Spaces:
Running
Running
File size: 23,111 Bytes
c3b1d58 3792905 c3b1d58 c92df66 c3b1d58 c92df66 75b5552 c3b1d58 c92df66 c3b1d58 6ec7960 3792905 c3b1d58 c7e50ec c3b1d58 c7e50ec c3b1d58 345d19b c3b1d58 c7e50ec c3b1d58 c92df66 c3b1d58 c92df66 c3b1d58 c92df66 c3b1d58 4489b3a c3b1d58 6fb3663 c3b1d58 345d19b 14b5f32 c3b1d58 3244846 c3b1d58 8b83f9c c3b1d58 c92df66 c3b1d58 c92df66 dad6950 c92df66 c3b1d58 c7e50ec c3b1d58 c7e50ec cd90730 c3b1d58 c7e50ec c92df66 30f269c c92df66 30f269c c92df66 6a91fa4 c92df66 345d19b c92df66 14b5f32 7ef4e98 f6bca8a 7ef4e98 c92df66 7ef4e98 c7e50ec 7ef4e98 c7e50ec 7ef4e98 0b2fd02 c7e50ec 869982c 09cff43 6ec7960 c7e50ec 318aaab 6ec7960 318aaab 68c65a0 869982c 2caeae6 c92df66 7203d3a c92df66 2caeae6 6ec7960 869982c d755d1c c7e50ec |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 |
import json
import sys
import os
import re
import time
import logging
import mimetypes
import tempfile
from datetime import datetime
from pathlib import Path
from urllib.parse import urlparse
from typing import List, Dict, Tuple, Union, Optional
import requests
import validators
import gradio as gr
from diskcache import Cache
from bs4 import BeautifulSoup
from fake_useragent import UserAgent
from cleantext import clean
import qrcode
import zipfile
# Setup logging with detailed configuration
logging.basicConfig(
level=logging.INFO,
format='%(asctime)s - %(levelname)s - [%(filename)s:%(lineno)d] - %(message)s',
handlers=[
logging.StreamHandler(),
logging.FileHandler('app.log', encoding='utf-8')
])
logger = logging.getLogger(__name__)
class URLProcessor:
def __init__(self):
self.session = requests.Session()
self.timeout = 10 # seconds
self.session.headers.update({
'User-Agent': UserAgent().random,
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Accept-Language': 'en-US,en;q=0.5',
'Accept-Encoding': 'gzip, deflate, br',
'Connection': 'keep-alive',
'Upgrade-Insecure-Requests': '1'
})
def advanced_text_cleaning(self, text: str) -> str:
"""Robust text cleaning with version compatibility"""
try:
cleaned_text = clean(
text,
to_ascii=True,
lower=True,
no_line_breaks=True,
no_urls=True,
no_emails=True,
no_phone_numbers=True,
no_numbers=False,
no_digits=False,
no_currency_symbols=True,
no_punct=False
).strip()
return cleaned_text
except Exception as e:
logger.warning(f"Text cleaning error: {e}. Using fallback method.")
