PDF to HTML in Golang

This page describes how to convert PDF to HTML in Golang 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 Github
go get github.com/pdfcrowd/pdfcrowd-go

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

package main

import (
    "os"
    "fmt"
    "github.com/pdfcrowd/pdfcrowd-go"
)

func main() {
    // create the API client instance
    client := pdfcrowd.NewPdfToHtmlClient("demo", "ce544b6ea52a5621fb9d55f8b542d14d")

    // run the conversion and write the result to a file
    err := client.ConvertFileToFile("/path/to/logo.pdf", "logo.html")

    // check for the conversion error
    handleError(err)
}

func handleError(err error) {
    if err != nil {
        // report the error
        why, ok := err.(pdfcrowd.Error)
        if ok {
            os.Stderr.WriteString(fmt.Sprintf("Pdfcrowd Error: %s\n", why))
        } else {
            os.Stderr.WriteString(fmt.Sprintf("Generic Error: %s\n", err))
        }

        // rethrow or handle the exception
        panic(err.Error())
    }
}
package main

import (
    "os"
    "fmt"
    "github.com/pdfcrowd/pdfcrowd-go"
)

func main() {
    // create the API client instance
    client := pdfcrowd.NewPdfToHtmlClient("demo", "ce544b6ea52a5621fb9d55f8b542d14d")

    // run the conversion and store the result into the "html" variable
    html, err := client.ConvertFile("/path/to/logo.pdf")

    // check for the conversion error
    handleError(err)

    // at this point the "html" variable contains HTML raw data and
    // can be sent in an HTTP response, saved to a file, etc.
}

func handleError(err error) {
    if err != nil {
        // report the error
        why, ok := err.(pdfcrowd.Error)
        if ok {
            os.Stderr.WriteString(fmt.Sprintf("Pdfcrowd Error: %s\n", why))
        } else {
            os.Stderr.WriteString(fmt.Sprintf("Generic Error: %s\n", err))
        }

        // rethrow or handle the exception
        panic(err.Error())
    }
}
package main

import (
    "os"
    "fmt"
    "github.com/pdfcrowd/pdfcrowd-go"
)

func main() {
    // create the API client instance
    client := pdfcrowd.NewPdfToHtmlClient("demo", "ce544b6ea52a5621fb9d55f8b542d14d")

    // create an output stream for the conversion result
    outputStream, err := os.Create("logo.html")

    // check for a file creation error
    handleError(err)

    // close the output stream
    defer outputStream.Close()

    // run the conversion and write the result into the output stream
    err = client.ConvertFileToStream("/path/to/logo.pdf", outputStream)

    // check for the conversion error
    handleError(err)
}

func handleError(err error) {
    if err != nil {
        // report the error
        why, ok := err.(pdfcrowd.Error)
        if ok {
            os.Stderr.WriteString(fmt.Sprintf("Pdfcrowd Error: %s\n", why))
        } else {
            os.Stderr.WriteString(fmt.Sprintf("Generic Error: %s\n", err))
        }

        // rethrow or handle the exception
        panic(err.Error())
    }
}
package main

import (
    "os"
    "fmt"
    "github.com/pdfcrowd/pdfcrowd-go"
)

func main() {
    // create the API client instance
    client := pdfcrowd.NewPdfToHtmlClient("demo", "ce544b6ea52a5621fb9d55f8b542d14d")

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

    // check for the conversion error
    handleError(err)
}

func handleError(err error) {
    if err != nil {
        // report the error
        why, ok := err.(pdfcrowd.Error)
        if ok {
            os.Stderr.WriteString(fmt.Sprintf("Pdfcrowd Error: %s\n", why))
        } else {
            os.Stderr.WriteString(fmt.Sprintf("Generic Error: %s\n", err))
        }

        // rethrow or handle the exception
        panic(err.Error())
    }
}
package main

import (
    "os"
    "fmt"
    "github.com/pdfcrowd/pdfcrowd-go"
)

func main() {
    // create the API client instance
    client := pdfcrowd.NewPdfToHtmlClient("demo", "ce544b6ea52a5621fb9d55f8b542d14d")

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

    // check for the conversion error
    handleError(err)

    // at this point the "html" variable contains HTML raw data and
    // can be sent in an HTTP response, saved to a file, etc.
}

func handleError(err error) {
    if err != nil {
        // report the error
        why, ok := err.(pdfcrowd.Error)
        if ok {
            os.Stderr.WriteString(fmt.Sprintf("Pdfcrowd Error: %s\n", why))
        } else {
            os.Stderr.WriteString(fmt.Sprintf("Generic Error: %s\n", err))
        }

        // rethrow or handle the exception
        panic(err.Error())
    }
}
package main

import (
    "os"
    "fmt"
    "github.com/pdfcrowd/pdfcrowd-go"
)

func main() {
    // create the API client instance
    client := pdfcrowd.NewPdfToHtmlClient("demo", "ce544b6ea52a5621fb9d55f8b542d14d")

    // create an output stream for the conversion result
    outputStream, err := os.Create("invoice.html")

    // check for a file creation error
    handleError(err)

    // close the output stream
    defer outputStream.Close()

    // run the conversion and write the result into the output stream
    err = client.ConvertUrlToStream("https://pdfcrowd.com/static/pdf/apisamples/invoice.pdf", outputStream)

    // check for the conversion error
    handleError(err)
}

func handleError(err error) {
    if err != nil {
        // report the error
        why, ok := err.(pdfcrowd.Error)
        if ok {
            os.Stderr.WriteString(fmt.Sprintf("Pdfcrowd Error: %s\n", why))
        } else {
            os.Stderr.WriteString(fmt.Sprintf("Generic Error: %s\n", err))
        }

        // rethrow or handle the exception
        panic(err.Error())
    }
}
package main

import (
    "os"
    "fmt"
    "github.com/pdfcrowd/pdfcrowd-go"
    "io/ioutil"
)

func readFile(fileName string) []byte {
    content, err := ioutil.ReadFile(fileName)
    handleError(err)
    return content
}

func main() {
    // create the API client instance
    client := pdfcrowd.NewPdfToHtmlClient("demo", "ce544b6ea52a5621fb9d55f8b542d14d")

    // run the conversion and write the result to a file
    err := client.ConvertRawDataToFile(readFile("/path/to/hello_world.pdf"), "logo.html")

    // check for the conversion error
    handleError(err)
}

func handleError(err error) {
    if err != nil {
        // report the error
        why, ok := err.(pdfcrowd.Error)
        if ok {
            os.Stderr.WriteString(fmt.Sprintf("Pdfcrowd Error: %s\n", why))
        } else {
            os.Stderr.WriteString(fmt.Sprintf("Generic Error: %s\n", err))
        }

        // rethrow or handle the exception
        panic(err.Error())
    }
}
package main

import (
    "os"
    "fmt"
    "github.com/pdfcrowd/pdfcrowd-go"
    "io/ioutil"
)

func readFile(fileName string) []byte {
    content, err := ioutil.ReadFile(fileName)
    handleError(err)
    return content
}

func main() {
    // create the API client instance
    client := pdfcrowd.NewPdfToHtmlClient("demo", "ce544b6ea52a5621fb9d55f8b542d14d")

    // run the conversion and store the result into the "html" variable
    html, err := client.ConvertRawData(readFile("/path/to/hello_world.pdf"))

    // check for the conversion error
    handleError(err)

    // at this point the "html" variable contains HTML raw data and
    // can be sent in an HTTP response, saved to a file, etc.
}

func handleError(err error) {
    if err != nil {
        // report the error
        why, ok := err.(pdfcrowd.Error)
        if ok {
            os.Stderr.WriteString(fmt.Sprintf("Pdfcrowd Error: %s\n", why))
        } else {
            os.Stderr.WriteString(fmt.Sprintf("Generic Error: %s\n", err))
        }

        // rethrow or handle the exception
        panic(err.Error())
    }
}
package main

import (
    "os"
    "fmt"
    "github.com/pdfcrowd/pdfcrowd-go"
    "io/ioutil"
)

func readFile(fileName string) []byte {
    content, err := ioutil.ReadFile(fileName)
    handleError(err)
    return content
}

func main() {
    // create the API client instance
    client := pdfcrowd.NewPdfToHtmlClient("demo", "ce544b6ea52a5621fb9d55f8b542d14d")

    // create an output stream for the conversion result
    outputStream, err := os.Create("logo.html")

    // check for a file creation error
    handleError(err)

    // close the output stream
    defer outputStream.Close()

    // run the conversion and write the result into the output stream
    err = client.ConvertRawDataToStream(readFile("/path/to/hello_world.pdf"), outputStream)

    // check for the conversion error
    handleError(err)
}

func handleError(err error) {
    if err != nil {
        // report the error
        why, ok := err.(pdfcrowd.Error)
        if ok {
            os.Stderr.WriteString(fmt.Sprintf("Pdfcrowd Error: %s\n", why))
        } else {
            os.Stderr.WriteString(fmt.Sprintf("Generic Error: %s\n", err))
        }

        // rethrow or handle the exception
        panic(err.Error())
    }
}
package main

import (
    "os"
    "fmt"
    "github.com/pdfcrowd/pdfcrowd-go"
)

func main() {
    // create the API client instance
    client := pdfcrowd.NewPdfToHtmlClient("demo", "ce544b6ea52a5621fb9d55f8b542d14d")

    // configure the conversion
    client.SetDebugLog(true)

    // run the conversion and write the result to a file
    err := client.ConvertFileToFile("/path/to/logo.pdf", "logo.html")

    // check for the conversion error
    handleError(err)
    
    // print URL to the debug log
    fmt.Println("Debug log url:", client.GetDebugLogUrl())
    
    // print the number of available conversion credits in your account
    fmt.Println("Remaining credit count:", client.GetRemainingCreditCount())
    
    // print the number of credits consumed by the conversion
    fmt.Println("Consumed credit count:", client.GetConsumedCreditCount())
    
    // print the unique ID of the conversion
    fmt.Println("Job id:", client.GetJobId())
    
    // print the total number of pages in the output document
    fmt.Println("Page count:", client.GetPageCount())
    
    // print the size of the output in bytes
    fmt.Println("Output size:", client.GetOutputSize())
}

func handleError(err error) {
    if err != nil {
        // report the error
        why, ok := err.(pdfcrowd.Error)
        if ok {
            os.Stderr.WriteString(fmt.Sprintf("Pdfcrowd Error: %s\n", why))
        } else {
            os.Stderr.WriteString(fmt.Sprintf("Generic Error: %s\n", err))
        }

        // rethrow or handle the exception
        panic(err.Error())
    }
}

Troubleshooting

API Method Reference

Refer for details to the API Method Reference.