diff --git "a/app.py" "b/app.py"
--- "a/app.py"
+++ "b/app.py"
@@ -1,4103 +1,71 @@
-import os
-import re
-from http import HTTPStatus
-from typing import Dict, List, Optional, Tuple
-import base64
-import mimetypes
-import PyPDF2
-import docx
-import cv2
-import numpy as np
-from PIL import Image
-import pytesseract
-import requests
-from urllib.parse import urlparse, urljoin
-from bs4 import BeautifulSoup
-import html2text
-import json
-import time
-import webbrowser
-import urllib.parse
-import copy
-import html
-
-import gradio as gr
-from huggingface_hub import InferenceClient
-from tavily import TavilyClient
-from huggingface_hub import HfApi
-import tempfile
-from openai import OpenAI
-from mistralai import Mistral
-
-# Gradio supported languages for syntax highlighting
-GRADIO_SUPPORTED_LANGUAGES = [
- "python", "c", "cpp", "markdown", "latex", "json", "html", "css", "javascript", "jinja2", "typescript", "yaml", "dockerfile", "shell", "r", "sql", "sql-msSQL", "sql-mySQL", "sql-mariaDB", "sql-sqlite", "sql-cassandra", "sql-plSQL", "sql-hive", "sql-pgSQL", "sql-gql", "sql-gpSQL", "sql-sparkSQL", "sql-esper", None
-]
-
-def get_gradio_language(language):
- return language if language in GRADIO_SUPPORTED_LANGUAGES else None
-
-# Search/Replace Constants
-SEARCH_START = "<<<<<<< SEARCH"
-DIVIDER = "======="
-REPLACE_END = ">>>>>>> REPLACE"
-
-# Configuration
-HTML_SYSTEM_PROMPT = """ONLY USE HTML, CSS AND JAVASCRIPT. If you want to use ICON make sure to import the library first. Try to create the best UI possible by using only HTML, CSS and JAVASCRIPT. MAKE IT RESPONSIVE USING MODERN CSS. Use as much as you can modern CSS for the styling, if you can't do something with modern CSS, then use custom CSS. Also, try to elaborate as much as you can, to create something unique. ALWAYS GIVE THE RESPONSE INTO A SINGLE HTML FILE
-
-For website redesign tasks:
-- Use the provided original HTML code as the starting point for redesign
-- Preserve all original content, structure, and functionality
-- Keep the same semantic HTML structure but enhance the styling
-- Reuse all original images and their URLs from the HTML code
-- Create a modern, responsive design with improved typography and spacing
-- Use modern CSS frameworks and design patterns
-- Ensure accessibility and mobile responsiveness
-- Maintain the same navigation and user flow
-- Enhance the visual design while keeping the original layout structure
-
-If an image is provided, analyze it and use the visual information to better understand the user's requirements.
-
-Always respond with code that can be executed or rendered directly.
-
-Always output only the HTML code inside a ```html ... ``` code block, and do not include any explanations or extra text. Do NOT add the language name at the top of the code output."""
-
-TRANSFORMERS_JS_SYSTEM_PROMPT = """You are an expert web developer creating a transformers.js application. You will generate THREE separate files: index.html, index.js, and style.css.
-
-IMPORTANT: You MUST output ALL THREE files in the following format:
-
-```html
-
-```
-
-```javascript
-// index.js content here
-```
-
-```css
-/* style.css content here */
-```
-
-Requirements:
-1. Create a modern, responsive web application using transformers.js
-2. Use the transformers.js library for AI/ML functionality
-3. Create a clean, professional UI with good user experience
-4. Make the application fully responsive for mobile devices
-5. Use modern CSS practices and JavaScript ES6+ features
-6. Include proper error handling and loading states
-7. Follow accessibility best practices
-
-The index.html should contain the basic HTML structure and link to the CSS and JS files.
-The index.js should contain all the JavaScript logic including transformers.js integration.
-The style.css should contain all the styling for the application.
-
-Always output only the three code blocks as shown above, and do not include any explanations or extra text."""
-
-SVELTE_SYSTEM_PROMPT = """You are an expert Svelte developer creating a modern Svelte application. You will generate ONLY the custom files that need user-specific content for the user's requested application.
