Load file from local disk Leave feedback

from groupdocs.parser import Parser

# Specify the file path (absolute or relative)
file_path = "sample.docx"

# Create an instance of Parser class with the file path
with Parser(file_path) as parser:
    # Extract text from the document
    text_reader = parser.get_text()
    
    if text_reader is not None:
        # Print the extracted text
        print(text_reader.read_to_end())
    else:
        print("Text extraction isn't supported for this format")

Supply Agreement  |  Harbor Lane Provisions and Northwind Coffee Roasters  |  Confidential



Supply Agreement
Harbor Lane Provisions and Northwind Coffee Roasters
1. Parties
Buyer: Harbor Lane Provisions, 18 Quayside Road, Port Ellery, represented by Lena Park, Procurement Lead.
Supplier: Northwind Coffee Roasters, 4 Roastery Lane, Millbrook, represented by Alex Chen.
This agreement takes effect on 12 January 2026 and replaces the agreement of January 2023.
[TRUNCATED]

from groupdocs.parser import Parser

# Specify an absolute file path
file_path = "sample.pdf"

# Create an instance of Parser class
with Parser(file_path) as parser:
    # Get document info
    doc_info = parser.get_document_info()
    
    print(f"File type: {doc_info.file_type.file_format}")
    print(f"Page count: {doc_info.page_count}")
    print(f"File size: {doc_info.size} bytes")

File type: Portable Document Format File
Page count: 4
File size: 622772 bytes

from groupdocs.parser import Parser
import os

def process_files_from_directory(directory_path):
    """Process all supported documents in a directory"""
    
    # Get all files in the directory
    for filename in sorted(os.listdir(directory_path)):
        file_path = os.path.join(directory_path, filename)
        
        # Skip if not a file
        if not os.path.isfile(file_path):
            continue
        
        try:
            print(f"\nProcessing: {filename}")
            
            # Create parser instance
            with Parser(file_path) as parser:
                # Get document info
                doc_info = parser.get_document_info()
                print(f"  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:
                    text = text_reader.read_to_end()
                    print(f"  Characters: {len(text)}")
                    
        except Exception as e:
            print(f"  Error: {e}")

# Process every document in the ./documents folder
process_files_from_directory("documents")

Processing: annual-report.pdf
  Type: Portable Document Format File
  Pages: 4
  Characters: 4570

Processing: inventory.xlsx
  Type: Microsoft Excel Open XML Spreadsheet
  Pages: 2
  Characters: 4352

[TRUNCATED]

from groupdocs.parser import Parser
import os

def safe_load_document(file_path):
    """Safely load a document with error handling"""
    
    # Check if file exists
    if not os.path.exists(file_path):
        print(f"Error: File not found - {file_path}")
        return None
    
    try:
        # Create parser instance
        parser = Parser(file_path)
        print(f"Document loaded successfully: {file_path}")
        return parser
        
    except Exception as e:
        print(f"Error loading document: {e}")
        return None

# Try to load a document
parser = safe_load_document("sample.pdf")

if parser is not None:
    try:
        # Extract data
        text_reader = parser.get_text()
        if text_reader is not None:
            print(text_reader.read_to_end())
        else:
            print("Text extraction isn't supported for this format")
    finally:
        # Always release the parser
        parser.dispose()

Document loaded successfully: sample.pdf
                                                                                       Investor relations


Annual Report 2025  |  Port Ellery
Annual Report 2025


1. Overview
Harbor Lane Provisions supplies specialty food to 1,265 independent grocers, cafes and restaurants from its
[TRUNCATED]