance.
    client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # Specify the mapping of HTML content width to the PDF page width.
    # To fine-tune the layout, you can specify an exact viewport width, such as '960px'.
    client.setContentViewportWidth('balanced')

    # Run the conversion and save the result to a file.
    client.convertStringToFile('<html><body><h1>Hello World!</h1></body></html>', 'HelloWorld.pdf')
    
except pdfcrowd.Error as why:
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))
    raise

HTML string to in-memory PDF

import pdfcrowd
import sys

try:
    # Create an API client instance.
    client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # Run the conversion and store the result in the `pdf` variable.
    pdf = client.convertString('<html><body><h1>Hello World!</h1></body></html>')

    # at this point the "pdf" variable contains PDF raw data and
    # can be sent in an HTTP response, saved to a file, etc.
    
except pdfcrowd.Error as why:
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))
    raise

HTML string to PDF stream

import pdfcrowd
import sys

try:
    # Create an API client instance.
    client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # Create an output stream for the conversion result
    output_stream = open('HelloWorld.pdf', 'wb')

    # run the conversion and write the result to the output stream.
    client.convertStringToStream('<html><body><h1>Hello World!</h1></body></html>', output_stream)

    # Close the output stream.
    output_stream.close()
    
except pdfcrowd.Error as why:
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))
    raise

Get info about the current conversion

import pdfcrowd
import sys

try:
    # Create an API client instance.
    client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # Specify the mapping of HTML content width to the PDF page width.
    # To fine-tune the layout, you can specify an exact viewport width, such as '960px'.
    client.setDebugLog(True)

    # Run the conversion and save the result to a file.
    client.convertFileToFile('/path/to/MyLayout.html', 'MyLayout.pdf')
    
    # print URL of the debug log
    print('Debug log url: {}'.format(client.getDebugLogUrl()))
    
    # print the number of conversion credits remaining in your account
    print('Remaining credit count: {}'.format(client.getRemainingCreditCount()))
    
    # print the number of credits used for the conversion
    print('Consumed credit count: {}'.format(client.getConsumedCreditCount()))
    
    # print the unique identifier for the conversion
    print('Job id: {}'.format(client.getJobId()))
    
    # print total number of pages in the output document
    print('Page count: {}'.format(client.getPageCount()))
    
    # print size of the output data in bytes
    print('Output size: {}'.format(client.getOutputSize()))
    
except pdfcrowd.Error as why:
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))
    raise

Advanced examples

Customize the page size and the orientation

import pdfcrowd
import sys

try:
    # Create an API client instance.
    client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # Configure the conversion.
    client.setPageSize('Letter')
    client.setOrientation('landscape')
    client.setNoMargins(True)

    # Run the conversion and save the result to a file.
    client.convertUrlToFile('http://www.example.com', 'letter_landscape.pdf')
    
except pdfcrowd.Error as why:
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))
    raise

Put the source URL in the header and the page number in the footer

import pdfcrowd
import sys

try:
    # Create an API client instance.
    client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # Configure the conversion.
    client.setHeaderHeight('15mm')
    client.setFooterHeight('10mm')
    client.setHeaderHtml('<a class=\'pdfcrowd-source-url\' data-pdfcrowd-placement=\'href-and-content\'></a>')
    client.setFooterHtml('<center><span class=\'pdfcrowd-page-number\'></span></center>')
    client.setMarginTop('0')
    client.setMarginBottom('0')

    # Run the conversion and save the result to a file.
    client.convertUrlToFile('http://www.example.com', 'header_footer.pdf')
    
except pdfcrowd.Error as why:
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))
    raise

Create fillable PDF form

import pdfcrowd
import sys

try:
    # Create an API client instance.
    client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # Configure the conversion.
    client.setEnablePdfForms(True)

    # Run the conversion and save the result to a file.
    client.convertStringToFile('<html><body>Enter name:<input type=text></body></html>', 'form.pdf')
    
except pdfcrowd.Error as why:
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))
    raise

Zoom the HTML document

import pdfcrowd
import sys

try:
    # Create an API client instance.
    client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # Configure the conversion.
    client.setScaleFactor(300)

