PDF to text API in Python with PDF.co Web API

PDF.co Web API is the flexible Web API that includes full set of functions from e-signature requests to data extraction, OCR, images recognition, pdf splitting and pdf splitting. Can also generate barcodes and read barcodes from images, scans and pdf.

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

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

ConvertPdfToTextFromUploadedFile.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 TXT file name DestinationFile = ".\\result.txt" # Some of advanced options available through profiles: # (JSON can be single/double-quoted and contain comments.) # { # "profiles": [ # { # "profile1": { # "ExtractInvisibleText": true, // Invisible text extraction. Values: true / false # "ExtractShadowLikeText": true, // Shadow-like text extraction. Values: true / false # "ExtractAnnotations": true, // Whether to extract PDF annotations. # "CheckPermissions": true, // Ignore document permissions. Values: true / false # "DetectNewColumnBySpacesRatio": 1.2, // A ratio affecting number of spaces between words. # } # } # ] # } # Sample profile that sets advanced conversion options # Advanced options are properties of TextExtractor class from ByteScout Text Extractor SDK used in the back-end: # https://cdn.bytescout.com/help/BytescoutPDFExtractorSDK/html/8a2bae5a-346f-8338-b5aa-6f3522dca0d4.htm Profiles = '{ "profiles": [ { "profile1": { "TrimSpaces": "False", "PreserveFormattingOnTextExtraction": "True", "Unwrap": "True" } } ] }' def main(args = None): uploadedFileUrl = uploadFile(SourceFile) if (uploadedFileUrl != None): convertPdfToText(uploadedFileUrl, DestinationFile) def convertPdfToText(uploadedFileUrl, destinationFile): """Converts PDF To Text 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["url"] = uploadedFileUrl parameters["profiles"] = Profiles # Prepare URL for 'PDF To Text' API request url = "{}/pdf/convert/to/text".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:

Related Samples: