64 lines
2.1 KiB
Python
64 lines
2.1 KiB
Python
"""Pry — Export 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 html
|
|
import logging
|
|
from datetime import UTC
|
|
from typing import Any
|
|
|
|
from fastapi import APIRouter, Body
|
|
|
|
from deps import scraper
|
|
from errors import ScrapeError
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
router = APIRouter(tags=["Export"])
|
|
|
|
@router.post("/v1/export", tags=["Export"], summary="Export scraped content in multiple formats")
|
|
async def export_data(url: str = Body(...), format: str = "json") -> dict[str, Any]:
|
|
"""Export scraped content in multiple formats: json, csv, txt, rss.
|
|
Firecrawl only does markdown."""
|
|
result = await scraper.scrape(url)
|
|
if result.get("status") != "ok":
|
|
raise ScrapeError(result.get("error") or "Export failed")
|
|
content = result.get("content", "")
|
|
title = result.get("title", url)
|
|
|
|
if format == "json":
|
|
return {
|
|
"success": True,
|
|
"data": {"url": url, "title": title, "content": content, "format": "json"},
|
|
}
|
|
elif format == "csv":
|
|
import csv
|
|
import io
|
|
|
|
buf = io.StringIO()
|
|
w = csv.writer(buf)
|
|
w.writerow(["url", "title", "content"])
|
|
w.writerow([url, title, content[:50000]])
|
|
return {"success": True, "data": {"csv": buf.getvalue(), "format": "csv"}}
|
|
elif format == "rss":
|
|
from datetime import datetime
|
|
|
|
safe_title = html.escape(title)
|
|
safe_url = html.escape(url)
|
|
rss = f"""<?xml version="1.0"?>
|
|
<rss version="2.0"><channel>
|
|
<title>Pry: {safe_title}</title>
|
|
<link>{safe_url}</link>
|
|
<description>Scraped content from {safe_url}</description>
|
|
<item><title>{safe_title}</title><link>{safe_url}</link>
|
|
<description><![CDATA[{content[:50000]}]]></description>
|
|
<pubDate>{datetime.now(UTC).strftime("%a, %d %b %Y %H:%M:%S UTC")}</pubDate>
|
|
</item></channel></rss>"""
|
|
return {"success": True, "data": {"rss": rss, "format": "rss"}}
|
|
return {"success": True, "data": {"text": content[:100000], "format": "txt"}}
|