-
-IMPORTANT: You MUST output files in the following format. Generate ONLY the files needed for the user's specific request:
-
-```svelte
-
-```
-
-```css
-/* src/app.css content here */
-```
-
-If you need additional components for the user's specific app, add them like:
-```svelte
-
-```
-
-Requirements:
-1. Create a modern, responsive Svelte application based on the user's specific request
-2. Use TypeScript for better type safety
-3. Create a clean, professional UI with good user experience
-4. Make the application fully responsive for mobile devices
-5. Use modern CSS practices and Svelte best practices
-6. Include proper error handling and loading states
-7. Follow accessibility best practices
-8. Use Svelte's reactive features effectively
-9. Include proper component structure and organization
-10. Generate ONLY components that are actually needed for the user's requested application
-
-Files you should generate:
-- src/App.svelte: Main application component (ALWAYS required)
-- src/app.css: Global styles (ALWAYS required)
-- src/lib/[ComponentName].svelte: Additional components (ONLY if needed for the user's specific app)
-
-The other files (index.html, package.json, vite.config.ts, tsconfig files, svelte.config.js, src/main.ts, src/vite-env.d.ts) are provided by the Svelte template and don't need to be generated.
-
-Always output only the two code blocks as shown above, and do not include any explanations or extra text."""
-
-SVELTE_SYSTEM_PROMPT_WITH_SEARCH = """You are an expert Svelte developer creating a modern Svelte application. You have access to real-time web search. When needed, use web search to find the latest information, best practices, or specific Svelte technologies.
-
-You will generate ONLY the custom files that need user-specific content.
-
-IMPORTANT: You MUST output ONLY the custom files in the following format:
-
-```svelte
-
-```
-
-```css
-/* src/app.css content here -->
-```
-
-Requirements:
-1. Create a modern, responsive Svelte application
-2. Use TypeScript for better type safety
-3. Create a clean, professional UI with good user experience
-4. Make the application fully responsive for mobile devices
-5. Use modern CSS practices and Svelte best practices
-6. Include proper error handling and loading states
-7. Follow accessibility best practices
-8. Use Svelte's reactive features effectively
-9. Include proper component structure and organization
-10. Use web search to find the latest Svelte patterns, libraries, and best practices
-
-The files you generate are:
-- src/App.svelte: Main application component (your custom app logic)
-- src/app.css: Global styles (your custom styling)
-
-The other files (index.html, package.json, vite.config.ts, tsconfig files, svelte.config.js, src/main.ts, src/vite-env.d.ts) are provided by the Svelte template and don't need to be generated.
-
-Always output only the two code blocks as shown above, and do not include any explanations or extra text."""
-
-TRANSFORMERS_JS_SYSTEM_PROMPT_WITH_SEARCH = """You are an expert web developer creating a transformers.js application. You have access to real-time web search. When needed, use web search to find the latest information, best practices, or specific technologies for transformers.js.
-
-You will generate THREE separate files: index.html, index.js, and style.css.
-
-IMPORTANT: You MUST output ALL THREE files in the following format:
-
-```html
-
-```
-
-```javascript
-// index.js content here
-```
-
-```css
-/* style.css content here */
-```
-
-Requirements:
-1. Create a modern, responsive web application using transformers.js
-2. Use the transformers.js library for AI/ML functionality
-3. Use web search to find current best practices and latest transformers.js features
-4. Create a clean, professional UI with good user experience
-5. Make the application fully responsive for mobile devices
-6. Use modern CSS practices and JavaScript ES6+ features
-7. Include proper error handling and loading states
-8. Follow accessibility best practices
-
-The index.html should contain the basic HTML structure and link to the CSS and JS files.
-The index.js should contain all the JavaScript logic including transformers.js integration.
-The style.css should contain all the styling for the application.
-
-Always output only the three code blocks as shown above, and do not include any explanations or extra text."""
-
-GENERIC_SYSTEM_PROMPT = """You are an expert {language} developer. Write clean, idiomatic, and runnable {language} code for the user's request. If possible, include comments and best practices. Output ONLY the code inside a ``` code block, and do not include any explanations or extra text. If the user provides a file or other context, use it as a reference. If the code is for a script or app, make it as self-contained as possible. Do NOT add the language name at the top of the code output."""