text = re.sub(r'[\x00-\x1F\x7F-\x9F]', '', text) # Remove control characters
text = text.encode('ascii', 'ignore').decode('ascii') # Remove non-ASCII characters
text = re.sub(r'\s+', ' ', text) # Normalize whitespace
return text.strip()
def validate_url(self, url: str) -> Dict:
"""Validate URL format and accessibility"""
try:
if not validators.url(url):
return {'is_valid': False, 'message': 'Invalid URL format'}
response = self.session.head(url, timeout=self.timeout)
response.raise_for_status()
return {'is_valid': True, 'message': 'URL is valid and accessible'}
except Exception as e:
return {'is_valid': False, 'message': f'URL validation failed: {str(e)}'}
def fetch_content(self, url: str) -> Optional[Dict]:
"""Universal content fetcher with special case handling"""
try:
# Google Drive document handling
if 'drive.google.com' in url:
return self._handle_google_drive(url)
# Google Calendar ICS handling
if 'calendar.google.com' in url and 'ical' in url:
return self._handle_google_calendar(url)
# Standard HTML processing
return self._fetch_html_content(url)
except Exception as e:
logger.error(f"Content fetch failed: {e}")
return None
def _handle_google_drive(self, url: str) -> Optional[Dict]:
"""Process Google Drive file links"""
try:
file_id = re.search(r'/file/d/([a-zA-Z0-9_-]+)', url)
if not file_id:
logger.error(f"Invalid Google Drive URL: {url}")
return None
direct_url = f"https://drive.google.com/uc?export=download&id={file_id.group(1)}"
response = self.session.get(direct_url, timeout=self.timeout)
response.raise_for_status()
return {
'content': response.text,
'content_type': response.headers.get('Content-Type', ''),
'timestamp': datetime.now().isoformat()
}
except Exception as e:
logger.error(f"Google Drive processing failed: {e}")
return None
def _handle_google_calendar(self, url: str) -> Optional[Dict]:
"""Process Google Calendar ICS feeds"""
try:
response = self.session.get(url, timeout=self.timeout)
response.raise_for_status()
return {
'content': response.text,
'content_type': 'text/calendar',
'timestamp': datetime.now().isoformat()
}
except Exception as e:
logger.error(f"Calendar fetch failed: {e}")
return None
def _fetch_html_content(self, url: str) -> Optional[Dict]:
"""Standard HTML content processing"""
try:
response = self.session.get(url, timeout=self.timeout)
response.raise_for_status()
soup = BeautifulSoup(response.text, 'html.parser')
# Remove unwanted elements
for element in soup(['script', 'style', 'nav', 'footer', 'header', 'meta', 'link']):
element.decompose()
# Extract main content
main_content = soup.find('main') or soup.find('article') or soup.body
# Clean and structure content
text_content = main_content.get_text(separator='\n', strip=True)
cleaned_content = self.advanced_text_cleaning(text_content)
return {
'content': cleaned_content,
'content_type': response.headers.get('Content-Type', ''),
'timestamp': datetime.now().isoformat()
}
except Exception as e:
logger.error(f"HTML processing failed: {e}")
return None
class FileProcessor:
"""Class to handle file processing"""
def __init__(self, max_file_size: int = 2 * 1024 * 1024 * 1024): # 2GB default
self.max_file_size = max_file_size
self.supported_text_extensions = {'.txt', '.md', '.csv', '.json', '.xml'}
def is_text_file(self, filepath: str) -> bool:
"""Check if file is a text file"""
try:
mime_type, _ = mimetypes.guess_type(filepath)
return (mime_type and mime_type.startswith('text/')) or \
(os.path.splitext(filepath)[1].lower() in self.supported_text_extensions)
except Exception:
return False
def process_file(self, file) -> List[Dict]:
"""Process uploaded file with enhanced error handling"""
if not file:
return []
dataset = []
try:
file_size = os.path.getsize(file.name)
if file_size > self.max_file_size:
logger.warning(f"File size ({file_size} bytes) exceeds maximum allowed size")
return []
with tempfile.TemporaryDirectory() as temp_dir:
if zipfile.is_zipfile(file.name):
dataset.extend(self._process_zip_file(file.name, temp_dir))
else:
dataset.extend(self._process_single_file(file))
except Exception as e:
logger.error(f"Error processing file: {str(e)}")
return []
return dataset
def _process_zip_file(self, zip_path, temp_dir):
"""Extract and process files within a ZIP archive."""
