Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -5,39 +5,23 @@ from datetime import datetime, timedelta
|
|
| 5 |
import time
|
| 6 |
import os
|
| 7 |
|
| 8 |
-
def
|
| 9 |
"""
|
| 10 |
-
Get
|
| 11 |
"""
|
| 12 |
if not github_token:
|
| 13 |
-
return 0
|
| 14 |
|
| 15 |
-
# Calculate exact date range
|
| 16 |
end_date = datetime.now()
|
| 17 |
start_date = end_date - timedelta(days=days)
|
| 18 |
|
| 19 |
-
# Format dates in ISO format with timezone
|
| 20 |
-
from_date = start_date.strftime('%Y-%m-%dT%H:%M:%SZ')
|
| 21 |
-
to_date = end_date.strftime('%Y-%m-%dT%H:%M:%SZ')
|
| 22 |
-
|
| 23 |
-
# GraphQL query - get detailed contribution data
|
| 24 |
query = """
|
| 25 |
query($username: String!, $from: DateTime!, $to: DateTime!) {
|
| 26 |
user(login: $username) {
|
| 27 |
contributionsCollection(from: $from, to: $to) {
|
| 28 |
contributionCalendar {
|
| 29 |
totalContributions
|
| 30 |
-
weeks {
|
| 31 |
-
contributionDays {
|
| 32 |
-
contributionCount
|
| 33 |
-
date
|
| 34 |
-
}
|
| 35 |
-
}
|
| 36 |
}
|
| 37 |
-
totalCommitContributions
|
| 38 |
-
totalIssueContributions
|
| 39 |
-
totalPullRequestContributions
|
| 40 |
-
totalPullRequestReviewContributions
|
| 41 |
}
|
| 42 |
}
|
| 43 |
}
|
|
@@ -45,8 +29,8 @@ def get_contribution_count_graphql(username, github_token, days=30):
|
|
| 45 |
|
| 46 |
variables = {
|
| 47 |
"username": username,
|
| 48 |
-
"from":
|
| 49 |
-
"to":
|
| 50 |
}
|
| 51 |
|
| 52 |
headers = {
|
|
@@ -58,283 +42,132 @@ def get_contribution_count_graphql(username, github_token, days=30):
|
|
| 58 |
response = requests.post(
|
| 59 |
'https://api.github.com/graphql',
|
| 60 |
json={'query': query, 'variables': variables},
|
| 61 |
-
headers=headers
|
| 62 |
-
timeout=10
|
| 63 |
)
|
| 64 |
|
| 65 |
if response.status_code == 200:
|
| 66 |
data = response.json()
|
| 67 |
-
|
| 68 |
-
# Check for errors in response
|
| 69 |
-
if 'errors' in data:
|
| 70 |
-
return 0, f"GraphQL Error: {data['errors']}"
|
| 71 |
-
|
| 72 |
if 'data' in data and data['data'] and data['data']['user']:
|
| 73 |
-
|
| 74 |
-
|
| 75 |
-
# Get the total contributions from the calendar
|
| 76 |
-
total = contrib_collection['contributionCalendar']['totalContributions']
|
| 77 |
-
|
| 78 |
-
# Detailed breakdown (for debugging)
|
| 79 |
-
commits = contrib_collection.get('totalCommitContributions', 0)
|
| 80 |
-
issues = contrib_collection.get('totalIssueContributions', 0)
|
| 81 |
-
prs = contrib_collection.get('totalPullRequestContributions', 0)
|
| 82 |
-
reviews = contrib_collection.get('totalPullRequestReviewContributions', 0)
|
| 83 |
-
|
| 84 |
-
debug_info = f"Total: {total} (Commits: {commits}, Issues: {issues}, PRs: {prs}, Reviews: {reviews})"
|
| 85 |
-
|
| 86 |
-
return total, debug_info
|
| 87 |
-
else:
|
| 88 |
-
return 0, "User not found or no data"
|
| 89 |
-
else:
|
| 90 |
-
return 0, f"HTTP Error {response.status_code}: {response.text[:200]}"
|
| 91 |
-
|
| 92 |
except Exception as e:
|
| 93 |
-
|
| 94 |
-
|
| 95 |
-
def is_uae_location(location):
|
| 96 |
-
"""
|
| 97 |
-
Check if location string indicates UAE - case insensitive matching
|
| 98 |
-
"""
|
| 99 |
-
if not location:
|
| 100 |
-
return False
|
| 101 |
-
|
| 102 |
-
# Convert to lowercase and strip whitespace for comparison
|
| 103 |
-
location_lower = location.lower().strip()
|
| 104 |
-
|
| 105 |
-