-
-# System prompt with search capability
-HTML_SYSTEM_PROMPT_WITH_SEARCH = """ONLY USE HTML, CSS AND JAVASCRIPT. If you want to use ICON make sure to import the library first. Try to create the best UI possible by using only HTML, CSS and JAVASCRIPT. MAKE IT RESPONSIVE USING MODERN CSS. Use as much as you can modern CSS for the styling, if you can't do something with modern CSS, then use custom CSS. Also, try to elaborate as much as you can, to create something unique. ALWAYS GIVE THE RESPONSE INTO A SINGLE HTML FILE
-
-You have access to real-time web search. When needed, use web search to find the latest information, best practices, or specific technologies.
-
-For website redesign tasks:
-- Use the provided original HTML code as the starting point for redesign
-- Preserve all original content, structure, and functionality
-- Keep the same semantic HTML structure but enhance the styling
-- Reuse all original images and their URLs from the HTML code
-- Use web search to find current design trends and best practices for the specific type of website
-- Create a modern, responsive design with improved typography and spacing
-- Use modern CSS frameworks and design patterns
-- Ensure accessibility and mobile responsiveness
-- Maintain the same navigation and user flow
-- Enhance the visual design while keeping the original layout structure
-
-If an image is provided, analyze it and use the visual information to better understand the user's requirements.
-
-Always respond with code that can be executed or rendered directly.
-
-Always output only the HTML code inside a ```html ... ``` code block, and do not include any explanations or extra text. Do NOT add the language name at the top of the code output."""
-
-GENERIC_SYSTEM_PROMPT_WITH_SEARCH = """You are an expert {language} developer. You have access to real-time web search. When needed, use web search to find the latest information, best practices, or specific technologies for {language}.
-
-Write clean, idiomatic, and runnable {language} code for the user's request. If possible, include comments and best practices. Output ONLY the code inside a ``` code block, and do not include any explanations or extra text. If the user provides a file or other context, use it as a reference. If the code is for a script or app, make it as self-contained as possible. Do NOT add the language name at the top of the code output."""
-
-# Follow-up system prompt for modifying existing HTML files
-FollowUpSystemPrompt = f"""You are an expert web developer modifying an existing project.
-The user wants to apply changes based on their request.
-You MUST output ONLY the changes required using the following SEARCH/REPLACE block format. Do NOT output the entire file.
-Explain the changes briefly *before* the blocks if necessary, but the code changes THEMSELVES MUST be within the blocks.
-
-IMPORTANT: When the user reports an ERROR MESSAGE, analyze it carefully to determine which file needs fixing:
-- ImportError/ModuleNotFoundError → Fix requirements.txt by adding missing packages
-- Syntax errors in Python code → Fix app.py or the main Python file
-- HTML/CSS/JavaScript errors → Fix the respective HTML/CSS/JS files
-- Configuration errors → Fix config files, Docker files, etc.
-
-For Python applications (Gradio/Streamlit), the project structure typically includes:
-- app.py (main application file)
-- requirements.txt (dependencies)
-- Other supporting files as needed
-
-Format Rules:
-1. Start with {SEARCH_START}
-2. Provide the exact lines from the current code that need to be replaced.
-3. Use {DIVIDER} to separate the search block from the replacement.
-4. Provide the new lines that should replace the original lines.
-5. End with {REPLACE_END}
-6. You can use multiple SEARCH/REPLACE blocks if changes are needed in different parts of the file.
-7. To insert code, use an empty SEARCH block (only {SEARCH_START} and {DIVIDER} on their lines) if inserting at the very beginning, otherwise provide the line *before* the insertion point in the SEARCH block and include that line plus the new lines in the REPLACE block.
-8. To delete code, provide the lines to delete in the SEARCH block and leave the REPLACE block empty (only {DIVIDER} and {REPLACE_END} on their lines).
-9. IMPORTANT: The SEARCH block must *exactly* match the current code, including indentation and whitespace.
-10. For multi-file projects, specify which file you're modifying by starting with the filename before the search/replace block.
-
-Example Modifying Code:
-```
-Some explanation...
-{SEARCH_START}
-
Old Title
-{DIVIDER}
- New Title
-{REPLACE_END}
-{SEARCH_START}
- ', html_content.find(' str:
- """Create search/replace blocks that generate and insert ONLY ONE text-to-image result.
