Arafath10's picture
Update main.py
920f2ce verified
raw
history blame
2.09 kB
from fastapi import FastAPI, File, UploadFile, HTTPException
from fastapi.responses import HTMLResponse
from fastapi.responses import StreamingResponse
from fastapi.responses import FileResponse
from fastapi.middleware.cors import CORSMiddleware
from pydantic import BaseModel
from io import StringIO
import os
app = FastAPI()
app.add_middleware(
CORSMiddleware,
allow_origins=["*"],
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
)
import nest_asyncio
import asyncio
from playwright.async_api import async_playwright
# Apply nest_asyncio to allow nested asyncio.run() calls
nest_asyncio.apply()
async def scrape_links():
async with async_playwright() as p:
browser = await p.chromium.launch(headless=True)
page = await browser.new_page()
# Block unnecessary resources to speed up loading
await page.route("**/*", lambda route: route.continue_() if route.request.resource_type in ["document", "script"] else route.abort())
# Open the target website
await page.goto('https://www.fool.com/earnings/call-transcripts/2024/01/24/tesla-tsla-q4-2023-earnings-call-transcript/', wait_until='domcontentloaded')
# Wait for a short time to ensure dynamic content is loaded
await page.wait_for_timeout(10)
# Extract all links
links = await page.query_selector_all('a')
result = []
for link in links:
href = await link.get_attribute('href')
result.append({'href': href})
# Extract all text content
elements = await page.query_selector_all('body *')
for element in elements:
text_content = await element.text_content()
if text_content and text_content.strip():
result.append({'text': text_content.strip()})
await browser.close()
return result
@app.post("/get_webscrapet_data")
async def get_webscrapet_data(url):
# Run the scraping function
results = asyncio.run(scrape_links())
print(results)
return results