import random from django.core.management.base import BaseCommand from django.db import transaction from django.contrib.auth import get_user_model from categories.models import Category from posts.models import Post from comments.models import Comment from likes.models import LikePost, LikeComment from follows.models import FollowUser, FollowCategory try: from faker import Faker except ImportError: Faker = None class Command(BaseCommand): help = 'Generates fake data for testing: Users, Posts, Comments, Likes, Follows' def handle(self, *args, **kwargs): if not Faker: self.stdout.write(self.style.ERROR('Faker library is not installed. Please install it using: pip install faker')) return fake = Faker() User = get_user_model() # Configuration NUM_USERS = 300 NUM_CATEGORIES = 20 NUM_POSTS = 5000 NUM_COMMENTS = 3589 # Approximate numbers for relationships NUM_POST_LIKES = 10000 NUM_COMMENT_LIKES = 5000 NUM_FOLLOWS = 2000 NUM_CATEGORY_FOLLOWS = 1000 self.stdout.write('Starting data generation...') with transaction.atomic(): # 1. Users self.stdout.write(f'Creating {NUM_USERS} users...') users = [] for i in range(NUM_USERS): # Simple check to avoid duplicates if running multiple times without cleanup username = fake.user_name() + str(i) email = fake.email() if not User.objects.filter(username=username).exists(): user = User( username=username, email=email, first_name=fake.first_name(), last_name=fake.last_name(), is_active=True, bio=fake.text(max_nb_chars=150) ) user.set_password('password123') users.append(user) # Using bulk_create for speed (signals won't fire) User.objects.bulk_create(users, ignore_conflicts=True) # Fetch all users to have IDs all_users = list(User.objects.all()) self.stdout.write(self.style.SUCCESS(f'Created {len(users)} new users. Total: {len(all_users)}')) # 2. Categories self.stdout.write(f'Creating {NUM_CATEGORIES} categories...') categories = [] for _ in range(NUM_CATEGORIES): title = fake.unique.word().capitalize() + " " + fake.word() if not Category.objects.filter(title=title).exists(): categories.append(Category( title=title, description=fake.text(max_nb_chars=200), created_by=random.choice(all_users) )) Category.objects.bulk_create(categories, ignore_conflicts=True) all_categories = list(Category.objects.all()) self.stdout.write(self.style.SUCCESS(f'Created categories. Total: {len(all_categories)}')) # 3. Posts self.stdout.write(f'Creating {NUM_POSTS} posts...') posts = [] for _ in range(NUM_POSTS): user = random.choice(all_users) category = random.choice(all_categories) if all_categories and random.random() > 0.2 else None posts.append(Post( created_by=user, category=category, content=fake.paragraph(nb_sentences=random.randint(1, 5)), audience=random.choice(['PUBLIC', 'FOLLOWERS', 'ONLY_ME']) )) Post.objects.bulk_create(posts) all_posts = list(Post.objects.all()) self.stdout.write(self.style.SUCCESS(f'Created {len(posts)} posts.')) # 4. Comments self.stdout.write(f'Creating {NUM_COMMENTS} comments...') comments = [] for _ in range(NUM_COMMENTS): post = random.choice(all_posts) user = random.choice(all_users) comments.append(Comment( post=post, created_by=user, content=fake.sentence() )) Comment.objects.bulk_create(comments) all_comments = list(Comment.objects.all()) self.stdout.write(self.style.SUCCESS(f'Created {len(comments)} comments.')) # 5. Follows (User) self.stdout.write(f'Creating ~{NUM_FOLLOWS} user follows...') follows = [] seen_follows = set() # Get existing to avoid duplicates in seen_follows if needed, but for speed we might just try # A simple loop ensuring uniqueness in memory before saving while len(follows) < NUM_FOLLOWS: u1 = random.choice(all_users) u2 = random.choice(all_users) if u1 != u2 and (u1.id, u2.id) not in seen_follows: # Check DB existence loosely or just rely on ignore_conflicts follows.append(FollowUser(follower=u1, followed=u2)) seen_follows.add((u1.id, u2.id)) FollowUser.objects.bulk_create(follows, ignore_conflicts=True) self.stdout.write(self.style.SUCCESS(f'Follows created.')) # 6. Follows (Category) self.stdout.write(f'Creating ~{NUM_CATEGORY_FOLLOWS} category follows...') cat_follows = [] seen_cat_follows = set() while len(cat_follows) < NUM_CATEGORY_FOLLOWS: u = random.choice(all_users) c = random.choice(all_categories) if (u.id, c.id) not in seen_cat_follows: cat_follows.append(FollowCategory(user=u, category=c)) seen_cat_follows.add((u.id, c.id)) FollowCategory.objects.bulk_create(cat_follows, ignore_conflicts=True) # 7. Post Likes self.stdout.write(f'Creating ~{NUM_POST_LIKES} post likes...') post_likes = [] seen_post_likes = set() while len(post_likes) < NUM_POST_LIKES: u = random.choice(all_users) p = random.choice(all_posts) if (u.id, p.id) not in seen_post_likes: post_likes.append(LikePost(user=u, post=p)) seen_post_likes.add((u.id, p.id)) LikePost.objects.bulk_create(post_likes, ignore_conflicts=True) # 8. Comment Likes self.stdout.write(f'Creating ~{NUM_COMMENT_LIKES} comment likes...') comment_likes = [] seen_comment_likes = set() while len(comment_likes) < NUM_COMMENT_LIKES: u = random.choice(all_users) c = random.choice(all_comments) if (u.id, c.id) not in seen_comment_likes: comment_likes.append(LikeComment(user=u, comment=c)) seen_comment_likes.add((u.id, c.id)) LikeComment.objects.bulk_create(comment_likes, ignore_conflicts=True) self.stdout.write(self.style.SUCCESS('Done! Database seeded successfully.'))