-
- Replaces the first detected placeholder; if none found, inserts one image near the top of .
- """
- if not prompt or not prompt.strip():
- return ""
-
- import re
-
- # Detect placeholders similarly to the multi-image version
- placeholder_patterns = [
- r'
]*src=["\'](?:placeholder|dummy|sample|example)[^"\']*["\'][^>]*>',
- r'
]*src=["\']https?://via\.placeholder\.com[^"\']*["\'][^>]*>',
- r'
]*src=["\']https?://picsum\.photos[^"\']*["\'][^>]*>',
- r'
]*src=["\']https?://dummyimage\.com[^"\']*["\'][^>]*>',
- r'
]*alt=["\'][^"\']*placeholder[^"\']*["\'][^>]*>',
- r'
]*class=["\'][^"\']*placeholder[^"\']*["\'][^>]*>',
- r'
]*id=["\'][^"\']*placeholder[^"\']*["\'][^>]*>',
- r'
]*src=["\']data:image[^"\']*["\'][^>]*>',
- r'
]*src=["\']#["\'][^>]*>',
- r'
]*src=["\']about:blank["\'][^>]*>',
- ]
-
- placeholder_images = []
- for pattern in placeholder_patterns:
- matches = re.findall(pattern, html_content, re.IGNORECASE)
- if matches:
- placeholder_images.extend(matches)
-
- # Fallback to any
if no placeholders
- if not placeholder_images:
- img_pattern = r'
]*>'
- placeholder_images = re.findall(img_pattern, html_content)
-
- # Generate a single image
- image_html = generate_image_with_qwen(prompt, 0)
- if image_html.startswith("Error"):
- return ""
-
- # Replace first placeholder if present
- if placeholder_images:
- placeholder = placeholder_images[0]
- placeholder_clean = re.sub(r'\s+', ' ', placeholder.strip())
- placeholder_variations = [
- placeholder_clean,
- placeholder_clean.replace('"', "'"),
- placeholder_clean.replace("'", '"'),
- re.sub(r'\s+', ' ', placeholder_clean),
- placeholder_clean.replace(' ', ' '),
- ]
- blocks = []
- for variation in placeholder_variations:
- blocks.append(f"""{SEARCH_START}
-{variation}
-{DIVIDER}
-{image_html}
-{REPLACE_END}""")
- return '\n\n'.join(blocks)
-
- # Otherwise insert after
- if '', html_content.find(', just append
- return f"{SEARCH_START}\n\n{DIVIDER}\n{image_html}\n{REPLACE_END}"
-
-def create_image_replacement_blocks_from_input_image(html_content: str, user_prompt: str, input_image_data, max_images: int = 1) -> str:
- """Create search/replace blocks using image-to-image generation with a provided input image.
-
- Mirrors placeholder detection from create_image_replacement_blocks but uses generate_image_to_image.
- """
- if not user_prompt:
- return ""
-
- import re
-
- placeholder_patterns = [
- r'
]*src=["\'](?:placeholder|dummy|sample|example)[^"\']*["\'][^>]*>',
- r'
]*src=["\']https?://via\.placeholder\.com[^"\']*["\'][^>]*>',
- r'
]*src=["\']https?://picsum\.photos[^"\']*["\'][^>]*>',
- r'
]*src=["\']https?://dummyimage\.com[^"\']*["\'][^>]*>',
- r'
]*alt=["\'][^"\']*placeholder[^"\']*["\'][^>]*>',
- r'
]*class=["\'][^"\']*placeholder[^"\']*["\'][^>]*>',
- r'
]*id=["\'][^"\']*placeholder[^"\']*["\'][^>]*>',
- r'
]*src=["\']data:image[^"\']*["\'][^>]*>',
- r'
]*src=["\']#["\'][^>]*>',
- r'
]*src=["\']about:blank["\'][^>]*>',
- ]
-
- placeholder_images = []
- for pattern in placeholder_patterns:
- matches = re.findall(pattern, html_content, re.IGNORECASE)
- placeholder_images.extend(matches)
-
- if not placeholder_images:
- img_pattern = r'
]*>'
- placeholder_images = re.findall(img_pattern, html_content)
-
- div_placeholder_patterns = [
- r']*class=["\'][^"\']*(?:image|img|photo|picture)[^"\']*["\'][^>]*>.*?
