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

PDF.co Web API is the Rest API that provides set of data extraction functions, tools for documents manipulation, splitting and merging of pdf files. Includes built-in OCR, images recognition, can generate 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)

ConvertPdfToCSVFromUploadedFile.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 CSV file name DestinationFile = ".\\result.csv" # Some of advanced options available through profiles: # (JSON can be single/double-quoted and contain comments.) # { # "profiles": [ # { # "profile1": { # "CSVSeparatorSymbol": ",", // Separator symbol. # "CSVQuotaionSymbol": "\"", // Quotation symbol. # "ExtractInvisibleText": true, // Invisible text extraction. Values: true / false # "ExtractShadowLikeText": true, // Shadow-like text extraction. Values: true / false # "LineGroupingMode": "None", // Values: "None", "GroupByRows", "GroupByColumns", "JoinOrphanedRows" # "ColumnDetectionMode": "ContentGroupsAndBorders", // Values: "ContentGroupsAndBorders", "ContentGroups", "Borders", "BorderedTables" # "Unwrap": false, // Unwrap grouped text in table cells. Values: true / false # "ShrinkMultipleSpaces": false, // Shrink multiple spaces in table cells that affect column detection. Values: true / false # "DetectNewColumnBySpacesRatio": 1, // Spacing ratio that affects column detection. # "CustomExtractionColumns": [ 0, 50, 150, 200, 250, 300 ], // Explicitly specify columns coordinates for table extraction. # "CheckPermissions": true, // Ignore document permissions. Values: true / false # } # } # ] # } # Advanced Conversation Options Profiles = "{ 'profiles': [ { 'profile1': { 'TextFromImagesAndVectorsAndFonts': '|' } } ] }" def main(args = None): uploadedFileUrl = uploadFile(SourceFile) if (uploadedFileUrl != None): convertPdfToCSV(uploadedFileUrl, DestinationFile) def convertPdfToCSV(uploadedFileUrl, destinationFile): """Converts PDF To CSV using PDF.co Web API""" # Prepare URL for 'PDF To CSV' API request url = "{}/pdf/convert/to/csv?name={}&password={}&pages={}&url={}&profiles={}".format( BASE_URL, os.path.basename(destinationFile), Password, Pages, uploadedFileUrl, Profiles ) # Execute request and get response as JSON response = requests.get(url, headers={ "x-api-key": API_KEY, "content-type": "application/octet-stream" }) 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()

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit PDF.co Web API Home Page

Explore PDF.co Web API Documentation

Explore Samples

Sign Up for PDF.co Web API Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples

VIDEO

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit PDF.co Web API Home Page

Explore PDF.co Web API Documentation

Explore Samples

Sign Up for PDF.co Web API Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples

Related Samples: