From 4808d633a170a7732a45016da47390a9d5e3638d Mon Sep 17 00:00:00 2001
From: Matheus Felipe <50463866+matheusfelipeog@users.noreply.github.com>
Date: Tue, 11 Jan 2022 03:59:18 -0300
Subject: [PATCH] Implement functions to find links in a text/file

---
 scripts/validate/links.py | 42 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)
 create mode 100644 scripts/validate/links.py

diff --git a/scripts/validate/links.py b/scripts/validate/links.py
new file mode 100644
index 00000000..b7895097
--- /dev/null
+++ b/scripts/validate/links.py
@@ -0,0 +1,42 @@
+# -*- coding: utf-8 -*-
+
+import sys
+import re
+from typing import List
+
+
+def find_links_in_text(text: str) -> List[str]:
+    """Find links in a text and return a list of URLs."""
+
+    link_pattern = re.compile(r'((?:https?://|www\d{0,3}[.]|[a-z0-9.\-]+[.][a-z]{2,4}/)(?:[^\s()<>]+|\(([^\s()<>]+|(\([^\s()<>]+\)))*\))+(?:\(([^\s()<>]+|(\([^\s()<>]+\)))*\)|[^\s`!()\[\]{};:\'\".,<>?«»“”‘’]))')
+
+    raw_links = re.findall(link_pattern, text)
+
+    links = [
+        str(raw_link[0]).rstrip('/') for raw_link in raw_links
+    ]
+
+    return links
+
+
+def find_links_in_file(filename: str) -> List[str]:
+    """Find links in a file and return a list of URLs from text file."""
+
+    with open(filename, mode='r', encoding='utf-8') as file:
+        readme = file.read()
+        index_section = readme.find('## Index')
+        content = readme[index_section:]
+
+    links = find_links_in_text(content)
+
+    return links
+
+
+if __name__ == '__main__':
+    num_args = len(sys.argv)
+
+    if num_args < 2:
+        print('No .md file passed')
+        sys.exit(1)
+
+    links = find_links_in_file(sys.argv[1])