    # Run the conversion and save the result to a file.
    client.convertUrlToFile('http://www.example.com', 'zoom_300.pdf')
    
except pdfcrowd.Error as why:
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))
    raise

Set PDF metadata

import pdfcrowd
import sys

try:
    # Create an API client instance.
    client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # Configure the conversion.
    client.setAuthor('Pdfcrowd')
    client.setTitle('Hello World')
    client.setSubject('Demo')
    client.setKeywords('Pdfcrowd,demo')

    # Run the conversion and save the result to a file.
    client.convertUrlToFile('http://www.example.com', 'with_metadata.pdf')
    
except pdfcrowd.Error as why:
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))
    raise

Create a Powerpoint like presentation from an HTML document

import pdfcrowd
import sys

try:
    # Create an API client instance.
    client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # Configure the conversion.
    client.setPageLayout('single-page')
    client.setPageMode('full-screen')
    client.setInitialZoomType('fit-page')
    client.setOrientation('landscape')
    client.setNoMargins(True)

    # Run the conversion and save the result to a file.
    client.convertUrlToFile('https://pdfcrowd.com/api/', 'slide_show.pdf')
    
except pdfcrowd.Error as why:
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))
    raise

Convert an HTML document section

import pdfcrowd
import sys

try:
    # Create an API client instance.
    client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # Configure the conversion.
    client.setElementToConvert('#main')

    # Run the conversion and save the result to a file.
    client.convertUrlToFile('https://pdfcrowd.com/api/', 'html_part.pdf')
    
except pdfcrowd.Error as why:
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))
    raise

Inject an HTML code

import pdfcrowd
import sys

try:
    # Create an API client instance.
    client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # Configure the conversion.
    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)')

    # Run the conversion and save the result to a file.
    client.convertUrlToFile('http://www.example.com', 'html_inject.pdf')
    
except pdfcrowd.Error as why:
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))
    raise

Convert a responsive web page as it appears on a large device

import pdfcrowd
import sys

try:
    # Create an API client instance.
    client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # Configure the conversion.
    client.setContentViewportWidth('large')
    client.setNoMargins(True)

    # Run the conversion and save the result to a file.
    client.convertUrlToFile('https://getbootstrap.com/', 'bootstrap.pdf')
    
except pdfcrowd.Error as why:
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))
    raise

Create an in-memory archive (ZIP) and convert it

import pdfcrowd
import sys
import io
import zipfile

try:
    # Create an API client instance.
    client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # Create a ZIP archive.
    in_stream = io.BytesIO()
    with zipfile.ZipFile(in_stream, 'w', zipfile.ZIP_DEFLATED) as zip_file:
        # Add HTML content to the archive.
        zip_file.writestr('index.html', '''<html>
            <head>
                <style>
                 @font-face
                 {
                     font-family: 'OpenSans';
                     src: url(fonts/OpenSans.ttf) format('truetype');
                 }
        
                 h1
                 {
                     font-family: OpenSans;
                 }
                </style>
            </head>
            <body>
                <h1>Hello World</h1>
                <img src='images/logo.png'>
            </body>
        </html>''')

        # Add required local files to the archive.
        with open("/your-path-to/fonts/OpenSans.ttf", "rb") as in_file:
            zip_file.writestr("fonts/OpenSans.ttf", in_file.read())
        with open("/your-path-to/images/logo.png", "rb") as in_file:
            zip_file.writestr("images/logo.png", in_file.read())
    in_stream.seek(0)

    # Create an output stream for the conversion result
    output_stream = open('HelloFromZip.pdf', 'wb')

    # run the conversion and write the result to the output stream.
    client.convertStreamToStream(in_stream, output_stream)

    # Close the output stream.
    output_stream.close()
    
except pdfcrowd.Error as why:
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))
    raise

Renderer debugging - highlight HTML elements

import pdfcrowd
import sys

try:
    # Create an API client instance.
    client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # Configure the conversion.
    client.setCustomJavascript('libPdfcrowd.highlightHtmlElements({backgroundColor: \'rgba(255, 191, 0, 0.1)\', borderColor:null})')

