Initial commit: Thread Ripper containerized application

thread_ripper/models.py

@@ -0,0 +1,52 @@
+from typing import List, Optional, Dict, Any
+from pydantic import BaseModel, Field
+from datetime import datetime
+
+class MediaItem(BaseModel):
+    type: str = "image"
+    url: str
+    alt_text: Optional[str] = None
+
+class PostSegment(BaseModel):
+    index: int
+    author_handle: str
+    author_name: Optional[str] = None
+    author_avatar: Optional[str] = None
+    timestamp: Optional[str] = None
+    url: Optional[str] = None
+    text: str
+    is_author: bool = True
+    images: List[MediaItem] = Field(default_factory=list)
+    stats: Dict[str, str] = Field(default_factory=dict)
+
+class RippedThread(BaseModel):
+    id: str
+    original_url: str
+    canonical_url: str
+    author_handle: str
+    author_name: str
+    author_avatar: Optional[str] = None
+    created_at: str
+    title: str
+    segments: List[PostSegment]
+    stitched_markdown: str
+    stitched_text: str
+    stitched_html: str
+    segment_count: int
+    total_words: int
+    saved_at: datetime = Field(default_factory=datetime.utcnow)
+
+class RipRequest(BaseModel):
+    url: str
+    mode: str = "author_only"  # 'author_only' or 'all_replies'
+    max_scrolls: int = 6
+
+class HistorySummary(BaseModel):
+    id: str
+    title: str
+    author_handle: str
+    author_name: str
+    segment_count: int
+    total_words: int
+    saved_at: str
+    original_url: str