Parse Word Documents using REST API in Python

ParseWordDocuments_Python.md

Learn how to parse Word documents using a REST API in Python: https://blog.groupdocs.cloud/2021/11/29/parse-word-documents-using-rest-api-in-python/

The following topics shall be covered in this article:

1. Word Document Parser REST API and Python SDK
2. Parse Word Documents and Extract Images using REST API in Node.js
3. Extract Text from Word Documents using a REST API

ParseWordDocuments_Python_Configurations.py

client_id = "da0c487d-c1c0-45ae-b7bf-43eaf53c5ad5"
client_secret = "479db2b01dcb93a3d4d20efb16dea971"

configuration = groupdocs_parser_cloud.Configuration(client_id, client_secret)
configuration.api_base_url = "https://api.groupdocs.cloud"
my_storage = ""

ParseWordDocuments_Python_Download.py

# API initializations
file_api = groupdocs_parser_cloud.FileApi.from_config(configuration)
folder_api = groupdocs_parser_cloud.FolderApi.from_config(configuration)

# Get files list
request = groupdocs_parser_cloud.GetFilesListRequest("parser/images/sample_docx/", my_storage);
response = folder_api.get_files_list(request)

# Download images one by one
for data in response.value:
    # Create download file request
    request = groupdocs_parser_cloud.DownloadFileRequest(data.path, my_storage)
    # Download file
    response = file_api.download_file(request)
    # Move downloaded file to your working directory
    shutil.move(response, "C:\\Files\\parser\\")

ParseWordDocuments_Python_ExtractImages.py

# API initialization
parseApi = groupdocs_parser_cloud.ParseApi.from_config(configuration)

# Define image options
options = groupdocs_parser_cloud.ImagesOptions()
options.file_info = groupdocs_parser_cloud.FileInfo()
options.file_info.file_path = "sample.docx"

# Create images request
request = groupdocs_parser_cloud.ImagesRequest(options)

# Get images
result = parseApi.images(request)

ParseWordDocuments_Python_ExtractText.py

# API initialization
parseApi = groupdocs_parser_cloud.ParseApi.from_config(configuration)

# Define text options
options = groupdocs_parser_cloud.TextOptions()
options.file_info = groupdocs_parser_cloud.FileInfo()
options.file_info.file_path = "sample.docx"

# Create text request
request = groupdocs_parser_cloud.TextRequest(options)

# Get text
result = parseApi.text(request)
print("Text: " + result.text)

ParseWordDocuments_Python_Upload.py

# Create instance of the API
file_api = groupdocs_parser_cloud.FileApi.from_config(configuration)

# Create upload file request
request = groupdocs_parser_cloud.UploadFileRequest("sample.docx", "C:\\Files\\parser\\sample.docx", my_storage)

# Upload file
response = file_api.upload_file(request)