Created
          June 26, 2023 01:31 
        
      - 
      
- 
        Save Xnuvers007/ef5818089cf23b05825f721f1b8e5d18 to your computer and use it in GitHub Desktop. 
    This is code for get all link href from website and get result where that link to redirect it
  
        
  
    
      This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
      Learn more about bidirectional Unicode characters
    
  
  
    
  | import requests | |
| from urllib.parse import urljoin | |
| def get_redirected_url(url): | |
| response = requests.head(url, allow_redirects=True) | |
| return response.url | |
| def get_all_links(url): | |
| response = requests.get(url) | |
| if response.status_code == 200: | |
| base_url = response.url | |
| html_content = response.text | |
| links = html_content.split('href="')[1:] | |
| for link in links: | |
| link_url = link.split('"')[0] | |
| absolute_url = urljoin(base_url, link_url) | |
| redirected_url = get_redirected_url(absolute_url) | |
| print(f"{absolute_url} -> {redirected_url}") | |
| else: | |
| print(f"Failed to retrieve content from {url} (Status code: {response.status_code})") | |
| # Usage example | |
| get_all_links('https://www.halodoc.com/artikel/search/Pusing') | 
  
    Sign up for free
    to join this conversation on GitHub.
    Already have an account?
    Sign in to comment