Converted date_aired to datetime object and BSON Date for MongoDB

Author: ShafathZ

backend/mongo/AnimeDocument.py

@@ -1,4 +1,5 @@
 from pydantic import BaseModel
+from datetime import datetime
 from typing import List, Dict
 
 # Class to Model a typical Anime Document
@@ -12,7 +13,7 @@ class AnimeDocument(BaseModel):
     demographic: str                # Primary demographic
     age_rating: str                 # g | pg | pg-13 | r | r+ | rx
     cover_image_url: str            # link to MAL image (not CDN)
-    date_aired: str                 # date aired in YYYY-MM-DD
+    date_aired: datetime            # date aired as datetime (YYYY-MM-DD stored, not hr/mins/secs/ms)
     status: str                     # finished_airing | currently_airing | not_aired
     episode_count: int              # number of episodes in the anime
     avg_episode_len_mins: int       # average duration per episode in mins

data/anime_scrape.py

@@ -1,5 +1,6 @@
 import json
 import time
+from datetime import datetime
 from typing import List, Dict
 
 import pandas as pd
@@ -48,6 +49,7 @@ def _normalize_from_mal(item: Dict) -> Dict:
     studios = node.get("studios", [])
     publishing_company = studios[0].get("name", "Unknown") if studios else "Unknown"
     synopsis = node.get("synopsis").replace("[Written by MAL Rewrite]", "").strip()
+    date_aired = (datetime.strptime(node.get("start_date"), "%Y-%m-%d"))
 
     # Alt titles (in case main is not en)
     alt_titles = node.get("alternative_titles")
@@ -67,7 +69,7 @@ def _normalize_from_mal(item: Dict) -> Dict:
         "genres": genres,
         "demographic": demographic,
         "cover_image_url": node.get("main_picture").get("medium", ""),
-        "date_aired": node.get("start_date"),
+        "date_aired": date_aired,
         "status": node.get("status", "not_aired"),
         "episode_count": node.get("num_episodes", 0),
         "publishing_company": publishing_company,

data/populate_mongo_db_scraped.py

@@ -30,6 +30,9 @@ def clean_data():
     # Project current name as its own node_name column (since they may not be english, but useful data)
     anime_df["node_name"] = anime_df["name"]
 
+    # Convert date_aired to datetime
+    anime_df["date_aired"] = pd.to_datetime(anime_df["date_aired"], format="mixed")
+
     # Filter out animes without English Names (check alt_titles dict for "en" key, and ensure it is not empty value)
     anime_df = anime_df[anime_df["alt_titles"].apply(lambda x: "en" in x and x["en"] != "")]