68 lines
2.3 KiB
Python
68 lines
2.3 KiB
Python
"""Pry — Transform router (remaining api.py routes).
|
|
|
|
Auto-extracted from api.py during the router-split refactor.
|
|
"""
|
|
|
|
# SPDX-License-Identifier: MIT
|
|
# Copyright (c) 2026 Rug Munch Media LLC
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import logging
|
|
from typing import Any
|
|
|
|
from fastapi import APIRouter, Body
|
|
|
|
from deps import scraper
|
|
from errors import InvalidRequestError, ScrapeError
|
|
from pryextras import TransformEngine
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
router = APIRouter(tags=["Transform"])
|
|
|
|
@router.post("/v1/transform", tags=["Transform"], summary="Transform data to multiple formats")
|
|
async def transform_data(
|
|
data: list[dict[str, Any]] = Body(...), format: str = "csv"
|
|
) -> dict[str, Any]:
|
|
te = TransformEngine()
|
|
if format == "csv":
|
|
result = te.to_csv(data)
|
|
elif format == "sql":
|
|
result = "\n".join(te.to_sql(row) for row in data)
|
|
elif format == "html":
|
|
result = te.to_html_table(data)
|
|
elif format == "markdown":
|
|
result = te.to_markdown_table(data)
|
|
else:
|
|
raise InvalidRequestError(f"Unknown format: {format}")
|
|
return {"success": True, "data": {"output": result, "format": format}}
|
|
|
|
|
|
@router.post("/v1/pipe", tags=["Transform"], summary="Scrape and transform via data pipeline")
|
|
async def data_pipeline(data: dict[str, Any] = Body(...)) -> dict[str, Any]:
|
|
url = data.get("url", "")
|
|
transform = data.get("transform", "json")
|
|
result = await scraper.scrape(url, {"bypass_cloudflare": True})
|
|
if result.get("status") != "ok":
|
|
raise ScrapeError(result.get("error") or "Pipeline failed")
|
|
content = result.get("content", "")
|
|
title = result.get("title", url)
|
|
if transform == "sql":
|
|
from pryextras import TransformEngine
|
|
|
|
te = TransformEngine()
|
|
output = te.to_sql({"url": url, "title": title, "content": content[:50000]})
|
|
elif transform == "csv":
|
|
import csv
|
|
import io
|
|
|
|
buf = io.StringIO()
|
|
w = csv.writer(buf)
|
|
w.writerow(["url", "title", "content"])
|
|
w.writerow([url, title, content[:50000]])
|
|
output = buf.getvalue()
|
|
else:
|
|
output = json.dumps({"url": url, "title": title, "content": content[:100000]}, indent=2)
|
|
return {"success": True, "data": {"url": url, "output": output, "format": transform}}
|