PDF to HTML Ruby Examples

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

Basic examples
Rails examples

Basic examples

PDF file to HTML file

require "pdfcrowd"

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

    # run the conversion and write the result to a file
    client.convertFileToFile("/path/to/logo.pdf", "logo.html")

rescue Pdfcrowd::Error => why
    STDERR.puts "Pdfcrowd Error: #{why}"
    raise
end

PDF file to in-memory HTML

require "pdfcrowd"

begin
    # create the API client instance
    client = Pdfcrowd::PdfToHtmlClient.new("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.

rescue Pdfcrowd::Error => why
    STDERR.puts "Pdfcrowd Error: #{why}"
    raise
end

PDF file to HTML stream

require "pdfcrowd"

begin
    # create the API client instance
    client = Pdfcrowd::PdfToHtmlClient.new("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()

rescue Pdfcrowd::Error => why
    STDERR.puts "Pdfcrowd Error: #{why}"
    raise
end

PDF url to HTML file

require "pdfcrowd"

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

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

rescue Pdfcrowd::Error => why
    STDERR.puts "Pdfcrowd Error: #{why}"
    raise
end

PDF url to in-memory HTML

require "pdfcrowd"

begin
    # create the API client instance
    client = Pdfcrowd::PdfToHtmlClient.new("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.

rescue Pdfcrowd::Error => why
    STDERR.puts "Pdfcrowd Error: #{why}"
    raise
end

PDF url to HTML stream

require "pdfcrowd"

begin
    # create the API client instance
    client = Pdfcrowd::PdfToHtmlClient.new("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()

rescue Pdfcrowd::Error => why
    STDERR.puts "Pdfcrowd Error: #{why}"
    raise
end

In-memory PDF to HTML file

require "pdfcrowd"

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

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

rescue Pdfcrowd::Error => why
    STDERR.puts "Pdfcrowd Error: #{why}"
    raise
end

In-memory PDF to in-memory HTML

require "pdfcrowd"

begin
    # create the API client instance
    client = Pdfcrowd::PdfToHtmlClient.new("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.

rescue Pdfcrowd::Error => why
    STDERR.puts "Pdfcrowd Error: #{why}"
    raise
end

In-memory PDF to HTML stream

require "pdfcrowd"

begin
    # create the API client instance
    client = Pdfcrowd::PdfToHtmlClient.new("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()

rescue Pdfcrowd::Error => why
    STDERR.puts "Pdfcrowd Error: #{why}"
    raise
end

Get info about the current conversion

require "pdfcrowd"

begin
    # create the API client instance
    client = Pdfcrowd::PdfToHtmlClient.new("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
    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
    STDERR.puts "Pdfcrowd Error: #{why}"
    raise
end

Rails examples

PDF file to HTML in Rails

require "pdfcrowd"

class DemoController < ApplicationController
    def convert
        # the recommended method is POST
        # may be restricted by ":via => :post" in your routes.rb
        if ! request.post?
            return render text: "POST is allowed only", status: 400
        end

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

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

            # send the result and set HTTP response headers
            send_data html,
                      :type => "text/html",
                      :disposition => "attachment; filename*=UTF-8''#{ERB::Util.url_encode('logo.html')}"
        rescue Pdfcrowd::Error => why
            # send the error in the HTTP response
            render plain: why.getMessage(), status: why.getCode()
        end
    end
end

PDF url to HTML in Rails

require "pdfcrowd"

class DemoController < ApplicationController
    def convert
        # the recommended method is POST
        # may be restricted by ":via => :post" in your routes.rb
        if ! request.post?
            return render text: "POST is allowed only", status: 400
        end

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

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

            # send the result and set HTTP response headers
            send_data html,
                      :type => "text/html",
                      :disposition => "attachment; filename*=UTF-8''#{ERB::Util.url_encode('invoice.html')}"
        rescue Pdfcrowd::Error => why
            # send the error in the HTTP response
            render plain: why.getMessage(), status: why.getCode()
        end
    end
end

In-memory PDF to HTML in Rails

require "pdfcrowd"

class DemoController < ApplicationController
    def convert
        # the recommended method is POST
        # may be restricted by ":via => :post" in your routes.rb
        if ! request.post?
            return render text: "POST is allowed only", status: 400
        end

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

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

            # send the result and set HTTP response headers
            send_data html,
                      :type => "text/html",
                      :disposition => "attachment; filename*=UTF-8''#{ERB::Util.url_encode('logo.html')}"
        rescue Pdfcrowd::Error => why
            # send the error in the HTTP response
            render plain: why.getMessage(), status: why.getCode()
        end
    end
end