From 8af9b08921269e2bb65f36397b47fab4a1b657e1 Mon Sep 17 00:00:00 2001
From: ANDRI ANDRI <47277287+lamcodeofpwnosec@users.noreply.github.com>
Date: Mon, 21 Oct 2024 21:44:06 +0700
Subject: [PATCH] add new features

---
 README.md                      |  3 +++
 features/download_archived.sh  | 12 ++++++++++++
 features/filter_by_date.sh     | 19 +++++++++++++++++++
 features/filter_by_mimetype.sh | 15 +++++++++++++++
 features/track_changes.sh      | 15 +++++++++++++++
 features/verbose_mode.sh       | 13 +++++++++++++
 6 files changed, 77 insertions(+)
 create mode 100644 features/download_archived.sh
 create mode 100644 features/filter_by_date.sh
 create mode 100644 features/filter_by_mimetype.sh
 create mode 100644 features/track_changes.sh
 create mode 100644 features/verbose_mode.sh

diff --git a/README.md b/README.md
index a8d1a99..e0beff7 100644
--- a/README.md
+++ b/README.md
@@ -15,6 +15,9 @@ The script retrieves a list of URLs that have been archived over time, offering
  * `curl`, `sed`, and `tee` should be installed on the system (most Unix-based systems come with these tools by default).
 
 ## Steps to Install and Run
+You can now use `./wayback.sh -help` to display the help menu and description for each feature. Each feature is now modular and easy to maintain or expand.
+
+
 1. Clone or Download the Script
 ```
 git clone https://github.com/lamcodeofpwnosec/Waybash.git
diff --git a/features/download_archived.sh b/features/download_archived.sh
new file mode 100644
index 0000000..4eadde3
--- /dev/null
+++ b/features/download_archived.sh
@@ -0,0 +1,12 @@
+#!/bin/bash
+# Download Archived Pages feature
+
+echo "Enter your Domain Name:"
+read domain
+
+mkdir -p "$domain-archived-pages"
+cat "$domain.txt" | while read url; do
+    wget "http://web.archive.org/web/$url" -P "$domain-archived-pages/"
+done
+
+echo "Download complete. Archived pages are saved in the $domain-archived-pages/ folder."
diff --git a/features/filter_by_date.sh b/features/filter_by_date.sh
new file mode 100644
index 0000000..0421ffe
--- /dev/null
+++ b/features/filter_by_date.sh
@@ -0,0 +1,19 @@
+#!/bin/bash
+# Filter by Date Range feature
+# Description: Filters Wayback Machine URLs by a specific date range.
+
+echo "Enter the start date (YYYYMMDD):"
+read start_date
+echo "Enter the end date (YYYYMMDD):"
+read end_date
+
+echo "Enter your Domain Name:"
+read domain
+
+curl "http://web.archive.org/cdx/search/cdx?url=*.$domain/*&output=json&fl=original&collapse=urlkey&from=$start_date&to=$end_date" -s -k --insecure --path-as-is \
+    | sed 's/\["//g' \
+    | sed 's/"\],//g' \
+    | sort -u \
+    | tee -a "$domain-$start_date-to-$end_date.txt"
+
+echo "Crawling complete. The results are saved in $domain-$start_date-to-$end_date.txt"
diff --git a/features/filter_by_mimetype.sh b/features/filter_by_mimetype.sh
new file mode 100644
index 0000000..78a78e7
--- /dev/null
+++ b/features/filter_by_mimetype.sh
@@ -0,0 +1,15 @@
+#!/bin/bash
+# Filter by MIME Type feature
+
+echo "Enter your Domain Name:"
+read domain
+echo "Enter the MIME type to filter (e.g., text/html, image/jpeg):"
+read mime_type
+
+curl "http://web.archive.org/cdx/search/cdx?url=*.$domain/*&output=json&fl=original,mimetype&filter=!mimetype:$mime_type&collapse=urlkey" -s -k --insecure --path-as-is \
+    | sed 's/\["//g' \
+    | sed 's/"\],//g' \
+    | sort -u \
+    | tee -a "$domain_filtered_by_mime_type.txt"
+
+echo "Crawling complete. The filtered results (MIME type: $mime_type) are saved in $domain_filtered_by_mime_type.txt"
diff --git a/features/track_changes.sh b/features/track_changes.sh
new file mode 100644
index 0000000..32df48f
--- /dev/null
+++ b/features/track_changes.sh
@@ -0,0 +1,15 @@
+#!/bin/bash
+# Track URL Changes Over Time feature
+
+echo "Enter your Domain Name:"
+read domain
+echo "Enter the specific URL to track changes (e.g., /path/to/page):"
+read url_path
+
+curl "http://web.archive.org/cdx/search/cdx?url=$domain$url_path&output=json&fl=timestamp,original" -s -k --insecure --path-as-is \
+    | sed 's/\["//g' \
+    | sed 's/"\],//g' \
+    | sort -u \
+    | tee -a "$domain$url_path_change_log.txt"
+
+echo "Tracking complete. Changes to $url_path are saved in $domain$url_path_change_log.txt"
diff --git a/features/verbose_mode.sh b/features/verbose_mode.sh
new file mode 100644
index 0000000..c4ef414
--- /dev/null
+++ b/features/verbose_mode.sh
@@ -0,0 +1,13 @@
+#!/bin/bash
+# Verbose Mode feature
+
+echo "Enter your Domain Name:"
+read domain
+
+curl "http://web.archive.org/cdx/search/cdx?url=*.$domain/*&output=json&fl=original&collapse=urlkey" -v -k --insecure --path-as-is \
+    | sed 's/\["//g' \
+    | sed 's/"\],//g' \
+    | sort -u \
+    | tee -a "$domain_verbose.txt"
+
+echo "Verbose crawling complete. The results are saved in $domain_verbose.txt"