Spaces:
Running
Running
File size: 16,736 Bytes
314bf31 a4303b2 314bf31 0b28455 59084a2 ab98d81 314bf31 6952cd8 314bf31 59084a2 314bf31 5165383 0b28455 5165383 314bf31 0b28455 5165383 0b28455 5165383 0b28455 5165383 0b28455 5165383 314bf31 0b28455 314bf31 0b28455 5165383 0b28455 5165383 314bf31 59084a2 ab98d81 59084a2 314bf31 5165383 f745765 99d9847 f745765 99d9847 f745765 99d9847 59084a2 99d9847 189c6eb f506fc8 189c6eb 99d9847 189c6eb 99d9847 ab98d81 189c6eb 59084a2 189c6eb 99d9847 6952cd8 5165383 99d9847 5165383 99d9847 5165383 99d9847 5165383 0b28455 59084a2 5165383 59084a2 5165383 0b28455 6952cd8 5165383 99d9847 59084a2 5165383 f745765 ab98d81 5165383 99d9847 5165383 ab98d81 0b28455 5165383 0b28455 5165383 f745765 ab98d81 5165383 ab98d81 5165383 ab98d81 0b28455 5165383 f745765 ab98d81 f745765 6952cd8 99d9847 f745765 6952cd8 f745765 99d9847 5165383 99d9847 f745765 99d9847 f745765 99d9847 f745765 5165383 f745765 6952cd8 99d9847 f745765 ab98d81 f745765 99d9847 f745765 ab98d81 f745765 ab98d81 f745765 99d9847 5165383 f745765 99d9847 f745765 99d9847 f745765 ab98d81 99d9847 f745765 ab98d81 99d9847 f745765 ab98d81 99d9847 5165383 ab98d81 f745765 |
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 |
# app.py
import gradio as gr
from bs4 import BeautifulSoup
import requests
from sentence_transformers import SentenceTransformer
import faiss
import numpy as np
import asyncio
import aiohttp
import re
import base64
# Initialize models and variables
embedding_model = SentenceTransformer('all-MiniLM-L6-v2')
faiss_index = None
bookmarks = []
fetch_cache = {}
# Define the categories
CATEGORIES = [
"Social Media",
"News and Media",
"Education and Learning",
"Entertainment",
"Shopping and E-commerce",
"Finance and Banking",
"Technology",
"Health and Fitness",
"Travel and Tourism",
"Food and Recipes",
"Sports",
"Arts and Culture",
"Government and Politics",
"Business and Economy",
"Science and Research",
"Personal Blogs and Journals",
"Job Search and Careers",
"Music and Audio",
"Videos and Movies",
"Reference and Knowledge Bases",
]
def parse_bookmarks(file_content):
soup = BeautifulSoup(file_content, 'html.parser')
extracted_bookmarks = []
for link in soup.find_all('a'):
url = link.get('href')
title = link.text.strip()
if url and title:
extracted_bookmarks.append({'url': url, 'title': title})
return extracted_bookmarks
async def fetch_url_info(session, bookmark):
url = bookmark['url']
if url in fetch_cache:
bookmark.update(fetch_cache[url])
return bookmark
try:
async with session.get(url, timeout=5) as response:
bookmark['etag'] = response.headers.get('ETag', 'N/A')
bookmark['status_code'] = response.status
if response.status >= 400:
bookmark['dead_link'] = True
bookmark['description'] = ''
else:
bookmark['dead_link'] = False
content = await response.text()
soup = BeautifulSoup(content, 'html.parser')
# Extract meta description or Open Graph description
meta_description = soup.find('meta', attrs={'name': 'description'})
og_description = soup.find('meta', attrs={'property': 'og:description'})
if og_description and og_description.get('content'):
description = og_description.get('content')
elif meta_description and meta_description.get('content'):
description = meta_description.get('content')
else:
description = ''
bookmark['description'] = description
except Exception as e:
bookmark['dead_link'] = True
bookmark['etag'] = 'N/A'
bookmark['status_code'] = 'N/A'
bookmark['description'] = ''
finally:
fetch_cache[url] = {
'etag': bookmark.get('etag'),
'status_code': bookmark.get('status_code'),
'dead_link': bookmark.get('dead_link'),
'description': bookmark.get('description'),
}
return bookmark
async def process_bookmarks_async(bookmarks):
async with aiohttp.ClientSession() as session:
tasks = []
for bookmark in bookmarks:
task = asyncio.ensure_future(fetch_url_info(session, bookmark))
tasks.append(task)
await asyncio.gather(*tasks)
def generate_summary(bookmark):
description = bookmark.get('description', '')
if description:
bookmark['summary'] = description
else:
title = bookmark.get('title', '')
if title:
bookmark['summary'] = title
else:
bookmark['summary'] = 'No summary available.'