result = []
with zipfile.ZipFile(zip_path, 'r') as zip_ref:
zip_ref.extractall(temp_dir)
for extracted_file in os.listdir(temp_dir):
extracted_file_path = os.path.join(temp_dir, extracted_file)
if os.path.isfile(extracted_file_path):
with open(extracted_file_path, 'r', encoding='utf-8', errors='ignore') as f:
result.append({
'source': 'file_from_zip',
'filename': extracted_file,
'content': f.read(),
'timestamp': datetime.now().isoformat()
})
return result
def _process_single_file(self, file) -> List[Dict]:
try:
file_stat = os.stat(file.name)
# For very large files, read in chunks and summarize
if file_stat.st_size > 100 * 1024 * 1024: # 100MB
logger.info(f"Processing large file: {file.name} ({file_stat.st_size} bytes)")
# Read first and last 1MB for extremely large files
content = ""
with open(file.name, 'r', encoding='utf-8', errors='ignore') as f:
content = f.read(1 * 1024 * 1024) # First 1MB
content += "\n...[Content truncated due to large file size]...\n"
# Seek to the last 1MB
f.seek(max(0, file_stat.st_size - 1 * 1024 * 1024))
content += f.read() # Last 1MB
else:
# Regular file processing
with open(file.name, 'r', encoding='utf-8', errors='ignore') as f:
content = f.read()
return [{
'source': 'file',
'filename': os.path.basename(file.name),
'file_size': file_stat.st_size,
'mime_type': mimetypes.guess_type(file.name)[0],
'created': datetime.fromtimestamp(file_stat.st_ctime).isoformat(),
'modified': datetime.fromtimestamp(file_stat.st_mtime).isoformat(),
'content': content,
'timestamp': datetime.now().isoformat()
}]
except Exception as e:
logger.error(f"File processing error: {e}")
return []
def generate_qr(json_data):
"""Generate QR code from JSON data and return the file path."""
try:
# Try first with automatic version selection
qr = qrcode.QRCode(
error_correction=qrcode.constants.ERROR_CORRECT_L,
box_size=10,
border=4,
)
qr.add_data(json_data)
qr.make(fit=True)
img = qr.make_image(fill_color="black", back_color="white")
temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".png")
img.save(temp_file.name)
return temp_file.name
except Exception as e:
# If the data is too large for a QR code
logger.error(f"QR generation error: {e}")
# Create a simple QR with error message
qr = qrcode.QRCode(
version=1,
error_correction=qrcode.constants.ERROR_CORRECT_L,
box_size=10,
border=4,
)
qr.add_data("Error: Data too large for QR code")
qr.make(fit=True)
img = qr.make_image(fill_color="black", back_color="white")
temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".png")
img.save(temp_file.name)
return temp_file.name
def create_interface():
"""Create a comprehensive Gradio interface with advanced features and styling"""
css = """
body {
font-family: 'Inter', sans-serif;
background: linear-gradient(to bottom, #08041C, #030712); /* Dark cosmic background */
color: #ffffff;
}
.container {
max-width: 1200px;
margin: auto;
background-color: rgba(255, 255, 255, 0.06);
backdrop-filter: blur(12px);
border: 1px solid rgba(255, 255, 255, 0.1);
border-radius: 1rem;
box-shadow: 0 4px 12px rgba(0, 0, 0, 0.25);
padding: 2rem;
}
h1 {
color: #00FF00;
text-align: center;
text-shadow: 0 0 10px rgba(0, 255, 0, 0.8);
}
h2, h3, h4 {
color: #FF9900;
text-shadow: 0 0 10px rgba(255, 153, 0, 0.8);
}
.tab {
background-color: rgba(255, 255, 255, 0.06);
backdrop-filter: blur(12px);
border: 1px solid rgba(255, 255, 255, 0.1);
border-radius: 0.75rem;
margin-bottom: 1rem;
padding: 1.5rem;
}
.tab:hover {
background-color: rgba(255, 255, 255, 0.1);