    # Run the conversion and save the result to a file.
    client.convertUrlToFile('http://www.example.com', 'highlight_background.pdf')
    
except pdfcrowd.Error as why:
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))
    raise

Renderer debugging - borders with spacing around HTML elements

import pdfcrowd
import sys

try:
    # Create an API client instance.
    client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # Configure the conversion.
    client.setCustomJavascript('libPdfcrowd.highlightHtmlElements({borderColor: \'orange\', backgroundColor: null, padding: \'4px\', margin: \'4px\'})')

    # Run the conversion and save the result to a file.
    client.convertUrlToFile('http://www.example.com', 'highlight_borders.pdf')
    
except pdfcrowd.Error as why:
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))
    raise

Template rendering examples

Create PDF from JSON data

import pdfcrowd
import sys

try:
    # Create an API client instance.
    client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # Configure the conversion.
    client.setDataString("""{
            "name": "World",
            "product": "Pdfcrowd API"
        }""")

    # Run the conversion and save the result to a file.
    client.convertStringToFile('Hello {{ name }} from {{ product }}', 'output.pdf')
    
except pdfcrowd.Error as why:
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))
    raise

Create PDF from XML data

import pdfcrowd
import sys

try:
    # Create an API client instance.
    client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # Configure the conversion.
    client.setDataString("""<?xml version="1.0" encoding="UTF-8"?>
        <data>
          <name>World</name>
          <product>Pdfcrowd API</product>
        </data>""")

    # Run the conversion and save the result to a file.
    client.convertStringToFile('Hello {{ data.name }} from {{ data.product }}', 'output.pdf')
    
except pdfcrowd.Error as why:
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))
    raise

Create PDF from YAML data

import pdfcrowd
import sys

try:
    # Create an API client instance.
    client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # Configure the conversion.
    client.setDataString("""name: World
product: Pdfcrowd API""")

    # Run the conversion and save the result to a file.
    client.convertStringToFile('Hello {{ name }} from {{ product }}', 'output.pdf')
    
except pdfcrowd.Error as why:
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))
    raise

Create PDF from CSV data

import pdfcrowd
import sys

try:
    # Create an API client instance.
    client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # Configure the conversion.
    client.setDataString("""name,product
World,Pdfcrowd API""")

    # Run the conversion and save the result to a file.
    client.convertStringToFile('Hello {{ name }} from {{ product }}', 'output.pdf')
    
except pdfcrowd.Error as why:
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))
    raise

Django examples

Webpage to PDF in Django

import urllib.parse
from django.http import HttpResponse
from django.views.decorators.http import require_POST
import pdfcrowd

# The recommended method is POST.
@require_POST
def convert(request):
    try:
        # Create an API client instance.
        client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

        # Set HTTP response headers.
        response = HttpResponse(content_type='application/pdf')
        response['Cache-Control'] = 'max-age=0'
        response['Accept-Ranges'] = 'none'
        response['Content-Disposition'] = "attachment; filename*=UTF-8''" + urllib.parse.quote('example.pdf', safe='')

        # run the conversion and write the result to the output stream.
        client.convertUrlToStream('http://www.example.com', response)
        return response
    except pdfcrowd.Error as why:
        # Send the error in the HTTP response.
        return HttpResponse(why.getMessage(),
                            status=why.getCode(),
                            content_type='text/plain')

HTML file to PDF in Django

import urllib.parse
from django.http import HttpResponse
from django.views.decorators.http import require_POST
import pdfcrowd

# The recommended method is POST.
@require_POST
def convert(request):
    try:
        # Create an API client instance.
        client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

        # Set HTTP response headers.
        response = HttpResponse(content_type='application/pdf')
        response['Cache-Control'] = 'max-age=0'
        response['Accept-Ranges'] = 'none'
        response['Content-Disposition'] = "attachment; filename*=UTF-8''" + urllib.parse.quote('MyLayout.pdf', safe='')

