Extract images from document page area Leave feedback
On this page
GroupDocs.Parser allows extracting images from specific rectangular areas of a document page, enabling precise image extraction from defined regions.
- GroupDocs.Parser for Python via .NET installed
- Sample documents with images
- Understanding of coordinate systems
To extract images from a specific rectangular area:
from groupdocs.parser import Parser
from groupdocs.parser.options import PageAreaOptions
from groupdocs.parser.data import Rectangle, Point, Size
# Create an instance of Parser class
with Parser("./sample.pdf") as parser:
# Check if image extraction is supported
if not parser.features.images:
print("Image extraction not supported")
else:
# Define the area (upper-left corner, 300x100 pixels)
area = Rectangle(Point(0, 0), Size(300, 100))
# Create options for the area
options = PageAreaOptions(area)
# Extract images from the specified area
images = parser.get_images(options)
if images:
print(f"Images found in area:")
for idx, image in enumerate(images):
print(f" Image {idx + 1}: {image.file_type}, Page {image.page.index + 1}")
else:
print("No images found in the specified area")
The following sample file is used in this example: sample.pdf
Expected behavior: Returns only images that are located within the specified rectangular area.
To extract images from several predefined areas:
from groupdocs.parser import Parser
from groupdocs.parser.options import PageAreaOptions
from groupdocs.parser.data import Rectangle, Point, Size
import os
def extract_images_from_regions(file_path, regions, output_dir):
"""
Extract images from multiple predefined regions.
Args:
file_path: Path to document
regions: List of tuples (x, y, width, height)
output_dir: Directory to save images
"""
os.makedirs(output_dir, exist_ok=True)
with Parser(file_path) as parser:
if not parser.features.images:
print("Image extraction not supported")
return
for region_idx, (x, y, w, h) in enumerate(regions):
print(f"\nProcessing region {region_idx + 1}: ({x}, {y}, {w}x{h})")
# Create rectangle for this region
area = Rectangle(Point(x, y), Size(w, h))
options = PageAreaOptions(area)
# Extract images from this region
images = parser.get_images(options)
if images:
for img_idx, image in enumerate(images):
filename = f"region{region_idx + 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(" No images in this region")
# Define regions (e.g., header, body, footer)
regions = [
(0, 0, 600, 100), # Header region
(0, 100, 600, 700), # Body region
(0, 800, 600, 100) # Footer region
]
# Extract images from regions
extract_images_from_regions("document.pdf", regions, "region_images")
The following sample file is used in this example: document.pdf
region_images/region1_img1.jpeg (9 KB)
region_images/region2_img1.jpeg (9 KB)
region_images/region2_img2.jpeg (46 KB)
region_images/region2_img3.jpeg (60 KB)
region_images/region2_img4.jpeg (50 KB)
region_images/region2_img5.jpeg (61 KB)
Expected behavior: Extracts and saves images organized by the region they were found in.
To extract images from a specific area on a specific page:
from groupdocs.parser import Parser
from groupdocs.parser.options import PageAreaOptions
from groupdocs.parser.data import Rectangle, Point, Size
# Create an instance of Parser class
with Parser("document.pptx") as parser:
if not parser.features.images:
print("Image extraction not supported")
else:
# Get document info
info = parser.get_document_info()
# Process specific page (e.g., first page)
page_index = 0
if page_index < info.page_count:
# Define area (center of page, 400x300)
area = Rectangle(Point(100, 100), Size(400, 300))
options = PageAreaOptions(area)
# Extract images from the area on the specific page
images = parser.get_images(page_index, options)
if images:
print(f"Images on page {page_index + 1} in specified area:")
for image in images:
print(f" Type: {image.file_type}")
print(f" Position: ({image.rectangle.left}, {image.rectangle.top})")
print(f" Size: {image.rectangle.size.width}x{image.rectangle.size.height}")
else:
print(f"No images on page {page_index + 1} in specified area")
The following sample file is used in this example: document.pptx
Expected behavior: Extracts images from a specific area on a specific page.
To extract logo images from the header area:
from groupdocs.parser import Parser
from groupdocs.parser.options import PageAreaOptions
from groupdocs.parser.data import Rectangle, Point, Size
import os
def extract_header_logos(file_path, output_dir):
"""
Extract logo images from document header area.
