Extract images from document page Leave feedback

from groupdocs.parser import Parser

# Create an instance of Parser class
with Parser("./sample.pdf") as parser:
    # Check if image extraction is supported
    if not parser.features.images:
        print("Document doesn't support image extraction")
    else:
        # Extract images from page 0 (first page)
        page_index = 0
        images = parser.get_images(page_index)
    
        if images:
            print(f"Images on page {page_index + 1}:")
            for idx, image in enumerate(images):
                size = image.rectangle.size
                print(f"  Image {idx + 1}: {image.file_type}, size: {size.width}x{size.height}")
        else:
            print(f"No images on page {page_index + 1}")

from groupdocs.parser import Parser

# Create an instance of Parser class
with Parser("./sample.pptx") as parser:
    # Check if image extraction is supported
    if not parser.features.images:
        print("Document doesn't support image extraction")
    else:
        # Get document info
        info = parser.get_document_info()
    
        # Check if document has pages
        if info.page_count == 0:
            print("Document has no pages")
        else:
            # Iterate over pages
            total_images = 0
            for page_index in range(info.page_count):
                print(f"\nPage {page_index + 1}/{info.page_count}:")
        
                # Extract images from the current page
                images = parser.get_images(page_index)
        
                if images:
                    page_image_count = 0
                    for image in images:
                        print(f"  Type: {image.file_type}, Position: ({image.rectangle.left}, {image.rectangle.top})")
                        page_image_count += 1
            
                    print(f"  Total images on this page: {page_image_count}")
                    total_images += page_image_count
                else:
                    print("  No images on this page")
    
            print(f"\nTotal images in document: {total_images}")

from groupdocs.parser import Parser
import os

# Create output directory
output_dir = "images_by_page"
os.makedirs(output_dir, exist_ok=True)

# Create an instance of Parser class
with Parser("./sample.pdf") as parser:
    if not parser.features.images:
        print("Image extraction not supported")
    else:
        # Get document info
        info = parser.get_document_info()
    
        # Process each page
        for page_index in range(info.page_count):
            # Create page-specific directory
            page_dir = os.path.join(output_dir, f"page_{page_index + 1}")
            os.makedirs(page_dir, exist_ok=True)
        
            # Extract images from page
            images = parser.get_images(page_index)
        
            if images:
                for img_idx, image in enumerate(images):
                    # Generate filename
                    filename = f"image_{img_idx + 1}{image.file_type.extension}"
                    filepath = os.path.join(page_dir, filename)
                
                    # Save image
                    image.save(filepath)
                    print(f"Saved: {filepath}")
            else:
                print(f"No images on page {page_index + 1}")

from groupdocs.parser import Parser
import os

# Create an instance of Parser class
with Parser("./sample.docx") as parser:
    if not parser.features.images:
        print("Image extraction not supported")
    else:
        # Define pages to process (e.g., pages 1, 3, and 5)
        pages_to_process = [0, 2, 4]  # Zero-based indices
    
        output_dir = "selected_page_images"
        os.makedirs(output_dir, exist_ok=True)

        # A page index past the last page raises an error, so check the page count
        page_count = parser.get_document_info().page_count
    
        for page_index in pages_to_process:
            if page_index >= page_count:
                print(f"\nPage {page_index + 1} skipped: the document has {page_count} pages")
                continue

            print(f"\nProcessing page {page_index + 1}...")
        
            # Extract images from this page
            images = parser.get_images(page_index)
        
            if images:
                for img_idx, image in enumerate(images):
                    filename = f"page{page_index + 1}_img{img_idx + 1}{image.file_type.extension}"
                    filepath = os.path.join(output_dir, filename)
                    image.save(filepath)
                    print(f"  Saved: {filename}")
            else:
                print(f"  No images found on page {page_index + 1}")

from groupdocs.parser import Parser

def analyze_image_distribution(file_path):
    """
    Analyze how images are distributed across document pages.
    """
    with Parser(file_path) as parser:
        if not parser.features.images:
            print("Image extraction not supported")
            return
        
        info = parser.get_document_info()
        
        image_stats = []
        total_images = 0
        
        for page_index in range(info.page_count):
            images = parser.get_images(page_index)
            
            if images:
                # Count images on this page
                image_list = list(images)
                page_image_count = len(image_list)
                
                # Collect image types
                image_types = [img.file_type.extension for img in image_list]
                
                image_stats.append({
                    'page': page_index + 1,
                    'count': page_image_count,
                    'types': image_types
                })
                
                total_images += page_image_count
        
        # Print summary
        print(f"Document: {file_path}")
        print(f"Total pages: {info.page_count}")
        print(f"Total images: {total_images}")
        print(f"Average images per page: {total_images / info.page_count:.2f}\n")
        
        # Print per-page details
        for stat in image_stats:
            types_str = ", ".join(set(stat['types']))
            print(f"Page {stat['page']}: {stat['count']} images ({types_str})")

# Usage
analyze_image_distribution("sample.pdf")

Document: sample.pdf
Total pages: 4
Total images: 5
Average images per page: 1.25

Page 1: 2 images (.jpeg)
Page 2: 1 images (.jpeg)
Page 3: 1 images (.jpeg)
Page 4: 1 images (.jpeg)

from groupdocs.parser import Parser
import os

# Create output directory
output_dir = "first_images"
os.makedirs(output_dir, exist_ok=True)

# Create an instance of Parser class
with Parser("./sample.pdf") as parser:
    if not parser.features.images:
        print("Image extraction not supported")
    else:
        info = parser.get_document_info()
    
        for page_index in range(info.page_count):
            # Extract images from page
            images = parser.get_images(page_index)
        
            if images:
                # Get first image only
                first_image = images[0]

                filename = f"page_{page_index + 1}_first{first_image.file_type.extension}"
                filepath = os.path.join(output_dir, filename)
                first_image.save(filepath)
                print(f"Saved first image from page {page_index + 1}: {filename}")
            else:
                print(f"No images on page {page_index + 1}")