优化 Django 模型设计：解决重复爬虫任务和商品数据

from django.db import models

class StartUrl(models.Model):
    """起始URL表"""
    url = models.URLField(verbose_name="起始url", max_length=500, unique=True)

    class Meta:
        verbose_name = verbose_name_plural = '起始URL'

    def __str__(self):
        return self.url

class Product(models.Model):
    """商品表"""
    product_id = models.CharField(max_length=30, verbose_name='商品id', unique=True)
    title = models.CharField(max_length=500, verbose_name='商品标题')
    price = models.DecimalField(max_digits=10, decimal_places=2, blank=True, null=True, verbose_name='价格')
    sales = models.PositiveIntegerField(blank=True, null=True, verbose_name='销量')
    rating = models.FloatField(blank=True, null=True, verbose_name='评分')
    rating_count = models.PositiveIntegerField(blank=True, null=True, verbose_name='评分数')
    listing_date = models.DateField(blank=True, null=True, verbose_name='上架时间')
    release_date = models.DateField(blank=True, null=True, verbose_name='发售时间')
    brand = models.CharField(blank=True, null=True, max_length=100, verbose_name='品牌')
    platform = models.IntegerField(verbose_name='平台')
    seller = models.CharField(blank=True, null=True, max_length=100, verbose_name='卖家')
    img_url = models.URLField(blank=True, null=True, verbose_name='商品主图地址')
    product_details_url = models.URLField(max_length=500, blank=True, null=True, verbose_name='商品详情地址')
    spider_date = models.DateTimeField(blank=True, null=True, verbose_name='完成采集时间')

    class Meta:
        verbose_name = verbose_name_plural = '商品'

    def __str__(self):
        return self.title

from django.utils import timezone
from myapp.models.model_account import User

class SpiderTask(models.Model):
    """爬虫任务表"""
    PLATFORM_CHOICES = (
        (1, 'Amazon'),
        (2, 'Etsy'),
        (3, 'Temu'),
        (4, 'WalMart')
    )
    STATUS_CHOICES = (
        (0, '进行中'),
        (1, '已完成'),
        (2, '异常'),
    )
    TYPE_CHOICES = (
        (1, '列表页'),
        (2, '详情页'),
    )
    id = models.AutoField(primary_key=True, verbose_name='自增id')
    user = models.ForeignKey(User, on_delete=models.CASCADE, verbose_name='用户')
    start_url = models.ForeignKey(StartUrl, on_delete=models.CASCADE, verbose_name='起始url')
    platform = models.IntegerField(default=1, choices=PLATFORM_CHOICES, verbose_name='平台')
    name = models.CharField(verbose_name="爬虫名称", max_length=255)
    spider_type = models.IntegerField(choices=TYPE_CHOICES, default=1, verbose_name='采集页面类型')
    description = models.TextField(verbose_name="描述备注等", max_length=500, null=True, blank=True)
    completed = models.IntegerField(choices=STATUS_CHOICES, default=0, verbose_name='完成状态')
    created_at = models.DateTimeField(default=timezone.now, verbose_name='加入任务时间')
    collection_status = models.IntegerField(choices=STATUS_CHOICES, default=0, verbose_name='采集状态')
    completed_at = models.DateTimeField(null=True, blank=True, verbose_name='完成时间')
    products = models.ManyToManyField(Product, verbose_name='关联商品', related_name='tasks')

    class Meta:
        verbose_name = verbose_name_plural = '爬虫任务'
        unique_together = [['user', 'start_url']]

    def __str__(self):
        return f"{self.get_platform_display()} - {self.name}"

class SpiderUserFavorite(models.Model):
    """用户收藏表"""
    user = models.ForeignKey(User, on_delete=models.CASCADE, verbose_name='用户')
    product = models.ForeignKey(Product, on_delete=models.CASCADE, verbose_name='收藏商品')
    added_at = models.DateTimeField(default=timezone.now, verbose_name='收藏时间')
    note = models.TextField(blank=True, null=True, verbose_name='备注信息')
    tags = models.CharField(max_length=500, blank=True, null=True, verbose_name='备注标签')

    class Meta:
        verbose_name = verbose_name_plural = '用户收藏'
        unique_together = [['user', 'product']]

    def __str__(self):
        return f"{self.user.username} - {self.product.title}"

用户(User)
│
└──< 拥有多个
          │
爬虫任务(SpiderTask) >─── 属于 ────> 起始URL(StartUrl)
│           (多对一)          (一对多)
│
└───< 多对多 >───
          │
        商品(Product)