}
.warning {
background-color: #fff3cd;
color: #856404;
border-radius: 0.5rem;
padding: 1rem;
margin-bottom: 1rem;
}
.error {
background-color: #f8d7da;
color: #721c24;
border-radius: 0.5rem;
padding: 1rem;
margin-bottom: 1rem;
}
input[type="text"], input[type="file"] {
width: 100%;
padding: 0.75rem;
border-radius: 0.5rem;
background-color: rgba(0, 0, 0, 0.2);
color: #ffffff;
border: 1px solid #4a5568;
font-size: 1rem;
transition: border-color 0.3s ease;
}
input[type="text"]:focus, input[type="file"]:focus {
outline: none;
border-color: #00FF00;
box-shadow: 0 0 5px rgba(0, 255, 0, 0.7);
}
.btn-primary {
padding: 0.75rem 1.5rem;
border-radius: 1.5rem;
font-weight: 600;
cursor: pointer;
transition: transform 0.2s ease, box-shadow 0.2s ease, background-image 0.3s;
background-image: linear-gradient(to right, #00FF00, #00A300);
color: #000000;
border: none;
box-shadow: 0 0 8px rgba(0, 255, 0, 0.5);
}
.btn-primary:hover {
transform: scale(1.05);
box-shadow: 0 0 12px rgba(0, 255, 0, 0.7);
background-image: linear-gradient(to right, #00A300, #007D00);
}
.btn-secondary {
padding: 0.75rem 1.5rem;
border-radius: 1.5rem;
font-weight: 600;
cursor: pointer;
transition: transform 0.2s ease, box-shadow 0.2s ease, background-image 0.3s;
background-image: linear-gradient(to right, #FF9900, #FF6600);
color: #000000;
border: none;
box-shadow: 0 0 8px rgba(255, 153, 0, 0.5);
}
.btn-secondary:hover {
transform: scale(1.05);
box-shadow: 0 0 12px rgba(255, 153, 0, 0.7);
background-image: linear-gradient(to right, #FF6600, #CC4700);
}
textarea {
width: 100%;
padding: 0.75rem;
border-radius: 0.5rem;
background-color: rgba(0, 0, 0, 0.2);
color: #ffffff;
border: 1px solid #4a5568;
font-size: 1rem;
transition: border-color 0.3s ease;
min-height: 8rem;
}
textarea:focus {
outline: none;
border-color: #00FF00;
box-shadow: 0 0 5px rgba(0, 255, 0, 0.7);
}
.output-box {
background-color: rgba(0, 0, 0, 0.2);
border: 1px solid #4a5568;
border-radius: 0.5rem;
padding: 1rem;
overflow-x: auto;
color: #ffffff;
font-size: 1rem;
white-space: pre-wrap;
}
#json-editor {
background-color: rgba(0, 0, 0, 0.2);
color: #ffffff;
border: 1px solid #4a5568;
border-radius: 0.5rem;
padding: 1rem;
font-size: 1rem;
min-height: 20rem;
}
#json-editor:focus {
outline: none;
border-color: #00FF00;
box-shadow: 0 0 5px rgba(0, 255, 0, 0.7);
}
#url-input {
background-color: rgba(0, 0, 0, 0.2);
color: #ffffff;
border: 1px solid #4a5568;
border-radius: 0.5rem;
padding: 1rem;
font-size: 1rem;
min-height: 8rem;
}
#url-input:focus {
outline: none;
border-color: #00FF00;
box-shadow: 0 0 5px rgba(0, 255, 0, 0.7);
}
#output-text{
background-color: rgba(0, 0, 0, 0.2);
color: #ffffff;
border: 1px solid #4a5568;
border-radius: 0.5rem;
padding: 1rem;
font-size: 1rem;
}
"""
with gr.Blocks(css=css, title="Advanced Text & URL Processor") as interface:
gr.Markdown("# 🌐 Advanced URL & Text Processing Toolkit")
with gr.Tab("URL Processing") as url_tab:
url_input = gr.Textbox(
label="Enter URLs (comma or newline separated)",
lines=5,
placeholder="https://example1.com\nhttps://example2.com",
interactive=True,
elem_id="url-input"
)
with gr.Tab("File Input") as file_tab:
file_input = gr.File(
label="Upload text file or ZIP archive",
file_types=[".txt", ".zip", ".md", ".csv", ".json", ".xml"]
)
with gr.Tab("Text Input") as text_tab:
text_input = gr.Textbox(
label="Raw Text Input",
lines=5,
placeholder="Paste your text here...",
interactive=True
)
with gr.Tab("JSON Editor") as json_tab:
