Extract text areas Leave feedback

from groupdocs.parser import Parser

# Create an instance of Parser class
with Parser("./sample.pdf") as parser:
    # Extract text areas
    text_areas = parser.get_text_areas()
    
    # Check if text areas extraction is supported
    if text_areas is None:
        print("Text areas extraction isn't supported")
    else:
        # Iterate over text areas
        for area in text_areas:
            # Print page index, rectangle, and text
            print(f"Page: {area.page.index}, Rectangle: {area.rectangle}, Text: {area.text}")

from groupdocs.parser import Parser

# Create an instance of Parser class
with Parser("./sample.pdf") as parser:
    # Check if text areas extraction is supported
    if not parser.features.text_areas:
        print("Document doesn't support text areas 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
            for page_index in range(info.page_count):
                print(f"\nPage {page_index + 1}/{info.page_count}")
        
                # Extract text areas from the page
                text_areas = parser.get_text_areas(page_index)
        
                # Iterate over text areas
                if text_areas:
                    for area in text_areas:
                        # Print rectangle and text
                        rect = area.rectangle
                        print(f"Position: ({rect.left}, {rect.top}), Size: ({rect.size.width}x{rect.size.height})")
                        print(f"Text: {area.text}")

from groupdocs.parser import Parser
from groupdocs.parser.options import PageTextAreaOptions
from groupdocs.parser.data import Rectangle, Point, Size

# Create an instance of Parser class
with Parser("./sample.pdf") as parser:
    # Define the region (upper-left corner, 300x200 points)
    region = Rectangle(Point(0, 0), Size(300, 200))
    
    # Create options to extract only text areas with digits in the specified region
    options = PageTextAreaOptions(r"\d+", region)
    
    # Extract text areas
    text_areas = parser.get_text_areas(options)
    
    if text_areas is None:
        print("Text areas extraction isn't supported")
    else:
        # Iterate over filtered text areas
        for area in text_areas:
            print(f"Page: {area.page.index}, Rectangle: {area.rectangle}, Text: {area.text}")

from groupdocs.parser import Parser

# Create an instance of Parser class
with Parser("./sample.docx") as parser:
    # Extract text areas
    text_areas = parser.get_text_areas()
    
    if text_areas is None:
        print("Text areas extraction isn't supported")
    else:
        # Iterate over text areas
        for area in text_areas:
            # Get text style if available
            if area.text_style is not None:
                print(f"Text: {area.text}")
                print(f"Font: {area.text_style.font_name}")
                print(f"Size: {area.text_style.font_size}")
                print(f"Bold: {area.text_style.is_bold}")
                print(f"Italic: {area.text_style.is_italic}")
                print("---")

from groupdocs.parser import Parser
from groupdocs.parser.options import PageTextAreaOptions
from groupdocs.parser.data import Rectangle, Point, Size

def extract_from_regions(file_path, regions):
    """
    Extract text from specific regions of a document.
    
    Args:
        file_path: Path to the document
        regions: List of tuples (x, y, width, height)
    """
    with Parser(file_path) as parser:
        if not parser.features.text_areas:
            print("Text areas extraction not supported")
            return {}
        
        results = {}
        
        for idx, (x, y, w, h) in enumerate(regions):
            # Create rectangle for this region
            rect = Rectangle(Point(x, y), Size(w, h))
            options = PageTextAreaOptions(None, rect)
            
            # Extract text areas from this region
            areas = parser.get_text_areas(options)
            
            # Collect text from all areas in this region
            text_list = [area.text for area in areas] if areas else []
            results[f"region_{idx}"] = " ".join(text_list)
        
        return results

# 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 text from regions
extracted = extract_from_regions("sample.pdf", regions)
for region_name, text in extracted.items():
    print(f"{region_name}: {text[:100]}...")

region_0: Annual Report 2025  |  Port Ellery Investor relations Harbor Lane Provisions  |  Annual Report 2025 ...
region_1: Annual Report 2025  |  Port Ellery Annual Report 2025 1. Overview Harbor Lane Provisions supplies sp...
region_2: Harbor Lane Provisions  |  18 Quayside Road, Port Ellery  |   harborlane.example Harbor Lane Provisi...