How to convert PDF to HTML from uploaded file for PDF to HTML API in Python and PDF.co Web API

Learn in Simple Ways: How to Convert PDF to HTML from Uploaded File for PDF to HTML API in Python

This page displays the code samples for programming in Python. PDF.co Web API helps with PDF to HTML API in Python. PDF.co Web API is the Web API with a set of tools for documents manipulation, data conversion, data extraction, splitting and merging of documents. Includes image recognition, built-in OCR, barcode generation and barcode decoders to decode bar codes from scans, pictures and pdf.

Want to learn quickly? These fast application programming interfaces of PDF.co Web API for Python plus the instruction and the code below will help to learn how to convert PDF to HTML from uploaded file. Open your Python project and simply copy & paste the code and then run your app! Easy to understand tutorials are available along with installed PDF.co Web API if you’d like to learn more about the topic and the details of the API.

Free! Free! Free! ByteScout free trial version is available for FREE download from our website. Programming tutorials along with source code samples are assembled.

On-demand (REST Web API) version:
 Web API (on-demand version)

On-premise offline SDK for Windows:
 60 Day Free Trial (on-premise)

ConvertPdfToHtmlFromUploadedFile.py

      
import os
import requests # pip install requests

# The authentication key (API Key).
# Get your own by registering at https://app.pdf.co/documentation/api
API_KEY = "***************************************"

# Base URL for PDF.co Web API requests
BASE_URL = "https://api.pdf.co/v1"

# Source PDF file
SourceFile = ".\\sample.pdf"
# Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
Pages = ""
# PDF document password. Leave empty for unprotected documents.
Password = ""
# Destination Html file name
DestinationFile = ".\\result.html"
# Set to $true to get simplified HTML without CSS. Default is the rich HTML keeping the document design.
PlainHtml = False
# Set to $true if your document has the column layout like a newspaper.
ColumnLayout = False


def main(args = None):
    uploadedFileUrl = uploadFile(SourceFile)
    if (uploadedFileUrl != None):
        convertPdfToHtml(uploadedFileUrl, DestinationFile)


def convertPdfToHtml(uploadedFileUrl, destinationFile):
    """Converts PDF To Html using PDF.co Web API"""

    # Prepare requests params as JSON
    # See documentation: https://apidocs.pdf.co
    parameters = {}
    parameters["name"] = os.path.basename(destinationFile)
    parameters["password"] = Password
    parameters["pages"] = Pages
    parameters["simple"] = PlainHtml
    parameters["columns"] = ColumnLayout
    parameters["url"] = uploadedFileUrl

    # Prepare URL for 'PDF To Html' API request
    url = "{}/pdf/convert/to/html".format(BASE_URL)

    # Execute request and get response as JSON
    response = requests.post(url, data=parameters, headers={ "x-api-key": API_KEY })
    if (response.status_code == 200):
        json = response.json()

        if json["error"] == False:
            #  Get URL of result file
            resultFileUrl = json["url"]            
            # Download result file
            r = requests.get(resultFileUrl, stream=True)
            if (r.status_code == 200):
                with open(destinationFile, 'wb') as file:
                    for chunk in r:
                        file.write(chunk)
                print(f"Result file saved as \"{destinationFile}\" file.")
            else:
                print(f"Request error: {response.status_code} {response.reason}")
        else:
            # Show service reported error
            print(json["message"])
    else:
        print(f"Request error: {response.status_code} {response.reason}")


def uploadFile(fileName):
    """Uploads file to the cloud"""
    
    # 1. RETRIEVE PRESIGNED URL TO UPLOAD FILE.

    # Prepare URL for 'Get Presigned URL' API request
    url = "{}/file/upload/get-presigned-url?contenttype=application/octet-stream&name={}".format(
        BASE_URL, os.path.basename(fileName))
    
    # Execute request and get response as JSON
    response = requests.get(url, headers={ "x-api-key": API_KEY })
    if (response.status_code == 200):
        json = response.json()
        
        if json["error"] == False:
            # URL to use for file upload
            uploadUrl = json["presignedUrl"]
            # URL for future reference
            uploadedFileUrl = json["url"]

            # 2. UPLOAD FILE TO CLOUD.
            with open(fileName, 'rb') as file:
                requests.put(uploadUrl, data=file, headers={ "x-api-key": API_KEY, "content-type": "application/octet-stream" })

            return uploadedFileUrl
        else:
            # Show service reported error
            print(json["message"])    
    else:
        print(f"Request error: {response.status_code} {response.reason}")

    return None


if __name__ == '__main__':
    main()

VIDEO

ON-PREMISE OFFLINE SDK

Get 60 Day Free Trial

See also:

ON-DEMAND REST WEB API

Get Your API Key

See also: