|
|
from fastapi import FastAPI, HTTPException, Query |
|
|
from pydantic import BaseModel |
|
|
from playwright.async_api import async_playwright |
|
|
import asyncio |
|
|
import base64 |
|
|
import time |
|
|
from typing import Optional, List |
|
|
import uvicorn |
|
|
import logging |
|
|
|
|
|
app = FastAPI() |
|
|
|
|
|
logging.basicConfig(level=logging.INFO) |
|
|
logger = logging.getLogger("analyzer") |
|
|
|
|
|
class AnalysisResult(BaseModel): |
|
|
url: str |
|
|
load_time: float |
|
|
title: Optional[str] |
|
|
meta_description: Optional[str] |
|
|
og_image: Optional[str] |
|
|
seo_flags: List[str] |
|
|
accessibility_flags: List[str] |
|
|
screenshot_base64: str |
|
|
status_code: Optional[int] = None |
|
|
|
|
|
@app.get("/analyze", response_model=AnalysisResult) |
|
|
async def analyze_website(url: str): |
|
|
try: |
|
|
async with async_playwright() as p: |
|
|
browser = await p.chromium.launch(headless=True) |
|
|
context = await browser.new_context() |
|
|
page = await context.new_page() |
|
|
|
|
|
|
|
|
start_time = time.time() |
|
|
response = await page.goto(url, timeout=60000, wait_until='domcontentloaded') |
|
|
await page.wait_for_load_state("networkidle") |
|
|
load_time = round(time.time() - start_time, 2) |
|
|
|
|
|
|
|
|
screenshot = await page.screenshot(full_page=True) |
|
|
screenshot_base64 = base64.b64encode(screenshot).decode("utf-8") |
|
|
|
|
|
|
|
|
title = await page.title() |
|
|
meta_description = await page.eval_on_selector("meta[name='description']", "el => el.content") if await page.query_selector("meta[name='description']") else None |
|
|
og_image = await page.eval_on_selector("meta[property='og:image']", "el => el.content") if await page.query_selector("meta[property='og:image']") else None |
|
|
|
|
|
|
|
|
seo_flags = [] |
|
|
if not title: |
|
|
seo_flags.append("Missing <title>") |
|
|
if not meta_description: |
|
|
seo_flags.append("Missing meta description") |
|
|
if not await page.query_selector("h1"): |
|
|
seo_flags.append("Missing <h1> tag") |
|
|
if not og_image: |
|
|
seo_flags.append("Missing Open Graph image") |
|
|
|
|
|
|
|
|
accessibility_flags = [] |
|
|
images = await page.query_selector_all("img") |
|
|
for img in images: |
|
|
has_alt = await img.get_attribute("alt") |
|
|
if not has_alt: |
|
|
accessibility_flags.append("Image without alt attribute") |
|
|
break |
|
|
|
|
|
status_code = response.status if response else None |
|
|
|
|
|
await browser.close() |
|
|
|
|
|
return AnalysisResult( |
|
|
url=url, |
|
|
load_time=load_time, |
|
|
title=title, |
|
|
meta_description=meta_description, |
|
|
og_image=og_image, |
|
|
seo_flags=seo_flags, |
|
|
accessibility_flags=accessibility_flags, |
|
|
screenshot_base64=screenshot_base64, |
|
|
status_code=status_code |
|
|
) |
|
|
except Exception as e: |
|
|
logger.error(f"Analysis failed for {url}: {str(e)}") |
|
|
raise HTTPException(status_code=500, detail=f"Error analyzing {url}: {str(e)}") |
|
|
|
|
|
if __name__ == "__main__": |
|
|
uvicorn.run("main:app", host="0.0.0.0", port=8000, reload=True) |
|
|
|
