|
|
from fastapi import FastAPI |
|
|
from playwright.async_api import async_playwright |
|
|
|
|
|
app = FastAPI() |
|
|
|
|
|
async def scrape_google(query: str): |
|
|
url = ( |
|
|
"https://www.google.com/search" |
|
|
f"?q={query}" |
|
|
"&sxsrf=AE3TifOZcTbH54cOkE27wqRqSVEmaqb7fw%3A1750003707838" |
|
|
) |
|
|
async with async_playwright() as pw: |
|
|
browser = await pw.chromium.launch(headless=True) |
|
|
context = await browser.new_context() |
|
|
page = await context.new_page() |
|
|
|
|
|
|
|
|
try: |
|
|
btn = await page.wait_for_selector('button:has-text("I agree")', timeout=5000) |
|
|
await btn.click() |
|
|
except: |
|
|
pass |
|
|
|
|
|
await page.goto(url, wait_until="domcontentloaded") |
|
|
await page.wait_for_selector("h3") |
|
|
|
|
|
results = [] |
|
|
for h in await page.query_selector_all("h3"): |
|
|
try: |
|
|
link = await h.evaluate("(e) => e.closest('a').href") |
|
|
title = await h.inner_text() |
|
|
results.append({"title": title, "link": link}) |
|
|
except: |
|
|
continue |
|
|
|
|
|
await browser.close() |
|
|
return results |
|
|
|
|
|
@app.get("/search") |
|
|
async def search(query: str): |
|
|
data = await scrape_google(query.replace(" ", "+")) |
|
|
return {"query": query, "results": data} |
|
|
|