        # run the conversion and write the result to the output stream.
        client.convertFileToStream('/path/to/MyLayout.html', response)
        return response
    except pdfcrowd.Error as why:
        # Send the error in the HTTP response.
        return HttpResponse(why.getMessage(),
                            status=why.getCode(),
                            content_type='text/plain')

HTML string to PDF in Django

import urllib.parse
from django.http import HttpResponse
from django.views.decorators.http import require_POST
import pdfcrowd

# The recommended method is POST.
@require_POST
def convert(request):
    try:
        # Create an API client instance.
        client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

        # Set HTTP response headers.
        response = HttpResponse(content_type='application/pdf')
        response['Cache-Control'] = 'max-age=0'
        response['Accept-Ranges'] = 'none'
        response['Content-Disposition'] = "attachment; filename*=UTF-8''" + urllib.parse.quote('HelloWorld.pdf', safe='')

        # run the conversion and write the result to the output stream.
        client.convertStringToStream('<html><body><h1>Hello World!</h1></body></html>', response)
        return response
    except pdfcrowd.Error as why:
        # Send the error in the HTTP response.
        return HttpResponse(why.getMessage(),
                            status=why.getCode(),
                            content_type='text/plain')

Flask examples

Webpage to PDF in Flask

import urllib.parse
from flask import Flask, Response
import pdfcrowd

app = Flask(__name__)

# The recommended method is POST.
@app.route('/', methods=['POST'])
def convert():
    try:
        # Create an API client instance.
        client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

        # Run the conversion and store the result in the `pdf` variable.
        pdf = client.convertUrl('http://www.example.com');

        # Send the result and set HTTP response headers.
        response = Response(pdf, mimetype='application/pdf')
        response.headers['Cache-Control'] = 'max-age=0'
        response.headers['Accept-Ranges'] = 'none'
        response.headers['Content-Disposition'] = "attachment; filename*=UTF-8''" + urllib.parse.quote('example.pdf', safe='')
        return response
    except pdfcrowd.Error as why:
        # Send the error in the HTTP response.
        return Response(why.getMessage(),
                        status=why.getCode(),
                        mimetype='text/plain')

HTML file to PDF in Flask

import urllib.parse
from flask import Flask, Response
import pdfcrowd

app = Flask(__name__)

# The recommended method is POST.
@app.route('/', methods=['POST'])
def convert():
    try:
        # Create an API client instance.
        client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

        # Run the conversion and store the result in the `pdf` variable.
        pdf = client.convertFile('/path/to/MyLayout.html');

        # Send the result and set HTTP response headers.
        response = Response(pdf, mimetype='application/pdf')
        response.headers['Cache-Control'] = 'max-age=0'
        response.headers['Accept-Ranges'] = 'none'
        response.headers['Content-Disposition'] = "attachment; filename*=UTF-8''" + urllib.parse.quote('MyLayout.pdf', safe='')
        return response
    except pdfcrowd.Error as why:
        # Send the error in the HTTP response.
        return Response(why.getMessage(),
                        status=why.getCode(),
                        mimetype='text/plain')

HTML string to PDF in Flask

import urllib.parse
from flask import Flask, Response
import pdfcrowd

app = Flask(__name__)

# The recommended method is POST.
@app.route('/', methods=['POST'])
def convert():
    try:
        # Create an API client instance.
        client = pdfcrowd.HtmlToPdfClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

        # Run the conversion and store the result in the `pdf` variable.
        pdf = client.convertString('<html><body><h1>Hello World!</h1></body></html>');

        # Send the result and set HTTP response headers.
        response = Response(pdf, mimetype='application/pdf')
        response.headers['Cache-Control'] = 'max-age=0'
        response.headers['Accept-Ranges'] = 'none'
        response.headers['Content-Disposition'] = "attachment; filename*=UTF-8''" + urllib.parse.quote('HelloWorld.pdf', safe='')
        return response
    except pdfcrowd.Error as why:
        # Send the error in the HTTP response.
        return Response(why.getMessage(),
                        status=why.getCode(),
                        mimetype='text/plain')