Initial commit: Thread Ripper containerized application

thread_ripper/server.py

@@ -0,0 +1,113 @@
+import os
+from contextlib import asynccontextmanager
+from fastapi import FastAPI, HTTPException, Response
+from fastapi.staticfiles import StaticFiles
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import FileResponse, PlainTextResponse, HTMLResponse, JSONResponse
+from .models import RipRequest, RippedThread
+from .scraper import ThreadScraper
+from .storage import ThreadStorage
+
+DATA_DIR = os.environ.get("DATA_DIR", "data")
+storage = ThreadStorage(DATA_DIR)
+scraper = ThreadScraper(headless=True)
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    yield
+    await scraper.close()
+
+app = FastAPI(
+    title="Thread Ripper",
+    description="Containerized Thread Ripper for Meta Threads. Takes Threads links and stitches threads into single posts.",
+    version="1.0.0",
+    lifespan=lifespan
+)
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+@app.post("/api/rip", response_model=RippedThread)
+async def rip_endpoint(req: RipRequest):
+    """Rip a Threads post and its chained continuation posts."""
+    if not req.url or "threads." not in req.url:
+        raise HTTPException(status_code=400, detail="Invalid Threads URL. Please provide a valid threads.net or threads.com link.")
+
+    try:
+        ripped = await scraper.rip(url=req.url, mode=req.mode, max_scrolls=req.max_scrolls)
+        storage.save(ripped)
+        return ripped
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Failed to rip thread: {str(e)}")
+
+@app.get("/api/history")
+def get_history():
+    """Retrieve history of saved ripped threads."""
+    return storage.list_history()
+
+@app.get("/api/history/{thread_id}", response_model=RippedThread)
+def get_thread_by_id(thread_id: str):
+    """Get complete ripped thread by ID."""
+    thread = storage.get(thread_id)
+    if not thread:
+        raise HTTPException(status_code=404, detail="Thread not found")
+    return thread
+
+@app.delete("/api/history/{thread_id}")
+def delete_thread_by_id(thread_id: str):
+    """Delete thread from history."""
+    deleted = storage.delete(thread_id)
+    if not deleted:
+        raise HTTPException(status_code=404, detail="Thread not found")
+    return {"status": "success", "deleted_id": thread_id}
+
+@app.get("/api/download/{thread_id}/{format}")
+def download_thread(thread_id: str, format: str):
+    """Download thread in chosen format (.md, .txt, .html, .json)."""
+    thread = storage.get(thread_id)
+    if not thread:
+        raise HTTPException(status_code=404, detail="Thread not found")
+
+    safe_title = "".join(c for c in thread.author_handle if c.isalnum() or c in "-_")
+    filename_base = f"thread_{safe_title}_{thread_id}"
+
+    if format == "md" or format == "markdown":
+        return Response(
+            content=thread.stitched_markdown,
+            media_type="text/markdown; charset=utf-8",
+            headers={"Content-Disposition": f'attachment; filename="{filename_base}.md"'}
+        )
+    elif format == "txt" or format == "text":
+        return Response(
+            content=thread.stitched_text,
+            media_type="text/plain; charset=utf-8",
+            headers={"Content-Disposition": f'attachment; filename="{filename_base}.txt"'}
+        )
+    elif format == "html":
+        return Response(
+            content=thread.stitched_html,
+            media_type="text/html; charset=utf-8",
+            headers={"Content-Disposition": f'attachment; filename="{filename_base}.html"'}
+        )
+    elif format == "json":
+        return Response(
+            content=thread.model_dump_json(indent=2),
+            media_type="application/json; charset=utf-8",
+            headers={"Content-Disposition": f'attachment; filename="{filename_base}.json"'}
+        )
+    else:
+        raise HTTPException(status_code=400, detail="Supported formats: md, txt, html, json")
+
+@app.get("/api/health")
+def health_check():
+    return {"status": "ok", "app": "Thread Ripper", "version": "1.0.0"}
+
+# Mount static frontend directory
+static_dir = os.path.join(os.path.dirname(__file__), "static")
+if os.path.exists(static_dir):
+    app.mount("/", StaticFiles(directory=static_dir, html=True), name="static")