return bookmark
def assign_category(bookmark):
if bookmark.get('dead_link'):
bookmark['category'] = 'Dead Link'
return bookmark
summary = bookmark.get('summary', '').lower()
assigned_category = 'Uncategorized'
# Keywords associated with each category
category_keywords = {
"Social Media": ["social media", "networking", "friends", "connect", "posts", "profile"],
"News and Media": ["news", "journalism", "media", "headlines", "breaking news"],
"Education and Learning": ["education", "learning", "courses", "tutorial", "university", "academy", "study"],
"Entertainment": ["entertainment", "movies", "tv shows", "games", "comics", "fun"],
"Shopping and E-commerce": ["shopping", "e-commerce", "buy", "sell", "marketplace", "deals", "store"],
"Finance and Banking": ["finance", "banking", "investment", "money", "economy", "stock", "trading"],
"Technology": ["technology", "tech", "gadgets", "software", "computers", "innovation"],
"Health and Fitness": ["health", "fitness", "medical", "wellness", "exercise", "diet"],
"Travel and Tourism": ["travel", "tourism", "destinations", "hotels", "flights", "vacation"],
"Food and Recipes": ["food", "recipes", "cooking", "cuisine", "restaurant", "dining"],
"Sports": ["sports", "scores", "teams", "athletics", "matches", "leagues"],
"Arts and Culture": ["arts", "culture", "museum", "gallery", "exhibition", "artistic"],
"Government and Politics": ["government", "politics", "policy", "election", "public service"],
"Business and Economy": ["business", "corporate", "industry", "economy", "markets"],
"Science and Research": ["science", "research", "experiment", "laboratory", "study", "scientific"],
"Personal Blogs and Journals": ["blog", "journal", "personal", "diary", "thoughts", "opinions"],
"Job Search and Careers": ["jobs", "careers", "recruitment", "resume", "employment", "hiring"],
"Music and Audio": ["music", "audio", "songs", "albums", "artists", "bands"],
"Videos and Movies": ["video", "movies", "film", "clips", "trailers", "cinema"],
"Reference and Knowledge Bases": ["reference", "encyclopedia", "dictionary", "wiki", "knowledge", "information"],
}
for category, keywords in category_keywords.items():
for keyword in keywords:
if re.search(r'\b' + re.escape(keyword) + r'\b', summary):
assigned_category = category
break
if assigned_category != 'Uncategorized':
break
bookmark['category'] = assigned_category
return bookmark
def vectorize_and_index(bookmarks):
summaries = [bookmark['summary'] for bookmark in bookmarks]
embeddings = embedding_model.encode(summaries)
dimension = embeddings.shape[1]
faiss_idx = faiss.IndexFlatL2(dimension)
faiss_idx.add(np.array(embeddings))
return faiss_idx, embeddings
def display_bookmarks():
cards = ''
for i, bookmark in enumerate(bookmarks):
index = i + 1 # Start index at 1
status = "Dead Link" if bookmark.get('dead_link') else "Active"
title = bookmark['title']
url = bookmark['url']
etag = bookmark.get('etag', 'N/A')
summary = bookmark.get('summary', '')
category = bookmark.get('category', 'Uncategorized')
# Apply inline styles for dead links
if bookmark.get('dead_link'):
card_style = "" # No background color
text_style = "color: #D32F2F;" # Red text
else:
card_style = ""
text_style = ""
card_html = f'''
