all files added

src/Report/Report.py

@@ -0,0 +1,108 @@
+import os
+import PyPDF2
+from reportlab.lib.pagesizes import letter
+from reportlab.pdfgen import canvas
+from screeninfo import get_monitors
+import sys
+import codecs
+
+sys.stdout = codecs.getwriter("utf-8")(sys.stdout.buffer)
+
+def get_screen_size():
+    """Get the primary monitor screen size."""
+    try:
+        monitor = get_monitors()[0]  # Get primary monitor
+        screen_width = monitor.width
+        screen_height = monitor.height
+        return screen_width, int(screen_height * 1.5)  # Scale height
+    except Exception as e:
+        print(f"Error getting screen size: {e}")
+    return 1000, 1500  # Default size
+
+def add_padding_to_pdf(input_pdf, output_pdf, padding):
+    """Add padding to a PDF file."""
+    try:
+        reader = PyPDF2.PdfReader(input_pdf)
+        writer = PyPDF2.PdfWriter()
+
+        for page in reader.pages:
+            original_width = page.mediabox.width
+            original_height = page.mediabox.height
+
+            # New dimensions with padding
+            new_width = original_width + 2 * padding
+            new_height = original_height + 2 * padding
+
+            # Create a new canvas
+            packet = canvas.Canvas(output_pdf, pagesize=(new_width, new_height))
+            packet.translate(padding, padding)  # Center original content
+            packet.save()
+
+            writer.add_page(page)
+
+        with open(output_pdf, "wb") as out_file:
+            writer.write(out_file)
+
+        print(f"✅ Padding added: {input_pdf} -> {output_pdf}")
+
+    except Exception as e:
+        print(f"⚠️ Error adding padding to {input_pdf}: {e}")
+
+def merge_pdfs(pdf_list, output_path, elongated_files=[], normalize_size=True):
+    """Merge multiple PDFs into a single PDF."""
+    pdf_merger = PyPDF2.PdfMerger()
+
+    # Resolve absolute paths
+    pdf_list = [os.path.abspath(pdf) for pdf in pdf_list]
+
+    for pdf in pdf_list:
+        if not os.path.exists(pdf):
+            print(f"⚠️ File not found: {pdf}")
+            continue
+
+        try:
+            if pdf in elongated_files:
+                print(f"🔍 Processing elongated file: {pdf}")
+                # Add additional elongation logic here if needed
+            pdf_merger.append(pdf)
+            print(f"✅ Added: {pdf}")
+        except Exception as e:
+            print(f"⚠️ Could not add {pdf}: {e}")
+
+    try:
+        pdf_merger.write(output_path)
+        print(f"📄 Merged PDF saved as: {output_path}")
+    except Exception as e:
+        print(f"Error saving merged PDF: {e}")
+    finally:
+        pdf_merger.close()
+
+if __name__ == "__main__":
+    # List of PDF files to merge
+    pdf_files = [
+        "src/Report/1updated.pdf",
+        "data/reports/report_stats/2.pdf",
+        "data/reports/report_stats/3.pdf",
+        "data/reports/report_stats/objective.pdf",
+        "data/reports/template_PDF/brand marketing.pdf",
+        "data/reports/template_PDF/content marketing.pdf",
+        "data/reports/template_PDF/social media marketing.pdf",
+        "data/reports/report_stats/last.pdf"
+    ]
+
+    elongated_pdfs = [
+        "data/reports/template_PDF/brand marketing.pdf",
+        "data/reports/template_PDF/content marketing.pdf",
+        "data/reports/template_PDF/social media marketing.pdf"
+    ]
+
+    # Define output directory and strict file name
+    output_dir = "src/Report"
+    os.makedirs(output_dir, exist_ok=True)  # Create the directory if it doesn't exist
+    output_file = os.path.join(output_dir, "report.pdf")  # Enforce strict file name as report.pdf
+
+    # Merge the PDFs and save the result in the specified directory
+    merge_pdfs(pdf_files, output_file, elongated_files=elongated_pdfs)
+
+
+

src/Report/status.txt

@@ -0,0 +1 @@
+done

src/Report/updated1.py

@@ -0,0 +1,97 @@
+import sys
+from PyPDF2 import PdfReader, PdfWriter
+from reportlab.pdfgen import canvas
+from io import BytesIO
+
+def create_overlay_pdf(text, x, y, output_overlay_pdf, page_width, page_height, max_width):
+    packet = BytesIO()
+    can = canvas.Canvas(packet, pagesize=(page_width, page_height))
+
+    # Set initial font size
+    font_size = 44  # Larger font size to start with
+    can.setFont("Helvetica-Bold", font_size)
+    can.setFillColorRGB(0, 0, 0)  # Black text
+
+    # Measure the text width
+    text_width = can.stringWidth(text, "Helvetica-Bold", font_size)
+    
+    # If the text is too wide, reduce font size to fit within the max_width
+    if text_width > max_width:
+        font_size = 18  # Reduce font size if necessary
+        can.setFont("Helvetica-Bold", font_size)
+        text_width = can.stringWidth(text, "Helvetica-Bold", font_size)
+
+    # Convert page_width to float if it's a Decimal
+    page_width = float(page_width)  # Convert to float to avoid TypeError
+
+    # Dynamically calculate the x-coordinate to center the text
+    x_coordinate = (page_width - text_width) / 2  # Center the text horizontally
+
+    # Draw the string at the calculated position
+    can.drawString(x_coordinate, y, text)
+    can.save()
+
+    packet.seek(0)
+    with open(output_overlay_pdf, "wb") as overlay_file:
+        overlay_file.write(packet.getvalue())
+
+def merge_pdfs(input_pdf, overlay_pdf, output_pdf):
+    reader = PdfReader(input_pdf)
+    overlay = PdfReader(overlay_pdf)
+    writer = PdfWriter()
+
+    # Apply the overlay to the first page
+    original_page = reader.pages[0]
+    original_page.merge_page(overlay.pages[0])
+
+    writer.add_page(original_page)
+
+    # Add the remaining pages without the overlay
+    for page_num in range(1, len(reader.pages)):
+        writer.add_page(reader.pages[page_num])
+
+    with open(output_pdf, "wb") as output_file:
+        writer.write(output_file)
+
+if __name__ == "__main__":
+    # Retrieve company_name from command-line argument or use default
+    if len(sys.argv) > 1:
+        company_name = sys.argv[1]
+    else:
+        company_name = "Default_Company"
+
+    input_pdf_path = "data/reports/report_stats/1.pdf"
+    overlay_pdf_path = "src/Report/overlay_test.pdf"
+    output_pdf_path = "src/Report/1updated.pdf"
+
+    # Load the original PDF to get its dimensions
+    reader = PdfReader(input_pdf_path)
+    original_page = reader.pages[0]
+    page_width = original_page.mediabox.width
+    page_height = original_page.mediabox.height
+
+    # Start with conservative coordinates and adjust as needed
+    x_coordinate = 800  # Adjust as needed
+    y_coordinate = 600  # Adjust as needed
+    max_width = 500  # Maximum width for the text
+
+    # Step 1: Create the overlay PDF with the same size as the original page
+    create_overlay_pdf(company_name, x_coordinate, y_coordinate, overlay_pdf_path, page_width, page_height, max_width)
+    
+    # Step 2: Merge the overlay with the original PDF
+    merge_pdfs(input_pdf_path, overlay_pdf_path, output_pdf_path)
+
+    print(f"Generated PDF saved as {output_pdf_path} with company name: {company_name}")
+
+
+
+
+
+
+
+
+
+
+
+
+

src/analysis.py

@@ -0,0 +1,63 @@
+import subprocess
+import sys
+
+def install_requirements():
+    """Ensure dependencies are installed before running scripts."""
+    try:
+        subprocess.run([sys.executable, "-m", "pip", "install", "-r", "requirements.txt"], check=True)
+        print("✅ Dependencies installed successfully.")
+    except subprocess.CalledProcessError as e:
+        print(f"⚠️ Failed to install dependencies: {e}")
+
+def run_python_file(file_name, company_name):
+    """Run a Python script with subprocess."""
+    try:
+        result = subprocess.run(
+            [sys.executable, file_name, company_name],  
+            capture_output=True,
+            text=True
+        )
+
+        if result.returncode == 0:
+            return "success", result.stdout  
+        else:
+            return "error", f"Error in {file_name}: {result.stderr}"
+    except Exception as e:
+        return "error", f"An error occurred while running {file_name}: {str(e)}"
+
+def main():
+    if len(sys.argv) > 1:
+        company_name = sys.argv[1]
+    else:
+        company_name = "Default_Company"
+
+    install_requirements()  # Install requirements before execution
+
+    scripts = [
+        'src/input_analysis/product-analysis/product_analysis.py',
+        'src/input_analysis/competitor-analysis/competitor_analysis.py',
+        'src/input_analysis/Standarddeviation.py',
+        'src/input_analysis/renamebranding.py',
+        'src/input_analysis/path.py',
+        'src/input_analysis/feedback.py',
+        'src/brand.py',
+        'src/content.py',
+        'src/social.py',
+        'src/Report/updated1.py',
+        'src/Report/Report.py'
+    ]
+
+    for script in scripts:
+        status, message = run_python_file(script, company_name)
+        if status == "error":
+            print(message)
+            return
+        else:
+            print(f"{script} executed successfully.")
+
+    # ✅ After all scripts run successfully, mark the status as "done"
+    with open("src/Report/status.txt", "w") as f:
+        f.write("done")
+
+if __name__ == "__main__":
+    main()

