PDF Format Converter via Cloud Python SDK
Export PDF to Microsoft Office® Word, Excel, PowerPoint Presentations, Images, HTML and fixed-layout formats with Aspose.PDF Cloud Python SDK
Get Started
How to Convert PDF to DOCX Using SDK for Python
In order to convert PDF to DOCX, we’ll use Aspose.PDF Cloud Python SDK This Cloud SDK assists Python programmers in developing cloud-based PDF creator, annotator, editor, and converter apps using Python programming language via Aspose.PDF REST API. Simply create an account at Aspose for Cloud and get your application information. Once you have the App SID & key, you are ready to give the Aspose.PDF Cloud Python SDK. If the python package is hosted on Github, you can install directly from Github:
Installation from Github
pip install git+https://github.com/aspose-pdf-cloud/aspose-pdf-cloud-python.git
Package Manager Console Command
pip install asposepdfcloud
Convert PDF to DOCX via Python SDK
The Convert PDF to DOCX method uploads a local PDF file to Aspose Cloud Storage and converts it into a DOCX document. It uses the Aspose.PDF Cloud API, authenticates with AppSecret and AppKey, uploads the input PDF, requests the conversion in “Flow” mode for better text reflow, and saves the resulting DOCX file locally as sample.docx. Finally, it outputs the size of the converted file in bytes.
This sample code shows PDF to DOCX conversion via Cloud Python SDK Conversion
from asposepdfcloud import PdfApi, ApiClient, DocFormat
import shutil
import os
import json
from pathlib import Path
import logging
# Configure logging
logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
class PdfToDocxConvert:
"""Class for converting from PDF to DOCX using Aspose PDF Cloud API."""
def convert(self):
"""Convert PDF to Docx."""
localFolder = "C:\Samples"
storagePdfName = "sample.pdf"
storageTempFolder = "TempPdfCloud"
outputFileName = "output_docx_convert.docx"
# Get your AppSid and AppSecret from https://dashboard.aspose.cloud (free registration required).
self.pdf_api = PdfApi(ApiClient(AppSecret, AppSid))
if self.pdf_api:
file_path = localFolder + "/" + storagePdfName
self.pdf_api.upload_file(os.path.join(storageTempFolder, storagePdfName), file_path)
opts = {
"folder": storageTempFolder,
"format": DocFormat.DOCX
}
try:
response = self.pdf_api.put_pdf_in_storage_to_doc(storagePdfName, os.path.join(storageTempFolder, outputFileName), **opts)
if response.code == 200:
temp_file = self.pdf_api.download_file(storageTempFolder + '/' + outputFileName)
local_path = localFolder + '/' + outputFileName
shutil.move(temp_file, local_path)
logging.info(f"pdf_docx_convert(): PDF successfully converted to DOCX: '{outputFileName}'.")
else:
logging.error(f"pdf_docx_convert(): Failed to convert PDF to DOCX. Response code: {response.code}")
except Exception as e:
logging.error(f"pdf_docx_convert(): Error while converting PDF: {e}")
Save PDF as XLSX Files via Python SDK
The Convert Pdf To Xlsx method uploads a local PDF file to Aspose Cloud Storage and converts it into an Excel (XLSX) spreadsheet. Using the Aspose.PDF Cloud API with AppSid and AppSecret, it uploads the PDF, performs the conversion, saves the result locally as sample.xlsx, and then prints the file size of the converted spreadsheet in bytes.
This sample code shows PDF to XLSX conversion via Cloud Python SDK Conversion
from asposepdfcloud import PdfApi, ApiClient
import shutil
import os
import json
from pathlib import Path
import logging
# Configure logging
logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
class PdfToExcelConvert:
"""Class for converting from PDF to XLSX using Aspose PDF Cloud API."""
def convert(self):
"""Convert PDF to XLSX."""
localFolder = "C:\Samples"
storagePdfName = "sample.pdf"
storageTempFolder = "TempPdfCloud"
outputFileName = "output_excel_convert.xlsx"
# Get your AppSid and AppSecret from https://dashboard.aspose.cloud (free registration required).
self.pdf_api = PdfApi(ApiClient(AppSecret, AppSid))
if self.pdf_api:
file_path = localFolder + "/" + storagePdfName
self.pdf_api.upload_file(os.path.join(storageTempFolder, storagePdfName), file_path)
opts = { "folder": storageTempFolder }
try:
response = self.pdf_api.put_pdf_in_storage_to_xlsx(storagePdfName, os.path.join(storageTempFolder, outputFileName), **opts)
if response.code == 200:
temp_file = self.pdf_api.download_file(storageTempFolder + '/' + outputFileName)
local_path = localFolder + '/' + outputFileName
shutil.move(temp_file, local_path)
logging.info(f"pdf_excel_convert(): PDF successfully converted to XLSX: '{outputFileName}'.")