# Country-level keywords (highest priority)
|
| 106 |
-
country_keywords = [
|
| 107 |
-
'united arab emirates',
|
| 108 |
-
'uae',
|
| 109 |
-
'u.a.e',
|
| 110 |
-
'u.a.e.',
|
| 111 |
-
'emirates',
|
| 112 |
-
]
|
| 113 |
-
|
| 114 |
-
# City keywords (secondary check)
|
| 115 |
-
city_keywords = [
|
| 116 |
-
'dubai',
|
| 117 |
-
'abu dhabi',
|
| 118 |
-
'abudhabi',
|
| 119 |
-
'sharjah',
|
| 120 |
-
'ajman',
|
| 121 |
-
'ras al khaimah',
|
| 122 |
-
'ras al-khaimah',
|
| 123 |
-
'rak',
|
| 124 |
-
'fujairah',
|
| 125 |
-
'umm al quwain',
|
| 126 |
-
'umm al-quwain',
|
| 127 |
-
'al ain',
|
| 128 |
-
'dubayy',
|
| 129 |
-
'Ψ―Ψ¨Ω',
|
| 130 |
-
'Ψ§ΩΨ₯Ω
Ψ§Ψ±Ψ§Ψͺ'
|
| 131 |
-
]
|
| 132 |
-
|
| 133 |
-
# Check country keywords first (case insensitive)
|
| 134 |
-
for keyword in country_keywords:
|
| 135 |
-
if keyword.lower() in location_lower:
|
| 136 |
-
return True
|
| 137 |
-
|
| 138 |
-
# Then check city keywords (case insensitive)
|
| 139 |
-
for keyword in city_keywords:
|
| 140 |
-
if keyword.lower() in location_lower:
|
| 141 |
-
return True
|
| 142 |
|
| 143 |
-
return
|
| 144 |
|
| 145 |
-
def fetch_github_users(github_token=None, max_users=200, min_followers=
|
| 146 |
"""
|
| 147 |
-
Fetch GitHub users from UAE
|
|
|
|
| 148 |
"""
|
| 149 |
-
# Read token from environment variable if not provided
|
| 150 |
if not github_token:
|
| 151 |
github_token = os.getenv('GITHUB_TOKEN')
|
| 152 |
-
|
| 153 |
-
if not github_token:
|
| 154 |
-
return pd.DataFrame(), "β GitHub token is REQUIRED. Please provide a token with 'read:user' scope."
|
| 155 |
|
| 156 |
headers = {
|
| 157 |
'Accept': 'application/vnd.github.v3+json',
|
| 158 |
-
'Authorization': f'token {github_token}'
|
| 159 |
}
|
| 160 |
|
| 161 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 162 |
status_updates = []
|
| 163 |
-
total_api_calls = 0
|
| 164 |
-
contribution_errors = []
|
| 165 |
|
| 166 |
try:
|
| 167 |
-
|
| 168 |
-
|
| 169 |
-
|
| 170 |
-
|
| 171 |
-
|
| 172 |
-
|
| 173 |
-
|
| 174 |
-
|
| 175 |
-
|
| 176 |
-
|
| 177 |
-
|
| 178 |
-
|
| 179 |
-
|
| 180 |
-
|
| 181 |
-
|
| 182 |
-
|
| 183 |
-
|
| 184 |
-
|
| 185 |
-
|
| 186 |
-
|
| 187 |
-
|
| 188 |
-
for sort_by, order in sort_methods:
|
| 189 |
-
if total_api_calls >= 150:
|
| 190 |
-
break
|
| 191 |
-
|
| 192 |
-
search_url = f'https://api.github.com/search/users?q=location:{search_term}+followers:>={min_followers}&sort={sort_by}&order={order}&per_page=100'
|
| 193 |
-
|
| 194 |
-
response = requests.get(search_url, headers=headers)
|
| 195 |
-
total_api_calls += 1
|
| 196 |
-
|
| 197 |
-
if response.status_code == 200:
|
| 198 |
-
data = response.json()
|
| 199 |
-
users = data.get('items', [])
|
| 200 |
-
|
| 201 |
-
status_updates.append(f" π Search '{search_term}' by {sort_by}: {len(users)} users")
|
| 202 |
-
|
| 203 |
-
for user in users:
|
| 204 |
-
if user['login'] not in all_users:
|
| 205 |
-
if total_api_calls >= 150:
|
| 206 |
-
break
|
| 207 |
-
|
| 208 |
-
# Fetch detailed user info
|
| 209 |
-
user_response = requests.get(user['url'], headers=headers)
|
| 210 |
-
total_api_calls += 1
|
| 211 |
|
| 212 |
-
|
| 213 |
-
|
| 214 |
-
|
| 215 |
-
|
| 216 |
-
|
| 217 |
-
|
| 218 |
-
contributions, debug_info = get_contribution_count_graphql(
|
| 219 |
-
user['login'],
|
| 220 |
-
github_token,
|
| 221 |
-
days
|
| 222 |
-
)
|
| 223 |
-
|
| 224 |
-