src/brand.py

@@ -0,0 +1,416 @@
+import base64
+import os
+import sys
+import time
+from playwright.sync_api import sync_playwright
+from PIL import Image
+import pandas as pd
+
+def save_html_file(file_name, html_content):
+    with open(file_name, 'w') as file:
+        file.write(html_content)
+
+def encode_image_to_base64(image_path):
+    with open(image_path, "rb") as image_file:
+        return base64.b64encode(image_file.read()).decode('utf-8')
+
+# Allow user to upload images for logo and product images
+logo_image_path = r"src/templates_images/Component 3.png"
+cola_image_path = r"src/templates_images/Frame 52.png"  
+# Encode images to base64
+logo_base64 = encode_image_to_base64(logo_image_path)
+cola_base64 = encode_image_to_base64(cola_image_path)
+def save_html_file(file_name, html_content):
+    with open(file_name, 'w') as file:
+        file.write(html_content)
+
+def encode_image_to_base64(image_path):
+    try:
+        with open(image_path, "rb") as img_file:
+            return base64.b64encode(img_file.read()).decode("utf-8")
+    except FileNotFoundError:
+        print(f"Image not found: {image_path}")
+        return ""
+    except Exception as e:
+        print(f"Error encoding image {image_path}: {e}")
+        return ""
+# Function to generate HTML for Social Media Marketing
+# Function to generate HTML for Brand Marketing
+def generate_brand_marketing_html(product_image_base64_1, competitor_image_base64_1, product_image_base64_2, competitor_image_base64_2, donts_html, suggestions_html, company_name):
+    return f"""
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Brand Marketing Template</title>
+    <link href="https://fonts.googleapis.com/css2?family=Inter:wght@600&display=swap" rel="stylesheet">
+    <style>
+        body {{
+            font-family: 'Inter', sans-serif;
+            margin: 0;
+            padding: 10%;  /* Increased padding by 10% */
+            background-color: #fff;
+            font-size: 6px;
+        }}
+        @page {{
+            size: A4;
+            margin: 15px;  /* Increased margin to 15px */
+        }}
+        .header {{
+            display: flex;
+            justify-content: space-between;
+            align-items: center;
+            padding: 10px;  /* Increased padding to 10px */
+            background-color: #FFFFFF;
+            margin-bottom: 15px;  /* Increased margin between header and content */
+        }}
+        .header .logo {{
+            height: 25px;  /* Increased logo height */
+        }}
+        .container {{
+            display: flex;
+            flex-direction: column;
+            padding: 10px;  /* Increased padding to 10px */
+            flex-grow: 1;
+        }}
+        h1 {{
+            font-family: 'Times New Roman', serif;
+            font-size: 22px;  /* Increased font size */
+            font-weight: 500;
+            line-height: 1.2;
+            text-align: left;
+            margin-bottom: 15px;  /* Increased bottom margin */
+        }}
+        h2, p {{
+            font-size: 13px;  /* Increased font size */
+            font-weight: 400;
+            line-height: 1.4;
+            color: #000;
+        }}
+        .gap {{
+            font-size: 10px;
+            color: rgb(5, 5, 5);
+            font-weight: 100;
+        }}
+        .examples {{
+            font-size: 12px;  /* Increased font size */
+            color: green;
+        }}
+        .box-container {{
+            width: 100%;
+            display: flex;
+            flex-direction: column;
+            align-items: center;
+            margin-top: 15px;  /* Increased margin */
+        }}
+        .wraper {{
+            width: 100%;
+            height: 220px;  /* Increased height */
+            display: flex;
+            margin: 10px 0;  /* Increased margin */
+            border-radius: 12px;  /* Increased border radius */
+            overflow: hidden;
+            position: relative;
+        }}
+        .div-1 {{
+            flex: 1;
+            background-color: #ecbdbd; /* Pink background */
+            display: flex;
+            align-items: center;
+            justify-content: center;
+        }}
+        .div-2 {{
+            flex: 1;
+            background-color: #e6f9e6; /* Green background */
+            display: flex;
+            align-items: center;
+            justify-content: center;
+        }}
+        .wraper img {{
+            max-width: 90%;
+            max-height: 90%;
+            object-fit: contain;
+            border-radius: 8px;
+        }}
+        .vs-text {{
+            position: absolute;
+            left: 50%;
+            top: 50%;
+            transform: translate(-50%, -50%);
+            font-size: 18px;  /* Increased font size */
+            font-weight: bold;
+            color: black;
+        }}
+        .side-by-side-container {{
+            display: flex;
+            gap: 35px;  /* Increased gap between boxes */
+            margin-top: 45px;  /* Increased top margin */
+        }}
+        .pink-box, .green-box {{
+            flex: 1;
+            padding: 18px;  /* Increased padding */
+            margin-top: 15px;  /* Increased margin */
+            border-radius: 15px;  /* Increased border radius */
+            box-sizing: border-box;
+            height: auto;
+        }}
+        .pink-box {{
+            background-color: #ecbdbd;
+            color: red;
+            text-align: start;
+            display: flex;
+            flex-direction: column;
+            align-items: flex-start;
+        }}
+        .pink-box h6 {{
+            font-size: 16px;  /* Increased text size */
+            font-weight: bold;
+            margin: 8px 0;  /* Increased margin */
+            color: red;
+        }}
+        .green-box {{
+            background-color: #e6f9e6;
+            color: green;
+            text-align: start;
+            display: flex;
+            flex-direction: column;
+            align-items: flex-start;
+        }}
+        .green-box h6 {{
+            font-size: 16px;  /* Increased text size */
+            font-weight: bold;
+            margin: 8px 0;  /* Increased margin */
+            color: green;
+        }}
+        .case-study {{
+            font-size: 18px;  /* Increased font size */
+            color: green;
+            margin-top: 25px;  /* Increased margin */
+        }}
+        .container1 {{
+            font-size: 12px;  /* Increased font size */
+            color: green;
+            margin-top: 15px;  /* Increased margin */
+        }}
+        .case2 {{
+            font-size: 12px;  /* Increased font size */
+            color: rgb(1, 1, 1);
+            margin-top: 25px;  /* Increased margin */
+        }}
+        .case-study img {{
+            display: block;
+            max-width: 100%;
+            height: auto;
+            margin-top: 25px;  /* Increased margin */
+            border-radius: 10px;  /* Increased border radius */
+        }}
+    </style>
+</head>
+<body>
+    <div class="header">
+        <h1><span style="color:red;">Brand Marketing</span></h1>
+        <img src="data:image/png;base64,{logo_base64}" alt="Logo" class="logo">
+    </div>
+    <div class="container">
+        <p>{company_name} should use Brand Marketing effectively as the strategic promotion for identity, products, and services across all channels to create loyalty among consumers.</p>
+        <p class="gap"><span style="color: red;">Issue/Gap:</span> {company_name}'s current brand marketing efforts might not be reaching their full potential. A comprehensive analysis of brand messaging, target audience engagement across channels, and content strategy could reveal opportunities to optimize {company_name}'s marketing approach for greater reach and impact.</p>
+    </div>
+    <h2 class="examples"> Examples:</h2>
+    <div class="box-container">
+        <div class="wraper">
+            <div class="div-1"> <img src="data:image/png;base64,{product_image_base64_1}" alt="Product Image"></div>
+            <div class="vs-text">V/S</div>
+            <div class="div-2"> <img src="data:image/png;base64,{competitor_image_base64_1}" alt="Competitor Image"></div>
+        </div>
+        <div class="wraper">
+            <div class="div-1"> <img src="data:image/png;base64,{product_image_base64_2}" alt="Product Image"></div>
+            <div class="vs-text">V/S</div>
+            <div class="div-2"> <img src="data:image/png;base64,{competitor_image_base64_2}" alt="Competitor Image"></div>
+        </div>
+    </div>
+    <div class="side-by-side-container">
+        <div class="pink-box">
+            <h6>Drawbacks in Current Brand Marketing</h6>
+            <p>{donts_html}</p>
+        </div>
+        <div class="green-box">
+            <h6>How Banao Technologies Can Help</h6>
+            <p>{suggestions_html}</p>
+        </div>
+    </div>
+    <div class="case-study">
+        <h3>Case Study:</h3>
+        <div class="container1">
+            <p><span style="color: green;">Coca-Cola Brand Marketing using its iconic red color?</span></p>
+        </div>
+        <div class="case2">
+            <p>Coca-Cola uses its iconic red color, Spencerian script font, and "Open Happiness" slogan across all platforms, from its website to its social media pages to its countless physical advertisements.</p>
+            <img src="data:image/png;base64,{cola_base64}" alt="Cola" class="cola">
+        </div>
+    </div>
+</body>
+</html>
+
+    """
+
+# Function to parse "Product_output_cleaned.txt" for Don'ts and Suggestions specific to Brand Marketing
+def parse_cleaned_file_brand_marketing(file_path):
+    with open(file_path, "r") as file:
+        content = file.read()
+
+    sections = content.split("==================================================")
+    for section in sections:
+        lines = section.strip().split("\n")
+        if lines and "Brand Marketing" in lines[0]:
+            donts = []
+            suggestions = []
+            mode = None
+            for line in lines[1:]:
+                if line.startswith("Don'ts:"):
+                    mode = "donts"
+                elif line.startswith("Suggestions:"):
+                    mode = "suggestions"
+                elif mode == "donts" and line.startswith("-"):
+                    donts.append(line.lstrip("- "))
+                elif mode == "suggestions" and line.startswith("-"):
+                    suggestions.append(line.lstrip("- "))
+            return "<br>".join(donts), "<br>".join(suggestions)
+
+    return "", ""
+
+# Function to process Brand Marketing and generate HTML
+def process_brand_marketing(data, base_image_dir, output_file, cleaned_file_path, company_name):
+    # Filter for Brand Marketing category
+    brand_data = data[data["Category"] == "Brand Marketing"]
+    
+    if brand_data.empty:
+        print("No Brand Marketing data found in the provided Excel file.")
+        return
+
+    # Parse Don'ts and Suggestions
+    donts_html, suggestions_html = parse_cleaned_file_brand_marketing(cleaned_file_path)
+
+    # Ensure there are at least two rows
+    if len(brand_data) < 2:
+        print("Not enough rows for two product and competitor image comparisons.")
+        return
+
+    # Get the first two records (assuming these are needed)
+    brand_row_1 = brand_data.iloc[0]
+    brand_row_2 = brand_data.iloc[1]
+
+    product_image_path_1 = os.path.join(base_image_dir, brand_row_1["Product_Image_Name"])
+    competitor_image_path_1 = os.path.join(base_image_dir, brand_row_1["Competitor_Image_Name"])
+
+    product_image_path_2 = os.path.join(base_image_dir, brand_row_2["Product_Image_Name"])
+    competitor_image_path_2 = os.path.join(base_image_dir, brand_row_2["Competitor_Image_Name"])
+
+    # Encode images to Base64
+    product_image_base64_1 = encode_image_to_base64(product_image_path_1)
+    competitor_image_base64_1 = encode_image_to_base64(competitor_image_path_1)
+
+    product_image_base64_2 = encode_image_to_base64(product_image_path_2)
+    competitor_image_base64_2 = encode_image_to_base64(competitor_image_path_2)
+
+ # Generate HTML content
+    html_content = generate_brand_marketing_html(
+        product_image_base64_1,
+        competitor_image_base64_1,
+        product_image_base64_2,
+        competitor_image_base64_2,
+        donts_html,
+        suggestions_html,
+        company_name
+    )
+
+    # Save the HTML file
+    with open(output_file, "w", encoding="utf-8") as f:
+        f.write(html_content)
+
+    print(f"HTML file for Brand Marketing has been saved as: {output_file}")
+
+# Main script for Content Marketing
+if __name__ == "__main__":
+    if len(sys.argv) > 1:
+        company_name = sys.argv[1]  # The second argument passed will be the company_name
+    else:
+        company_name = "Default_Company"  # Default value if no argument is passed
+    # Load the Excel file
+    file_path = "Output File/excel/top_3_sd_results.xlsx"  # Replace with the path to your Excel file
+    data = pd.read_excel(file_path)
+
+    base_image_dir = ""  # Replace with the actual directory where your images are stored
+
+    # Path to the cleaned file with Don'ts and Suggestions
+    cleaned_file_path = "data/output_generated_file/Product_output_cleaned.txt"  # Replace with the path to your cleaned file
+
+    # Output HTML file
+    output_file = "src/templates/brand_marketing.html"
+
+    # Generate HTML for Content Marketing
+    process_brand_marketing(data, base_image_dir, output_file, cleaned_file_path, company_name)
+
+# Force UTF-8 encoding for terminal output
+sys.stdout.reconfigure(encoding='utf-8')
+
+def capture_screenshot_with_playwright(html_file_path, screenshot_path):
+    """
+    Capture a full-page screenshot of the HTML file directly using Playwright.
+    """
+    try:
+        # Launch Playwright in headless mode
+        with sync_playwright() as p:
+            browser = p.chromium.launch(headless=True)
+            page = browser.new_page()
+
+            # Open the HTML file in the browser
+            page.goto(f"file:///{os.path.abspath(html_file_path)}")
+            
+            # Capture the full-page screenshot
+            page.screenshot(path=screenshot_path, full_page=True)
+            print(f"Screenshot saved: {screenshot_path}")
+
+            browser.close()
+
+    except Exception as e:
+        print(f"Error capturing screenshot: {e}")
+
+def convert_png_to_pdf(png_path, company_name):
+    """
+    Convert a PNG image into a PDF strictly named as 'company_name brand marketing.pdf'
+    in the specified folder 'data/reports/template_PDF'.
+    """
+    try:
+        # Set the output folder and ensure it exists
+        output_folder = "data/reports/template_PDF"
+        os.makedirs(output_folder, exist_ok=True)
+
+        # Fixed PDF file name: 'brand marketing.pdf'
+        pdf_path = os.path.join(output_folder, "brand marketing.pdf")
+
+        # Convert the PNG to PDF
+        img = Image.open(png_path)
+        img.convert('RGB').save(pdf_path, "PDF")
+
+        print(f"PDF saved: {pdf_path}")
+    except Exception as e:
+        print(f"Error converting PNG to PDF: {e}")
+
+if __name__ == "__main__":
+    # Paths for demonstration
+    html_file_path = "src/templates/brand_marketing.html"
+    
+    # Screenshot saved in the folder: data/reports/template_ss
+    screenshot_folder = "data/reports/template_ss"
+    os.makedirs(screenshot_folder, exist_ok=True)
+    screenshot_path = os.path.join(screenshot_folder, "brand_marketing_screenshot.png")
+
+    # Ensure Playwright browsers are installed
+    os.system("playwright install")
+
+    # Capture screenshot
+    capture_screenshot_with_playwright(html_file_path, screenshot_path)
+
+    # Convert screenshot to PDF with the company name strictly as the filename
+    convert_png_to_pdf(screenshot_path, company_name)

