Spaces:
Running
Running
File size: 12,182 Bytes
5dc4327 | 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 | import datetime
from sqlalchemy import Column, Integer, TEXT, DateTime, inspect, func
from mfinder.db.settings_sql import BASE, SESSION
from mfinder.db.files_sql import Files, clean_movie_title, INSERTION_LOCK, reconnect_session, OperationalError
class SearchAnalytics(BASE):
__tablename__ = "search_analytics"
query = Column(TEXT, primary_key=True)
search_count = Column(Integer, default=1)
last_searched = Column(DateTime, default=datetime.datetime.utcnow)
def __init__(self, query):
self.query = query.strip().lower()
self.search_count = 1
self.last_searched = datetime.datetime.utcnow()
# Ensure table exists in DB automatically on module load
try:
session = SESSION()
bind = session.get_bind()
inspector = inspect(bind)
if not inspector.has_table("search_analytics"):
SearchAnalytics.__table__.create(bind=bind, checkfirst=True)
except Exception as _e:
pass
async def log_search_query(query_text: str):
"""Logs or increments search query count in analytics database."""
if not query_text or len(query_text.strip()) < 2:
return
clean_q = query_text.strip().lower()
session = SESSION()
try:
record = session.query(SearchAnalytics).filter_by(query=clean_q).first()
if record:
record.search_count += 1
record.last_searched = datetime.datetime.utcnow()
else:
record = SearchAnalytics(query=clean_q)
session.add(record)
session.commit()
except Exception as e:
session.rollback()
finally:
try:
SESSION.close()
except Exception:
pass
async def cleanup_old_search_analytics():
"""Deletes search records older than 7 days to maintain a clean weekly trending cycle."""
session = SESSION()
try:
one_week_ago = datetime.datetime.utcnow() - datetime.timedelta(days=7)
session.query(SearchAnalytics).filter(SearchAnalytics.last_searched < one_week_ago).delete()
session.commit()
except Exception:
session.rollback()
finally:
try:
SESSION.close()
except Exception:
pass
def extract_season(text: str) -> str:
if not text:
return None
import re
# Match S02, s2, S-2, s_2, S(2), Season 2, Season-02, s02e03, etc.
match = re.search(r'\b[sS](?:eason)?[\s_.-]*\(?(\d+)\)?(?:\b|[eE])', text)
if match:
season_num = int(match.group(1))
return f"S{season_num}"
return None
async def get_latest_uploaded_movies(limit: int = 25) -> list:
"""
Retrieves the latest distinct uploaded movies from the database files table,
sorted by newest created_at timestamp first.
Returns list of tuples: (cleaned_title, file_count, year, season_str)
"""
retries = 3
while retries > 0:
try:
with INSERTION_LOCK:
files = (
SESSION.query(Files.file_name, Files.caption)
.order_by(Files.created_at.desc(), Files.file_name.asc())
.limit(300)
.all()
)
movie_counts = {}
movie_years = {}
movie_seasons = {}
for f_name, caption in files:
title = clean_movie_title(f_name)
if title and len(title) >= 2:
movie_counts[title] = movie_counts.get(title, 0) + 1
if title not in movie_years:
import re
year_match = re.search(r'\b(19\d{2}|20[0-2]\d|2030)\b', f_name)
if year_match:
movie_years[title] = year_match.group(1)
# Extract season
season = extract_season(f_name)
if not season and caption:
season = extract_season(caption)
if season:
if title not in movie_seasons:
movie_seasons[title] = set()
movie_seasons[title].add(season)
latest_list = []
for title, count in movie_counts.items():
year = movie_years.get(title)
seasons = movie_seasons.get(title)
season_str = None
if seasons:
sorted_seasons = sorted(list(seasons), key=lambda s: int(s[1:]))
if len(sorted_seasons) > 1:
season_str = " & ".join(sorted_seasons)
else:
season_str = sorted_seasons[0]
latest_list.append((title, count, year, season_str))
if len(latest_list) >= limit:
break
return latest_list
except OperationalError:
reconnect_session()
retries -= 1
except Exception as e:
retries -= 1
finally:
try:
SESSION.close()
except Exception:
pass
return []
async def get_top_trending_movies(limit: int = 10) -> list:
"""
Retrieves top searched queries from the 7-day weekly cycle in search_analytics.