json_editor = gr.Textbox(
label="JSON Editor",
lines=20,
placeholder="View and edit your JSON data here...",
interactive=True,
elem_id="json-editor"
)
with gr.Tab("Scratchpad") as scratchpad_tab:
scratchpad = gr.Textbox(
label="Scratchpad",
lines=10,
placeholder="Quick notes or text collections...",
interactive=True
)
process_btn = gr.Button("Process Input", variant="primary")
qr_btn = gr.Button("Generate QR Code", variant="secondary")
output_text = gr.Textbox(label="Processing Results", interactive=False, elem_id="output-text")
output_file = gr.File(label="Processed Output")
qr_output = gr.Image(label="QR Code", type="filepath") # To display the generated QR code
def process_all_inputs(urls, file, text, notes):
"""Process all input types with progress tracking"""
try:
processor = URLProcessor()
file_processor = FileProcessor()
results = []
# Process URLs
if urls:
url_list = re.split(r'[,\n]', urls)
url_list = [url.strip() for url in url_list if url.strip()]
for url in url_list:
validation = processor.validate_url(url)
if validation.get('is_valid'):
content = processor.fetch_content(url)
if content:
results.append({
'source': 'url',
'url': url,
'content': content,
'timestamp': datetime.now().isoformat()
})
# Process files
if file:
results.extend(file_processor.process_file(file))
# Process text input
if text:
cleaned_text = processor.advanced_text_cleaning(text)
results.append({
'source': 'direct_input',
'content': cleaned_text,
'timestamp': datetime.now().isoformat()
})
# Generate output
if results:
output_dir = Path('output') / datetime.now().strftime('%Y-%m-%d')
output_dir.mkdir(parents=True, exist_ok=True)
output_path = output_dir / f'processed_{int(time.time())}.json'
with open(output_path, 'w', encoding='utf-8') as f:
json.dump(results, f, ensure_ascii=False, indent=2)
summary = f"Processed {len(results)} items successfully!"
json_data = json.dumps(results, indent=2) # Prepare JSON for QR code
return str(output_path), summary, json_data # Return JSON for editor
else:
return None, "No valid content to process.", ""
except Exception as e:
logger.error(f"Processing error: {e}")
return None, f"Error: {str(e)}", ""
def generate_qr_code(json_data):
"""Generate QR code from JSON data."""
if not json_data:
return "No data to encode."
qr_file = generate_qr(json_data)
return qr_file
process_btn.click(
process_all_inputs,
inputs=[url_input, file_input, text_input, scratchpad],
outputs=[output_file, output_text, json_editor]
)
qr_btn.click(generate_qr_code, inputs=[json_editor], outputs=[qr_output])
gr.Markdown("""
### Usage Guidelines
- **URL Processing**: Enter valid HTTP/HTTPS URLs, separated by commas or newlines.
- **File Input**: Upload text files orZIP archives containing text files.
- **Text Input**: Paste text directly for processing.
- **JSON Editor**: View the processed data in JSON format. This is automatically updated after processing.
- **Scratchpad**: Use this area for temporary notes or text snippets.
- Click "Process Input" to analyze the data. The results will be available for download and in the JSON Editor.
- Click "Generate QR Code" to create a QR code from the JSON data.
""")
return interface
def main():
# Configure system settings
mimetypes.init()
# Create and launch interface
interface = create_interface()
# Launch with proper configuration
interface.launch(
server_name="0.0.0.0",
server_port=7860,
show_error=True,
share=False,
inbrowser=True,
debug=True
)
if __name__ == "__main__":
main()
|