src/content.py

@@ -0,0 +1,404 @@
+import pandas as pd
+import base64
+import os
+import sys
+from playwright.sync_api import sync_playwright
+from PIL import Image
+
+def save_html_file(file_name, html_content):
+    with open(file_name, 'w') as file:
+        file.write(html_content)
+
+def encode_image_to_base64(image_path):
+    with open(image_path, "rb") as image_file:
+        return base64.b64encode(image_file.read()).decode('utf-8')
+
+# Allow user to upload images for logo and product images
+logo_image_path = r"src/templates_images/Component 3.png"
+# Encode images to base64
+logo_base64 = encode_image_to_base64(logo_image_path)
+def save_html_file(file_name, html_content):
+    with open(file_name, 'w') as file:
+        file.write(html_content)
+
+def encode_image_to_base64(image_path):
+    try:
+        with open(image_path, "rb") as img_file:
+            return base64.b64encode(img_file.read()).decode("utf-8")
+    except FileNotFoundError:
+        print(f"Image not found: {image_path}")
+        return ""
+    except Exception as e:
+        print(f"Error encoding image {image_path}: {e}")
+        return ""
+
+# Encode images to base64
+def generate_content_marketing_html(product_image_base64_1, competitor_image_base64_1, product_image_base64_2, competitor_image_base64_2, product_image_base64_3, competitor_image_base64_3, donts_html, suggestions_html, company_name):
+    return f"""
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Content Marketing Template</title>
+    <link href="https://fonts.googleapis.com/css2?family=Inter:wght@600&display=swap" rel="stylesheet">
+    <style>
+        body {{
+            font-family: 'Inter', sans-serif;
+            margin: 0;
+            padding: 10%;  /* Increased padding */
+            background-color: #fff;
+            font-size: 8px;  /* Increased font size */
+        }}
+        @page {{
+            size: A4;
+            margin: 15px;  /* Increased margin */
+        }}
+        .header {{
+            display: flex;
+            justify-content: space-between;
+            align-items: center;
+            padding: 10px;  /* Increased padding */
+            background-color: #FFFFFF;
+            margin-bottom: 15px;  /* Increased margin */
+        }}
+        .header .logo {{
+            height: 30px;  /* Increased logo height */
+        }}
+        .container {{
+            display: flex;
+            flex-direction: column;
+            padding: 10px;  /* Increased padding */
+            flex-grow: 1;
+        }}
+        h1 {{
+            font-family: 'Times New Roman', serif;
+            font-size: 24px;  /* Increased font size */
+            font-weight: 500;
+            line-height: 1.3;
+            text-align: left;
+            margin-bottom: 20px;  /* Increased bottom margin */
+        }}
+        h2, p {{
+            font-size: 13px;  /* Increased font size */
+            font-weight: 400;
+            line-height: 1.5;
+            color: #000;
+        }}
+        .gap {{
+            font-size: 11px;  /* Increased font size */
+            color: rgb(5, 5, 5);
+            font-weight: 100;
+        }}
+        .examples {{
+            font-size: 13px;  /* Increased font size */
+            color: green;
+        }}
+        .box-container {{
+            width: 100%;
+            display: flex;
+            flex-direction: column;
+            align-items: center;
+            margin-top: 20px;  /* Increased margin */
+        }}
+        .wraper {{
+            width: 100%;
+            height: 220px;  /* Increased height */
+            display: flex;
+            margin: 10px 0;  /* Increased margin */
+            border-radius: 12px;  /* Increased border radius */
+            overflow: hidden;
+            position: relative;
+        }}
+        .div-1 {{
+            flex: 1;
+            background-color: #ecbdbd; /* Pink background */
+            display: flex;
+            align-items: center;
+            justify-content: center;
+        }}
+        .div-2 {{
+            flex: 1;
+            background-color: #e6f9e6; /* Green background */
+            display: flex;
+            align-items: center;
+            justify-content: center;
+        }}
+        .wraper img {{
+            max-width: 90%;
+            max-height: 90%;
+            object-fit: contain;
+            border-radius: 8px;
+        }}
+        .vs-text {{
+            position: absolute;
+            left: 50%;
+            top: 50%;
+            transform: translate(-50%, -50%);
+            font-size: 18px;  /* Increased font size */
+            font-weight: bold;
+            color: black;
+        }}
+        .side-by-side-container {{
+            display: flex;
+            gap: 40px;  /* Increased gap between boxes */
+            margin-top: 50px;  /* Increased top margin */
+        }}
+        .pink-box, .green-box {{
+            flex: 1;
+            padding: 20px;  /* Increased padding */
+            margin-top: 20px;  /* Increased margin */
+            border-radius: 15px;  /* Increased border radius */
+            box-sizing: border-box;
+            height: auto;
+        }}
+        .pink-box {{
+            background-color: #ecbdbd;
+            color: red;
+            text-align: start;
+            display: flex;
+            flex-direction: column;
+            align-items: flex-start;
+        }}
+        .pink-box h6 {{
+            font-size: 14px;  /* Increased font size */
+            font-weight: bold;
+            margin: 10px 0;  /* Increased margin */
+            color: red;
+        }}
+        .green-box {{
+            background-color: #e6f9e6;
+            color: green;
+            text-align: start;
+            display: flex;
+            flex-direction: column;
+            align-items: flex-start;
+        }}
+        .green-box h6 {{
+            font-size: 14px;  /* Increased font size */
+            font-weight: bold;
+            margin: 10px 0;  /* Increased margin */
+            color: green;
+        }}
+    </style>
+</head>
+<body>
+    <div class="header">
+        <h1><span style="color:red;">Content Marketing</span></h1>
+        <img src="data:image/png;base64,{logo_base64}" alt="Logo" class="logo">
+    </div>
+    <div class="container">
+        <p>{company_name} should use Content Marketing effectively as the strategic promotion for identity, products, and services across all channels to create loyalty among consumers.</p>
+        <p class="gap"><span style="color: red;">Issue/Gap:</span> {company_name}'s current content marketing efforts might not be reaching their full potential. A comprehensive analysis of brand messaging, target audience engagement across channels, and content strategy could reveal opportunities to optimize {company_name}'s marketing approach for greater reach and impact.</p>
+    </div>
+    <h2 class="examples">Examples:</h2>
+    <div class="box-container">
+        <div class="wraper">
+            <div class="div-1"> 
+                <img src="data:image/png;base64,{product_image_base64_1}" alt="Product Image">
+            </div>
+            <div class="vs-text">V/S</div>
+            <div class="div-2">
+                <img src="data:image/png;base64,{competitor_image_base64_1}" alt="Competitor Image">
+            </div>
+        </div>
+        <div class="wraper">
+            <div class="div-1"> 
+                <img src="data:image/png;base64,{product_image_base64_2}" alt="Product Image">
+            </div>
+            <div class="vs-text">V/S</div>
+            <div class="div-2">
+                <img src="data:image/png;base64,{competitor_image_base64_2}" alt="Competitor Image">
+            </div>
+        </div>
+        <div class="wraper">
+            <div class="div-1"> 
+                <img src="data:image/png;base64,{product_image_base64_3}" alt="Product Image">
+            </div>
+            <div class="vs-text">V/S</div>
+            <div class="div-2">
+                <img src="data:image/png;base64,{competitor_image_base64_3}" alt="Competitor Image">
+            </div>
+        </div>
+    </div>
+    <div class="side-by-side-container">
+        <div class="pink-box">
+            <h6>Drawbacks in Current Content Marketing</h6>
+            <p>{donts_html}</p>
+        </div>
+        <div class="green-box">
+            <h6>How Banao Technologies Can Help</h6>
+            <p>{suggestions_html}</p>
+        </div>
+    </div>
+</body>
+</html>
+"""
+
+# Function to parse "Product_output_cleaned.txt" for Don'ts and Suggestions specific to Content Marketing
+def parse_cleaned_file_content_marketing(file_path):
+    with open(file_path, "r") as file:
+        content = file.read()
+
+    sections = content.split("==================================================")
+    for section in sections:
+        lines = section.strip().split("\n")
+        if lines and "Content Marketing" in lines[0]:
+            donts = []
+            suggestions = []
+            mode = None
+            for line in lines[1:]:
+                if line.startswith("Don'ts:"):
+                    mode = "donts"
+                elif line.startswith("Suggestions:"):
+                    mode = "suggestions"
+                elif mode == "donts" and line.startswith("-"):
+                    donts.append(line.lstrip("- "))
+                elif mode == "suggestions" and line.startswith("-"):
+                    suggestions.append(line.lstrip("- "))
+            return "<br>".join(donts), "<br>".join(suggestions)
+
+    return "", ""
+
+# Function to process Content Marketing and generate HTML
+def process_content_marketing(data, base_image_dir, output_file, cleaned_file_path, company_name):
+    # Filter for Content Marketing category
+    content_data = data[data["Category"] == "Content Marketing"]
+    
+    if content_data.empty:
+        print("No Content Marketing data found in the provided Excel file.")
+        return
+       # Parse Don'ts and Suggestions
+    donts_html, suggestions_html = parse_cleaned_file_content_marketing(cleaned_file_path)
+
+    # Ensure there are at least two rows
+    if len(content_data) < 3:
+         print("Not enough rows for two product and competitor image comparisons.")
+         return
+    # Get the first record (assuming one Content Marketing entry is needed)
+    # Get the first two records (assuming these are needed)
+    content_row_1 = content_data.iloc[0]
+    content_row_2 = content_data.iloc[1]
+    content_row_3 = content_data.iloc[2]
+
+    product_image_path_1 = os.path.join(base_image_dir, content_row_1["Product_Image_Name"])
+    competitor_image_path_1 = os.path.join(base_image_dir, content_row_1["Competitor_Image_Name"])
+
+    product_image_path_2 = os.path.join(base_image_dir, content_row_2["Product_Image_Name"])
+    competitor_image_path_2 = os.path.join(base_image_dir, content_row_2["Competitor_Image_Name"])
+
+    product_image_path_3 = os.path.join(base_image_dir, content_row_3["Product_Image_Name"])
+    competitor_image_path_3 = os.path.join(base_image_dir, content_row_3["Competitor_Image_Name"])
+
+    # Encode images to Base64
+    product_image_base64_1 = encode_image_to_base64(product_image_path_1)
+    competitor_image_base64_1 = encode_image_to_base64(competitor_image_path_1)
+
+    product_image_base64_2 = encode_image_to_base64(product_image_path_2)
+    competitor_image_base64_2 = encode_image_to_base64(competitor_image_path_2)
+
+    # Encode images to Base64
+    product_image_base64_3 = encode_image_to_base64(product_image_path_3)
+    competitor_image_base64_3 = encode_image_to_base64(competitor_image_path_3)
+
+    # Generate HTML content
+    html_content = generate_content_marketing_html(product_image_base64_1, competitor_image_base64_1, product_image_base64_2, competitor_image_base64_2, product_image_base64_3, competitor_image_base64_3, donts_html, suggestions_html, company_name)
+
+    # Save the HTML file
+    with open(output_file, "w", encoding="utf-8") as f:
+        f.write(html_content)
+
+    print(f"HTML file for Content Marketing has been saved as: {output_file}")
+
+# Main script for Content Marketing
+if __name__ == "__main__":
+    if len(sys.argv) > 1:
+        company_name = sys.argv[1]  # The second argument passed will be the company_name
+    else:
+        company_name = "Default_Company"  # Default value if no argument is passed
+    # Load the Excel file
+    file_path = "Output File/excel/top_3_sd_results.xlsx"  # Replace with the path to your Excel file
+    data = pd.read_excel(file_path)
+
+    # Set the base directory for images
+    base_image_dir = ""  # Replace with the actual directory where your images are stored
+
+    # Path to the cleaned file with Don'ts and Suggestions
+    cleaned_file_path = "data/output_generated_file/Product_output_cleaned.txt"
+    # Output HTML file
+    output_file = "src/templates/content_marketing.html"
+
+    # Generate HTML for Content Marketing
+    process_content_marketing(data, base_image_dir, output_file, cleaned_file_path, company_name)
+
+# Force UTF-8 encoding for terminal output
+sys.stdout.reconfigure(encoding='utf-8')
+
+def capture_screenshot_with_playwright(html_file_path, screenshot_path):
+    """
+    Capture a full-page screenshot of the HTML file directly using Playwright.
+    """
+    try:
+        # Launch Playwright in headless mode
+        with sync_playwright() as p:
+            browser = p.chromium.launch(headless=True)
+            page = browser.new_page()
+
+            # Open the HTML file in the browser
+            page.goto(f"file:///{os.path.abspath(html_file_path)}")
+            
+            # Capture the full-page screenshot
+            page.screenshot(path=screenshot_path, full_page=True)
+            print(f"Screenshot saved: {screenshot_path}")
+
+            browser.close()
+
+    except Exception as e:
+        print(f"Error capturing screenshot: {e}")
+
+def convert_png_to_pdf(png_path, company_name):
+    """
+    Convert a PNG image into a PDF strictly named as 'company_name brand marketing.pdf'
+    in the specified folder 'data/reports/template_PDF'.
+    """
+    try:
+        # Set the output folder and ensure it exists
+        output_folder = "data/reports/template_PDF"
+        os.makedirs(output_folder, exist_ok=True)
+
+        # Create the PDF file name as 'company_name brand marketing.pdf'
+        pdf_path = os.path.join(output_folder, "content marketing.pdf") 
+
+        # Convert the PNG to PDF
+        img = Image.open(png_path)
+        img.convert('RGB').save(pdf_path, "PDF")
+
+        print(f"PDF saved: {pdf_path}")
+    except Exception as e:
+        print(f"Error converting PNG to PDF: {e}")
+
+if __name__ == "__main__":
+    # Paths for demonstration
+    html_file_path = "src/templates/content_marketing.html"
+    
+    # Screenshot saved in the folder: data/reports/template_ss
+    screenshot_folder = "data/reports/template_ss"
+    os.makedirs(screenshot_folder, exist_ok=True)
+    screenshot_path = os.path.join(screenshot_folder, "content_marketing_screenshot.png")
+
+    # Ensure Playwright browsers are installed
+    os.system("playwright install")
+
+    # Capture screenshot
+    capture_screenshot_with_playwright(html_file_path, screenshot_path)
+
+    # Convert screenshot to PDF with the company name strictly as the filename
+    convert_png_to_pdf(screenshot_path, company_name)
+
+
+
+
+
+
+
+

