Load specific file formats Leave feedback

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

# Create LoadOptions for Markdown format
load_options = LoadOptions(FileType.MD)

# Open the file stream
with open("sample.md", "rb") as stream:
    # Create an instance of Parser class with LoadOptions
    with Parser(stream, load_options) as parser:
        # Extract text from the Markdown document
        text_reader = parser.get_text()
        
        if text_reader is not None:
            # Print the extracted text
            # Markdown is detected; text without special symbols is printed
            print(text_reader.read_to_end())
        else:
            print("Text extraction isn't supported")

Harbor Lane Provisions: wholesale ordering guide

Welcome to Harbor Lane Provisions, the specialty food wholesaler on the Quayside in Port Ellery. This guide explains how to open an account, place orders and receive deliveries.

Opening an account

1. Fill in the account form at [harborlane.example/account](https://harborlane.example/account).
2. Send us your resale certificate.
3. Lena Park confirms your account within two working days.

[TRUNCATED]

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

# Create LoadOptions for MHTML format
load_options = LoadOptions(FileType.MHTML)

# Load MHTML document
with Parser("email_page.mhtml", load_options) as parser:
    # Extract text
    text_reader = parser.get_text()
    
    if text_reader is not None:
        print(text_reader.read_to_end())

Subject: Harbor Lane Provisions - Wholesale specialty food Date: Thu, 15 Jan 2026 09:00:00 -0000 MIME-Version: 1.0 Content-Type: multipart/related; type="text/html"; boundary="----=_HarborLane_Archive_2026" ------=_HarborLane_Archive_2026 Content-Type: text/html; charset="utf-8" Content-Transfer-Encoding: 8bit Content-Location: https://harborlane.example/ 
 
 HYPERLINK "https://harborlane.example/" Home  HYPERLINK "https://harborlane.example/catalog" Catalog  HYPERLINK "https://harborlane
[TRUNCATED]

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

# Create LoadOptions for OTP (OpenDocument Presentation Template) format
load_options = LoadOptions(FileType.OTP)

# Load OTP document
with Parser("template.otp", load_options) as parser:
    # Get document info
    doc_info = parser.get_document_info()
    
    print(f"File type: {doc_info.file_type.file_format}")
    print(f"Pages: {doc_info.page_count}")
    
    # Extract text
    text_reader = parser.get_text()
    if text_reader is not None:
        print(text_reader.read_to_end())

File type: OpenDocument Presentation Template
Pages: 2
Harbor Lane Provisions presentation title
Subtitle, presenter and date
Slide title
First point in Arial 18Second pointThird pointHarbor Lane colours: harbor navy, sea teal, sand and coral

from groupdocs.parser import Parser
from groupdocs.parser.options import LoadOptions, FileType
import os

def get_file_format(file_path):
    """Detect file format based on extension"""
    
    _, ext = os.path.splitext(file_path)
    ext = ext.lower()
    
    format_map = {
        '.md': FileType.MD,
        '.markdown': FileType.MD,
        '.mhtml': FileType.MHTML,
        '.mht': FileType.MHTML,
        '.otp': FileType.OTP,
    }
    
    return format_map.get(ext)

def load_document_with_format(file_path):
    """Load document with appropriate format specification"""
    
    file_format = get_file_format(file_path)
    
    if file_format:
        print(f"Loading with explicit format: {file_format}")
        load_options = LoadOptions(file_format)
        parser = Parser(file_path, load_options)
    else:
        print("Loading with auto-detection")
        parser = Parser(file_path)
    
    return parser

# Usage examples
with load_document_with_format("webpage.mhtml") as parser:
    text_reader = parser.get_text()
    if text_reader is not None:
        print(text_reader.read_to_end())

Loading with explicit format: MIME HTML File(.mhtml)
Subject: Harbor Lane Provisions - Wholesale specialty food Date: Thu, 15 Jan 2026 09:00:00 -0000 MIME-Version: 1.0 Content-Type: multipart/related; type="text/html"; boundary="----=_HarborLane_Archive_2026" ------=_HarborLane_Archive_2026 Content-Type: text/html; charset="utf-8" Content-Transfer-Encoding: 8bit Content-Location: https://harborlane.example/ 
 
 HYPERLINK "https://harborlane.example/" Home  HYPERLINK "https://harborlane.examp
[TRUNCATED]

from groupdocs.parser.options import FileType

# Common document formats (auto-detected)
# - PDF
# - DOC, DOCX
# - XLS, XLSX
# - PPT, PPTX
# - TXT
# - etc.

# Formats that may require explicit specification:
formats_needing_specification = {
    "Markdown": FileType.MD,
    "MHTML": FileType.MHTML,
    "OTP": FileType.OTP,
}

for name, format_value in formats_needing_specification.items():
    print(f"{name}: {format_value}")

Markdown: Markdown Files(.md)
MHTML: MIME HTML File(.mhtml)
OTP: OpenDocument Presentation Template(.otp)

from groupdocs.parser import Parser
from groupdocs.parser.options import LoadOptions

def safe_load_with_format(file_path, file_format):
    """Safely load a document with specific format and error handling"""
    
    try:
        # Create LoadOptions
        load_options = LoadOptions(file_format)
        
        # Create Parser instance
        with Parser(file_path, load_options) as parser:
            # Verify loading was successful
            doc_info = parser.get_document_info()
            print(f"Document loaded: {doc_info.file_type.file_format}")
            
            # Extract text
            text_reader = parser.get_text()
            if text_reader is not None:
                return text_reader.read_to_end()
            else:
                print("Text extraction not supported")
                return None
                
    except Exception as e:
        print(f"Error loading document with format {file_format}: {e}")
        
        # Try loading without format specification
        try:
            print("Attempting to load with auto-detection...")
            with Parser(file_path) as parser:
                text_reader = parser.get_text()
                if text_reader is not None:
                    return text_reader.read_to_end()
        except Exception as e2:
            print(f"Auto-detection also failed: {e2}")
            return None

# Example usage
from groupdocs.parser.options import FileType
text = safe_load_with_format("document.md", FileType.MD)

Document loaded: Markdown Files