Spaces:
Sleeping
Sleeping
| from bs4 import BeautifulSoup | |
| import requests | |
| from requests.exceptions import HTTPError | |
| class WebScrapingService: | |
| def __init__(self): | |
| pass | |
| def scrape_text_from_url(self, url): | |
| try: | |
| response = requests.get(url) | |
| soup = BeautifulSoup(response.text, 'html.parser') | |
| unwanted_elements = ['footer', 'script', 'style', 'noscript'] | |
| for tag in unwanted_elements: | |
| for el in soup.find_all(tag): | |
| el.extract() | |
| text = ' '.join([p.text for p in soup.find_all('p')]) | |
| return text.strip() # Strip leading and trailing whitespaces | |
| except Exception as e: | |
| raise HTTPError(e) |