<div class="card" style="{card_style}">
<div class="card-content">
<input type="checkbox" class="bookmark-checkbox" data-index="{index-1}">
<h3 style="{text_style}">{index}. {title}</h3>
<p style="{text_style}"><strong>Category:</strong> {category}</p>
<p style="{text_style}"><strong>URL:</strong> <a href="{url}" target="_blank" style="{text_style}">{url}</a></p>
<p style="{text_style}"><strong>Status:</strong> {status}</p>
<p style="{text_style}"><strong>ETag:</strong> {etag}</p>
<p style="{text_style}"><strong>Summary:</strong> {summary}</p>
</div>
</div>
'''
cards += card_html
return cards
def process_uploaded_file(file):
global bookmarks, faiss_index
if file is None:
return "Please upload a bookmarks HTML file.", ''
try:
file_content = file.decode('utf-8')
except UnicodeDecodeError:
return "Error decoding the file. Please ensure it's a valid HTML file.", ''
bookmarks = parse_bookmarks(file_content)
if not bookmarks:
return "No bookmarks found in the uploaded file.", ''
# Asynchronously fetch bookmark info
asyncio.run(process_bookmarks_async(bookmarks))
# Generate summaries and assign categories
for bookmark in bookmarks:
generate_summary(bookmark)
assign_category(bookmark)
faiss_index, embeddings = vectorize_and_index(bookmarks)
message = f"Successfully processed {len(bookmarks)} bookmarks."
bookmark_html = display_bookmarks()
return message, bookmark_html
def chatbot_response(user_query):
if faiss_index is None or not bookmarks:
return "No bookmarks available. Please upload and process your bookmarks first."
# Vectorize user query
user_embedding = embedding_model.encode([user_query])
D, I = faiss_index.search(np.array(user_embedding), k=5) # Retrieve top 5 matches
# Generate response
response = ""
for idx in I[0]:
if idx < len(bookmarks):
bookmark = bookmarks[idx]
index = bookmarks.index(bookmark) + 1 # Start index at 1
response += f"{index}. Title: {bookmark['title']}\nURL: {bookmark['url']}\nCategory: {bookmark.get('category', 'Uncategorized')}\nSummary: {bookmark['summary']}\n\n"
return response.strip()
def edit_bookmark(bookmark_idx, new_title, new_url, new_category):
global faiss_index
try:
bookmark_idx = int(bookmark_idx) - 1 # Adjust index to match list (starting at 0)
if bookmark_idx < 0 or bookmark_idx >= len(bookmarks):
return "Invalid bookmark index.", display_bookmarks()
bookmarks[bookmark_idx]['title'] = new_title
bookmarks[bookmark_idx]['url'] = new_url
bookmarks[bookmark_idx]['category'] = new_category
# Re-fetch bookmark info
asyncio.run(process_bookmarks_async([bookmarks[bookmark_idx]]))
generate_summary(bookmarks[bookmark_idx])
# Rebuild the FAISS index
faiss_index, embeddings = vectorize_and_index(bookmarks)
message = "Bookmark updated successfully."
updated_html = display_bookmarks()
return message, updated_html
except Exception as e:
return f"Error: {str(e)}", display_bookmarks()
def delete_bookmarks(indices):
global faiss_index
try:
indices = sorted([int(idx) for idx in indices], reverse=True)
for idx in indices:
if 0 <= idx < len(bookmarks):
bookmarks.pop(idx)
# Rebuild the FAISS index
if bookmarks:
faiss_index, embeddings = vectorize_and_index(bookmarks)
else:
faiss_index = None
message = "Selected bookmarks deleted successfully."
