From 7be0512b5438edf4d434f325181e2e586ee65009 Mon Sep 17 00:00:00 2001
From: Matheus Felipe <50463866+matheusfelipeog@users.noreply.github.com>
Date: Wed, 12 Jan 2022 00:55:23 -0300
Subject: [PATCH] Check if a link is working

---
 scripts/validate/links.py | 79 ++++++++++++++++++++++++++++++++++++++-
 1 file changed, 78 insertions(+), 1 deletion(-)

diff --git a/scripts/validate/links.py b/scripts/validate/links.py
index bb84aac8..2dfbf7db 100644
--- a/scripts/validate/links.py
+++ b/scripts/validate/links.py
@@ -1,9 +1,12 @@
 # -*- coding: utf-8 -*-
 
-import sys
 import re
+import sys
+import random
 from typing import List, Tuple
 
+import requests
+
 
 def find_links_in_text(text: str) -> List[str]:
     """Find links in a text and return a list of URLs."""
@@ -55,6 +58,80 @@ def check_duplicate_links(links: List[str]) -> Tuple[bool, List]:
     return (has_duplicate, duplicates)
 
 
+def fake_user_agent() -> str:
+    """Faking user agent as some hosting services block not-whitelisted UA."""
+
+    user_agents = [
+        'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1467.0 Safari/537.36',
+        'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/605.1.15 (KHTML, like Gecko)',
+        'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36',
+        'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.71 Safari/537.36',
+    ]
+
+    return random.choice(user_agents)
+
+
+def get_host_from_link(link: str) -> str:
+
+    host = link.split('://', 1)[1]
+
+    # Remove routes, arguments and anchors
+    if '/' in host:
+        host = host.split('/', 1)[0]
+
+    elif '?' in host:
+        host = host.split('?', 1)[0]
+
+    elif '#' in host:
+        host = host.split('#', 1)[0]
+
+    return host
+
+
+def check_if_link_is_working(link: str) -> Tuple[bool, str]:
+    """Checks if a link is working.
+    
+    If an error is identified when the request for the link occurs,
+    the return will be a tuple with the first value True and the second
+    value a string containing the error message.
+
+    If no errors are identified, the return will be a tuple with the
+    first value False and the second an empty string.
+    """
+
+    has_error = False
+    error_message = ''
+
+    try:
+        resp = requests.get(link + '/', timeout=25, headers={
+            'User-Agent': fake_user_agent(),
+            'host': get_host_from_link(link)
+        })
+
+        code = resp.status_code
+        if code >= 400:
+            has_error = True
+            error_message = f'ERR:CLT: {code} : {link}'
+
+    except (TimeoutError, requests.exceptions.ConnectTimeout):
+        has_error = True
+        error_message = f'ERR:TMO: {link}'
+    
+    except requests.exceptions.SSLError as error:
+        has_error = True
+        error_message = f'ERR:SSL: {error} : {link}'
+    
+    except requests.exceptions.TooManyRedirects as error:
+        has_error = True
+        error_message = f'ERR:TMR: {error} : {link}'
+
+    except Exception as error:
+        has_error = True
+        error_message = f'ERR:UKN: {error} : {link}'
+    
+    return (has_error, error_message)
+
+
 if __name__ == '__main__':
     num_args = len(sys.argv)