if contributions == 0 and "Error" in debug_info:
|
| 225 |
-
contribution_errors.append(f"{user['login']}: {debug_info}")
|
| 226 |
-
|
| 227 |
-
all_users[user['login']] = {
|
| 228 |
-
'login': user_data.get('login', ''),
|
| 229 |
-
'name': user_data.get('name') or user_data.get('login', ''),
|
| 230 |
-
'avatar': user_data.get('avatar_url', ''),
|
| 231 |
-
'followers': user_data.get('followers', 0),
|
| 232 |
-
'public_repos': user_data.get('public_repos', 0),
|
| 233 |
-
'contributions': contributions,
|
| 234 |
-
'location': user_data.get('location', ''),
|
| 235 |
-
'bio': user_data.get('bio', ''),
|
| 236 |
-
'company': user_data.get('company', ''),
|
| 237 |
-
'debug_info': debug_info
|
| 238 |
-
}
|
| 239 |
-
|
| 240 |
-
if len(all_users) % 20 == 0:
|
| 241 |
-
status_updates.append(f" β
Processed {len(all_users)} unique UAE users...")
|
| 242 |
-
|
| 243 |
-
time.sleep(0.8) # Rate limiting - be more conservative
|
| 244 |
-
|
| 245 |
-
time.sleep(1.5)
|
| 246 |
-
|
| 247 |
-
elif response.status_code == 403:
|
| 248 |
-
status_updates.append(f"β οΈ Rate limit hit after {total_api_calls} calls")
|
| 249 |
-
break
|
| 250 |
-
elif response.status_code == 422:
|
| 251 |
-
continue
|
| 252 |
-
else:
|
| 253 |
-
status_updates.append(f" β Search error: {response.status_code}")
|
| 254 |
-
|
| 255 |
-
# Phase 2: Major cities
|
| 256 |
-
if len(all_users) < max_users * 1.5 and total_api_calls < 130:
|
| 257 |
-
status_updates.append(f"π Phase 2: Major city searches...")
|
| 258 |
-
|
| 259 |
-
cities = ['Dubai', 'Abu+Dhabi', 'Sharjah']
|
| 260 |
-
|
| 261 |
-
for city in cities:
|
| 262 |
-
if total_api_calls >= 150:
|
| 263 |
-
break
|
| 264 |
-
|
| 265 |
-
search_url = f'https://api.github.com/search/users?q=location:{city}+followers:>={min_followers}&sort=followers&order=desc&per_page=50'
|
| 266 |
-
response = requests.get(search_url, headers=headers)
|
| 267 |
-
total_api_calls += 1
|
| 268 |
-
|
| 269 |
-
if response.status_code == 200:
|
| 270 |
-
users = response.json().get('items', [])
|
| 271 |
-
|
| 272 |
-
for user in users[:25]:
|
| 273 |
-
if user['login'] not in all_users and total_api_calls < 150:
|
| 274 |
-
user_response = requests.get(user['url'], headers=headers)
|
| 275 |
-
total_api_calls += 1
|
| 276 |
|
| 277 |
-
if
|
| 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 |
for i, user in enumerate(top_users, 1):
|
| 312 |
user['rank'] = i
|
| 313 |
-
|
| 314 |
-
#
|
| 315 |
df = pd.DataFrame(top_users)
|
| 316 |
-
|
| 317 |
if not df.empty:
|
| 318 |
display_df = df[['rank', 'name', 'login', 'contributions', 'followers', 'public_repos', 'location']].copy()
|
| 319 |
display_df.columns = ['Rank', 'Name', 'Username', 'Contributions', 'Followers', 'Public Repos', 'Location']
|
| 320 |
display_df['GitHub Profile'] = df['login'].apply(lambda x: f"https://github.com/{x}")
|
| 321 |
-
|
| 322 |
-
status_message = f"
|
| 323 |
-
π Total unique users found: {len(all_users)}
|
| 324 |
-
π§ API calls made: {total_api_calls}
|
| 325 |
-
π
Date range: {datetime.now() - timedelta(days=days)} to {datetime.now()}
|
| 326 |
-
|
| 327 |
-
Recent status:
|
| 328 |
-
""" + "\n".join(status_updates[-6:])
|
| 329 |
-
|
| 330 |
-
if contribution_errors:
|
| 331 |
-
status_message += f"\n\nβ οΈ Contribution fetch errors: {len(contribution_errors)}"
|
| 332 |
-
status_message += f"\n(First 3: {', '.join(contribution_errors[:3])})"