',
- r']*id=["\'][^"\']*(?:image|img|photo|picture)[^"\']*["\'][^>]*>.*?
',
- ]
- for pattern in div_placeholder_patterns:
- matches = re.findall(pattern, html_content, re.IGNORECASE | re.DOTALL)
- placeholder_images.extend(matches)
-
- num_images_needed = len(placeholder_images)
- num_to_replace = min(num_images_needed, max(0, int(max_images)))
- if num_images_needed == 0:
- # No placeholders; generate one image to append (only if at least one upload is present)
- if num_to_replace <= 0:
- return ""
- prompts = extract_image_prompts_from_text(user_prompt, 1)
- if not prompts:
- return ""
- image_html = generate_image_to_image(input_image_data, prompts[0])
- if image_html.startswith("Error"):
- return ""
- return f"{SEARCH_START}\n\n{DIVIDER}\n{image_html}
\n{REPLACE_END}"
-
- if num_to_replace <= 0:
- return ""
- image_prompts = extract_image_prompts_from_text(user_prompt, num_to_replace)
-
- generated_images = []
- for i, prompt in enumerate(image_prompts):
- image_html = generate_image_to_image(input_image_data, prompt)
- if not image_html.startswith("Error"):
- generated_images.append((i, image_html))
-
- if not generated_images:
- return ""
-
- replacement_blocks = []
- for i, (prompt_index, generated_image) in enumerate(generated_images):
- if i < num_to_replace and i < len(placeholder_images):
- placeholder = placeholder_images[i]
- placeholder_clean = re.sub(r'\s+', ' ', placeholder.strip())
- placeholder_variations = [
- placeholder_clean,
- placeholder_clean.replace('"', "'"),
- placeholder_clean.replace("'", '"'),
- re.sub(r'\s+', ' ', placeholder_clean),
- placeholder_clean.replace(' ', ' '),
- ]
- for variation in placeholder_variations:
- replacement_blocks.append(f"""{SEARCH_START}
-{variation}
-{DIVIDER}
-{generated_image}
-{REPLACE_END}""")
- # Do not insert additional images beyond the uploaded count
-
- return '\n\n'.join(replacement_blocks)
-
-def apply_generated_images_to_html(html_content: str, user_prompt: str, enable_text_to_image: bool, enable_image_to_image: bool, input_image_data, image_to_image_prompt: str | None = None, text_to_image_prompt: str | None = None) -> str:
- """Apply text-to-image and/or image-to-image replacements to HTML content.
-
- If both toggles are enabled, text-to-image replacements run first, then image-to-image.
- """
- result = html_content
- try:
- # If an input image is provided and image-to-image is enabled, we only replace one image
- # and skip text-to-image to satisfy the requirement to replace exactly the number of uploaded images.
- if enable_image_to_image and input_image_data is not None and (result.strip().startswith('') or result.strip().startswith('') or result.strip().startswith(' str:
- """Apply search/replace changes to content (HTML, Python, etc.)"""
- if not changes_text.strip():
- return original_content
-
- # Split the changes text into individual search/replace blocks
- blocks = []
- current_block = ""
- lines = changes_text.split('\n')
-
- for line in lines:
- if line.strip() == SEARCH_START:
- if current_block.strip():
- blocks.append(current_block.strip())
- current_block = line + '\n'
- elif line.strip() == REPLACE_END:
- current_block += line + '\n'
- blocks.append(current_block.strip())
- current_block = ""
- else:
- current_block += line + '\n'
-
- if current_block.strip():
- blocks.append(current_block.strip())
-
- modified_content = original_content
-
- for block in blocks:
- if not block.strip():
- continue
-
- # Parse the search/replace block
- lines = block.split('\n')
- search_lines = []
- replace_lines = []
- in_search = False
- in_replace = False
-
- for line in lines:
- if line.strip() == SEARCH_START:
- in_search = True
- in_replace = False
- elif line.strip() == DIVIDER:
- in_search = False
- in_replace = True
- elif line.strip() == REPLACE_END:
- in_replace = False
- elif in_search:
- search_lines.append(line)
- elif in_replace:
- replace_lines.append(line)
-
- # Apply the search/replace
- if search_lines:
- search_text = '\n'.join(search_lines).strip()
- replace_text = '\n'.join(replace_lines).strip()
-
- if search_text in modified_content:
- modified_content = modified_content.replace(search_text, replace_text)
- else:
- print(f"Warning: Search text not found in content: {search_text[:100]}...")
