Spaces:
Sleeping
Sleeping
File size: 1,785 Bytes
e84fb4f d92c861 462e814 d92c861 9ba3ade d92c861 0f0c7dc fdf1d1f 462e814 0f0c7dc |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 |
from fastapi import FastAPI, HTTPException
from fastapi.middleware.cors import CORSMiddleware
from scraper import Scraper
try: from pip._internal.operations import freeze
except ImportError: # pip < 10.0
from pip.operations import freeze
pkgs = freeze.freeze()
for pkg in pkgs: print(pkg)
app = FastAPI()
app.add_middleware(
CORSMiddleware,
allow_origins=["*"],
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
)
@app.get("/get_scraped_data")
async def get_data(url: str):
import requests
from bs4 import BeautifulSoup
# URL of the page to scrape
#url = "https://www.imf.org/en/News/Articles/2024/03/21/pr2494-sri-lanka-imf-staff-level-agreement-for-second-review-sla"
url = url
# Send a GET request to the URL
response = requests.get(url)
# Check if the request was successful
if response.status_code == 200:
# Parse the page content
soup = BeautifulSoup(response.content, 'html.parser')
# Extract all text content (paragraphs, headers, etc.)
elements = soup.find_all(['p', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6'])
body_text = "\n".join([element.get_text().strip() for element in elements])
# Extract all links
links = []
for a_tag in soup.find_all('a', href=True):
links.append(a_tag['href'])
# Print the extracted information
print("Body Text:")
print(body_text)
print("\nLinks:")
for link in links:
print(link)
else:
print("Failed to retrieve the webpage")
return "done"
try:
data = await Scraper.scrape(url)
return data
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
|