|
| 333 |
-
|
| 334 |
return display_df, status_message
|
| 335 |
else:
|
| 336 |
return pd.DataFrame(), "β οΈ No users found\n" + "\n".join(status_updates)
|
| 337 |
-
|
| 338 |
except Exception as e:
|
| 339 |
return pd.DataFrame(), f"β Error: {str(e)}\n" + "\n".join(status_updates)
|
| 340 |
|
|
@@ -342,53 +175,49 @@ def search_users(df, search_term):
|
|
| 342 |
"""Filter users based on search term"""
|
| 343 |
if df is None or df.empty:
|
| 344 |
return df
|
|
|
|
| 345 |
if not search_term:
|
| 346 |
return df
|
| 347 |
-
|
| 348 |
search_term = search_term.lower()
|
| 349 |
mask = (
|
| 350 |
df['Name'].str.lower().str.contains(search_term, na=False) |
|
| 351 |
-
df['Username'].str.lower().str.contains(search_term, na=False)
|
| 352 |
-
df['Location'].str.lower().str.contains(search_term, na=False)
|
| 353 |
)
|
| 354 |
return df[mask]
|
| 355 |
|
| 356 |
# Create Gradio interface
|
| 357 |
with gr.Blocks(theme=gr.themes.Soft(), title="GitHub UAE Top Contributors") as app:
|
| 358 |
-
|
| 359 |
gr.Markdown("""
|
| 360 |
-
#
|
| 361 |
-
###
|
| 362 |
-
|
| 363 |
-
**This
|
| 364 |
-
|
| 365 |
-
β οΈ **IMPORTANT:** You MUST provide a GitHub Personal Access Token with `read:user` scope for accurate contribution counts.
|
| 366 |
-
|
| 367 |
-
**Confirmed to find:** YASSERRMD (Sharjah), zning1994 (Dubai), nkapila6 (Dubai), tschm (Abu Dhabi) and many more!
|
| 368 |
""")
|
| 369 |
-
|
| 370 |
with gr.Row():
|
| 371 |
token_input = gr.Textbox(
|
| 372 |
-
label="GitHub Personal Access Token (REQUIRED
|
| 373 |
-
placeholder="ghp_xxxxxxxxxxxx or
|
| 374 |
type="password",
|
| 375 |
scale=3
|
| 376 |
)
|
| 377 |
max_users_input = gr.Slider(
|
| 378 |
-
label="Max Contributors
|
| 379 |
minimum=10,
|
| 380 |
maximum=500,
|
| 381 |
value=200,
|
| 382 |
step=10,
|
| 383 |
scale=1
|
| 384 |
)
|
| 385 |
-
|
| 386 |
with gr.Row():
|
| 387 |
min_followers_input = gr.Slider(
|
| 388 |
-
label="Minimum Followers (
|
| 389 |
minimum=0,
|
| 390 |
-
maximum=
|
| 391 |
-
value=
|
| 392 |
step=1
|
| 393 |
)
|
| 394 |
days_input = gr.Slider(
|
|
@@ -398,97 +227,89 @@ with gr.Blocks(theme=gr.themes.Soft(), title="GitHub UAE Top Contributors") as a
|
|
| 398 |
value=30,
|
| 399 |
step=1
|
| 400 |
)
|
| 401 |
-
|
| 402 |
with gr.Row():
|
| 403 |
-
fetch_btn = gr.Button("π Fetch Top Contributors", variant="primary", size="lg")
|
| 404 |
-
|
| 405 |
-
status_msg = gr.Textbox(label="Status
|
| 406 |
-
|
| 407 |
with gr.Row():
|
| 408 |
search_box = gr.Textbox(
|
| 409 |
-
label="π Search
|
| 410 |
-
placeholder="
|
| 411 |
scale=4
|
| 412 |
)
|
| 413 |
clear_btn = gr.Button("Clear", scale=1)
|
| 414 |
-
|
|
|
|
| 415 |
full_data = gr.State(value=pd.DataFrame())
|
| 416 |
-
|
|
|
|
| 417 |
data_display = gr.Dataframe(
|
| 418 |
headers=["Rank", "Name", "Username", "Contributions", "Followers", "Public Repos", "Location", "GitHub Profile"],
|
| 419 |
datatype=["number", "str", "str", "number", "number", "number", "str", "str"],
|
| 420 |
wrap=True,
|
| 421 |
interactive=False
|
| 422 |
)
|
| 423 |
-
|
| 424 |
gr.Markdown("""
|
| 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 |
-
1. Go to: https://github.com/settings/tokens
|
| 450 |
-
2. Click "Generate new token (classic)"
|
| 451 |
-
3. Name it: "UAE Contributors Tracker"
|
| 452 |
-
4. **Check the `read:user` scope** (REQUIRED for GraphQL API)