src/input_analysis/Standarddeviation.py

@@ -0,0 +1,186 @@
+import pandas as pd
+import numpy as np
+
+# Load Excel files
+product_data = pd.read_excel("Output File/excel/product_analysis.xlsx")
+competitor_data = pd.read_excel("Output File/excel/competitor_analysis.xlsx")
+
+# Function to filter criteria based on available columns
+def filter_existing_criteria(data, criteria):
+    """
+    Filters a list of criteria to include only those present in the given DataFrame columns.
+
+    Args:
+        data: DataFrame containing the data.
+        criteria: List of criteria to filter.
+
+    Returns:
+        List of filtered criteria that exist in the DataFrame columns.
+    """
+    return [criterion for criterion in criteria if criterion in data.columns]
+
+# Define criteria for each category
+branding_criteria = [
+    "Logo Placement", "Consistency", "Alignment",
+    "Brand Colors", "Typography Consistency", "Brand Identity", "Template Consistency"
+]
+content_marketing_criteria = [
+    "Content Visibility", "Engagement Cues", "Storytelling",
+    "Aesthetic Coherence", "Content Relevance"
+]
+social_media_marketing_criteria = [
+    "Font Size", "Visibility of Text", "Alignment",
+    "Aesthetic Appeal", "Repetitiveness"
+]
+
+# Filter criteria based on available columns in the data
+branding_criteria_filtered = filter_existing_criteria(product_data, branding_criteria)
+content_marketing_criteria_filtered = filter_existing_criteria(product_data, content_marketing_criteria)
+social_media_marketing_criteria_filtered = filter_existing_criteria(product_data, social_media_marketing_criteria)
+
+# Helper function to calculate the mean value for a criterion
+def calculate_mean_criterion_value(product_data, competitor_data, criterion):
+    """
+    Calculate the mean of a criterion from both product and competitor data, ignoring NaN values.
+
+    Args:
+        product_data: DataFrame containing product data.
+        competitor_data: DataFrame containing competitor data.
+        criterion: The column name representing the criterion.
+
+    Returns:
+        Mean value of the criterion.
+    """
+    combined_values = np.concatenate([
+        product_data[criterion].dropna().values,
+        competitor_data[criterion].dropna().values,
+    ])
+    return np.nanmean(combined_values)
+
+# Helper function to calculate the score differences
+def calculate_score_differences(product_scores, competitor_scores, product_data, competitor_data, category_criteria):
+    """
+    Calculate the score differences, replacing NaN with mean values.
+
+    Args:
+        product_scores: Scores of a product post for the criteria.
+        competitor_scores: Scores of a competitor post for the criteria.
+        product_data: DataFrame containing product data.
+        competitor_data: DataFrame containing competitor data.
+        category_criteria: List of criteria in the category.
+
+    Returns:
+        Array of score differences.
+    """
+    score_diff = product_scores - competitor_scores
+    for k, diff in enumerate(score_diff):
+        if np.isnan(diff):
+            mean_value = calculate_mean_criterion_value(product_data, competitor_data, category_criteria[k])
+            score_diff[k] = mean_value
+    return score_diff
+
+# Main function to calculate the SD comparison matrix
+def calculate_sd_comparison_matrix(product_data, competitor_data, category_criteria):
+    """
+    Calculate a 6x6 SD Comparison Matrix for a specific category, replacing NaN differences with the mean of the criteria.
+    """
+    # If there are no criteria, return a DataFrame of zeros
+    if not category_criteria:
+        return pd.DataFrame(
+            np.zeros((6, 6)),
+            index=[f"Product_{i+1}" for i in range(6)],
+            columns=[f"Competitor_{j+1}" for j in range(6)]
+        )
+    
+    sd_matrix = np.zeros((6, 6))  # Initialize a 6x6 matrix for SD values
+
+    for i in range(6):  # Loop over product posts
+        for j in range(6):  # Loop over competitor posts
+            product_scores = product_data.iloc[i][category_criteria].values
+            competitor_scores = competitor_data.iloc[j][category_criteria].values
+
+            # Calculate score differences
+            score_diff = calculate_score_differences(
+                product_scores, competitor_scores, product_data, competitor_data, category_criteria
+            )
+
+            # Safely calculate the standard deviation
+            if len(score_diff) > 0:
+                sd_matrix[i, j] = np.std(score_diff)
+            else:
+                sd_matrix[i, j] = 0
+
+    # Convert to DataFrame for better readability
+    return pd.DataFrame(sd_matrix,
+                        index=[f"Product_{i+1}" for i in range(6)],
+                        columns=[f"Competitor_{j+1}" for j in range(6)])
+
+
+# Calculate SD matrices for each category
+branding_sd_matrix = calculate_sd_comparison_matrix(product_data, competitor_data, branding_criteria_filtered)
+content_marketing_sd_matrix = calculate_sd_comparison_matrix(product_data, competitor_data, content_marketing_criteria_filtered)
+social_media_marketing_sd_matrix = calculate_sd_comparison_matrix(product_data, competitor_data, social_media_marketing_criteria_filtered)
+
+# Function to find the top SD values ensuring non-repetitive product and competitor image pairs
+def find_top_non_repetitive_sd(sd_matrix, product_data, competitor_data, category, top_count=3):
+    """
+    Find the top SD values ensuring non-repetitive product and competitor image pairs within the same category.
+
+    Args:
+        sd_matrix: DataFrame representing the SD matrix.
+        product_data: DataFrame containing product data (to extract image names).
+        competitor_data: DataFrame containing competitor data (to extract image names).
+        category: String representing the category name.
+        top_count: Number of top results to return (default is 3).
+
+    Returns:
+        List of tuples containing category, product image name, competitor image name, and SD value.
+    """
+    used_product_images = set()
+    used_competitor_images = set()
+    top_results = []
+
+    for i in range(sd_matrix.shape[0]):
+        for j in range(sd_matrix.shape[1]):
+            if len(top_results) == top_count:
+                break
+
+            product_image = product_data.iloc[i]['Image']
+            competitor_image = competitor_data.iloc[j]['Image']
+            sd_value = sd_matrix.iloc[i, j]
+
+            if product_image not in used_product_images and competitor_image not in used_competitor_images:
+                top_results.append((category, product_image, competitor_image, sd_value))
+                used_product_images.add(product_image)
+                used_competitor_images.add(competitor_image)
+
+    return top_results
+
+# Find top non-repetitive SD results
+branding_top_3 = find_top_non_repetitive_sd(branding_sd_matrix, product_data, competitor_data, "Brand Marketing")
+content_marketing_top_3 = find_top_non_repetitive_sd(content_marketing_sd_matrix, product_data, competitor_data, "Content Marketing")
+social_media_marketing_top_3 = find_top_non_repetitive_sd(social_media_marketing_sd_matrix, product_data, competitor_data, "Social Media Marketing")
+
+# Combine results into a DataFrame
+all_top_3 = branding_top_3 + content_marketing_top_3 + social_media_marketing_top_3
+top_3_df = pd.DataFrame(
+    all_top_3,
+    columns=['Category', 'Product_Image_Name', 'Competitor_Image_Name', 'SD_Value']
+)
+
+# Save results to Excel
+top_3_df.to_excel("Output File/excel/top_3_sd_results.xlsx", index=False)
+
+# Print the results
+print("\nTop 3 SD Results DataFrame:")
+print(top_3_df)
+import os
+
+output_folder = "data/output_generated_file/Output File/excel"
+output_file_path = os.path.join(output_folder, "top_3_sd_results.xlsx")
+os.makedirs(output_folder, exist_ok=True)
+# Save results to the specified folder
+top_3_df.to_excel(output_file_path, index=False)
+
+# Print confirmation
+print(f"Top 3 SD Results saved in: {output_file_path}")

