Link Search Menu Expand Document

Make Searchable PDF From URL - Python

PDF Make Text Searchable or Unsearchable sample in Python demonstrating ‘Make Searchable PDF From URL’

MakeSearchablePdfFromUrl.py
import os
import requests # pip install requests

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

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

# Direct URL of source PDF file.
# You can also upload your own file into PDF.co and use it as url. Check "Upload File" samples for code snippets: https://github.com/bytescout/pdf-co-api-samples/tree/master/File%20Upload/    
SourceFileURL = "https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/pdf-make-searchable/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 = ""
# OCR language. "eng", "fra", "deu", "spa"  supported currently. Let us know if you need more.
Language = "eng"
# Destination PDF file name
DestinationFile = ".\\result.pdf"


def main(args = None):
    makeSearchablePDF(SourceFileURL, DestinationFile)


def makeSearchablePDF(uploadedFileUrl, destinationFile):
    """Make Uploaded PDF file Searchable 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["lang"] = Language
    parameters["url"] = uploadedFileUrl

    # Prepare URL for 'Make Searchable PDF' API request
    url = "{}/pdf/makesearchable".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()

PDF.co Web API: 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.

Get your PDF.co API key here!

Download Source Code (.zip)

return to the previous page explore PDF Make Text Searchable or Unsearchable endpoint