-
- return modified_content
-
-def apply_transformers_js_search_replace_changes(original_formatted_content: str, changes_text: str) -> str:
- """Apply search/replace changes to transformers.js formatted content (three files)"""
- if not changes_text.strip():
- return original_formatted_content
-
- # Parse the original formatted content to get the three files
- files = parse_transformers_js_output(original_formatted_content)
-
- # Split the changes text into individual search/replace blocks
- blocks = []
- current_block = ""
- lines = changes_text.split('\n')
-
- for line in lines:
- if line.strip() == SEARCH_START:
- if current_block.strip():
- blocks.append(current_block.strip())
- current_block = line + '\n'
- elif line.strip() == REPLACE_END:
- current_block += line + '\n'
- blocks.append(current_block.strip())
- current_block = ""
- else:
- current_block += line + '\n'
-
- if current_block.strip():
- blocks.append(current_block.strip())
-
- # Process each block and apply changes to the appropriate file
- for block in blocks:
- if not block.strip():
- continue
-
- # Parse the search/replace block
- lines = block.split('\n')
- search_lines = []
- replace_lines = []
- in_search = False
- in_replace = False
- target_file = None
-
- for line in lines:
- if line.strip() == SEARCH_START:
- in_search = True
- in_replace = False
- elif line.strip() == DIVIDER:
- in_search = False
- in_replace = True
- elif line.strip() == REPLACE_END:
- in_replace = False
- elif in_search:
- search_lines.append(line)
- elif in_replace:
- replace_lines.append(line)
-
- # Determine which file this change targets based on the search content
- if search_lines:
- search_text = '\n'.join(search_lines).strip()
- replace_text = '\n'.join(replace_lines).strip()
-
- # Check which file contains the search text
- if search_text in files['index.html']:
- target_file = 'index.html'
- elif search_text in files['index.js']:
- target_file = 'index.js'
- elif search_text in files['style.css']:
- target_file = 'style.css'
-
- # Apply the change to the target file
- if target_file and search_text in files[target_file]:
- files[target_file] = files[target_file].replace(search_text, replace_text)
- else:
- print(f"Warning: Search text not found in any transformers.js file: {search_text[:100]}...")
-
- # Reformat the modified files
- return format_transformers_js_output(files)
-
-# Updated for faster Tavily search and closer prompt usage
-# Uses 'advanced' search_depth and auto_parameters=True for speed and relevance
-
-def perform_web_search(query: str, max_results: int = 5, include_domains=None, exclude_domains=None) -> str:
- """Perform web search using Tavily with default parameters"""
- if not tavily_client:
- return "Web search is not available. Please set the TAVILY_API_KEY environment variable."
-
- try:
- # Use Tavily defaults with advanced search depth for better results
- search_params = {
- "search_depth": "advanced",
- "max_results": min(max(1, max_results), 20)
- }
- if include_domains is not None:
- search_params["include_domains"] = include_domains
- if exclude_domains is not None:
- search_params["exclude_domains"] = exclude_domains
-
- response = tavily_client.search(query, **search_params)
-
- search_results = []
- for result in response.get('results', []):
- title = result.get('title', 'No title')
- url = result.get('url', 'No URL')
- content = result.get('content', 'No content')
- search_results.append(f"Title: {title}\nURL: {url}\nContent: {content}\n")
-
- if search_results:
- return "Web Search Results:\n\n" + "\n---\n".join(search_results)
- else:
- return "No search results found."
-
- except Exception as e:
- return f"Search error: {str(e)}"
-
-def enhance_query_with_search(query: str, enable_search: bool) -> str:
- """Enhance the query with web search results if search is enabled"""
- if not enable_search or not tavily_client:
- return query
-
- # Perform search to get relevant information
- search_results = perform_web_search(query)
-
- # Combine original query with search results
- enhanced_query = f"""Original Query: {query}
-
-{search_results}
-
-Please use the search results above to help create the requested application with the most up-to-date information and best practices."""
