Initial commit — PlantGuideScraper project

backend/app/models/job.py

@@ -0,0 +1,27 @@
+from sqlalchemy import Column, Integer, String, DateTime, Text, Boolean, func
+
+from app.database import Base
+
+
+class Job(Base):
+    __tablename__ = "jobs"
+
+    id = Column(Integer, primary_key=True, index=True)
+    name = Column(String, nullable=False)
+    source = Column(String, nullable=False)
+    species_filter = Column(Text, nullable=True)  # JSON array of species IDs or NULL for all
+    only_without_images = Column(Boolean, default=False)  # If True, only scrape species with 0 images
+    max_images = Column(Integer, nullable=True)  # If set, only scrape species with fewer than N images
+    status = Column(String, default="pending", index=True)  # pending, running, paused, completed, failed
+    progress_current = Column(Integer, default=0)
+    progress_total = Column(Integer, default=0)
+    images_downloaded = Column(Integer, default=0)
+    images_rejected = Column(Integer, default=0)
+    celery_task_id = Column(String, nullable=True)
+    started_at = Column(DateTime, nullable=True)
+    completed_at = Column(DateTime, nullable=True)
+    error_message = Column(Text, nullable=True)
+    created_at = Column(DateTime, server_default=func.now())
+
+    def __repr__(self):
+        return f"<Job(id={self.id}, name='{self.name}', status='{self.status}')>"