updated_html = display_bookmarks()
return message, updated_html
except Exception as e:
return f"Error: {str(e)}", display_bookmarks()
def export_bookmarks():
if not bookmarks:
return None
# Create an HTML content similar to the imported bookmarks file
soup = BeautifulSoup("<!DOCTYPE NETSCAPE-Bookmark-file-1><Title>Bookmarks</Title><H1>Bookmarks</H1>", 'html.parser')
dl = soup.new_tag('DL')
for bookmark in bookmarks:
dt = soup.new_tag('DT')
a = soup.new_tag('A', href=bookmark['url'])
a.string = bookmark['title']
dt.append(a)
dl.append(dt)
soup.append(dl)
html_content = str(soup)
# Encode the HTML content to base64 for download
b64 = base64.b64encode(html_content.encode()).decode()
href = f'data:text/html;base64,{b64}'
return href
def build_app():
with gr.Blocks(css="app.css") as demo:
gr.Markdown("<h1>Bookmark Manager App</h1>")
with gr.Tab("Upload and Process Bookmarks"):
upload = gr.File(label="Upload Bookmarks HTML File", type='binary')
process_button = gr.Button("Process Bookmarks")
output_text = gr.Textbox(label="Output")
bookmark_display = gr.HTML(label="Bookmarks")
def update_bookmark_display(file):
message, html_content = process_uploaded_file(file)
return message, html_content
process_button.click(
update_bookmark_display,
inputs=upload,
outputs=[output_text, bookmark_display]
)
with gr.Tab("Chat with Bookmarks"):
user_input = gr.Textbox(label="Ask about your bookmarks")
chat_output = gr.Textbox(label="Chatbot Response")
chat_button = gr.Button("Send")
chat_button.click(
chatbot_response,
inputs=user_input,
outputs=chat_output
)
with gr.Tab("Manage Bookmarks"):
manage_output = gr.Textbox(label="Manage Output")
bookmark_display_manage = gr.HTML(label="Bookmarks")
refresh_button = gr.Button("Refresh Bookmark List")
select_all_checkbox = gr.Checkbox(label="Select All")
selected_indices = gr.Textbox(label="Selected Indices (comma-separated)", visible=False)
with gr.Row():
index_input = gr.Number(label="Bookmark Index (Starting from 1)", precision=0)
new_title_input = gr.Textbox(label="New Title")
new_url_input = gr.Textbox(label="New URL")
new_category_input = gr.Dropdown(label="New Category", choices=CATEGORIES)
edit_button = gr.Button("Edit Bookmark")
delete_button = gr.Button("Delete Selected Bookmarks")
export_button = gr.Button("Export Bookmarks")
download_link = gr.HTML(label="Download Exported Bookmarks")
def update_manage_display():
html_content = display_bookmarks()
return html_content
refresh_button.click(
update_manage_display,
inputs=None,
outputs=bookmark_display_manage
)
edit_button.click(
edit_bookmark,
inputs=[index_input, new_title_input, new_url_input, new_category_input],
outputs=[manage_output, bookmark_display_manage]
)
delete_button.click(
delete_bookmarks,
inputs=selected_indices,
outputs=[manage_output, bookmark_display_manage]
)
def provide_download_link():
href = export_bookmarks()
if href:
return f'<a href="{href}" download="bookmarks.html">Download Exported Bookmarks</a>'
else:
return "No bookmarks to export."
export_button.click(
provide_download_link,
inputs=None,
outputs=download_link
)
# Initial load of the bookmarks display
bookmark_display_manage.value = update_manage_display()
# Include JavaScript to handle checkbox selection and Select All functionality
demo.load(None, None, None, _js="""
function() {
// Handle Select All checkbox
document.querySelector('input[type="checkbox"][label="Select All"]').addEventListener('change', function() {
var checkboxes = document.querySelectorAll('.bookmark-checkbox');
for (var i = 0; i < checkboxes.length; i++) {
checkboxes[i].checked = this.checked;
}
});
// Update selected indices
function updateSelectedIndices() {
var checkboxes = document.querySelectorAll('.bookmark-checkbox');
var indices = [];
for (var i = 0; i < checkboxes.length; i++) {
if (checkboxes[i].checked) {
indices.push(checkboxes[i].getAttribute('data-index'));
}
}
document.querySelector('textarea[label="Selected Indices (comma-separated)"]').value = indices.join(',');
}
document.addEventListener('change', function(e) {
if (e.target && e.target.classList.contains('bookmark-checkbox')) {
updateSelectedIndices();
}
});
}
""")
demo.launch()
if __name__ == "__main__":
build_app()
|