PDF to HTML / Python Examples

import pdfcrowd
import sys

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

    # Run the conversion and save the result to a file.
    client.convertFileToFile('/path/to/logo.pdf', 'logo.html')

except pdfcrowd.Error as why:
    sys.stderr.write('PDFCrowd Error: {}\n'.format(why))
    raise

import pdfcrowd
import sys

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

    # Run the conversion and store the result in 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:
    sys.stderr.write('PDFCrowd Error: {}\n'.format(why))
    raise

import pdfcrowd
import sys

try:
    # Create an 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 to the output stream.
    client.convertFileToStream('/path/to/logo.pdf', output_stream)

    # Close the output stream.
    output_stream.close()

except pdfcrowd.Error as why:
    sys.stderr.write('PDFCrowd Error: {}\n'.format(why))
    raise

import pdfcrowd
import sys

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

    # Run the conversion and save the result to a file.
    client.convertUrlToFile('https://pdfcrowd.com/static/pdf/apisamples/invoice.pdf', 'invoice.html')

except pdfcrowd.Error as why:
    sys.stderr.write('PDFCrowd Error: {}\n'.format(why))
    raise

import pdfcrowd
import sys

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

    # Run the conversion and store the result in 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:
    sys.stderr.write('PDFCrowd Error: {}\n'.format(why))
    raise

import pdfcrowd
import sys

try:
    # Create an 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 to 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:
    sys.stderr.write('PDFCrowd Error: {}\n'.format(why))
    raise

import pdfcrowd
import sys

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

    # Run the conversion and save the result to a file.
    client.convertRawDataToFile(open('/path/to/hello_world.pdf', 'rb').read(), 'logo.html')

except pdfcrowd.Error as why:
    sys.stderr.write('PDFCrowd Error: {}\n'.format(why))
    raise

import pdfcrowd
import sys

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

    # Run the conversion and store the result in 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:
    sys.stderr.write('PDFCrowd Error: {}\n'.format(why))
    raise

import pdfcrowd
import sys

try:
    # Create an 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 to 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:
    sys.stderr.write('PDFCrowd Error: {}\n'.format(why))
    raise

import pdfcrowd
import sys

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

    # Configure the conversion.
    client.setDebugLog(True)

    # Run the conversion and save the result to a file.
    client.convertFileToFile('/path/to/logo.pdf', 'logo.html')
    
    # print URL pointing to the debug log for this request.
    print('Debug log url: {}'.format(client.getDebugLogUrl()))
    
    # print Number of conversion credits remaining in your account.
    print('Remaining credit count: {}'.format(client.getRemainingCreditCount()))
    
    # print Number of credits consumed for this conversion.
    print('Consumed credit count: {}'.format(client.getConsumedCreditCount()))
    
    # print Unique identifier assigned to this conversion job.
    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