-
- return enhanced_query
-
-def send_to_sandbox(code):
- # Add a wrapper to inject necessary permissions and ensure full HTML
- wrapped_code = f"""
-
-
-
-
-
-
-
-
- {code}
-
-
- """
- encoded_html = base64.b64encode(wrapped_code.encode('utf-8')).decode('utf-8')
- data_uri = f"data:text/html;charset=utf-8;base64,{encoded_html}"
- iframe = f''
- return iframe
-
-def demo_card_click(e: gr.EventData):
- try:
- # Get the index from the event data
- if hasattr(e, '_data') and e._data:
- # Try different ways to get the index
- if 'index' in e._data:
- index = e._data['index']
- elif 'component' in e._data and 'index' in e._data['component']:
- index = e._data['component']['index']
- elif 'target' in e._data and 'index' in e._data['target']:
- index = e._data['target']['index']
- else:
- # If we can't get the index, try to extract it from the card data
- index = 0
- else:
- index = 0
-
- # Ensure index is within bounds
- if index >= len(DEMO_LIST):
- index = 0
-
- return DEMO_LIST[index]['description']
- except (KeyError, IndexError, AttributeError) as e:
- # Return the first demo description as fallback
- return DEMO_LIST[0]['description']
-
-def extract_text_from_image(image_path):
- """Extract text from image using OCR"""
- try:
- # Check if tesseract is available
- try:
- pytesseract.get_tesseract_version()
- except Exception:
- return "Error: Tesseract OCR is not installed. Please install Tesseract to extract text from images. See install_tesseract.md for instructions."
-
- # Read image using OpenCV
- image = cv2.imread(image_path)
- if image is None:
- return "Error: Could not read image file"
-
- # Convert to RGB (OpenCV uses BGR)
- image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
-
- # Preprocess image for better OCR results
- # Convert to grayscale
- gray = cv2.cvtColor(image_rgb, cv2.COLOR_RGB2GRAY)
-
- # Apply thresholding to get binary image
- _, binary = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
-
- # Extract text using pytesseract
- text = pytesseract.image_to_string(binary, config='--psm 6')
-
- return text.strip() if text.strip() else "No text found in image"
-
- except Exception as e:
- return f"Error extracting text from image: {e}"
-
-def extract_text_from_file(file_path):
- if not file_path:
- return ""
- mime, _ = mimetypes.guess_type(file_path)
- ext = os.path.splitext(file_path)[1].lower()
- try:
- if ext == ".pdf":
- with open(file_path, "rb") as f:
- reader = PyPDF2.PdfReader(f)
- return "\n".join(page.extract_text() or "" for page in reader.pages)
- elif ext in [".txt", ".md"]:
- with open(file_path, "r", encoding="utf-8") as f:
- return f.read()
- elif ext == ".csv":
- with open(file_path, "r", encoding="utf-8") as f:
- return f.read()
- elif ext == ".docx":
- doc = docx.Document(file_path)
- return "\n".join([para.text for para in doc.paragraphs])
- elif ext.lower() in [".jpg", ".jpeg", ".png", ".bmp", ".tiff", ".tif", ".gif", ".webp"]:
- return extract_text_from_image(file_path)
- else:
- return ""
- except Exception as e:
- return f"Error extracting text: {e}"
-
-def extract_website_content(url: str) -> str:
- """Extract HTML code and content from a website URL"""
- try:
- # Validate URL
- parsed_url = urlparse(url)
- if not parsed_url.scheme:
- url = "https://" + url
- parsed_url = urlparse(url)
-
- if not parsed_url.netloc:
- return "Error: Invalid URL provided"
-
- # Set comprehensive headers to mimic a real browser request
- headers = {
- 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
- 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
- 'Accept-Language': 'en-US,en;q=0.9',
- 'Accept-Encoding': 'gzip, deflate, br',
- 'DNT': '1',
- 'Connection': 'keep-alive',
- 'Upgrade-Insecure-Requests': '1',
- 'Sec-Fetch-Dest': 'document',
- 'Sec-Fetch-Mode': 'navigate',
- 'Sec-Fetch-Site': 'none',
- 'Sec-Fetch-User': '?1',
- 'Cache-Control': 'max-age=0'
- }
-
- # Create a session to maintain cookies and handle redirects
- session = requests.Session()
- session.headers.update(headers)
-
- # Make the request with retry logic
- max_retries = 3
- for attempt in range(max_retries):
- try:
- response = session.get(url, timeout=15, allow_redirects=True)
- response.raise_for_status()
- break
- except requests.exceptions.HTTPError as e:
- if e.response.status_code == 403 and attempt < max_retries - 1:
- # Try with different User-Agent on 403
- session.headers['User-Agent'] = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
- continue
- else:
- raise
-
- # Get the raw HTML content with proper encoding
- try:
- # Try to get the content with automatic encoding detection
- response.encoding = response.apparent_encoding
- raw_html = response.text
- except:
- # Fallback to UTF-8 if encoding detection fails
- raw_html = response.content.decode('utf-8', errors='ignore')
-
- # Debug: Check if we got valid HTML
- if not raw_html.strip().startswith(' 10:
- print(f"Warning: This site has {len(script_tags)} script tags - it may be a JavaScript-heavy site")
- print("The content might be loaded dynamically and not available in the initial HTML")
-
- # Extract title
- title = soup.find('title')
- title_text = title.get_text().strip() if title else "No title found"
-
- # Extract meta description
- meta_desc = soup.find('meta', attrs={'name': 'description'})
- description = meta_desc.get('content', '') if meta_desc else ""
-
- # Extract main content areas for analysis
- content_sections = []
- main_selectors = [
- 'main', 'article', '.content', '.main-content', '.post-content',
- '#content', '#main', '.entry-content', '.post-body'
- ]
-
- for selector in main_selectors:
- elements = soup.select(selector)
- for element in elements:
- text = element.get_text().strip()
- if len(text) > 100: # Only include substantial content
- content_sections.append(text)
-
- # Extract navigation links for analysis
- nav_links = []
- nav_elements = soup.find_all(['nav', 'header'])
- for nav in nav_elements:
- links = nav.find_all('a')
- for link in links:
- link_text = link.get_text().strip()
- link_href = link.get('href', '')
- if link_text and link_href:
- nav_links.append(f"{link_text}: {link_href}")
-
- # Extract and fix image URLs in the HTML
- img_elements = soup.find_all('img')
- for img in img_elements:
- src = img.get('src', '')
- if src:
- # Handle different URL formats
- if src.startswith('//'):
- # Protocol-relative URL
- absolute_src = 'https:' + src
- img['src'] = absolute_src
- elif src.startswith('/'):
- # Root-relative URL
- absolute_src = urljoin(url, src)
- img['src'] = absolute_src
- elif not src.startswith(('http://', 'https://')):
- # Relative URL
- absolute_src = urljoin(url, src)
- img['src'] = absolute_src
- # If it's already absolute, keep it as is
-
- # Also check for data-src (lazy loading) and other common attributes
- data_src = img.get('data-src', '')
- if data_src and not src:
- # Use data-src if src is empty
- if data_src.startswith('//'):
- absolute_data_src = 'https:' + data_src
- img['src'] = absolute_data_src
- elif data_src.startswith('/'):
- absolute_data_src = urljoin(url, data_src)
- img['src'] = absolute_data_src
- elif not data_src.startswith(('http://', 'https://')):
- absolute_data_src = urljoin(url, data_src)
- img['src'] = absolute_data_src
- else:
- img['src'] = data_src
-
- # Also fix background image URLs in style attributes
- elements_with_style = soup.find_all(attrs={'style': True})
- for element in elements_with_style:
- style_attr = element.get('style', '')
- # Find and replace relative URLs in background-image
- import re
- bg_pattern = r'background-image:\s*url\(["\']?([^"\']+)["\']?\)'
- matches = re.findall(bg_pattern, style_attr, re.IGNORECASE)
- for match in matches:
- if match:
- if match.startswith('//'):
- absolute_bg = 'https:' + match
- style_attr = style_attr.replace(match, absolute_bg)
- elif match.startswith('/'):
- absolute_bg = urljoin(url, match)
- style_attr = style_attr.replace(match, absolute_bg)
- elif not match.startswith(('http://', 'https://')):
- absolute_bg = urljoin(url, match)
- style_attr = style_attr.replace(match, absolute_bg)
- element['style'] = style_attr
-
- # Fix background images in