PDF to HTML in Python

This page describes how to convert PDF to HTML in Python using the Pdfcrowd API. The API is easy to use and the integration takes only a few of lines of code.

Samples

Installation

Install the client library from PyPI
pip install pdfcrowd

We also offer other installation options.

Authentication

Authentication is needed in order to use the Pdfcrowd API. The credentials used for accessing the API are your Pdfcrowd username and the API key.

You can try out the API without registration using the following demo credentials:
  • Username: demo
  • API key: ce544b6ea52a5621fb9d55f8b542d14d

To get your personal API credentials, you can start a free API trial or buy the API license.

Examples

import pdfcrowd
import sys

try:
    # create the API client instance
    client = pdfcrowd.PdfToHtmlClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

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

    # rethrow or handle the exception
    raise
import pdfcrowd
import sys

try:
    # create the API client instance
    client = pdfcrowd.PdfToHtmlClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # run the conversion and store the result into the "html" variable
    html = client.convertFile('/path/to/logo.pdf')

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

    # rethrow or handle the exception
    raise
import pdfcrowd
import sys

try:
    # create the API client instance
    client = pdfcrowd.PdfToHtmlClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # create an output stream for the conversion result
    output_stream = open('logo.html', 'wb')

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

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

    # rethrow or handle the exception
    raise
import pdfcrowd
import sys

try:
    # create the API client instance
    client = pdfcrowd.PdfToHtmlClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # run the conversion and write the result to a file
    client.convertUrlToFile('https://pdfcrowd.com/static/pdf/apisamples/invoice.pdf', 'invoice.html')
except pdfcrowd.Error as why:
    # report the error
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))

    # rethrow or handle the exception
    raise
import pdfcrowd
import sys

try:
    # create the API client instance
    client = pdfcrowd.PdfToHtmlClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # run the conversion and store the result into the "html" variable
    html = client.convertUrl('https://pdfcrowd.com/static/pdf/apisamples/invoice.pdf')

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

    # rethrow or handle the exception
    raise
import pdfcrowd
import sys

try:
    # create the API client instance
    client = pdfcrowd.PdfToHtmlClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # create an output stream for the conversion result
    output_stream = open('invoice.html', 'wb')

    # run the conversion and write the result into the output stream
    client.convertUrlToStream('https://pdfcrowd.com/static/pdf/apisamples/invoice.pdf', output_stream)

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

    # rethrow or handle the exception
    raise
import pdfcrowd
import sys

try:
    # create the API client instance
    client = pdfcrowd.PdfToHtmlClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # run the conversion and write the result to a file
    client.convertRawDataToFile(open('/path/to/hello_world.pdf', 'rb').read(), 'logo.html')
except pdfcrowd.Error as why:
    # report the error
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))

    # rethrow or handle the exception
    raise
import pdfcrowd
import sys

try:
    # create the API client instance
    client = pdfcrowd.PdfToHtmlClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # run the conversion and store the result into the "html" variable
    html = client.convertRawData(open('/path/to/hello_world.pdf', 'rb').read())

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

    # rethrow or handle the exception
    raise
import pdfcrowd
import sys

try:
    # create the API client instance
    client = pdfcrowd.PdfToHtmlClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # create an output stream for the conversion result
    output_stream = open('logo.html', 'wb')

    # run the conversion and write the result into the output stream
    client.convertRawDataToStream(open('/path/to/hello_world.pdf', 'rb').read(), output_stream)

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

    # rethrow or handle the exception
    raise
import pdfcrowd
import sys

try:
    # create the API client instance
    client = pdfcrowd.PdfToHtmlClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d')

    # configure the conversion
    client.setDebugLog(True)

    # run the conversion and write the result to a file
    client.convertFileToFile('/path/to/logo.pdf', 'logo.html')
    
    # print URL to the debug log
    print('Debug log url: {}'.format(client.getDebugLogUrl()))
    
    # print the number of available conversion credits in your account
    print('Remaining credit count: {}'.format(client.getRemainingCreditCount()))
    
    # print the number of credits consumed by the conversion
    print('Consumed credit count: {}'.format(client.getConsumedCreditCount()))
    
    # print the unique ID of the conversion
    print('Job id: {}'.format(client.getJobId()))
    
    # print the total number of pages in the output document
    print('Page count: {}'.format(client.getPageCount()))
    
    # print the size of the output in bytes
    print('Output size: {}'.format(client.getOutputSize()))
except pdfcrowd.Error as why:
    # report the error
    sys.stderr.write('Pdfcrowd Error: {}\n'.format(why))

    # rethrow or handle the exception
    raise

Troubleshooting

API Method Reference

Refer for details to the API Method Reference.