This page contains various examples of using the PDF to Text API in Python. The examples are complete and fully functional. Read more about how to convert PDF to Text in Python.
import pdfcrowd import sys try: # create the API client instance client = pdfcrowd.PdfToTextClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d') # run the conversion and write the result to a file client.convertFileToFile('/path/to/invoice.pdf', 'invoice.txt') 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.PdfToTextClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d') # run the conversion and store the result into the "txt" variable txt = client.convertFile('/path/to/invoice.pdf') # at this point the "txt" variable contains TXT 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.PdfToTextClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d') # create an output stream for the conversion result output_stream = open('invoice.txt', 'wb') # run the conversion and write the result into the output stream client.convertFileToStream('/path/to/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.PdfToTextClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d') # run the conversion and write the result to a file client.convertUrlToFile('https://pdfcrowd.com/static/pdf/apisamples/invoice.pdf', 'invoice.txt') 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.PdfToTextClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d') # run the conversion and store the result into the "txt" variable txt = client.convertUrl('https://pdfcrowd.com/static/pdf/apisamples/invoice.pdf') # at this point the "txt" variable contains TXT 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.PdfToTextClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d') # create an output stream for the conversion result output_stream = open('invoice.txt', '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.PdfToTextClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d') # run the conversion and write the result to a file client.convertRawDataToFile(open('/path/to/hello_world.pdf', 'rb').read(), 'invoice.txt') 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.PdfToTextClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d') # run the conversion and store the result into the "txt" variable txt = client.convertRawData(open('/path/to/hello_world.pdf', 'rb').read()) # at this point the "txt" variable contains TXT 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.PdfToTextClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d') # create an output stream for the conversion result output_stream = open('invoice.txt', '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.PdfToTextClient('demo', 'ce544b6ea52a5621fb9d55f8b542d14d') # configure the conversion client.setDebugLog(True) client.setPageBreakMode('default') # run the conversion and write the result to a file client.convertFileToFile('/path/to/invoice.pdf', 'invoice.txt') # 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