'
- # Initialize enabledStates if it's empty (first load) or if paths have changed
if enabled_states is None or len(enabled_states) != num_qr_codes:
- enabled_states = list(range(num_qr_codes)) # Enable all by default or if QR count changes
-
+ enabled_states = list(range(num_qr_codes))
for i, path in enumerate(paths):
is_enabled = i in enabled_states
border = "border: 2px solid green;" if is_enabled else "border: 2px solid lightgray;"
opacity = "opacity: 1.0;" if is_enabled else "opacity: 0.5;"
viewport_html += f'
'
return viewport_html
- def process_inputs(urls, files, text, combine, crawl_depth): # Added crawl_depth parameter
+ def process_inputs(urls, files, text, combine, crawl_depth):
"""Process all inputs and generate QR codes"""
results = []
processing_status_messages = []
@@ -1679,11 +1548,9 @@ def create_modern_interface():
file_processor = EnhancedFileProcessor()
try:
- # Process JSON input
if text and text.strip():
try:
json_data = json.loads(text)
- # Wrap direct JSON input in a dictionary for consistency with file/URL output structure
results.append({
'source': 'json_input',
'extracted_data': json_data,
@@ -1696,38 +1563,30 @@ def create_modern_interface():
except Exception as e:
processing_status_messages.append(f"❌ Error processing direct JSON input: {str(e)}")
-
- # Process URLs
if urls and urls.strip():
url_list = re.split(r'[,\n]', urls)
url_list = [url.strip() for url in url_list if url.strip()]
for url in url_list:
- # Use the crawl_depth from the slider
processing_status_messages.append(f"🌐 Processing URL: {url} with crawl depth {crawl_depth}...")
content_result = url_processor.fetch_content_with_depth(url, max_steps=crawl_depth)
- if content_result and content_result.get('fetch_result') is not None: # Check if initial fetch was successful
- results.append(content_result)
- processing_status_messages.append(f"✅ Processed URL: {url} (Level 0)")
- # Add notes from the result if any
- if content_result.get('processing_notes'):
- processing_status_messages.append(f" Notes: {'; '.join(content_result['processing_notes'])}")
-
- # Optionally add status for linked extractions
- if content_result.get('linked_extractions'):
- num_linked_processed = len([r for r in content_result['linked_extractions'] if r and r.get('fetch_result') is not None])
- processing_status_messages.append(f" Found and processed {num_linked_processed}/{len(content_result['linked_extractions'])} direct links.")
- # Note: Detailed status for deeper levels would require traversing the result structure here.
-
+ if content_result: # Check if a result dictionary was returned
+ results.append(content_result)
+ if content_result.get('fetch_result') is not None:
+ processing_status_messages.append(f"✅ Processed URL: {url} (Level 0)")
+ if content_result.get('processing_notes'):
+ processing_status_messages.append(f" Notes: {'; '.join(content_result['processing_notes'])}")
+
+ if content_result.get('linked_extractions'):
+ num_linked_processed = len([r for r in content_result['linked_extractions'] if r and r.get('fetch_result') is not None])
+ processing_status_messages.append(f" Found and processed {num_linked_processed}/{len(content_result['linked_extractions'])} direct links.")
+ else:
+ processing_status_messages.append(f"❌ Failed to process URL: {url}")
+ if content_result.get('processing_notes'):
+ processing_status_messages.append(f" Notes: {'; '.join(content_result['processing_notes'])}")
else:
- processing_status_messages.append(f"❌ Failed to process URL: {url}")
- # Add notes from the result even if fetch failed
- if content_result and content_result.get('processing_notes'):
- processing_status_messages.append(f" Notes: {'; '.join(content_result['processing_notes'])}")
- elif content_result and content_result.get('note'): # Handle the 'note' key from validation/invalid steps
- processing_status_messages.append(f" Notes: {content_result['note']}")
+ processing_status_messages.append(f"❌ Failed to process URL: {url} (No result returned)")
- # Process files
if files:
for file in files:
processing_status_messages.append(f"📁 Processing file: {file.name}...")
@@ -1735,22 +1594,18 @@ def create_modern_interface():
if file_results:
results.extend(file_results)
processing_status_messages.append(f"✅ Processed file: {file.name}")
- # Add notes from file processing results
for res in file_results:
if res.get('processing_notes'):
processing_status_messages.append(f" Notes for {res.get('filename', 'item')}: {'; '.join(res['processing_notes'])}")
else:
processing_status_messages.append(f"❌ Failed to process file: {file.name}")
-
- # Generate QR codes
qr_paths = []
final_json_output = None
if results:
- # Use the collected results (list of dicts) for QR code generation
qr_paths = generate_qr_codes(results, combine)
- final_json_output = results # Show the structured data in the JSON output box
+ final_json_output = results
if qr_paths:
processing_status_messages.append(f"✅ Successfully generated {len(qr_paths)} QR codes.")
@@ -1760,82 +1615,73 @@ def create_modern_interface():
else:
processing_status_messages.append("⚠️ No valid content collected from inputs.")
-
except Exception as e:
logger.error(f"Overall processing error in process_inputs: {e}")
processing_status_messages.append(f"❌ An unexpected error occurred during processing: {str(e)}")
- # Return processed data for the chatbot state
return (
final_json_output,
- [str(path) for path in qr_paths], # Gradio Gallery expects list of paths (strings)
- "\n".join(processing_status_messages), # Join status messages
- final_json_output # Pass the processed data to the chatbot_data state
+ [str(path) for path in qr_paths],
+ "\n".join(processing_status_messages),
+ final_json_output
)
def on_qr_generation(qr_paths_list):
- # When QR codes are generated, update the state with the list of paths
- # and initialize the enabled_qr_codes state with all indices enabled
if qr_paths_list is None:
num_qrs = 0
else:
num_qrs = len(qr_paths_list)
initial_enabled_states = list(range(num_qrs))
- return qr_paths_list, initial_enabled_states # Return paths list and initial enabled state
+ return qr_paths_list, initial_enabled_states
- # Link events
example_btn.click(load_example, inputs=[], outputs=text_input)
- clear_btn.click(clear_input, inputs=[], outputs=[url_input, file_input, text_input, chatbot_data]) # Clear all inputs including chatbot data state
+ clear_btn.click(clear_input, inputs=[], outputs=[url_input, file_input, text_input, chatbot_data])
process_btn.click(
process_inputs,
- inputs=[url_input, file_input, text_input, combine_data, crawl_depth_slider], # Pass crawl_depth_slider value
- outputs=[output_json, output_gallery, output_text, chatbot_data] # Output to chatbot_data state
- ).then( # Chain a .then() to update the QR paths state and trigger viewport update
+ inputs=[url_input, file_input, text_input, combine_data, crawl_depth_slider],
+ outputs=[output_json, output_gallery, output_text, chatbot_data]
+ ).then(
on_qr_generation,
- inputs=[output_gallery], # Get the list of paths from the gallery output
- outputs=[qr_code_paths, enabled_qr_codes] # Update the state variables
+ inputs=[output_gallery],
+ outputs=[qr_code_paths, enabled_qr_codes]
)
- # The viewport tab's select event will trigger update_viewport to render the grid
viewport_tab.select(update_viewport, inputs=[qr_code_paths, enabled_qr_codes], outputs=[viewport_output])
- # Chatbot interactions
send_msg_btn.click(
respond_to_chat,
- inputs=[chat_input, chat_history, chatbot_data], # Pass chatbot_data state
- outputs=[chatbot, chatbot_data] # Update chatbot display and chatbot_data state
+ inputs=[chat_input, chat_history, chatbot_data],
+ outputs=[chatbot, chatbot_data]
).then(
- lambda: "", # Clear the input box after sending
+ lambda: "",
inputs=None,
outputs=chat_input
)
- chat_input.submit( # Allow sending message by pressing Enter
+ chat_input.submit(
respond_to_chat,
- inputs=[chat_input, chat_history, chatbot_data], # Pass chatbot_data state
- outputs=[chatbot, chatbot_data] # Update chatbot display and chatbot_data state
+ inputs=[chat_input, chat_history, chatbot_data],
+ outputs=[chatbot, chatbot_data]
).then(
- lambda: "", # Clear the input box after sending
+ lambda: "",
inputs=None,
outputs=chat_input
)
clear_chat_btn.click(
- lambda: [], # Clear chat history
+ lambda: [],
inputs=None,
outputs=chatbot
)
-
- # Add helpful documentation
gr.Markdown("""
### 🚀 Features
- - **Enhanced URL Scraping**: Extracts HTML text, title, meta description, links, and attempts parsing JSON/XML from URLs based on content type. Supports crawling links up to a specified depth.
- - **Advanced File Processing**: Reads various text-based files (.txt, .md, .log etc.), HTML, XML, CSV, and attempts text extraction from common documents (.pdf, .docx, .rtf, .odt - *requires extra dependencies*).
+ - **Enhanced URL Scraping**: Extracts HTML text, title, meta description, links, and attempts parsing JSON/XML from URLs based on content type. Supports crawling links up to a specified depth. **(Now performs real fetching)**
+ - **Advanced File Processing**: Reads various text-based files (.txt, .md, .log etc.), HTML, XML, CSV, and attempts text extraction from common documents (.pdf, .docx, .rtf, .odt - *requires extra dependencies*). **(Now performs real file processing)**
- **Smart JSON Handling**: Parses valid JSON from direct input, files (.json or content), or URLs.
- - **Archive Support**: Extracts and processes supported files from .zip, .tar, .gz archives.
+ - **Archive Support**: Extracts and processes supported files from .zip, .tar, .gz archives. **(Now performs real extraction)**
- **Robust Encoding Detection**: Uses `chardet` for reliable character encoding identification.
- **Structured Output**: Provides a consistent JSON output format containing raw content (if applicable), extracted data, and processing notes for each processed item.
- **Sequential QR Codes**: Maintains data integrity across multiple codes by chunking the combined/individual processed data.
@@ -1846,7 +1692,7 @@ def create_modern_interface():
1. **URLs**: Enter multiple URLs separated by commas or newlines. The processor will attempt to fetch and structure the content based on its type, following links up to the specified **Crawl Depth**.
2. **Files**: Upload any type of file. The processor will attempt to handle supported text-based files, archives (.zip, .tar, .gz), and specific document/structured formats.
3. **JSON**: Use the "Direct JSON Input" tab for pasting JSON data. The system also tries to detect JSON content in file uploads and URLs. Use the "Load Example" button to see a sample JSON structure.
- 4. **Dependencies**: Processing PDF, DOCX, RTF, and ODT files requires installing optional Python libraries. Check the console logs for warnings if a library is missing.
+ 4. **Dependencies**: Processing PDF, DOCX, RTF, and ODT files requires installing optional Python libraries (`PyPDF2`, `python-docx`, `pyth`, `odfpy`). Check the console logs for warnings if a library is missing.
5. **QR Codes**: Choose whether to "Combine all data into sequence" or generate separate sequences for each input item.
6. **Processing**: Monitor the "Processing Status" box for real-time updates and notes about errors or processing steps.
7. **Output**: The "Processed Data" JSON box shows the structured data extracted from your inputs. The "Generated QR Codes" gallery shows the QR code images.
@@ -1862,24 +1708,18 @@ def create_modern_interface():
def main():
"""Initialize and launch the application"""
try:
- # Configure system settings
mimetypes.init()
-
- # Create and launch interface
interface = create_modern_interface()
-
- # Launch with configuration
interface.launch(
share=False,
- debug=False, # Set to True for more verbose Gradio logging
+ debug=False,
show_error=True,
show_api=False
)
except Exception as e:
logger.error(f"Application startup error: {e}")
- # Optionally print a user-friendly message before exiting
print(f"\nFatal Error: {e}\nCheck the logs for details.")
- raise # Re-raise the exception to ensure the process exits if launch fails
+ raise
if __name__ == "__main__":
main()
'
- viewport_html += f'
' # Use /file= for Gradio to serve static files
+ viewport_html += f''
viewport_html += f''
viewport_html += '
'
viewport_html += '