SimklBackup.json to Letterboxd CSV for Import

simkl-letterboxd.py

import json
import csv
import sys
from datetime import datetime

def parse_simkl_to_letterboxd(input_file, output_file):
    try:
        with open(input_file, 'r', encoding='utf-8') as f:
            data = json.load(f)
    except FileNotFoundError:
        print(f"Error: The file '{input_file}' was not found.")
        return
    except json.JSONDecodeError:
        print(f"Error: Failed to decode JSON from '{input_file}'.")
        return

    # Letterboxd CSV Headers
    headers = [
        'tmdbID', 
        'imdbID', 
        'Title', 
        'Year', 
        'Rating10', 
        'WatchedDate', 
        'Tags'
    ]

    records = []

    # STRICT MODE: Only looking at movies and anime. 
    # Standard 'shows' are excluded entirely.
    categories = ['movies', 'anime']

    print(f"Processing entries from: {input_file}...")

    for category in categories:
        items = data.get(category, [])
        
        for entry in items:
            # 1. Skip items that are strictly "Plan to Watch" 
            if entry.get('status') == 'plantowatch':
                continue

            # 2. STRICT FILTER: 
            # If we are processing Anime, ignore it if it is a TV series.
            # We only want 'movie', 'special', or 'ona' if they fit your criteria.
            if category == 'anime' and entry.get('anime_type') == 'tv':
                continue

            # 3. Extract the inner metadata object
            # Simkl puts movie metadata in 'movie', but anime metadata in 'show'
            metadata = entry.get('movie') or entry.get('show')
            
            if not metadata:
                continue

            ids = metadata.get('ids', {})
            
            # 4. Extract Identifiers
            tmdb_id = ids.get('tmdb', '')
            imdb_id = ids.get('imdb', '')
            title = metadata.get('title', '')
            year = metadata.get('year', '')

            # 5. Extract User Data
            user_rating = entry.get('user_rating', '') 
            
            # Date Parsing
            raw_date = entry.get('last_watched_at')
            watched_date = ''
            if raw_date:
                try:
                    # Parse ISO format and output YYYY-MM-DD
                    dt = datetime.strptime(raw_date, "%Y-%m-%dT%H:%M:%SZ")
                    watched_date = dt.strftime("%Y-%m-%d")
                except ValueError:
                    watched_date = raw_date[:10]

            # 6. Inclusion Logic
            # We include it if the user has Rated it, Completed it, or has a Watch Date.
            is_completed = entry.get('status') == 'completed'
            is_watching = entry.get('status') == 'watching'
            
            if not (user_rating or watched_date or is_completed or is_watching):
                continue

            # 7. Tags
            tags_list = ['Simkl Import', category]
            # Optional: Add specific tag for anime type (e.g., "movie", "ona")
            if category == 'anime':
                tags_list.append(entry.get('anime_type', 'unknown'))
            
            tags_string = ",".join(tags_list)

            records.append({
                'tmdbID': tmdb_id,
                'imdbID': imdb_id,
                'Title': title,
                'Year': year,
                'Rating10': user_rating,
                'WatchedDate': watched_date,
                'Tags': tags_string
            })

    # Write to CSV
    if records:
        try:
            with open(output_file, 'w', newline='', encoding='utf-8') as csvfile:
                writer = csv.DictWriter(csvfile, fieldnames=headers)
                writer.writeheader()
                writer.writerows(records)
            print(f"Success! Processed {len(records)} items (Strict Mode: No TV).")
            print(f"Output saved to: {output_file}")
        except IOError as e:
            print(f"Error writing to file: {e}")
    else:
        print("No eligible entries found to export.")

if __name__ == "__main__":
    INPUT_FILENAME = 'SimklBackup.json'
    OUTPUT_FILENAME = 'letterboxd_strict_import.csv'
    
    parse_simkl_to_letterboxd(INPUT_FILENAME, OUTPUT_FILENAME)