Get supported file formats Leave feedback

from groupdocs.parser.options import FileType

# Get all supported file types
supported_file_types = FileType.get_supported_file_types()

# Iterate through the collection
for file_type in sorted(supported_file_types, key=lambda x: x.extension):
    print(f"{file_type.extension} - {file_type.file_format}")

print(f"\nTotal supported formats: {len(supported_file_types)}")

.7z - 7z Archive File
.azw3 - AZW3
.bmp - Bitmap Image File
.bz2 - Bzip2 Archive File
.chm - Compiled HTML Help File
.csv - Comma Separated Values File
.doc - Microsoft Word Document
.docm - Word Open XML Macro-Enabled Document
.docx - Microsoft Word Open XML Document
.dot - Word Document Template
[TRUNCATED]

from groupdocs.parser.options import FileType

# Get all supported file types
supported_file_types = FileType.get_supported_file_types()

# Define format categories
word_formats = [".doc", ".docx", ".docm", ".dot", ".dotx", ".dotm", ".odt", ".ott", ".rtf"]
excel_formats = [".xls", ".xlsx", ".xlsm", ".xlsb", ".xlt", ".xltx", ".xltm", ".ods"]
pdf_formats = [".pdf"]

print("Word Processing Formats:")
for file_type in supported_file_types:
    if file_type.extension.lower() in word_formats:
        print(f"  {file_type.extension} - {file_type.file_format}")

print("Spreadsheet Formats:")
for file_type in supported_file_types:
    if file_type.extension.lower() in excel_formats:
        print(f"  {file_type.extension} - {file_type.file_format}")

print("PDF Formats:")
for file_type in supported_file_types:
    if file_type.extension.lower() in pdf_formats:
        print(f"  {file_type.extension} - {file_type.file_format}")

Word Processing Formats:
  .doc - Microsoft Word Document
  .dot - Word Document Template
  .docx - Microsoft Word Open XML Document
  .docm - Word Open XML Macro-Enabled Document
  .dotx - Word Open XML Document Template
  .dotm - Word Open XML Macro-Enabled Document Template
  .odt - OpenDocument Text Document
  .ott - OpenDocument Document Template
  .rtf - Rich Text Format File
[TRUNCATED]

from groupdocs.parser.options import FileType

def is_format_supported(extension):
    """Check if a file format is supported by GroupDocs.Parser"""
    supported_file_types = FileType.get_supported_file_types()
    
    for file_type in supported_file_types:
        if file_type.extension.lower() == extension.lower():
            return True
    return False

# Check various formats
formats_to_check = [".pdf", ".docx", ".xlsx", ".txt", ".unknown"]

for ext in formats_to_check:
    if is_format_supported(ext):
        print(f"{ext} - Supported")
    else:
        print(f"{ext} - Not Supported")

.pdf - Supported
.docx - Supported
.xlsx - Supported
.txt - Supported
.unknown - Not Supported

from groupdocs.parser.options import FileType

# Get all supported file types
supported_file_types = FileType.get_supported_file_types()

# Display format details
print("Supported Document Formats:\n")
print(f"{'Extension':<12} {'Format Name':<50}")
print("-" * 62)

for file_type in sorted(supported_file_types, key=lambda x: x.extension):
    print(f"{file_type.extension:<12} {file_type.file_format:<50}")

Supported Document Formats:

Extension    Format Name                                       
--------------------------------------------------------------
.7z          7z Archive File                                   
.azw3        AZW3                                              
.bmp         Bitmap Image File                                 
.bz2         Bzip2 Archive File                                
.chm         Compiled HTML Help File                           
.csv         Comma Separ
[TRUNCATED]

import os

from groupdocs.parser import Parser
from groupdocs.parser.options import FileType

def process_file(file_path):
    """Process a file if its format is supported"""

    # Get file extension
    _, ext = os.path.splitext(file_path)

    # Check if format is supported
    supported_file_types = FileType.get_supported_file_types()
    is_supported = any(ft.extension.lower() == ext.lower() for ft in supported_file_types)

    if not is_supported:
        print(f"Error: File format '{ext}' is not supported")
        return False

    # Process the file
    with Parser(file_path) as parser:
        doc_info = parser.get_document_info()
        print(f"Processing: {file_path}")
        print(f"Format: {doc_info.file_type.file_format}")
        print(f"Pages: {doc_info.page_count}")

        # Extract text
        text_reader = parser.get_text()
        if text_reader is None:
            print("Text extraction isn't supported for this format")
            return False

        text = text_reader.read_to_end()
        print(f"Text extraction successful: {len(text)} characters")
        return True

# Example usage
process_file("sample.pdf")
process_file("sample.docx")

Processing: sample.pdf
Format: Portable Document Format File
Pages: 4
Text extraction successful: 4570 characters
Processing: sample.docx
Format: Microsoft Word Open XML Document
Pages: 2
Text extraction successful: 2584 characters