"""
os.makedirs(output_dir, exist_ok=True)
with Parser(file_path) as parser:
if not parser.features.images:
print("Image extraction not supported")
return
# Define header area (top 150 pixels, full width)
header_area = Rectangle(Point(0, 0), Size(1000, 150))
options = PageAreaOptions(header_area)
# Extract images from header
images = parser.get_images(options)
if images:
print(f"Found {len(images)} images in header\n")
for idx, image in enumerate(images):
filename = f"logo_{idx + 1}{image.file_type.extension}"
filepath = os.path.join(output_dir, filename)
image.save(filepath)
print(f"Saved logo: {filename}")
else:
print("No images found in header area")
# Usage
extract_header_logos("invoice.pdf", "extracted_logos")
The following sample file is used in this example: invoice.pdf
Binary file (JPEG, 10 KB)
Expected behavior: Extracts logo or brand images typically found in document headers.
To extract images from document quadrants:
from groupdocs.parser import Parser
from groupdocs.parser.options import PageAreaOptions
from groupdocs.parser.data import Rectangle, Point, Size
def extract_by_quadrant(file_path, page_width=600, page_height=800):
"""
Extract images by document quadrant (TL, TR, BL, BR).
"""
# Define quadrants
quadrant_size_w = page_width // 2
quadrant_size_h = page_height // 2
quadrants = {
'Top-Left': Rectangle(Point(0, 0), Size(quadrant_size_w, quadrant_size_h)),
'Top-Right': Rectangle(Point(quadrant_size_w, 0), Size(quadrant_size_w, quadrant_size_h)),
'Bottom-Left': Rectangle(Point(0, quadrant_size_h), Size(quadrant_size_w, quadrant_size_h)),
'Bottom-Right': Rectangle(Point(quadrant_size_w, quadrant_size_h), Size(quadrant_size_w, quadrant_size_h))
}
with Parser(file_path) as parser:
if not parser.features.images:
print("Image extraction not supported")
return
for quadrant_name, area in quadrants.items():
options = PageAreaOptions(area)
images = parser.get_images(options)
if images:
image_list = list(images)
print(f"{quadrant_name}: {len(image_list)} images")
else:
print(f"{quadrant_name}: 0 images")
# Usage
extract_by_quadrant("layout.pdf")
The following sample file is used in this example: layout.pdf
Top-Left: 2 images
Top-Right: 1 images
Bottom-Left: 4 images
Bottom-Right: 3 images
Expected behavior: Categorizes and counts images by their location in document quadrants.
To filter images by size within an area:
from groupdocs.parser import Parser
from groupdocs.parser.options import PageAreaOptions
from groupdocs.parser.data import Rectangle, Point, Size
import os
def extract_large_images_from_area(file_path, area_rect, min_width, min_height, output_dir):
"""
Extract images larger than specified size from an area.
"""
os.makedirs(output_dir, exist_ok=True)
with Parser(file_path) as parser:
if not parser.features.images:
print("Image extraction not supported")
return
options = PageAreaOptions(area_rect)
images = parser.get_images(options)
if not images:
print("No images found in area")
return
saved_count = 0
for image in images:
# Check image size
size = image.rectangle.size
if size.width >= min_width and size.height >= min_height:
filename = f"large_image_{saved_count + 1}{image.file_type.extension}"
filepath = os.path.join(output_dir, filename)
image.save(filepath)
print(f"Saved: {filename} ({size.width}x{size.height})")
saved_count += 1
print(f"\nTotal large images saved: {saved_count}")
# Usage - extract images larger than 100x100 from center area
center_area = Rectangle(Point(100, 100), Size(400, 600))
extract_large_images_from_area("document.pdf", center_area, 100, 100, "large_images")
The following sample file is used in this example: document.pdf
large_images/large_image_1.jpeg (46 KB)
large_images/large_image_2.jpeg (60 KB)
large_images/large_image_3.jpeg (50 KB)
large_images/large_image_4.jpeg (61 KB)
Expected behavior: Extracts only images that meet the minimum size criteria within the specified area.
- Always check
parser.features.imagesbefore extracting images - Coordinates are in document-specific units (points or pixels)
- The origin (0, 0) is at the top-left corner
- Images partially overlapping the area boundary are included
- Use
get_images(page_index, options)to extract from a specific page area - Empty collections are returned if no images are found in the area (not
None)
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.
