Untitled

mail@pastecode.io avatar
unknown
plain_text
a year ago
1.3 kB
6
Indexable
Never
import requests
from bs4 import BeautifulSoup

# Replace 'your_url_here' with the URL of the webpage containing the PDF
url = 'http://shankar8332.pythonanywhere.com/'

# Send an HTTP GET request to the webpage
response = requests.get(url)

# Check if the request was successful (status code 200)
if response.status_code == 200:
    # Parse the HTML content of the webpage using BeautifulSoup
    soup = BeautifulSoup(response.text, 'html.parser')
    
    # Find the link to the PDF (you may need to inspect the webpage's HTML structure)
    pdf_link = soup.find('a', href=True, attrs={'href': lambda x: x.endswith('.pdf')})
    
    if pdf_link:
        # Get the URL of the PDF
        pdf_url = url + pdf_link['href']
        
        # Download the PDF file
        pdf_response = requests.get(pdf_url)
        
        if pdf_response.status_code == 200:
            # Save the PDF to a local file
            with open('downloaded_file.pdf', 'wb') as pdf_file:
                pdf_file.write(pdf_response.content)
            print('PDF downloaded successfully.')
        else:
            print('Failed to download the PDF.')
    else:
        print('No PDF link found on the webpage.')
else:
    print('Failed to access the webpage.')