From cdaec2da179b37e0504aa658f0d233198b13f574 Mon Sep 17 00:00:00 2001
From: navanchauhan <navanchauhan@gmail.com>
Date: Fri, 20 May 2022 18:30:27 -0600
Subject: [PATCH] added code

---
 database.py |  49 +++++++++++++++++++++
 main.py     | 122 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 171 insertions(+)
 create mode 100644 database.py
 create mode 100644 main.py

diff --git a/database.py b/database.py
new file mode 100644
index 0000000..369cf97
--- /dev/null
+++ b/database.py
@@ -0,0 +1,49 @@
+import sqlalchemy
+from sqlalchemy import create_engine
+from sqlalchemy import Table, Column, Integer, String, MetaData, ForeignKey, PickleType
+from sqlalchemy import insert
+from sqlalchemy.orm import sessionmaker
+from sqlalchemy.exc import IntegrityError
+
+#database_url = "sqlite:///jlm.db"
+
+meta = MetaData()
+
+movies_table = Table(
+    "movies",
+    meta,
+    Column("trakt_id", Integer, primary_key=True, autoincrement=False),
+    Column("title", String),
+    Column("overview", String),
+    Column("genres", String),
+    Column("year", Integer),
+    Column("released", String),
+    Column("runtime", Integer),
+    Column("country", String),
+    Column("language", String),
+    Column("rating", Integer),
+    Column("votes", Integer),
+    Column("comment_count", Integer),
+    Column("tagline", String),
+    Column("embeddings", PickleType)
+
+)
+
+def init_db_stuff(database_url: str):
+    engine = create_engine(database_url)
+    meta.create_all(engine)
+    Session = sessionmaker(bind=engine)
+    return engine, Session
+"""
+    movie = {
+        "title": movie["movie"]["title"],
+        "overview": movie["movie"]["overview"],
+        "genres": movie["movie"]["genres"],
+        "language": movie["movie"]["language"],
+        "year": movie["movie"]["year"],
+        "trakt_id": movie["movie"]["ids"]["trakt"],
+        "released": movie["movie"]["released"],
+        "runtime": movie["movie"]["runtime"],
+        "country": movie["movie"]["country"]
+    }
+"""
\ No newline at end of file
diff --git a/main.py b/main.py
new file mode 100644
index 0000000..1030a62
--- /dev/null
+++ b/main.py
@@ -0,0 +1,122 @@
+import requests
+import os
+from database import *
+from tqdm import tqdm
+
+from datetime import datetime
+
+import time
+
+trakt_id = os.getenv("TRAKT_ID")
+trakt_se = os.getenv("TRAKT_SE")
+
+max_requests = 5000 # How many requests do you want to make 
+req_count = 0
+
+years = "1900-2021"
+page = 1
+extended = "full" # Required to get additional information 
+limit = "10" # No of entires per request
+languages = "en" # Limit to particular language
+
+api_base = "https://api.trakt.tv"
+database_url = "sqlite:///jlm.db"
+
+headers = {
+	"Content-Type": "application/json",
+	"trakt-api-version": "2",
+	"trakt-api-key": trakt_id
+}
+
+params = {
+	"query": "",
+	"years": years,
+	"page": page,
+	"extended": extended,
+	"limit": limit,
+	"languages": languages
+}
+
+
+def create_movie_dict(movie: dict):
+	movie = {
+		"title": movie["movie"]["title"],
+		"overview": movie["movie"]["overview"],
+		"genres": movie["movie"]["genres"],
+		"language": movie["movie"]["language"],
+		"year": int(movie["movie"]["year"]),
+		"trakt_id": movie["movie"]["ids"]["trakt"],
+		"released": movie["movie"]["released"],
+		"runtime": int(movie["movie"]["runtime"]),
+		"country": movie["movie"]["country"],
+		"rating": int(movie["movie"]["rating"]),
+		"votes": int(movie["movie"]["votes"]),
+		"comment_count": int(movie["movie"]["comment_count"]),
+		"tagline": movie["movie"]["tagline"]
+	}
+	return movie
+
+
+
+params["limit"] = 1
+res = requests.get(f"{api_base}/search/movie",headers=headers,params=params)
+total_items = res.headers["x-pagination-item-count"]
+
+print(f"There are {total_items} movies")
+print(f"Started from page {page}")
+
+"""
+movies = []
+params["limit"] = limit
+res = requests.get(f"{api_base}/search/movie",headers=headers,params=params)
+
+if res.status_code == 200:
+	for movie in res.json():
+		movies.append(create_movie_dict(movie))
+		print(create_movie_dict(movie)["title"])
+"""
+engine, Session = init_db_stuff(database_url)
+
+start_time = datetime.now()
+
+for page in tqdm(range(2990,max_requests+10)):
+	if req_count == 999:
+		seconds_to_sleep = 300 - (datetime.now() - start_time).seconds
+		if seconds_to_sleep < 1:
+			seconds_to_sleep = 100
+		print(f"Sleeping {seconds_to_sleep}s")
+		# Need to respect their rate limitting
+		time.sleep(seconds_to_sleep)
+		start_time = datetime.now()
+		req_count = 0
+
+	params["page"] = page
+	params["limit"] = int(int(total_items)/max_requests)
+	movies = []
+	res = requests.get(f"{api_base}/search/movie",headers=headers,params=params)
+
+	if res.status_code == 500:
+		break
+	elif res.status_code == 200:
+		None
+	else:
+		print(f"OwO Code {res.status_code}")
+
+	for movie in res.json():
+		movies.append(create_movie_dict(movie))
+
+	with engine.connect() as conn:
+		for movie in movies:
+			with conn.begin() as trans:
+				stmt = insert(movies_table).values(
+					trakt_id=movie["trakt_id"], title=movie["title"], genres=" ".join(movie["genres"]),
+					language=movie["language"], year=movie["year"], released=movie["released"],
+					runtime=movie["runtime"], country=movie["country"], overview=movie["overview"],
+					rating=movie["rating"], votes=movie["votes"], comment_count=movie["comment_count"],
+					tagline=movie["tagline"])
+				try:
+					result = conn.execute(stmt)
+					trans.commit()
+				except IntegrityError:
+					trans.rollback()
+	req_count += 1