src/input_analysis/competitor-analysis/competitor_analysis.py

@@ -0,0 +1,237 @@
+import base64
+import requests
+from PIL import Image
+import io
+import json
+import logging
+import json
+import pandas as pd
+import re
+
+
+IMAGE_ANALYSES_KEY = "Image Analyses"
+# Configure logging
+logging.basicConfig(level=logging.INFO)
+
+import os
+api_key = os.environ.get("OPENAI_API_KEY")
+
+# Function to encode the image to base64
+def encode_image(image_path):
+    try:
+        with Image.open(image_path) as img:
+            img.thumbnail((800, 800))  # Resize image
+            buffer = io.BytesIO()
+            img.save(buffer, format="JPEG", quality=85)
+            encoded_image = base64.b64encode(buffer.getvalue()).decode('utf-8')
+            return encoded_image
+    except Exception as e:
+        logging.error(f"Failed to encode image {image_path}: {e}")
+        return None
+
+# Function to get image dimensions
+def get_image_dimensions(image_path):
+    try:
+        with Image.open(image_path) as img:
+            return img.size  # returns (width, height)
+    except Exception as e:
+        logging.error(f"Failed to get dimensions for image {image_path}: {e}")
+        return (0, 0)
+
+# Image paths for analysis
+image_paths = [
+    "data/competitor/image1.jpeg",
+    "data/competitor/image2.jpeg",
+    "data/competitor/image3.jpeg",
+    "data/competitor/image4.jpeg",
+    "data/competitor/image5.jpeg",
+    "data/competitor/image6.jpeg"
+]
+
+# Headers for the OpenAI API request
+headers = {
+    "Content-Type": "application/json",
+    "Authorization": f"Bearer {api_key}"
+}
+
+# Competitor information (context for analysis)
+competitor_information = """
+The competitor is a leading brand in the digital marketing space known for its consistent visual branding and innovative designs on social media. They target a tech-savvy audience aged 20-35 with a focus on modern aesthetics, engaging storytelling, and minimalist yet powerful branding.
+"""
+
+system_message = """
+Analyze the branding, content marketing, and social media marketing effectiveness of a company for the provided Instagram post image.
+Evaluate it based on the following criteria and return a detailed JSON structure. Each criterion should have an individual score (0-10), and the total score for the category should be the average of its criteria.
+Give 9 or above only when it's extraordinary. Industry standard 7-8
+### Categories and Definitions:
+
+#### Branding:
+- **Logo Placement**: Is the logo perfectly sized, clearly visible, and well-positioned without being intrusive?
+- **Brand Colors**: Are brand colors used consistently and without deviations?
+- **Typography**: Are the fonts aligned with the brand identity, consistent in style, and visually appealing?
+- **Brand Identity**: Does the post effectively reflect the brand's unique persona and messaging?
+- **Visual Hierarchy**: Are key elements prioritized effectively to guide the viewer’s attention?
+- **Template Consistency**: Are templates consistent with previous posts, reflecting a uniform design approach?
+- **Messaging Alignment**: Is the brand messaging clear, consistent, and reflective of the brand's tone?
+- **Subtle Branding**: Does the branding strike the right balance (not overly subtle or excessive)?
+- **Overbranding**: Does the post avoid overwhelming and distracting brand elements?
+- **Creative Variations**: Are there innovative and creative design variations in the post?
+
+#### Content Marketing:
+- **Content Visibility**: Is the primary content clear and highlighted effectively?
+- **Engagement Cues**: Are clear and compelling calls-to-action (CTAs) present and engaging?
+- **Information Overload**: Does the post avoid over-saturated visuals or excessive text?
+- **Storytelling**: Does the post convey a relevant and engaging narrative that resonates with the audience?
+- **Content Variety**: Are the posts diverse and free of monotonous or repetitive elements?
+- **Typography Consistency**: Is the typography visually attractive and consistent throughout the design?
+- **Aesthetic Coherence**: Do all elements harmonize to create a visually appealing composition?
+- **Content Relevance**: Is the content relevant to the brand and its target audience?
+- **Stock Elements**: Does the design avoid excessive use of generic or stock imagery?
+
+#### Social Media Marketing:
+- **Font Size**: Are fonts appropriately sized and legible on various screen sizes?
+- **Visibility of Text**: Is the text easy to read, with proper contrast, placement, and spacing?
+- **Logo Placement**: Does the logo placement avoid disrupting the design's aesthetic appeal?
+- **Consistency**: Does the post maintain design cohesion across elements?
+- **Alignment**: Are elements aligned professionally, creating a balanced and clean layout?
+- **Aesthetic Appeal**: Is the overall design visually engaging and suitable for the platform?
+- **Brand Elements**: Are brand assets (like logos, icons, or visuals) used effectively and sparingly?
+- **Repetitiveness**: Does the design avoid repetitive themes and offer fresh creative ideas?
+
+### Output JSON Format:
+### Only return the following format strictly
+
+{
+    "Branding Score": total_avg_score, explanation.
+    "criteria_name": score, explanation.
+    "criteria_name": score, explanation.
+
+    "Content Marketing Score": total_avg_score, explanation.
+    "criteria_name": score, explanation.
+    "criteria_name": score, explanation.
+
+    "Social Media Marketing Score": total_avg_score, explanation.
+    "criteria_name": score, explanation.
+    "criteria_name": score, explanation.
+}
+"""
+
+# Function to request analysis from OpenAI API
+def request_analysis(system_message, user_message, model="gpt-4o-mini", max_tokens=1500):
+    payload = {
+        "model": model,
+        "messages": [
+            {"role": "system", "content": system_message},
+            {"role": "user", "content": user_message}
+        ],
+        "max_tokens": max_tokens
+    }
+    logging.debug(f"Payload Sent: {json.dumps(payload, indent=4)}")
+    response = requests.post("https://api.openai.com/v1/chat/completions", headers=headers, json=payload)
+
+    if response.status_code == 200:
+        try:
+            return response.json().get("choices", [{}])[0].get("message", {}).get("content", "Unexpected response format")
+        except Exception as e:
+            logging.error(f"Error parsing response: {e}")
+            logging.debug(f"Raw Response: {response.text}")
+            return "Error parsing the response."
+    else:
+        logging.error(f"API Error: {response.status_code}, {response.text}")
+        return "Error with the API request."
+
+# Initialize structured output for the analyses
+output_structure = {
+   IMAGE_ANALYSES_KEY: []
+}
+
+# Loop through each image for analysis
+for image_path in image_paths:
+    base64_image = encode_image(image_path)
+    if not base64_image:
+        output_structure[IMAGE_ANALYSES_KEY].append({
+            "Image": image_path,
+            "Analysis": "Failed to encode image."
+        })
+        continue
+
+    width, height = get_image_dimensions(image_path)
+    user_message = f"""
+    Company Information: {competitor_information}
+    Analyze the Instagram post with dimensions {width}x{height} pixels. Image data: {base64_image}
+    """
+
+    try:
+        analysis_result = request_analysis(system_message, user_message)
+        try:
+            # Parse result and ensure it matches the required format
+            parsed_result = json.loads(analysis_result)
+        except json.JSONDecodeError:
+            logging.warning(f"Response not in expected JSON format for {image_path}: {analysis_result}")
+            parsed_result = {"Raw Response": analysis_result}
+
+        output_structure[IMAGE_ANALYSES_KEY].append({
+            "Image": image_path,
+            "Analysis": parsed_result
+        })
+    except Exception as err:
+        logging.error(f"Error analyzing image {image_path}: {err}")
+        output_structure[IMAGE_ANALYSES_KEY].append({
+            "Image": image_path,
+            "Analysis": "Error analyzing the image."
+        })
+
+# Write structured output to file
+with open("Output File/json/competitor_analysis.json", "w") as f:
+    json.dump(output_structure, f, indent=4)
+
+logging.info("Analysis completed and saved to competitor_analysis.json")
+
+
+def json_to_excel(json_file, excel_file):
+    """
+    Parse the JSON file and convert it to an Excel file with structured scores and raw JSON responses.
+
+    Args:
+        json_file (str): Path to the input JSON file.
+        excel_file (str): Path to the output Excel file.
+    """
+    # Load JSON data from the file
+    with open(json_file, 'r') as file:
+        data = json.load(file)
+
+    # Prepare a list to hold structured data
+    structured_data = []
+
+    # Regex patterns to extract scores and criteria
+    score_pattern = r'"([a-zA-Z\s]+)":\s*(\d+),'  # Matches "Criteria Name": Score,
+
+    # Iterate over "Image Analyses" entries
+    for analysis in data.get("Image Analyses", []):
+        # Extract image name
+        image = analysis.get("Image", "Unknown")
+
+        # Extract raw response
+        raw_response = analysis.get("Analysis", {}).get("Raw Response", "")
+
+        # Dictionary to hold extracted data for the image
+        image_data = {"Image": image, "Raw JSON Response": raw_response}
+
+        # Extract criteria and scores using regex
+        matches = re.findall(score_pattern, raw_response)
+        for criterion, score in matches:
+            image_data[criterion.strip()] = int(score)  # Add criteria as columns
+
+        # Append image data to structured list
+        structured_data.append(image_data)
+
+    # Convert structured data to DataFrame
+    df = pd.DataFrame(structured_data)
+
+    # Write DataFrame to Excel
+    df.to_excel(excel_file, index=False)
+    print(f"Data successfully written to {excel_file}")
+# Example usage
+json_file_path = "Output File/json/competitor_analysis.json"  # Input JSON file
+excel_file_path = "Output File/excel/competitor_analysis.xlsx"  # Output Excel file
+json_to_excel(json_file_path, excel_file_path)

