Upload 4 files

app/database/crud.py

@@ -186,9 +186,11 @@ async def save_chapter(
     content: str,
     title: Optional[str] = None,
     url: Optional[str] = None,
+    content_hindi: Optional[str] = None,
+    title_hindi: Optional[str] = None,
 ) -> Chapter:
     """
-    Save a chapter to the database.
+    Save a chapter to the database (English + Hindi).
     If a chapter with the same number already exists for this novel,
     it will raise an IntegrityError (caught by caller).
     """
@@ -198,7 +200,9 @@ async def save_chapter(
         novel_id=novel_id,
         chapter_number=chapter_number,
         title=title or f"Chapter {chapter_number}",
+        title_hindi=title_hindi,
         content=content,
+        content_hindi=content_hindi,
         url=url,
         word_count=word_count,
     )

app/database/models.py

@@ -2,7 +2,7 @@
 ============================================
 Database Models (Tables)
 - Novel: Stores novel metadata & scraping status
-- Chapter: Stores individual chapter content
+- Chapter: Stores individual chapter content (English + Hindi)
 ============================================
 """
 
@@ -25,80 +25,48 @@ from sqlalchemy.orm import relationship
 from app.database.connection import Base
 
 
-# ============================================
-# Enums for Status Tracking
-# ============================================
 class NovelStatus(str, enum.Enum):
-    """Status of a novel's scraping process."""
-    QUEUED = "queued"                    # Waiting in queue
-    LOGGING_IN = "logging_in"           # Attempting login
-    SCRAPING = "scraping"               # Actively scraping chapters
-    PAUSED_CAPTCHA = "paused_captcha"   # Waiting for manual intervention
-    PAUSED_ERROR = "paused_error"       # Paused due to error
-    COMPLETED = "completed"             # All chapters scraped
-    FAILED = "failed"                   # Permanently failed
+    QUEUED = "queued"
+    LOGGING_IN = "logging_in"
+    SCRAPING = "scraping"
+    PAUSED_CAPTCHA = "paused_captcha"
+    PAUSED_ERROR = "paused_error"
+    COMPLETED = "completed"
+    FAILED = "failed"
 
 
-# ============================================
-# Novel Model
-# ============================================
 class Novel(Base):
-    """
-    Stores metadata about each novel being scraped.
-    """
     __tablename__ = "novels"
 
     id = Column(Integer, primary_key=True, autoincrement=True)
-    
-    # --- Basic Info ---
     title = Column(String(500), nullable=False, default="Unknown Novel")
-    url = Column(String(2000), nullable=False)  # Starting URL
-    current_url = Column(String(2000), nullable=True)  # Current page URL
-    
-    # --- Credentials (for login) ---
+    title_hindi = Column(String(500), nullable=True)  # Hindi translated title
+    url = Column(String(2000), nullable=False)
+    current_url = Column(String(2000), nullable=True)
     login_email = Column(String(500), nullable=True)
-    login_password = Column(String(500), nullable=True)  # In production, encrypt this!
-    
-    # --- Scraping Config ---
+    login_password = Column(String(500), nullable=True)
     next_button_selector = Column(
-        String(500), 
-        nullable=False,
+        String(500), nullable=False,
         default="a.next_page, a[rel='next'], .next-chap, button.next-chapter"
     )
     content_selector = Column(
-        String(500),
-        nullable=False,
+        String(500), nullable=False,
         default=".chapter-content, .reading-content, #chapter-content, .text-left"
     )
-    
-    # --- Status Tracking ---
-    status = Column(
-        SQLEnum(NovelStatus),
-        nullable=False,
-        default=NovelStatus.QUEUED
-    )
+    status = Column(SQLEnum(NovelStatus), nullable=False, default=NovelStatus.QUEUED)
     chapters_scraped = Column(Integer, default=0)
     last_error = Column(Text, nullable=True)
-    
-    # --- Captcha/Intervention ---
     screenshot_path = Column(String(1000), nullable=True)
     needs_intervention = Column(Boolean, default=False)
-    
-    # --- Timestamps ---
-    created_at = Column(
-        DateTime(timezone=True),
-        default=lambda: datetime.now(timezone.utc)
-    )
+    created_at = Column(DateTime(timezone=True), default=lambda: datetime.now(timezone.utc))
     updated_at = Column(
         DateTime(timezone=True),
         default=lambda: datetime.now(timezone.utc),
         onupdate=lambda: datetime.now(timezone.utc)
     )
 
-    # --- Relationships ---
     chapters = relationship(
-        "Chapter",
-        back_populates="novel",
+        "Chapter", back_populates="novel",
         cascade="all, delete-orphan",
         order_by="Chapter.chapter_number",
         lazy="selectin",
@@ -108,49 +76,26 @@ class Novel(Base):
         return f"<Novel(id={self.id}, title='{self.title}', status={self.status})>"
 
 
-# ============================================
-# Chapter Model
-# ============================================
 class Chapter(Base):
-    """
-    Stores individual chapter content.
-    Each chapter belongs to a Novel.
-    """
     __tablename__ = "chapters"
 
     id = Column(Integer, primary_key=True, autoincrement=True)
-    
-    # --- Foreign Key ---
-    novel_id = Column(
-        Integer,
-        ForeignKey("novels.id", ondelete="CASCADE"),
-        nullable=False,
-        index=True,
-    )
-    
-    # --- Chapter Data ---
+    novel_id = Column(Integer, ForeignKey("novels.id", ondelete="CASCADE"), nullable=False, index=True)
     chapter_number = Column(Integer, nullable=False)
     title = Column(String(1000), nullable=True, default="")
-    content = Column(Text, nullable=False)  # The actual chapter text
-    url = Column(String(2000), nullable=True)  # URL where this was scraped from
+    title_hindi = Column(String(1000), nullable=True)        # ✅ Hindi title
+    content = Column(Text, nullable=False)                    # English content
+    content_hindi = Column(Text, nullable=True)              # ✅ Hindi content
+    url = Column(String(2000), nullable=True)
     word_count = Column(Integer, default=0)
-    
-    # --- Timestamps ---
-    scraped_at = Column(
-        DateTime(timezone=True),
-        default=lambda: datetime.now(timezone.utc)
-    )
+    scraped_at = Column(DateTime(timezone=True), default=lambda: datetime.now(timezone.utc))
 
-    # --- Relationships ---
     novel = relationship("Novel", back_populates="chapters")
 
-    # --- Constraints ---
     __table_args__ = (
-        # Ensure no duplicate chapters for same novel
         UniqueConstraint("novel_id", "chapter_number", name="uq_novel_chapter"),
-        # Index for faster queries
         Index("ix_chapter_novel_number", "novel_id", "chapter_number"),
     )
 
     def __repr__(self):
-        return f"<Chapter(id={self.id}, novel_id={self.novel_id}, ch={self.chapter_number})>"
+        return f"<Chapter(id={self.id}, novel_id={self.novel_id}, ch={self.chapter_number})>"