|
| 453 |
-
5. Generate and copy the token
|
| 454 |
-
6. Paste above OR set environment variable: `export GITHUB_TOKEN="ghp_..."`
|
| 455 |
-
|
| 456 |
-
---
|
| 457 |
-
|
| 458 |
-
**Processing Time:** 2-5 minutes depending on settings
|
| 459 |
-
|
| 460 |
-
**Note:** If you see 0 contributions for highly active users, there may be a GraphQL API error (check status output).
|
| 461 |
""")
|
| 462 |
-
|
|
|
|
| 463 |
def fetch_and_display(token, max_users, min_followers, days):
|
| 464 |
df, msg = fetch_github_users(token if token else None, int(max_users), int(min_followers), int(days))
|
| 465 |
return df, df, msg
|
| 466 |
-
|
| 467 |
def filter_data(df, search):
|
| 468 |
if df is None or df.empty:
|
| 469 |
return df
|
| 470 |
return search_users(df, search)
|
| 471 |
-
|
| 472 |
def clear_search(df):
|
| 473 |
return "", df
|
| 474 |
-
|
| 475 |
fetch_btn.click(
|
| 476 |
fn=fetch_and_display,
|
| 477 |
inputs=[token_input, max_users_input, min_followers_input, days_input],
|
| 478 |
outputs=[full_data, data_display, status_msg]
|
| 479 |
)
|
| 480 |
-
|
| 481 |
search_box.change(
|
| 482 |
fn=filter_data,
|
| 483 |
inputs=[full_data, search_box],
|
| 484 |
outputs=data_display
|
| 485 |
)
|
| 486 |
-
|
| 487 |
clear_btn.click(
|
| 488 |
fn=clear_search,
|
| 489 |
inputs=[full_data],
|
| 490 |
outputs=[search_box, data_display]
|
| 491 |
)
|
| 492 |
|
|
|
|
| 493 |
if __name__ == "__main__":
|
| 494 |
app.launch()
|
|
|
|
| 5 |
import time
|
| 6 |
import os
|
| 7 |
|
| 8 |
+
def get_contribution_count(username, github_token, days=30):
|
| 9 |
"""
|
| 10 |
+
Get accurate contribution count using GitHub GraphQL API
|
| 11 |
"""
|
| 12 |
if not github_token:
|
| 13 |
+
return 0
|
| 14 |
|
|
|
|
| 15 |
end_date = datetime.now()
|
| 16 |
start_date = end_date - timedelta(days=days)
|
| 17 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
query = """
|
| 19 |
query($username: String!, $from: DateTime!, $to: DateTime!) {
|
| 20 |
user(login: $username) {
|
| 21 |
contributionsCollection(from: $from, to: $to) {
|
| 22 |
contributionCalendar {
|
| 23 |
totalContributions
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
}
|
| 26 |
}
|
| 27 |
}
|
|
|
|
| 29 |
|
| 30 |
variables = {
|
| 31 |
"username": username,
|
| 32 |
+
"from": start_date.isoformat(),
|
| 33 |
+
"to": end_date.isoformat()
|
| 34 |
}
|
| 35 |
|
| 36 |
headers = {
|
|
|
|
| 42 |
response = requests.post(
|
| 43 |
'https://api.github.com/graphql',
|
| 44 |
json={'query': query, 'variables': variables},
|
| 45 |
+
headers=headers
|
|
|
|
| 46 |
)
|
| 47 |
|
| 48 |
if response.status_code == 200:
|
| 49 |
data = response.json()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
if 'data' in data and data['data'] and data['data']['user']:
|
| 51 |
+
return data['data']['user']['contributionsCollection']['contributionCalendar']['totalContributions']
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
except Exception as e:
|
| 53 |
+
print(f"Error fetching contributions for {username}: {e}")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
|
| 55 |
+
return 0
|
| 56 |
|
| 57 |
+
def fetch_github_users(github_token=None, max_users=200, min_followers=10, days=30):
|
| 58 |
"""
|
| 59 |
+
Fetch GitHub users from UAE directly using GitHub API
|
| 60 |
+
Sorted by contributions (primary) and followers (secondary)
|
| 61 |
"""
|
|
|
|
| 62 |
if not github_token:
|
| 63 |
github_token = os.getenv('GITHUB_TOKEN')
