Extract images from document page Leave feedback
On this page
GroupDocs.Parser allows you to extract images from specific pages of a document, providing fine-grained control over image extraction.
- GroupDocs.Parser for Python via .NET installed
- Sample documents with multiple pages
- Basic understanding of page indexing (zero-based)
To extract images from a particular page:
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}")
The following sample file is used in this example: sample.pdf
Images on page 1:
Image 1: JPEG Image(.jpeg), size: 150x45
Image 2: JPEG Image(.jpeg), size: 375x234
Expected behavior: Returns only the images from the specified page, or an empty collection if the page has no images.
To process images page by page:
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}")
The following sample file is used in this example: sample.pptx
Page 1/3:
Type: Portable Network Graphic(.png), Position: (30, 20)
Type: JPEG Image(.jpeg), Position: (140, 130)
Total images on this page: 2
Page 2/3:
Type: JPEG Image(.jpeg), Position: (40, 110)
Type: JPEG Image(.jpeg), Position: (380, 110)
Total images on this page: 2
[TRUNCATED]
Expected behavior: Iterates through all pages and extracts images from each page individually, showing page-specific image counts.
To save images organized by page number:
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}")
The following sample file is used in this example: sample.pdf
images_by_page/page_1/image_1.jpeg (10 KB)
images_by_page/page_1/image_2.jpeg (88 KB)
images_by_page/page_2/image_1.jpeg (122 KB)
images_by_page/page_3/image_1.jpeg (160 KB)
images_by_page/page_4/image_1.jpeg (93 KB)
Expected behavior: Creates separate directories for each page and saves extracted images with organized naming.
To extract images from selected pages:
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}")
The following sample file is used in this example: sample.docx
selected_page_images/page1_img1.png (4 KB)
selected_page_images/page1_img2.jpeg (176 KB)
Expected behavior: Extracts images only from the specified pages, skipping others.
To analyze image distribution across pages:
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")
The following sample file is used in this example: 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)
To extract only the first image from each page:
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}")
The following sample file is used in this example: sample.pdf
first_images/page_1_first.jpeg (10 KB)
first_images/page_2_first.jpeg (122 KB)
first_images/page_3_first.jpeg (160 KB)
first_images/page_4_first.jpeg (93 KB)
Expected behavior: Extracts and saves only the first image found on each page.
- Page indices are zero-based (first page is index 0)
- Use
get_document_info()to determine the total number of pages - Check
parser.features.imagesbefore extracting images - Empty collections are returned for pages without images (not
None) - Page-by-page extraction is memory-efficient for large documents
- The method returns
Noneonly if image extraction is not supported for the document format
Was this page helpful?
Any additional feedback you'd like to share with us?
Please tell us how we can improve this page.
Thank you for your feedback!
We value your opinion. Your feedback will help us improve our documentation.