src/input_analysis/feedback.py

@@ -0,0 +1,221 @@
+import openai
+import os
+import requests
+import logging
+import json
+import re
+
+import os
+api_key = os.environ.get("OPENAI_API_KEY")
+
+# Define the paths to the input files and output file
+input_dir = r"data/output_generated_file"
+branding_file = os.path.join(input_dir, 'Product_branding.txt')
+content_marketing_file = os.path.join(input_dir, 'Product_content_marketing.txt')
+smm_file = os.path.join(input_dir, 'Product_smm.txt')
+
+# Function to read file content
+def read_file(file_path):
+    try:
+        with open(file_path, 'r', encoding='utf-8') as file:
+            return file.read()
+    except UnicodeDecodeError:
+        # Try opening with a different encoding if utf-8 fails
+        with open(file_path, 'r', encoding='ISO-8859-1') as file:
+            return file.read()
+
+# Read the content from the three files
+branding_content = read_file(branding_file)
+content_marketing_content = read_file(content_marketing_file)
+smm_content = read_file(smm_file)
+
+# LLM request function based on your provided syntax
+def request_analysis(system_message, user_message, model="gpt-4o-mini", max_tokens=1500):
+    headers = {
+        'Authorization': f'Bearer {openai.api_key}',
+        'Content-Type': 'application/json'
+    }
+    payload = {
+        "model": model,
+        "messages": [
+            {"role": "system", "content": system_message},
+            {"role": "user", "content": user_message}
+        ],
+        "max_tokens": max_tokens
+    }
+    response = requests.post("https://api.openai.com/v1/chat/completions", headers=headers, json=payload)
+
+    if response.status_code == 200:
+        try:
+            return response.json().get("choices", [{}])[0].get("message", {}).get("content", "Unexpected response format")
+        except Exception as e:
+            logging.error(f"Error parsing response: {e}")
+            logging.debug(f"Raw Response: {response.text}")
+            return "Error parsing the response."
+    else:
+        logging.error(f"Request failed with status code {response.status_code}")
+        return f"Error: {response.status_code}"
+
+# Function to extract "Don'ts" using regex
+def extract_donts(text):
+    pattern = re.findall(r"(?:-\s*Don't\s+|-\s*)([^\n]+)", text)
+    return [f"Don't {dont.strip()}" for dont in pattern if not dont.startswith("Don't")]
+
+# Retry logic for getting "Don'ts" from GPT
+def get_donts_with_retry(content, category, retries=10):
+    system_message = (
+        "You are an expert in branding, content marketing, and social media marketing. "
+        "Based on the provided content, generate a list of 3-6 word 'Don'ts' for the company. "
+        "Ensure each point MUST start with 'Don't' and write them as concise, actionable bullet points."
+    )
+
+    user_message = f"Category: {category}\nContent:\n{content}\n\nPlease provide the 'Don'ts' in bullet points."
+    
+    for attempt in range(retries):
+        response = request_analysis(system_message, user_message)
+        donts = extract_donts(response)
+        
+        # If we get valid "Don'ts", return them
+        if donts:
+            return [clean_text(dont) for dont in donts]
+        
+        logging.info(f"Attempt {attempt + 1} for category {category} yielded no data. Retrying...")
+    
+    # If all attempts fail, return an empty or default list
+    logging.warning(f"All retry attempts for {category} failed. No 'Don'ts' found.")
+    return ["No relevant 'Don'ts' found after retries."]
+
+# Function to clean text by removing unwanted characters (quotes, commas, periods)
+def clean_text(text):
+    cleaned_text = re.sub(r'[\"\'.,]+', '', text).strip()
+    return cleaned_text
+
+# Get "Don'ts" with retry logic for each category
+branding_donts_cleaned = get_donts_with_retry(branding_content, "Brand Marketing")
+content_marketing_donts_cleaned = get_donts_with_retry(content_marketing_content, "Content Marketing")
+smm_donts_cleaned = get_donts_with_retry(smm_content, "Social Media Marketing")
+
+# Store results in a dictionary
+donts_output = {
+    "Brand Marketing": branding_donts_cleaned,
+    "Content Marketing": content_marketing_donts_cleaned,
+    "Social Media Marketing": smm_donts_cleaned
+}
+
+# Print cleaned results
+print(json.dumps(donts_output, indent=4))
+
+# Save cleaned output to a file
+output_file = os.path.join(input_dir, 'Product_donts_output_cleaned.txt')
+with open(output_file, 'w') as file:
+    for category, dont_list in donts_output.items():
+        file.write(f"{category}:\n")
+        for dont in dont_list:
+            file.write(f"- {dont}\n")
+        file.write("\n")
+
+print(f"Cleaned output saved to {output_file}")
+
+
+
+
+# Function to strip unwanted characters (quotes, commas, periods, etc.)
+def clean_text(text):
+    # Remove quotes, commas, periods, and extra whitespace
+    cleaned_text = re.sub(r'[\"\'.,]+', '', text).strip()
+    return cleaned_text
+
+# Function to strip inverted commas from list items
+def strip_inverted_commas(items):
+    return [item.replace('"', '').replace("'", "").strip() for item in items]
+
+# Function to send requests to OpenAI API
+def request_analysis(system_message, user_message, model="gpt-4", max_tokens=1500):
+    headers = {
+        'Authorization': f'Bearer {openai.api_key}',
+        'Content-Type': 'application/json'
+    }
+    payload = {
+        "model": model,
+        "messages": [
+            {"role": "system", "content": system_message},
+            {"role": "user", "content": user_message}
+        ],
+        "max_tokens": max_tokens
+    }
+    response = requests.post("https://api.openai.com/v1/chat/completions", headers=headers, json=payload)
+    if response.status_code == 200:
+        try:
+            return response.json().get("choices", [{}])[0].get("message", {}).get("content", "Unexpected response format")
+        except Exception as e:
+            logging.error(f"Error parsing response: {e}")
+            return "Error parsing the response."
+    else:
+        logging.error(f"Request failed with status code {response.status_code}")
+        return f"Error: {response.status_code}"
+
+# Function to generate suggestions from GPT
+def get_suggestions_from_gpt(product_donts, category):
+    system_message = """
+    You are an expert marketing consultant. Based on the company's weaknesses, generate a list of suggestions for each category.
+    The number of suggestions should match the number of "Don'ts" provided.
+    Each suggestion should be 3-6 words, practical, and tailored to address the specific weakness.
+    Provide output as a clean list without numbers, brackets, or extra formatting.
+    """
+    user_message = f"""
+    Category: {category}
+    Product Company's Weaknesses (Don'ts): {product_donts}
+    Provide only the suggestions list as output, separated by new lines.
+    """
+    response = request_analysis(system_message, user_message)
+    if response != "Error parsing the response.":
+        # Clean up the response by removing unwanted symbols
+        suggestions = [clean_text(line.strip().replace("-", "").strip()) for line in response.strip().split("\n") if line.strip()]
+        return suggestions
+    return []
+
+# Generate lists of suggestions for each category
+branding_suggestions = get_suggestions_from_gpt(branding_donts_cleaned, "Brand Marketing")
+content_marketing_suggestions = get_suggestions_from_gpt(content_marketing_donts_cleaned, "Content Marketing")
+smm_suggestions = get_suggestions_from_gpt(smm_donts_cleaned, "Social Media Marketing")
+
+# Prepare output dictionary
+output = {
+    "Brand Marketing": branding_suggestions,
+    "Content Marketing": content_marketing_suggestions,
+    "Social Media Marketing": smm_suggestions
+}
+
+# Print the output for verification
+for category, items in output.items():
+    print(f"{category}:")
+    for item in items:
+        print(f'- {item}')
+    print()
+
+# Save output to a file
+output_file = os.path.join("data", "output_generated_file", "Product_suggestions_output_cleaned.txt")
+
+
+print("This branding don't ")
+print(branding_donts_cleaned)
+
+# Save cleaned output to a file
+output_file = os.path.join(input_dir, 'Product_output_cleaned.txt')
+
+with open(output_file, 'w') as file:
+    for category in donts_output.keys():
+        # Write the category
+        file.write(f"{category}:\n")
+        file.write("Don'ts:\n")
+        # Write the "Don'ts"
+        for dont in donts_output[category]:
+            file.write(f"- {dont}\n")
+        file.write("\nSuggestions:\n")
+        # Write the corresponding suggestions
+        suggestions = output[category]
+        for suggestion in suggestions:
+            file.write(f"- {suggestion}\n")
+        file.write("\n" + "="*50 + "\n\n")
+
+print(f"All outputs saved to {output_file}")

src/input_analysis/path.py

@@ -0,0 +1,68 @@
+import os
+
+# Define the paths
+input_dir = 'data/top_3_images'
+output_dir = 'data/output_generated_file'
+
+# Ensure output directory exists
+if not os.path.exists(output_dir):
+    os.makedirs(output_dir)
+
+# Loop over all .txt files in the 'D' folder
+for filename in os.listdir(input_dir):
+    if filename.endswith('.txt'):
+        file_path = os.path.join(input_dir, filename)
+
+        # Read the content of each text file
+        with open(file_path, 'r') as file:
+            file_content = file.read()
+
+        # Determine if it's a product or competitor
+        is_product = 'product' in filename.lower()
+        if is_product:
+            branding_file = os.path.join(output_dir, 'Product_branding.txt')
+            content_marketing_file = os.path.join(output_dir, 'Product_content_marketing.txt')
+            smm_file = os.path.join(output_dir, 'Product_smm.txt')
+        else:
+            branding_file = os.path.join(output_dir, 'Competitor_branding.txt')
+            content_marketing_file = os.path.join(output_dir, 'Competitor_content_marketing.txt')
+            smm_file = os.path.join(output_dir, 'Competitor_smm.txt')
+
+        # Split the content into lines
+        lines = file_content.split('\n')
+
+        # Prepare content variables for each category
+        branding_content = []
+        content_marketing_content = []
+        smm_content = []
+
+        current_category = None
+
+        # Iterate over lines to categorize them based on detected categories
+        for line in lines:
+            if "Branding" in line:
+                current_category = 'Branding'
+            elif "Content Marketing" in line:
+                current_category = 'Content Marketing'
+            elif "Social Media Marketing" in line:
+                current_category = 'Social Media Marketing'
+
+            # Append line to the corresponding category
+            if current_category == 'Branding':
+                branding_content.append(line)
+            elif current_category == 'Content Marketing':
+                content_marketing_content.append(line)
+            elif current_category == 'Social Media Marketing':
+                smm_content.append(line)
+
+        # Write the extracted data into their respective files (overwrite the files)
+        with open(branding_file, 'w') as bf:  # 'w' mode will overwrite the file
+            bf.write('\n'.join(branding_content) + '\n\n')  # Add the new content
+
+        with open(content_marketing_file, 'w') as cmf:  # 'w' mode will overwrite the file
+            cmf.write('\n'.join(content_marketing_content) + '\n\n')
+
+        with open(smm_file, 'w') as smf:  # 'w' mode will overwrite the file
+            smf.write('\n'.join(smm_content) + '\n\n')
+
+        print(f"Processed {filename} and saved data into {branding_file}, {content_marketing_file}, and {smm_file}")

