Get document info Leave feedback

from groupdocs.parser import Parser

# Create an instance of Parser class
with Parser("./sample.docx") as parser:
    # Get the document info
    doc_info = parser.get_document_info()
    
    # Print document information
    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")
    
    # Print file extension
    print(f"File extension: {doc_info.file_type.extension}")

File type: Microsoft Word Open XML Document
Page count: 2
File size: 263263 bytes
File extension: .docx

from groupdocs.parser import Parser

# Open the file stream
with open("sample.pdf", "rb") as stream:
    # Create an instance of Parser class with the stream
    with Parser(stream) as parser:
        # Get the document info
        doc_info = parser.get_document_info()
        
        # Print document information
        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

def process_document(file_path):
    with Parser(file_path) as parser:
        # Get document information
        doc_info = parser.get_document_info()
        
        print(f"Processing: {file_path}")
        print(f"Type: {doc_info.file_type.file_format}")
        print(f"Pages: {doc_info.page_count}")
        print(f"Size: {doc_info.size / 1024:.2f} KB")
        
        # Process based on page count
        if doc_info.page_count > 0:
            print("Document has pages, proceeding with text extraction...")
            text_reader = parser.get_text()
            if text_reader is not None:
                print(text_reader.read_to_end())
        else:
            print("Document has no pages or page count is not available")

# Process different document types
process_document("sample.pdf")

Processing: sample.pdf
Type: Portable Document Format File
Pages: 4
Size: 608.18 KB
Document has pages, proceeding with text extraction...
                                                                                       Investor relations

Annual Report 2025  |  Port Ellery
Annual Report 2025
[TRUNCATED]

from groupdocs.parser import Parser

with Parser("./sample.docx") as parser:
    # Get document info
    doc_info = parser.get_document_info()
    
    print(f"Total pages: {doc_info.page_count}")
    
    # Iterate through pages
    for page_index in range(doc_info.page_count):
        # Extract text from each page
        print(f"\n--- Page {page_index + 1} ---")
        text_reader = parser.get_text(page_index)
        if text_reader is not None:
            page_text = text_reader.read_to_end()
            print(f"Characters: {len(page_text)}")

Total pages: 2

--- Page 1 ---
Characters: 974

--- Page 2 ---
Characters: 1610

from groupdocs.parser import Parser
from groupdocs.parser.exceptions import UnsupportedDocumentFormatException

# A Word document, and an audio recording that isn't a document
for path in ("./sample.docx", "./voice-memo.wav"):
    try:
        with Parser(path) as parser:
            doc_info = parser.get_document_info()
            print(f"{path}: {doc_info.file_type.file_format}, {doc_info.page_count} pages")

            # Some formats may not have page count
            if doc_info.page_count == 0:
                print("Page count is not available for this format")
    except UnsupportedDocumentFormatException:
        print(f"{path}: this document format isn't supported")
    except FileNotFoundError:
        print(f"File not found: {path}")

./sample.docx: Microsoft Word Open XML Document, 2 pages
./voice-memo.wav: this document format isn't supported