PDF to Text Ruby Examples

require "pdfcrowd"

begin
    # create the API client instance
    client = Pdfcrowd::PdfToTextClient.new("demo", "ce544b6ea52a5621fb9d55f8b542d14d")

    # run the conversion and write the result to a file
    client.convertFileToFile("/path/to/invoice.pdf", "invoice.txt")
rescue Pdfcrowd::Error => why
    # report the error
    STDERR.puts "Pdfcrowd Error: #{why}"

    # rethrow or handle the exception
    raise
end

require "pdfcrowd"

begin
    # create the API client instance
    client = Pdfcrowd::PdfToTextClient.new("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.
rescue Pdfcrowd::Error => why
    # report the error
    STDERR.puts "Pdfcrowd Error: #{why}"

    # rethrow or handle the exception
    raise
end

require "pdfcrowd"

begin
    # create the API client instance
    client = Pdfcrowd::PdfToTextClient.new("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()
rescue Pdfcrowd::Error => why
    # report the error
    STDERR.puts "Pdfcrowd Error: #{why}"

    # rethrow or handle the exception
    raise
end

require "pdfcrowd"

begin
    # create the API client instance
    client = Pdfcrowd::PdfToTextClient.new("demo", "ce544b6ea52a5621fb9d55f8b542d14d")

    # run the conversion and write the result to a file
    client.convertUrlToFile("https://pdfcrowd.com/static/pdf/apisamples/invoice.pdf", "invoice.txt")
rescue Pdfcrowd::Error => why
    # report the error
    STDERR.puts "Pdfcrowd Error: #{why}"

    # rethrow or handle the exception
    raise
end

require "pdfcrowd"

begin
    # create the API client instance
    client = Pdfcrowd::PdfToTextClient.new("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.
rescue Pdfcrowd::Error => why
    # report the error
    STDERR.puts "Pdfcrowd Error: #{why}"

    # rethrow or handle the exception
    raise
end

require "pdfcrowd"

begin
    # create the API client instance
    client = Pdfcrowd::PdfToTextClient.new("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()
rescue Pdfcrowd::Error => why
    # report the error
    STDERR.puts "Pdfcrowd Error: #{why}"

    # rethrow or handle the exception
    raise
end

require "pdfcrowd"

begin
    # create the API client instance
    client = Pdfcrowd::PdfToTextClient.new("demo", "ce544b6ea52a5621fb9d55f8b542d14d")

    # run the conversion and write the result to a file
    client.convertRawDataToFile(open('/path/to/hello_world.pdf', 'rb').read(), "invoice.txt")
rescue Pdfcrowd::Error => why
    # report the error
    STDERR.puts "Pdfcrowd Error: #{why}"

    # rethrow or handle the exception
    raise
end

require "pdfcrowd"

begin
    # create the API client instance
    client = Pdfcrowd::PdfToTextClient.new("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.
rescue Pdfcrowd::Error => why
    # report the error
    STDERR.puts "Pdfcrowd Error: #{why}"

    # rethrow or handle the exception
    raise
end

require "pdfcrowd"

begin
    # create the API client instance
    client = Pdfcrowd::PdfToTextClient.new("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()
rescue Pdfcrowd::Error => why
    # report the error
    STDERR.puts "Pdfcrowd Error: #{why}"

    # rethrow or handle the exception
    raise
end

require "pdfcrowd"

begin
    # create the API client instance
    client = Pdfcrowd::PdfToTextClient.new("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
    puts "Debug log url: #{client.getDebugLogUrl()}"
    
    # print the number of available conversion credits in your account
    puts "Remaining credit count: #{client.getRemainingCreditCount()}"
    
    # print the number of credits consumed by the conversion
    puts "Consumed credit count: #{client.getConsumedCreditCount()}"
    
    # print the unique ID of the conversion
    puts "Job id: #{client.getJobId()}"
    
    # print the total number of pages in the output document
    puts "Page count: #{client.getPageCount()}"
    
    # print the size of the output in bytes
    puts "Output size: #{client.getOutputSize()}"
rescue Pdfcrowd::Error => why
    # report the error
    STDERR.puts "Pdfcrowd Error: #{why}"

    # rethrow or handle the exception
    raise
end