Improve title and video quality & update python and packages

Pipfile

@@ -19,8 +19,10 @@ jinja2 = "*"
 apscheduler = "*"
 python-dateutil = "*"
 bencodepy = "*"
+pydantic-settings = "*"
+fake-useragent = "*"
 
 [dev-packages]
 
 [requires]
-python_version = "3.10"
+python_version = "3.11"

api/main.py

@@ -9,8 +9,7 @@ from fastapi.middleware.cors import CORSMiddleware
 from fastapi.staticfiles import StaticFiles
 from fastapi.templating import Jinja2Templates
 
-from api import schemas
-from db import database, crud
+from db import database, crud, schemas
 from utils import scrap
 
 logging.basicConfig(format="%(levelname)s::%(asctime)s - %(message)s", datefmt="%d-%b-%y %H:%M:%S", level=logging.INFO)

beamup.json

@@ -1,4 +1,4 @@
 {
     "projectName": "stremio-tamilblasters",
-    "lastCommit": "c2828d5"
+    "lastCommit": "b98ac2d"
 }

db/config.py

@@ -1,4 +1,4 @@
-from pydantic import BaseSettings
+from pydantic_settings import BaseSettings
 
 
 class Settings(BaseSettings):

db/crud.py

@@ -4,8 +4,10 @@ from uuid import uuid4
 
 from imdb import Cinemagoer, IMDbDataAccessError
 
-from api import schemas
+from db import schemas
 from db.models import TamilBlasterMovie
+from db.schemas import Stream
+from utils.parser import extract_stream_details
 
 ia = Cinemagoer()
 
@@ -23,7 +25,7 @@ async def get_movies_meta(catalog: str, skip: int = 0, limit: int = 100):
     unique_names = []
 
     for movie in movies:
-        meta_data = schemas.Meta.parse_obj(movie)
+        meta_data = schemas.Meta.model_validate(movie.model_dump())
         meta_data.id = movie.imdb_id if movie.imdb_id else movie.tamilblaster_id
         if movie.name not in unique_names:
             movies_meta.append(meta_data)
@@ -44,25 +46,19 @@ async def get_movies_data(video_id: str, video_type: str = "movie") -> list[Opti
     return movie_data
 
 
-async def get_movie_streams(video_id: str):
+async def get_movie_streams(video_id: str) -> list[Stream]:
     movies_data = await get_movies_data(video_id)
     if not movies_data:
         return []
 
     stream_data = []
     for movie_data in movies_data:
-        for name, info_hash in movie_data.video_qualities.items():
-            stream_data.append(
-                {
-                    "name": name,
-                    "infoHash": info_hash,
-                }
-            )
+        stream_data.extend(extract_stream_details(movie_data.video_qualities))
 
     return stream_data
 
 
-async def get_series_streams(video_id: str, season: int, episode: str):
+async def get_series_streams(video_id: str, season: int, episode: str) -> list[Stream]:
     series_data = await get_movies_data(video_id, video_type="series")
     if not series_data:
         return []
@@ -70,13 +66,7 @@ async def get_series_streams(video_id: str, season: int, episode: str):
     stream_data = []
     for series in series_data:
         if series.episode == episode and series.season == season:
-            for name, info_hash in series.video_qualities.items():
-                stream_data.append(
-                    {
-                        "name": name,
-                        "infoHash": info_hash,
-                    }
-                )
+            stream_data.extend(extract_stream_details(series.video_qualities))
 
     return stream_data
 

db/schemas.py

@@ -21,7 +21,8 @@ class Movie(BaseModel):
 
 
 class Stream(BaseModel):
-    name: str
+    name: str | None = None
+    description: str | None = None
     infoHash: str
 
 

runtime.txt

@@ -1 +1 @@
-python-3.10.11
+python-3.11.3

utils/parser.py

@@ -0,0 +1,52 @@
+import re
+
+from db.schemas import Stream
+
+
+def extract_stream_details(video_qualities: dict) -> list[Stream]:
+    stream_list = []
+    for quality_string, hash_value in video_qualities.items():
+        stream_details = {}
+
+        # Quality
+        quality = re.search(
+            r"(4K|\d{3,4}p|HQ HDRip|HDRip|HQ PreDVDRip|HQ Real-PreDVDRip|HQ-Real PreDVDRip|HQ-S Print)", quality_string
+        )
+        if quality:
+            quality = quality.group(0)
+        else:
+            quality = "N/A"
+
+        # Size
+        size = re.search(r"(\d+(\.\d+)?(MB|GB))", quality_string)
+        if size:
+            size = size.group(0)
+        else:
+            size = "N/A"
+
+        # Languages
+        lang_dict = {
+            "Tam": "Tamil",
+            "Mal": "Malayalam",
+            "Tel": "Telugu",
+            "Kan": "Kannada",
+            "Hin": "Hindi",
+            "Eng": "English",
+        }
+
+        languages = []
+        for short, full in lang_dict.items():
+            if re.search(f"({short}|{full})", quality_string, re.IGNORECASE):
+                languages.append(full)
+
+        stream_details["name"] = "TamilBlasters"
+
+        # Concatenate the description components
+        stream_details["description"] = f"{quality}, {size}, {' + '.join(languages)}"
+
+        # Add the info hash
+        stream_details["infoHash"] = hash_value
+
+        stream_list.append(Stream(**stream_details))
+
+    return stream_list

utils/scrap.py

@@ -8,6 +8,7 @@ import re
 import cloudscraper
 import requests
 from bs4 import BeautifulSoup
+from fake_useragent import UserAgent
 from dateutil.parser import parse as dateparser
 from requests.adapters import HTTPAdapter
 from urllib3.util.retry import Retry
@@ -15,7 +16,7 @@ from urllib3.util.retry import Retry
 from db import database, crud
 from utils.torrent import get_info_hash_from_url
 
-homepage = "https://www.1tamilblasters.site"
+homepage = "https://www.1tamilblasters.co"
 
 tamil_blaster_links = {
     "tamil": {
@@ -57,7 +58,9 @@ tamil_blaster_links = {
 
 
 def get_scrapper_session():
+    ua = UserAgent()
     session = requests.session()
+    session.headers = {"User-Agent": ua.random}
     adapter = HTTPAdapter(max_retries=Retry(total=10, read=10, connect=10, backoff_factor=0.3))
     session.mount("http://", adapter)
     session.mount("https://", adapter)