src/input_analysis/product-analysis/product_analysis.py

@@ -0,0 +1,236 @@
+import base64
+import requests
+from PIL import Image
+import io
+import json
+import logging
+import json
+import pandas as pd
+import re
+
+# Define constants
+API_URL = "https://api.openai.com/v1/chat/completions"
+IMAGE_ANALYSES_KEY = "Image Analyses"
+import os
+api_key = os.environ.get("OPENAI_API_KEY")
+# Configure logging
+logging.basicConfig(level=logging.INFO)
+
+# Function to encode the image to base64
+def encode_image(image_path):
+    try:
+        with Image.open(image_path) as img:
+            img.thumbnail((800, 800))  # Resize image
+            buffer = io.BytesIO()
+            img.save(buffer, format="JPEG", quality=85)
+            encoded_image = base64.b64encode(buffer.getvalue()).decode('utf-8')
+            return encoded_image
+    except Exception as e:
+        logging.error(f"Failed to encode image {image_path}: {e}")
+        return None
+
+# Function to get image dimensions
+def get_image_dimensions(image_path):
+    try:
+        with Image.open(image_path) as img:
+            return img.size  # returns (width, height)
+    except Exception as e:
+        logging.error(f"Failed to get dimensions for image {image_path}: {e}")
+        return (0, 0)
+
+# Image paths for analysis
+image_paths = [
+    "data/product/image1.jpeg",
+    "data/product/image2.jpeg",
+    "data/product/image3.jpeg",
+    "data/product/image4.jpeg",
+    "data/product/image5.jpeg",
+    "data/product/image6.jpeg"
+]
+
+# Headers for the OpenAI API request
+headers = {
+    "Content-Type": "application/json",
+    "Authorization": f"Bearer {api_key}"
+}
+
+# System Message for Brutal Analysis
+system_message = """
+Analyze the branding, content marketing, and social media marketing effectiveness of a company for the provided Instagram post image.
+Evaluate it with extreme scrutiny, judging harshly and penalizing even minor mistakes or deviations. Scores (0-10) should reflect an unforgiving critique.
+A score of 10 should be nearly unattainable, and anything below basic industry standards should score no more than 5. BUT GIVE GOOD SCORE WHEREVER THEY REALLY REALLY DESERVE IT.
+The final evaluation must highlight deficiencies prominently, even if they appear minor.
+
+### Categories and Criteria:
+#### Branding:
+- **Logo Usage**: Penalize heavily if the logo is not perfectly sized, clearly visible, or appropriately placed.
+- **Brand Colors**: Deduct points for any deviations or inconsistencies in brand colors.
+- **Typography**: Strictly penalize if fonts do not align with the brand identity or lack consistency.
+- **Brand Identity**: Judge if the design fails to reflect the unique persona of the brand.
+- **Visual Hierarchy**: Critique poor prioritization of key elements, even slightly.
+- **Template Consistency**: Penalize mismatched templates or lack of a uniform design approach.
+- **Messaging Alignment**: Deduct heavily for vague or inconsistent brand messaging.
+- **Subtle Branding**: Punish overly subtle or excessive branding.
+- **Overbranding**: Penalize for overwhelming, distracting brand elements.
+- **Variations**: Critique lack of variety or creative innovation in the post.
+
+#### Content Marketing:
+- **Content Visibility**: Penalize cluttered designs or poorly highlighted content.
+- **Engagement Cues**: Harshly judge unclear or missing calls-to-action.
+- **Information Overload**: Deduct for over-saturated visuals or excessive text.
+- **Storytelling**: Penalize weak, unengaging, or irrelevant narratives.
+- **Content Variety**: Deduct for monotony or repetition across posts.
+- **Typography Consistency**: Penalize for inconsistent or unattractive typography.
+- **Aesthetic Coherence**: Heavily penalize jarring or unappealing designs.
+- **Content Relevance**: Deduct for off-brand or irrelevant posts.
+- **Stock Elements**: Heavily penalize excessive reliance on generic or stock imagery.
+
+#### Social Media Marketing:
+- **Font Size**: Penalize unreadable or poorly sized text, even slightly.
+- **Visibility of Text**: Deduct for hard-to-read text due to placement or design choices.
+- **Logo Placement**: Harshly critique logos that disrupt the aesthetic.
+- **Consistency**: Deduct for designs that lack cohesion or consistency.
+- **Alignment**: Penalize for poorly aligned elements or uneven layouts.
+- **Aesthetic Appeal**: Heavily penalize designs that lack visual allure or professionalism.
+- **Brand Elements**: Critique insufficient or overused brand assets.
+- **Repetitiveness**: Harshly penalize repetitive themes or lack of creative diversity.
+
+### Output JSON Format:
+### Only return the following format strictly
+
+{
+    "Branding Score": total_avg_score, explanation.
+    "criteria_name": score, explanation.
+    "criteria_name": score, explanation.
+
+    "Content Marketing Score": total_avg_score, explanation.
+    "criteria_name": score, explanation.
+    "criteria_name": score, explanation.
+
+    "Social Media Marketing Score": total_avg_score, explanation.
+    "criteria_name": score, explanation.
+    "criteria_name": score, explanation.
+}
+"""
+
+# Example product information string
+product_information = "This product is an eco-friendly, high-performance water bottle designed to keep beverages cold for up to 24 hours. Made with BPA-free materials, it features a sleek design with a customizable logo space."
+
+# Function to request analysis from OpenAI API
+def request_analysis(system_message, user_message, model="gpt-4o-mini", max_tokens=1500):
+    payload = {
+        "model": model,
+        "messages": [
+            {"role": "system", "content": system_message},
+            {"role": "user", "content": f"{user_message} Product Information: {product_information}"}
+        ],
+        "max_tokens": max_tokens
+    }
+    logging.debug(f"Payload Sent: {json.dumps(payload, indent=4)}")
+    response = requests.post(API_URL, headers=headers, json=payload)
+
+    if response.status_code == 200:
+        try:
+            return response.json().get("choices", [{}])[0].get("message", {}).get("content", "Unexpected response format")
+        except Exception as e:
+            logging.error(f"Error parsing response: {e}")
+            logging.debug(f"Raw Response: {response.text}")
+            return "Error parsing the response."
+    else:
+        logging.error(f"API Error: {response.status_code}, {response.text}")
+        return "Error with the API request."
+
+# Initialize structured output for the analyses
+output_structure = {
+    IMAGE_ANALYSES_KEY: []
+}
+
+# Loop through each image for analysis
+for image_path in image_paths:
+    base64_image = encode_image(image_path)
+    if not base64_image:
+        output_structure[IMAGE_ANALYSES_KEY].append({
+            "Image": image_path,
+            "Analysis": "Failed to encode image."
+        })
+        continue
+
+    width, height = get_image_dimensions(image_path)
+    user_message = f"Analyze the Instagram post with dimensions {width}x{height} pixels. Image data: {base64_image}"
+
+    try:
+        analysis_result = request_analysis(system_message, user_message)
+        try:
+            # Parse result and ensure it matches the required format
+            parsed_result = json.loads(analysis_result)
+        except json.JSONDecodeError:
+            logging.warning(f"Response not in expected JSON format for {image_path}: {analysis_result}")
+            parsed_result = {"Raw Response": analysis_result}
+
+        output_structure[IMAGE_ANALYSES_KEY].append({
+            "Image": image_path,
+            "Analysis": parsed_result
+        })
+    except Exception as err:
+        logging.error(f"Error analyzing image {image_path}: {err}")
+        output_structure[IMAGE_ANALYSES_KEY].append({
+            "Image": image_path,
+            "Analysis": "Error analyzing the image."
+        })
+
+# Write structured output to file
+with open("Output File/json/product_analysis.json", "w") as f:
+    json.dump(output_structure, f, indent=4)
+
+
+logging.info("Analysis completed and saved to product_analysis.json")
+
+
+def json_to_excel(json_file, excel_file):
+    """
+    Parse the JSON file and convert it to an Excel file with structured scores and raw JSON responses.
+
+    Args:
+        json_file (str): Path to the input JSON file.
+        excel_file (str): Path to the output Excel file.
+    """
+    # Load JSON data from the file
+    with open(json_file, 'r') as file:
+        data = json.load(file)
+
+    # Prepare a list to hold structured data
+    structured_data = []
+
+    # Regex patterns to extract scores and criteria
+    score_pattern = r'"([a-zA-Z\s]+)":\s*(\d+),'  # Matches "Criteria Name": Score,
+
+    # Iterate over "Image Analyses" entries
+    for analysis in data.get("Image Analyses", []):
+        # Extract image name
+        image = analysis.get("Image", "Unknown")
+
+        # Extract raw response
+        raw_response = analysis.get("Analysis", {}).get("Raw Response", "")
+
+        # Dictionary to hold extracted data for the image
+        image_data = {"Image": image, "Raw JSON Response": raw_response}
+
+        # Extract criteria and scores using regex
+        matches = re.findall(score_pattern, raw_response)
+        for criterion, score in matches:
+            image_data[criterion.strip()] = int(score)  # Add criteria as columns
+
+        # Append image data to structured list
+        structured_data.append(image_data)
+
+    # Convert structured data to DataFrame
+    df = pd.DataFrame(structured_data)
+
+    # Write DataFrame to Excel
+    df.to_excel(excel_file, index=False)
+    print(f"Data successfully written to {excel_file}")
+
+# Example usage
+json_file_path = "Output File/json/product_analysis.json"  # Input JSON file
+excel_file_path = "Output File/excel/product_analysis.xlsx"  # Output Excel file
+json_to_excel(json_file_path, excel_file_path)

src/input_analysis/renamebranding.py

@@ -0,0 +1,63 @@
+import pandas as pd
+import os
+import re  # For sanitizing the filenames
+
+# Define file paths
+product_analysis_path = "Output File/excel/product_analysis.xlsx"
+competitor_analysis_path = "Output File/excel/competitor_analysis.xlsx"
+top_3_df_path = "Output File/excel/top_3_sd_results.xlsx"
+
+# Read the data from Excel files
+product_data = pd.read_excel(product_analysis_path)
+competitor_data = pd.read_excel(competitor_analysis_path)
+top_3_df = pd.read_excel(top_3_df_path)
+
+# Create directory D if not exists
+output_dir = "data/top_3_images"
+if not os.path.exists(output_dir):
+    os.makedirs(output_dir)
+
+# Check columns to make sure we are accessing the correct data
+print("Product Data Columns:", product_data.columns)
+print("Competitor Data Columns:", competitor_data.columns)
+
+# Function to sanitize filenames (remove any invalid characters)
+def sanitize_filename(name):
+    # Replace any character that's not alphanumeric, space, or underscore with an underscore
+    return re.sub(r'[^\w\s-]', '_', name).strip().replace(' ', '_')
+
+# Process Product Image Names
+for image_name in top_3_df['Product_Image_Name']:
+    # Sanitize the image name to avoid invalid filename characters
+    sanitized_image_name = sanitize_filename(image_name)
+
+    # Fetch raw JSON response for the image in Product data by matching 'Image' column
+    product_response = product_data.loc[product_data['Image'] == image_name, 'Raw JSON Response'].values
+    if len(product_response) > 0:
+        raw_response = product_response[0]
+        if raw_response:  # Check if the response is not empty
+            with open(f"{output_dir}/{sanitized_image_name}.txt", 'w') as file:
+                file.write(raw_response)  # Write raw response as text
+            print(f"Saved Raw Text for Product image: {sanitized_image_name}")
+        else:
+            print(f"Empty Raw JSON Response for Product image: {sanitized_image_name}")
+    else:
+        print(f"Product image name '{image_name}' not found.")
+
+# Process Competitor Image Names
+for image_name in top_3_df['Competitor_Image_Name']:
+    # Sanitize the image name to avoid invalid filename characters
+    sanitized_image_name = sanitize_filename(image_name)
+
+    # Fetch raw JSON response for the image in Competitor data by matching 'Image' column
+    competitor_response = competitor_data.loc[competitor_data['Image'] == image_name, 'Raw JSON Response'].values
+    if len(competitor_response) > 0:
+        raw_response = competitor_response[0]
+        if raw_response:  # Check if the response is not empty
+            with open(f"{output_dir}/{sanitized_image_name}.txt", 'w') as file:
+                file.write(raw_response)  # Write raw response as text
+            print(f"Saved Raw Text for Competitor image: {sanitized_image_name}")
+        else:
+            print(f"Empty Raw JSON Response for Competitor image: {sanitized_image_name}")
+    else:
+        print(f"Competitor image name '{image_name}' not found.")

