Spaces:
Sleeping
Sleeping
| import requests | |
| from bs4 import BeautifulSoup | |
| import os | |
| # URL setup | |
| base_url = "http://74.208.61.158:8888" | |
| page_url = base_url + "/list-pdfs" # if the PDF links are on the home page | |
| # Directory for storing PDFs | |
| pdf_dir = "pdf_downloads" | |
| os.makedirs(pdf_dir, exist_ok=True) | |
| # Fetch the webpage | |
| response = requests.get(page_url) | |
| response.raise_for_status() # will raise an exception for HTTP error codes | |
| # Parse the webpage | |
| soup = BeautifulSoup(response.content, 'html.parser') | |
| # Find all PDF links | |
| for link in soup.find_all('a', href=True): | |
| href = link['href'] | |
| if href.endswith('.pdf'): | |
| pdf_url = base_url + href | |
| pdf_response = requests.get(pdf_url) | |
| pdf_response.raise_for_status() | |
| # Write the PDF to a file | |
| pdf_filename = os.path.join(pdf_dir, href.split('/')[-1]) | |
| with open(pdf_filename, 'wb') as file: | |
| file.write(pdf_response.content) | |
| print(f"Downloaded: {pdf_filename}") |