Returns list of tuples: (movie_title, file_count)
"""
# Trigger weekly cleanup of old search records
await cleanup_old_search_analytics()
retries = 3
while retries > 0:
try:
with INSERTION_LOCK:
one_week_ago = datetime.datetime.utcnow() - datetime.timedelta(days=7)
top_records = (
SESSION.query(SearchAnalytics)
.filter(SearchAnalytics.last_searched >= one_week_ago)
.order_by(SearchAnalytics.search_count.desc(), SearchAnalytics.last_searched.desc())
.limit(50)
.all()
)
if not top_records:
return []
trending_movies = []
seen_titles = set()
for rec in top_records:
q = rec.query
files = (
SESSION.query(Files.file_name, Files.caption)
.filter(Files.file_name.ilike(f"%{q}%"))
.limit(50)
.all()
)
if files:
for f_name, caption in files:
title = clean_movie_title(f_name)
if title and len(title) >= 2:
t_key = title.lower()
if t_key not in seen_titles:
seen_titles.add(t_key)
count = SESSION.query(Files).filter(Files.file_name.ilike(f"%{title}%")).count()
# Extract year and seasons from matched files
import re
year = None
seasons = set()
for fn, cap in files:
if clean_movie_title(fn) == title:
year_match = re.search(r'\b(19\d{2}|20[0-2]\d|2030)\b', fn)
if year_match:
year = year_match.group(1)
season = extract_season(fn)
if not season and cap:
season = extract_season(cap)
if season:
seasons.add(season)
season_str = None
if seasons:
sorted_seasons = sorted(list(seasons), key=lambda s: int(s[1:]))
if len(sorted_seasons) > 1:
season_str = " & ".join(sorted_seasons)
else:
season_str = sorted_seasons[0]
trending_movies.append((title, count if count > 0 else len(files), year, season_str))
if len(trending_movies) >= limit:
break
if len(trending_movies) >= limit:
break
return trending_movies
except OperationalError:
reconnect_session()
retries -= 1
except Exception:
retries -= 1
finally:
try:
SESSION.close()
except Exception:
pass
return []
from sqlalchemy import BigInteger
class UserInteraction(BASE):
__tablename__ = "user_interactions"
user_id = Column(BigInteger, primary_key=True)
last_active = Column(DateTime, default=datetime.datetime.utcnow)
def __init__(self, user_id):
self.user_id = user_id
self.last_active = datetime.datetime.utcnow()
# Ensure table exists in DB automatically on module load
try:
session = SESSION()
bind = session.get_bind()
inspector = inspect(bind)
if not inspector.has_table("user_interactions"):
UserInteraction.__table__.create(bind=bind, checkfirst=True)
except Exception as _e:
pass
async def log_user_interaction(user_id: int):
if not user_id:
return
session = SESSION()
try:
record = session.query(UserInteraction).filter_by(user_id=user_id).first()
if record:
record.last_active = datetime.datetime.utcnow()
else:
record = UserInteraction(user_id=user_id)
session.add(record)
session.commit()
except Exception as e:
session.rollback()
finally:
try:
SESSION.close()
except Exception:
pass
async def get_today_active_users_count() -> int:
session = SESSION()
try:
now = datetime.datetime.utcnow()
local_now = now + datetime.timedelta(hours=5, minutes=30)
local_today_start = datetime.datetime(local_now.year, local_now.month, local_now.day)
utc_today_start = local_today_start - datetime.timedelta(hours=5, minutes=30)
count = session.query(UserInteraction).filter(UserInteraction.last_active >= utc_today_start).count()
return count
except Exception:
return 0
finally:
try:
SESSION.close()
except Exception:
pass
def get_movie_quality_sync(title: str) -> str:
from mfinder.db.files_sql import Files
from mfinder.utils.helpers import detect_file_quality
session = SESSION()
try:
files = (
session.query(Files.file_name)
.filter(Files.file_name.ilike(f"%{title}%"))
.order_by(Files.created_at.desc())
.limit(10)
.all()
)
if not files:
return "HD"
for (f_name,) in files:
if detect_file_quality(f_name) == "Theatre Print [Clear Audio]":
return "Theatre Print [Clear Audio]"
return "HD"
except Exception:
return "HD"
finally:
try:
session.close()
except Exception:
pass
|