From d985756c9a1ea7096c1cd24ac01caa54c6a1122d Mon Sep 17 00:00:00 2001
From: Chan Wei Nick <weinick92@gmail.com>
Date: Tue, 25 Mar 2025 09:21:39 +0800
Subject: [PATCH] push compareHostname

---
 .gitignore         |  5 +++++
 README.md          |  5 +++++
 compareHostname.py | 36 ++++++++++++++++++++++++++++++++++++
 3 files changed, 46 insertions(+)
 create mode 100644 compareHostname.py

diff --git a/.gitignore b/.gitignore
index 0a19790..901c25b 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,3 +1,8 @@
+# Nick self-add
+
+# sensitive files that could not be shared
+rawFiles/
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
diff --git a/README.md b/README.md
index 0a006e2..1f8ed25 100644
--- a/README.md
+++ b/README.md
@@ -1,2 +1,7 @@
 # SW_PythonScripts
+
 Random Scripts for Making Life Easier
+
+## compareHostname.py
+
+Allows to compare between 2 text files, 'hostname="{...}"', and print out unique hostnames for easier management
\ No newline at end of file
diff --git a/compareHostname.py b/compareHostname.py
new file mode 100644
index 0000000..e234a40
--- /dev/null
+++ b/compareHostname.py
@@ -0,0 +1,36 @@
+import re
+
+def extract_hostnames(file_path):
+    hostname_pattern = r'hostname="([^"]+)"'
+    hostnames = set()  # Use a set to avoid duplicates within the same file
+
+    try:
+        with open(file_path, 'r', encoding='utf-8') as file:
+            for line in file:
+                matches = re.findall(hostname_pattern, line)
+                hostnames.update(matches)
+    except FileNotFoundError:
+        print(f"File not found: {file_path}")
+    except Exception as e:
+        print(f"An error occurred: {e}")
+
+    return hostnames
+
+if __name__ == "__main__":
+    file1 = "rawFiles/file1.txt"
+    file2 = "rawFiles/file2.txt"
+
+    hostnames_file1 = extract_hostnames(file1)
+    hostnames_file2 = extract_hostnames(file2)
+
+    # Find unduplicated hostnames
+    unique_to_file1 = hostnames_file1 - hostnames_file2
+    unique_to_file2 = hostnames_file2 - hostnames_file1
+
+    print("Hostnames unique to file1:")
+    for hostname in unique_to_file1:
+        print(hostname)
+
+    print("\nHostnames unique to file2:")
+    for hostname in unique_to_file2:
+        print(hostname)
\ No newline at end of file