|
|
|
|
|
|
|
|
|
|
| 64 |
|
| 65 |
headers = {
|
| 66 |
'Accept': 'application/vnd.github.v3+json',
|
|
|
|
| 67 |
}
|
| 68 |
|
| 69 |
+
if github_token:
|
| 70 |
+
headers['Authorization'] = f'token {github_token}'
|
| 71 |
+
|
| 72 |
+
all_users = []
|
| 73 |
+
|
| 74 |
+
# Search locations in UAE - KEEP THE ORIGINAL WORKING APPROACH
|
| 75 |
+
locations = [
|
| 76 |
+
'Dubai', 'Abu Dhabi', 'Sharjah', 'Ajman',
|
| 77 |
+
'United Arab Emirates', 'UAE',
|
| 78 |
+
'Ras Al Khaimah', 'Fujairah', 'Umm Al Quwain'
|
| 79 |
+
]
|
| 80 |
+
|
| 81 |
status_updates = []
|
|
|
|
|
|
|
| 82 |
|
| 83 |
try:
|
| 84 |
+
for location in locations:
|
| 85 |
+
status_updates.append(f"π Searching users in {location}...")
|
| 86 |
+
|
| 87 |
+
# Search users by location and followers
|
| 88 |
+
search_url = f'https://api.github.com/search/users?q=location:{location}+followers:>={min_followers}&sort=followers&order=desc&per_page=100'
|
| 89 |
+
|
| 90 |
+
response = requests.get(search_url, headers=headers)
|
| 91 |
+
|
| 92 |
+
if response.status_code == 200:
|
| 93 |
+
data = response.json()
|
| 94 |
+
users = data.get('items', [])
|
| 95 |
+
|
| 96 |
+
for user in users:
|
| 97 |
+
if not any(u['login'] == user['login'] for u in all_users):
|
| 98 |
+
# Fetch detailed user info
|
| 99 |
+
user_url = user['url']
|
| 100 |
+
user_response = requests.get(user_url, headers=headers)
|
| 101 |
+
|
| 102 |
+
if user_response.status_code == 200:
|
| 103 |
+
user_data = user_response.json()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 104 |
|
| 105 |
+
# Verify location contains UAE-related keywords (case insensitive)
|
| 106 |
+
user_location = (user_data.get('location') or '').lower()
|
| 107 |
+
# Keywords are already lowercase for comparison
|
| 108 |
+
uae_keywords = ['dubai', 'abu dhabi', 'sharjah', 'ajman', 'uae', 'u.a.e',
|
| 109 |
+
'united arab emirates', 'ras al khaimah', 'fujairah',
|
| 110 |
+
'umm al quwain', 'emirates', 'abudhabi', 'rak']
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 111 |
|
| 112 |
+
# Check if any UAE keyword exists in the lowercased location
|
| 113 |
+
if not any(keyword in user_location for keyword in uae_keywords):
|
| 114 |
+
continue
|
| 115 |
+
|
| 116 |
+
# Get accurate contribution count using GraphQL (FIX: Use GraphQL instead of Events API)
|
| 117 |
+
contributions = get_contribution_count(user['login'], github_token, days)
|
| 118 |
+
|
| 119 |
+
all_users.append({
|
| 120 |
+
'login': user_data.get('login', ''),
|
| 121 |
+
'name': user_data.get('name', user_data.get('login', '')),
|
| 122 |
+
'avatar': user_data.get('avatar_url', ''),
|
| 123 |
+
'followers': user_data.get('followers', 0),
|
| 124 |
+
'public_repos': user_data.get('public_repos', 0),
|
| 125 |
+
'contributions': contributions,
|
| 126 |
+
'location': user_data.get('location', ''),
|
| 127 |
+
'bio': user_data.get('bio', ''),
|
| 128 |
+
'company': user_data.get('company', ''),
|
| 129 |
+
})
|
| 130 |
+
|
| 131 |
+
time.sleep(0.5) # Rate limiting
|
| 132 |
+
|
| 133 |
+
if len(all_users) >= max_users * 2: # Fetch more to ensure we get top contributors
|
| 134 |
+
break
|
| 135 |
+
|
| 136 |
+
status_updates.append(f"β
Found {len(users)} users in {location}")
|
| 137 |
+
time.sleep(1) # Rate limiting between searches
|
| 138 |
+
|
| 139 |
+
elif response.status_code == 403:
|
| 140 |
+
status_updates.append(f"β οΈ Rate limit reached. Please add a GitHub token.")