src/social.py

@@ -0,0 +1,424 @@
+import pandas as pd
+import base64
+import os
+import sys
+from playwright.sync_api import sync_playwright
+from PIL import Image
+
+def save_html_file(file_name, html_content):
+    with open(file_name, 'w') as file:
+        file.write(html_content)
+
+def encode_image_to_base64(image_path):
+    with open(image_path, "rb") as image_file:
+        return base64.b64encode(image_file.read()).decode('utf-8')
+
+# Allow user to upload images for logo and product images
+logo_image_path = r"src/templates_images/Component 3.png"
+haldiram_image_path = r"src/templates_images/Frame 57.png"
+# Encode images to base64
+logo_base64 = encode_image_to_base64(logo_image_path)
+haldiram_base64 = encode_image_to_base64(haldiram_image_path)
+def save_html_file(file_name, html_content):
+    with open(file_name, 'w') as file:
+        file.write(html_content)
+
+def encode_image_to_base64(image_path):
+    try:
+        with open(image_path, "rb") as img_file:
+            return base64.b64encode(img_file.read()).decode("utf-8")
+    except FileNotFoundError:
+        print(f"Image not found: {image_path}")
+        return ""
+    except Exception as e:
+        print(f"Error encoding image {image_path}: {e}")
+        return ""
+
+# Function to generate HTML for Social Media Marketing
+def generate_social_media_marketing_html(product_image_base64_1, competitor_image_base64_1, product_image_base64_2, competitor_image_base64_2, product_image_base64_3, competitor_image_base64_3, donts_html, suggestions_html, company_name):
+    return f"""
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Social Marketing Template</title>
+    <link href="https://fonts.googleapis.com/css2?family=Inter:wght@600&display=swap" rel="stylesheet">
+    <style>
+        body {{
+            font-family: 'Inter', sans-serif;
+            margin: 0;
+            padding: 10%;  /* Increased padding by 10% */
+            background-color: #fff;
+            font-size: 6px;
+        }}
+        @page {{
+            size: A4;
+            margin: 15px;  /* Increased margin to 15px */
+        }}
+        .header {{
+            display: flex;
+            justify-content: space-between;
+            align-items: center;
+            padding: 10px;  /* Increased padding to 10px */
+            background-color: #FFFFFF;
+            margin-bottom: 15px;  /* Increased margin between header and content */
+        }}
+        .header .logo {{
+            height: 25px;  /* Increased logo height */
+        }}
+        .container {{
+            display: flex;
+            flex-direction: column;
+            padding: 10px;  /* Increased padding to 10px */
+            flex-grow: 1;
+        }}
+        h1 {{
+            font-family: 'Times New Roman', serif;
+            font-size: 22px;  /* Increased font size */
+            font-weight: 500;
+            line-height: 1.2;
+            text-align: left;
+            margin-bottom: 15px;  /* Increased bottom margin */
+        }}
+        h2, p {{
+            font-size: 13px;  /* Increased font size */
+            font-weight: 400;
+            line-height: 1.4;
+            color: #000;
+        }}
+        .gap {{
+            font-size: 10px;
+            color: rgb(5, 5, 5);
+            font-weight: 100;
+        }}
+        .examples {{
+            font-size: 12px;  /* Increased font size */
+            color: green;
+        }}
+        .box-container {{
+            width: 100%;
+            display: flex;
+            flex-direction: column;
+            align-items: center;
+            margin-top: 15px;  /* Increased margin */
+        }}
+        .wraper {{
+            width: 100%;
+            height: 220px;  /* Increased height */
+            display: flex;
+            margin: 10px 0;  /* Increased margin */
+            border-radius: 12px;  /* Increased border radius */
+            overflow: hidden;
+            position: relative;
+        }}
+        .div-1 {{
+            flex: 1;
+            background-color: #ecbdbd; /* Pink background */
+            display: flex;
+            align-items: center;
+            justify-content: center;
+        }}
+        .div-2 {{
+            flex: 1;
+            background-color: #e6f9e6; /* Green background */
+            display: flex;
+            align-items: center;
+            justify-content: center;
+        }}
+        .wraper img {{
+            max-width: 90%;
+            max-height: 90%;
+            object-fit: contain;
+            border-radius: 8px;
+        }}
+        .vs-text {{
+            position: absolute;
+            left: 50%;
+            top: 50%;
+            transform: translate(-50%, -50%);
+            font-size: 18px;  /* Increased font size */
+            font-weight: bold;
+            color: black;
+        }}
+        .side-by-side-container {{
+            display: flex;
+            gap: 35px;  /* Increased gap between boxes */
+            margin-top: 45px;  /* Increased top margin */
+        }}
+        .pink-box, .green-box {{
+            flex: 1;
+            padding: 18px;  /* Increased padding */
+            margin-top: 15px;  /* Increased margin */
+            border-radius: 15px;  /* Increased border radius */
+            box-sizing: border-box;
+            height: auto;
+        }}
+        .pink-box {{
+            background-color: #ecbdbd;
+            color: red;
+            text-align: start;
+            display: flex;
+            flex-direction: column;
+            align-items: flex-start;
+        }}
+        .pink-box h6 {{
+            font-size: 16px;  /* Increased text size */
+            font-weight: bold;
+            margin: 8px 0;  /* Increased margin */
+            color: red;
+        }}
+        .green-box {{
+            background-color: #e6f9e6;
+            color: green;
+            text-align: start;
+            display: flex;
+            flex-direction: column;
+            align-items: flex-start;
+        }}
+        .green-box h6 {{
+            font-size: 16px;  /* Increased text size */
+            font-weight: bold;
+            margin: 8px 0;  /* Increased margin */
+            color: green;
+        }}
+        .case-study {{
+            font-size: 18px;  /* Increased font size */
+            color: green;
+            margin-top: 25px;  /* Increased margin */
+        }}
+        .container1 {{
+            font-size: 12px;  /* Increased font size */
+            color: green;
+            margin-top: 15px;  /* Increased margin */
+        }}
+        .case2 {{
+            font-size: 12px;  /* Increased font size */
+            color: rgb(1, 1, 1);
+            margin-top: 25px;  /* Increased margin */
+        }}
+        .case-study img {{
+            display: block;
+            max-width: 100%;
+            height: auto;
+            margin-top: 25px;  /* Increased margin */
+            border-radius: 10px;  /* Increased border radius */
+        }}
+    </style>
+</head>
+<body>
+    <div class="header">
+        <h1><span style="color:red;">Social Media Marketing</span></h1>
+        <img src="data:image/png;base64,{logo_base64}" alt="Logo" class="logo">
+    </div>
+    <div class="container">
+            <p>{company_name} should use Social Media Marketing effectively as the strategic promotion for identity, products, and services across all channels to create loyalty among consumers.</p>
+        <p class="gap"><span style="color: red;">Issue/Gap:</span> {company_name}'s current social media marketing efforts might not be reaching their full potential. A comprehensive analysis of brand messaging, target audience engagement across channels, and content strategy could reveal opportunities to optimize {company_name}'s marketing approach for greater reach and impact.</p>
+        
+        </div>
+            <h2 class="examples"> Examples:</h2>
+            <div class="box-container">
+            <div class="wraper">
+                <div class="div-1"> <img src="data:image/png;base64,{product_image_base64_1}" alt="Product Image"></div>
+                <div class="vs-text">V/S</div>
+                <div class="div-2"> <img src="data:image/png;base64,{competitor_image_base64_1}" alt="Competitor Image"></div>
+            </div>
+            <div class="wraper">
+                <div class="div-1"> <img src="data:image/png;base64,{product_image_base64_2}" alt="Product Image"></div>
+                <div class="vs-text">V/S</div>
+                <div class="div-2"> <img src="data:image/png;base64,{competitor_image_base64_2}" alt="Competitor Image"></div>
+            </div>
+            <div class="wraper">
+                <div class="div-1"> <img src="data:image/png;base64,{product_image_base64_3}" alt="Product Image"></div>
+                <div class="vs-text">V/S</div>
+                <div class="div-2"> <img src="data:image/png;base64,{competitor_image_base64_3}" alt="Competitor Image"></div>
+            </div>
+        </div>
+        <div class="side-by-side-container">
+            <div class="pink-box">
+                <h6>Drawbacks in Current Social Media Marketing</h6>
+                <p>{donts_html}</p>
+            </div>
+            <div class="green-box">
+                <h6>How Banao Technologies Can Help</h6>
+                <p>{suggestions_html}</p>
+            </div>
+        </div>
+        <div class="case-study">
+            <h3><span style="color: green;">Case Study:</span></h3>
+            <div class="container1">
+                <p><span style="color: green;">We Helped HaldiRam's to Grow</span></p>
+            </div>
+            <div class="case2">
+                <p> Using different techniques we Banao helped Haldiram's to reach 54k followers and generate a revenue of 4.75 Lakh in 3 months </p>
+                <img src="data:image/png;base64,{haldiram_base64}" alt="Haldiram" class="haldiram">
+            </div>
+      </div>
+    </div>
+</body>
+</html>
+
+
+    """
+
+# Function to parse "Product_output_cleaned.txt" for Don'ts and Suggestions specific to Social Media Marketing
+def parse_cleaned_file_social_media(file_path):
+    with open(file_path, "r") as file:
+        content = file.read()
+
+    sections = content.split("==================================================")
+    for section in sections:
+        lines = section.strip().split("\n")
+        if lines and "Social Media Marketing" in lines[0]:
+            donts = []
+            suggestions = []
+            mode = None
+            for line in lines[1:]:
+                if line.startswith("Don'ts:"):
+                    mode = "donts"
+                elif line.startswith("Suggestions:"):
+                    mode = "suggestions"
+                elif mode == "donts" and line.startswith("-"):
+                    donts.append(line.lstrip("- "))
+                elif mode == "suggestions" and line.startswith("-"):
+                    suggestions.append(line.lstrip("- "))
+            return "<br>".join(donts), "<br>".join(suggestions)
+
+    return "", ""
+
+# Function to process Social Media Marketing and generate HTML
+def process_social_media_marketing(data, base_image_dir, output_file, cleaned_file_path,company_name):
+    # Filter for Social Media Marketing category
+    social_media_data = data[data["Category"] == "Social Media Marketing"]
+    
+    if social_media_data.empty:
+        print("No Social Media Marketing data found in the provided Excel file.")
+        return
+    # Parse Don'ts and Suggestions
+    donts_html, suggestions_html = parse_cleaned_file_social_media(cleaned_file_path)
+
+    # Ensure there are at least two rows
+    if len(social_media_data) < 3:
+         print("Not enough rows for two product and competitor image comparisons.")
+         return
+    # Get the first record (assuming one Content Marketing entry is needed)
+    # Get the first two records (assuming these are needed)
+    social_media_row_1 = social_media_data.iloc[0]
+    social_media_row_2 = social_media_data.iloc[1]
+    social_media_row_3 = social_media_data.iloc[2]
+
+    product_image_path_1 = os.path.join(base_image_dir, social_media_row_1["Product_Image_Name"])
+    competitor_image_path_1 = os.path.join(base_image_dir, social_media_row_1["Competitor_Image_Name"])
+
+    product_image_path_2 = os.path.join(base_image_dir, social_media_row_2["Product_Image_Name"])
+    competitor_image_path_2 = os.path.join(base_image_dir, social_media_row_2["Competitor_Image_Name"])
+
+    product_image_path_3 = os.path.join(base_image_dir, social_media_row_3["Product_Image_Name"])
+    competitor_image_path_3 = os.path.join(base_image_dir, social_media_row_3["Competitor_Image_Name"])
+
+    # Encode images to Base64
+    product_image_base64_1 = encode_image_to_base64(product_image_path_1)
+    competitor_image_base64_1 = encode_image_to_base64(competitor_image_path_1)
+
+    product_image_base64_2 = encode_image_to_base64(product_image_path_2)
+    competitor_image_base64_2 = encode_image_to_base64(competitor_image_path_2)
+
+    product_image_base64_3 = encode_image_to_base64(product_image_path_3)
+    competitor_image_base64_3 = encode_image_to_base64(competitor_image_path_3)
+
+    # Generate HTML content
+    html_content = generate_social_media_marketing_html(product_image_base64_1, competitor_image_base64_1, product_image_base64_2, competitor_image_base64_2, product_image_base64_3, competitor_image_base64_3, donts_html, suggestions_html, company_name)
+
+    # Save the HTML file
+    with open(output_file, "w", encoding="utf-8") as f:
+        f.write(html_content)
+
+    print(f"HTML file for Social Media Marketing has been saved as: {output_file}")
+
+# Main script for Social Media Marketing
+if __name__ == "__main__":
+    if len(sys.argv) > 1:
+        company_name = sys.argv[1]  # The second argument passed will be the company_name
+    else:
+        company_name = "Default_Company"  # Default value if no argument is passed
+    # Load the Excel file
+    file_path = "Output File/excel/top_3_sd_results.xlsx"  # Replace with the path to your Excel file
+    data = pd.read_excel(file_path)
+
+    # Set the base directory for images
+    base_image_dir = ""  # Replace with the actual directory where your images are stored
+
+    # Path to the cleaned file with Don'ts and Suggestions
+    cleaned_file_path = "data/output_generated_file/Product_output_cleaned.txt"   # Replace with the path to your cleaned file
+
+    # Output HTML file
+    output_file = "src/templates/social_marketing.html"
+
+    # Generate HTML for Social Media Marketing
+    process_social_media_marketing(data, base_image_dir, output_file, cleaned_file_path, company_name)
+
+# Force UTF-8 encoding for terminal output
+sys.stdout.reconfigure(encoding='utf-8')
+
+def capture_screenshot_with_playwright(html_file_path, screenshot_path):
+    """
+    Capture a full-page screenshot of the HTML file directly using Playwright.
+    """
+    try:
+        # Launch Playwright in headless mode
+        with sync_playwright() as p:
+            browser = p.chromium.launch(headless=True)
+            page = browser.new_page()
+
+            # Open the HTML file in the browser
+            page.goto(f"file:///{os.path.abspath(html_file_path)}")
+            
+            # Capture the full-page screenshot
+            page.screenshot(path=screenshot_path, full_page=True)
+            print(f"Screenshot saved: {screenshot_path}")
+
+            browser.close()
+
+    except Exception as e:
+        print(f"Error capturing screenshot: {e}")
+
+def convert_png_to_pdf(png_path, company_name):
+    """
+    Convert a PNG image into a PDF strictly named as 'company_name brand marketing.pdf'
+    in the specified folder 'data/reports/template_PDF'.
+    """
+    try:
+        # Set the output folder and ensure it exists
+        output_folder = "data/reports/template_PDF"
+        os.makedirs(output_folder, exist_ok=True)
+
+        # Create the PDF file name as 'company_name brand marketing.pdf'
+        # Create the PDF file name as 'company_name brand marketing.pdf'
+        pdf_path = os.path.join(output_folder, "social media marketing.pdf")
+       
+
+        # Convert the PNG to PDF
+        img = Image.open(png_path)
+        img.convert('RGB').save(pdf_path, "PDF")
+
+        print(f"PDF saved: {pdf_path}")
+    except Exception as e:
+        print(f"Error converting PNG to PDF: {e}")
+
+if __name__ == "__main__":
+    # Paths for demonstration
+    html_file_path = "src/templates/social_marketing.html"
+    
+    # Screenshot saved in the folder: data/reports/template_ss
+    screenshot_folder = "data/reports/template_ss"
+    os.makedirs(screenshot_folder, exist_ok=True)
+    screenshot_path = os.path.join(screenshot_folder, "social_marketing_screenshot.png")
+
+    # Ensure Playwright browsers are installed
+    os.system("playwright install")
+
+    # Capture screenshot
+    capture_screenshot_with_playwright(html_file_path, screenshot_path)
+
+    # Convert screenshot to PDF with the company name strictly as the filename
+    convert_png_to_pdf(screenshot_path, company_name)