else:
logging.error(f"pdf_excel_convert(): Failed to convert PDF to XLSX. Response code: {response.code}")
except Exception as e:
logging.error(f"pdf_excel_convert(): Error while converting PDF: {e}")
Convert PDF to PowerPoint Presentations via Python SDK
The Convert Pdf To Pptx method uploads a local PDF file to Aspose Cloud Storage and converts it into a PowerPoint (PPTX) presentation. Using the Aspose.PDF Cloud API with AppSid and AppSecret, it uploads the PDF, processes the conversion, saves the output locally as sample.pptx, and prints the size of the generated presentation in bytes.
This sample code shows PDF to PowerPoint conversion via Cloud Python SDK Conversion
from asposepdfcloud import PdfApi, ApiClient
import shutil
import os
import json
from pathlib import Path
import logging
# Configure logging
logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
class PdfToPowerpointConvert:
"""Class for converting from PDF to PPTX using Aspose PDF Cloud API."""
def convert(self):
"""Convert PDF to PPTX."""
localFolder = "C:\Samples"
storagePdfName = "sample.pdf"
storageTempFolder = "TempPdfCloud"
outputFileName = "output_powerpoint_convert.pptx"
# Get your AppSid and AppSecret from https://dashboard.aspose.cloud (free registration required).
self.pdf_api = PdfApi(ApiClient(AppSecret, AppSid))
if self.pdf_api:
file_path = localFolder + "/" + storagePdfName
self.pdf_api.upload_file(os.path.join(storageTempFolder, storagePdfName), file_path)
opts = { "folder": storageTempFolder }
try:
response = self.pdf_api.put_pdf_in_storage_to_pptx(storagePdfName, os.path.join(storageTempFolder, outputFileName), **opts)
if response.code == 200:
temp_file = self.pdf_api.download_file(storageTempFolder + '/' + outputFileName)
local_path = localFolder + '/' + outputFileName
shutil.move(temp_file, local_path)
logging.info(f"pdf_powerpoint_convert(): PDF successfully converted to PPTX: '{outputFileName}'.")
else:
logging.error(f"pdf_powerpoint_convert(): Failed to convert PDF to PPTX. Response code: {response.code}")
except Exception as e:
logging.error(f"pdf_powerpoint_convert(): Error while converting PDF: {e}")
Portable Document Format PDF to HTML Conversion via Python SDK
The Convert Pdf To Html() method uploads a local PDF file to Aspose Cloud Storage and converts it into an HTML format. Using the Aspose.PDF Cloud API with AppSid and AppSecret, it uploads the PDF, performs the conversion, saves the output as a ZIP archive (sample-html.zip) containing the HTML and related resources, and prints the size of the generated file in bytes.
This sample code shows PDF to HTML conversion via Cloud Python SDK Conversion
from asposepdfcloud import PdfApi, ApiClient, OutputFormat
import shutil
import os
import json
from pathlib import Path
import logging
# Configure logging
logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
class PdfToHtmlConvert:
"""Class for converting from PDF to HTML using Aspose PDF Cloud API."""
def convert(self):
"""Convert PDF to HTML."""
localFolder = "C:\Samples"
storagePdfName = "sample.pdf"
storageTempFolder = "TempPdfCloud"
outputFileName = "output_html_convert.zip"
# Get your AppSid and AppSecret from https://dashboard.aspose.cloud (free registration required).
self.pdf_api = PdfApi(ApiClient(AppSecret, AppSid))
if self.pdf_api:
file_path = localFolder + "/" + storagePdfName
self.pdf_api.upload_file(os.path.join(storageTempFolder, storagePdfName), file_path)
opts = { "folder": storageTempFolder, "output_format": OutputFormat.ZIP }
try:
response = self.pdf_api.put_pdf_in_storage_to_html(storagePdfName, os.path.join(storageTempFolder, outputFileName), **opts)
if response.code == 200:
temp_file = self.pdf_api.download_file(storageTempFolder + '/' + outputFileName)
local_path = localFolder + '/' + outputFileName
shutil.move(temp_file, local_path)
logging.info(f"pdf_html_convert(): PDF successfully converted to HTML: '{outputFileName}'.")
else:
logging.error(f"pdf_html_convert(): Failed to convert PDF to HTML. Response code: {response.code}")
except Exception as e:
logging.error(f"pdf_html_convert(): Error while converting PDF: {e}")
Other Supported Conversions
You can also convert many other file formats