|
| 141 |
+
break
|
| 142 |
+
else:
|
| 143 |
+
status_updates.append(f"β Error searching {location}: {response.status_code}")
|
| 144 |
+
|
| 145 |
+
if len(all_users) >= max_users * 2:
|
| 146 |
+
break
|
| 147 |
+
|
| 148 |
+
# Sort by CONTRIBUTIONS FIRST (descending), then by followers (descending)
|
| 149 |
+
all_users.sort(key=lambda x: (x['contributions'], x['followers']), reverse=True)
|
| 150 |
+
|
| 151 |
+
# Take top contributors based on max_users
|
| 152 |
+
top_users = all_users[:max_users]
|
| 153 |
+
|
| 154 |
+
# Add rank based on contribution order
|
| 155 |
for i, user in enumerate(top_users, 1):
|
| 156 |
user['rank'] = i
|
| 157 |
+
|
| 158 |
+
# Convert to DataFrame
|
| 159 |
df = pd.DataFrame(top_users)
|
| 160 |
+
|
| 161 |
if not df.empty:
|
| 162 |
display_df = df[['rank', 'name', 'login', 'contributions', 'followers', 'public_repos', 'location']].copy()
|
| 163 |
display_df.columns = ['Rank', 'Name', 'Username', 'Contributions', 'Followers', 'Public Repos', 'Location']
|
| 164 |
display_df['GitHub Profile'] = df['login'].apply(lambda x: f"https://github.com/{x}")
|
| 165 |
+
|
| 166 |
+
status_message = f"β
Successfully fetched top {len(df)} contributors (last {days} days)\n" + "\n".join(status_updates[-5:])
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 167 |
return display_df, status_message
|
| 168 |
else:
|
| 169 |
return pd.DataFrame(), "β οΈ No users found\n" + "\n".join(status_updates)
|
| 170 |
+
|
| 171 |
except Exception as e:
|
| 172 |
return pd.DataFrame(), f"β Error: {str(e)}\n" + "\n".join(status_updates)
|
| 173 |
|
|
|
|
| 175 |
"""Filter users based on search term"""
|
| 176 |
if df is None or df.empty:
|
| 177 |
return df
|
| 178 |
+
|
| 179 |
if not search_term:
|
| 180 |
return df
|
| 181 |
+
|
| 182 |
search_term = search_term.lower()
|
| 183 |
mask = (
|
| 184 |
df['Name'].str.lower().str.contains(search_term, na=False) |
|
| 185 |
+
df['Username'].str.lower().str.contains(search_term, na=False)
|
|
|
|
| 186 |
)
|
| 187 |
return df[mask]
|
| 188 |
|
| 189 |
# Create Gradio interface
|
| 190 |
with gr.Blocks(theme=gr.themes.Soft(), title="GitHub UAE Top Contributors") as app:
|
| 191 |
+
|
| 192 |
gr.Markdown("""
|
| 193 |
+
# π Top 200 GitHub Contributors in UAE (Last 30 Days)
|
| 194 |
+
### Ranked by Contributions Using GitHub GraphQL API
|
| 195 |
+
|
| 196 |
+
**This version uses the WORKING search from v1 + ACCURATE GraphQL contribution counting**
|
|
|
|
|
|
|
|
|
|
|
|
|
| 197 |
""")
|
| 198 |
+
|
| 199 |
with gr.Row():
|
| 200 |
token_input = gr.Textbox(
|
| 201 |
+
label="GitHub Personal Access Token (REQUIRED for GraphQL)",
|
| 202 |
+
placeholder="ghp_xxxxxxxxxxxx or leave empty to use GITHUB_TOKEN env var",
|
| 203 |
type="password",
|
| 204 |
scale=3
|
| 205 |
)
|
| 206 |
max_users_input = gr.Slider(
|
| 207 |
+
label="Max Contributors",
|
| 208 |
minimum=10,
|
| 209 |
maximum=500,
|
| 210 |
value=200,
|
| 211 |
step=10,
|
| 212 |
scale=1
|
| 213 |
)
|
| 214 |
+
|
| 215 |
with gr.Row():
|
| 216 |
min_followers_input = gr.Slider(
|
| 217 |
+
label="Minimum Followers (for initial search)",
|
| 218 |
minimum=0,
|
| 219 |
+
maximum=100,
|
| 220 |
+
value=10,
|
| 221 |
step=1
|
| 222 |
)
|
| 223 |
days_input = gr.Slider(
|
|
|
|
| 227 |
value=30,
|
| 228 |
step=1
|
| 229 |
)
|
| 230 |
+
|
| 231 |
with gr.Row():
|
| 232 |
+
fetch_btn = gr.Button("π Fetch Top Contributors from GitHub", variant="primary", size="lg")
|
| 233 |
+
|
| 234 |
+
status_msg = gr.Textbox(label="Status", interactive=False, lines=3)
|
| 235 |
+
|
| 236 |
with gr.Row():
|
| 237 |
search_box = gr.Textbox(
|
| 238 |
+
label="π Search by Name or Username",
|
| 239 |
+
placeholder="Type to search...",
|
| 240 |
scale=4
|
| 241 |
)
|
| 242 |
clear_btn = gr.Button("Clear", scale=1)
|
| 243 |
+
|
| 244 |
+
# Store the full dataframe
|
| 245 |
full_data = gr.State(value=pd.DataFrame())
|
| 246 |
+
|
| 247 |
+
# Display dataframe
|
| 248 |
data_display = gr.Dataframe(
|
| 249 |
headers=["Rank", "Name", "Username", "Contributions", "Followers", "Public Repos", "Location", "GitHub Profile"],
|
| 250 |
datatype=["number", "str", "str", "number", "number", "number", "str", "str"],
|
| 251 |
wrap=True,
|
| 252 |
interactive=False
|
| 253 |
)
|
| 254 |
+
|
| 255 |
gr.Markdown("""
|
| 256 |
---
|
| 257 |
+
**What Changed from Original:**
|
| 258 |
+
- β
Kept the WORKING search approach (searches Dubai, Abu Dhabi, Sharjah, UAE, etc.)
|
| 259 |
+
- β
Fixed contribution counting: Now uses GitHub GraphQL API for ACCURATE counts
|
| 260 |
+
- β
GraphQL returns the EXACT number from user's contribution graph (not estimated from events)
|
| 261 |
+
|
| 262 |
+
**Original Problem:**
|
| 263 |
+
- Events API only returns ~100 events and misses many contributions
|
| 264 |
+
- GraphQL API returns the actual total contributions for the date range
|
| 265 |
+
|
| 266 |
+
**Ranking:**
|
| 267 |
+
- Primary: Contributions in last N days (accurate from GraphQL)
|
| 268 |
+
- Secondary: Followers count
|
| 269 |
+
|
| 270 |
+
**Token Setup (REQUIRED):**
|
| 271 |
+
1. Go to [GitHub Settings > Tokens](https://github.com/settings/tokens)
|
| 272 |
+
2. Generate new token (classic)
|
| 273 |
+
3. Select scope: `read:user` (REQUIRED for GraphQL)
|
| 274 |
+
4. Copy and paste above OR set `GITHUB_TOKEN` env var
|
| 275 |
+
|
| 276 |
+
**Why Token is Required:**
|
| 277 |
+
- REST API works without token but with rate limits
|
| 278 |
+
- GraphQL API REQUIRES authentication
|
| 279 |
+
- Without token: can search users but contributions will be 0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 280 |
""")
|
| 281 |
+
|
| 282 |
+
# Event handlers
|
| 283 |
def fetch_and_display(token, max_users, min_followers, days):
|
| 284 |
df, msg = fetch_github_users(token if token else None, int(max_users), int(min_followers), int(days))
|
| 285 |
return df, df, msg
|
| 286 |
+
|
| 287 |
def filter_data(df, search):
|
| 288 |
if df is None or df.empty:
|
| 289 |
return df
|
| 290 |
return search_users(df, search)
|
| 291 |
+
|
| 292 |
def clear_search(df):
|
| 293 |
return "", df
|
| 294 |
+
|
| 295 |
fetch_btn.click(
|
| 296 |
fn=fetch_and_display,
|
| 297 |
inputs=[token_input, max_users_input, min_followers_input, days_input],
|
| 298 |
outputs=[full_data, data_display, status_msg]
|
| 299 |
)
|
| 300 |
+
|
| 301 |
search_box.change(
|
| 302 |
fn=filter_data,
|
| 303 |
inputs=[full_data, search_box],
|
| 304 |
outputs=data_display
|
| 305 |
)
|
| 306 |
+
|
| 307 |
clear_btn.click(
|
| 308 |
fn=clear_search,
|
| 309 |
inputs=[full_data],
|
| 310 |
outputs=[search_box, data_display]
|
| 311 |
)
|
| 312 |
|
| 313 |
+
# Launch the app
|
| 314 |
if __name__ == "__main__":
|
| 315 |
app.launch()
|