Added support for email notifications via SNMP.

diff-web.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 # Description: Monitor a website for changes.
-# Usage: python3 diff-web.py
+# Usage: python3 diff-web.py https://example.com --email user@example.com
 # Author: Justin Oros
 # Source: https://github.com/JustinOros
 
@@ -9,50 +9,36 @@ import hashlib
 import os
 import time
 import argparse
-from urllib.parse import urlparse, urlunparse, parse_qsl, urlencode
+from urllib.parse import urlparse, urlunparse, parse_qs, urlencode
 from datetime import datetime
-from bs4 import BeautifulSoup, Comment
+from bs4 import BeautifulSoup
+import smtplib
+from email.mime.text import MIMEText
 
-# List of known tracking parameters to strip
+SMTP_SERVER = "smtp.gmail.com"
-TRACKING_PARAMS = {
+SMTP_PORT = 587
-    'utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',
+SMTP_USERNAME = os.getenv("EMAIL_USER")
-    'fbclid', 'gclid', 'mc_cid', 'mc_eid', 'ref', 'ref_src'
+SMTP_PASSWORD = os.getenv("EMAIL_PASS")
-}
+EMAIL_FROM = SMTP_USERNAME
 
 def normalize_url(url):
-    if not urlparse(url).scheme:
-        url = 'https://' + url
-    return strip_tracking_params(url)
-
-def strip_tracking_params(url):
     parsed = urlparse(url)
-    clean_query = [(k, v) for k, v in parse_qsl(parsed.query) if k not in TRACKING_PARAMS]
+    if not parsed.scheme:
-    new_query = urlencode(clean_query)
+        url = 'https://' + url
+        parsed = urlparse(url)
+
+    query = parse_qs(parsed.query)
+    stripped_query = {k: v for k, v in query.items() if not k.startswith(('utm_', 'fbclid', 'gclid'))}
+    new_query = urlencode(stripped_query, doseq=True)
     return urlunparse(parsed._replace(query=new_query))
 
 def fetch_content(url):
     response = requests.get(url, timeout=10)
     response.raise_for_status()
-    return response.text
+    soup = BeautifulSoup(response.text, 'html.parser')
-
+    for tag in soup(["script", "style", "noscript", "iframe", "svg", "canvas"]):
-def clean_content(html):
-    soup = BeautifulSoup(html, 'html.parser')
-
-    # Remove dynamic or non-content elements
-    for tag in soup(['script', 'style', 'noscript', 'meta']):
         tag.decompose()
-
+    return soup.get_text(separator=' ', strip=True)
-    # Remove HTML comments
-    for comment in soup.find_all(string=lambda text: isinstance(text, Comment)):
-        comment.extract()
-
-    # Remove tracking params from all anchor links
-    for a in soup.find_all('a', href=True):
-        a['href'] = strip_tracking_params(a['href'])
-
-    # Get visible text, normalize whitespace
-    text = soup.get_text(separator=' ', strip=True)
-    return ' '.join(text.split())
 
 def get_hash(content):
     return hashlib.sha256(content.encode('utf-8')).hexdigest()
@@ -67,16 +53,32 @@ def get_cache_filename(url):
     domain = urlparse(url).netloc
     return f".{domain}.cache"
 
-def timestamp():
-    return datetime.now().strftime("%Y-%m-%d %H:%M:%S")
-
 def log_message(message, log_file, quiet=False):
     if not quiet:
         print(message)
     with open(log_file, 'a') as f:
         f.write(message + '\n')
 
-def monitor_website(url, interval, log_file_override=None, max_checks=None, quiet=False):
+def timestamp():
+    return datetime.now().strftime('%Y-%m-%d %H:%M:%S')
+
+def send_email(subject, body, recipients):
+    if not SMTP_USERNAME or not SMTP_PASSWORD:
+        print("Email credentials not configured in environment.")
+        return
+    msg = MIMEText(body)
+    msg['Subject'] = subject
+    msg['From'] = EMAIL_FROM
+    msg['To'] = ", ".join(recipients)
+    try:
+        with smtplib.SMTP(SMTP_SERVER, SMTP_PORT) as server:
+            server.starttls()
+            server.login(SMTP_USERNAME, SMTP_PASSWORD)
+            server.sendmail(EMAIL_FROM, recipients, msg.as_string())
+    except Exception as e:
+        print(f"Failed to send email: {e}")
+
+def monitor_website(url, interval, log_file_override=None, quiet=False, recipients=None):
     url = normalize_url(url)
     domain = urlparse(url).netloc
     log_file = get_log_filename(url, log_file_override)
@@ -84,13 +86,10 @@ def monitor_website(url, interval, log_file_override=None, max_checks=None, quie
 
     log_message(f"[{timestamp()}] Monitoring {domain}", log_file, quiet)
 
-    checks_done = 0
-
     while True:
         try:
-            raw_html = fetch_content(url)
+            current_content = fetch_content(url)
-            cleaned_text = clean_content(raw_html)
+            current_hash = get_hash(current_content)
-            current_hash = get_hash(cleaned_text)
         except Exception as e:
             log_message(f"[{timestamp()}] [ERROR] Failed to fetch {url}: {e}", log_file, quiet)
             time.sleep(interval)
@@ -101,20 +100,18 @@ def monitor_website(url, interval, log_file_override=None, max_checks=None, quie
             with open(cache_file, 'r') as f:
                 old_hash = f.read().strip()
             is_changed = current_hash != old_hash
-
             if is_changed:
                 log_message(f"[{timestamp()}] Change detected on {url}", log_file, quiet)
+                if recipients:
+                    subject = f"Website Change Detected: {domain}"
+                    body = f"A change was detected on {url} at {timestamp()}."
+                    send_email(subject, body, recipients)
         else:
             log_message(f"[{timestamp()}] First-time check for {url}: storing baseline.", log_file, quiet)
 
         with open(cache_file, 'w') as f:
             f.write(current_hash)
 
-        checks_done += 1
-        if max_checks is not None and checks_done >= max_checks:
-            log_message(f"[{timestamp()}] Reached max checks ({max_checks}). Stopping.", log_file, quiet)
-            break
-
         time.sleep(interval)
 
 if __name__ == "__main__":
@@ -124,15 +121,19 @@ if __name__ == "__main__":
                         help="Time interval between checks in seconds (default: 60).")
     parser.add_argument("-l", "--log", type=str,
                         help="Optional log file name (default: domain.tld.log)")
-    parser.add_argument("-c", "--count", type=int,
-                        help="Optional number of times to check before stopping.")
     parser.add_argument("-q", "--quiet", action="store_true",
-                        help="Quiet mode: suppress console output")
+                        help="Suppress console output.")
+    parser.add_argument("-e", "--email", nargs='+',
+                        help="Email address(es) to notify on changes.")
 
     args = parser.parse_args()
+    log_file = get_log_filename(args.url, args.log)
     try:
-        monitor_website(args.url, args.time, args.log, args.count, args.quiet)
+        monitor_website(args.url, args.time, args.log, args.quiet, args.email)
     except KeyboardInterrupt:
-        log_file = get_log_filename(args.url, args.log)
+        message = f"[{timestamp()}] Monitoring halted by user (^C)."
-        log_message(f"[{timestamp()}] Monitoring stopped by user (KeyboardInterrupt).", log_file, args.quiet)
+        if not args.quiet:
+            print(message)
+        with open(log_file, 'a') as f:
+            f.write(message + '\n')