scraper.py

# Import necessary libraries
import requests
from bs4 import BeautifulSoup
import pandas as pd

class WebScraper:
    def __init__(self, urls):
        self.urls = urls
        self.data = pd.DataFrame()

    def scrape(self):
        for url in self.urls:
            response = requests.get(url)
            soup = BeautifulSoup(response.text, 'html.parser')
            text = ' '.join(map(lambda p: p.text, soup.find_all('p')))
            self.data = self.data.append({'url': url, 'content': text}, ignore_index=True)

    def get_data(self):
        return self.data