joshsmith01 · September 4, 2019 18:00 · Sep 4, 2019
diff --git a/findstring.sh b/findstring.sh
@@ -0,0 +1,61 @@
+#!/bin/bash
+# -----------  SET COLORS  -----------
+COLOR_RED=$'\e[31m'
+COLOR_CYAN=$'\e[36m'
+COLOR_YELLOW=$'\e[33m'
+COLOR_GREEN=$'\e[32m'
+COLOR_RESET=$'\e[0m'
+COLOR_HIGHLIGHT_FOUND=$'\e[0;30;42m'
+#DOMAIN=https://www.efficiencyofmovement.com
+
+
+echo "Let's search a website for a specfici string of text"
+read -rp "Enter the full URL: " DOMAIN
+echo "Cool, I have the URL of: $DOMAIN"
+read -rp "Now input the string you want to search for: " STRING
+
+
+spin()
+{
+  spinner="/|\\-/|\\-"
+  while :
+  do
+    for i in `seq 0 7`
+    do
+      echo -n "${spinner:$i:1}"
+      echo -en "\010"
+      sleep 1
+    done
+  done
+}
+
+spin &
+SPIN_PID=$!
+trap 'kill -9 $SPIN_PID' $(seq 0 15)
+## get all the working 200 URLs from a website
+wget --spider --force-html -r "$DOMAIN" 2>&1 |
+  grep '^--' | awk '{ print $3 }' |
+  grep -E -v '\.(css|js|json|map|xml|png|gif|jpg|jpeg|JPG|bmp|txt|pdf|webmanifest)(\?.*)?$' |
+  grep -E -v '\?(p|replytocom)=' |
+  grep -E -v '\/wp-content\/uploads\/' |
+  grep -E -v '\/feed\/' |
+  grep -E -v '\/category\/' |
+  grep -E -v '\/tag\/' |
+  grep -E -v '\/page\/' |
+  grep -E -v '\/widgets.php$' |
+  grep -E -v '\/wp-json\/' |
+  grep -E -v '\/xmlrpc' |
+  grep -E '[/]$' |
+  sort -u \
+    > log.txt
+
+#input="log.txt"
+while IFS= read -r line; do
+
+  if wget -q "$line" -O - | grep --color=always -ni -C 1 "$STRING"; then
+    echo ${COLOR_RESET}${COLOR_GREEN}"Found (a) match(es) on: ${COLOR_HIGHLIGHT_FOUND}$line"${COLOR_RESET}
+  else
+    echo ${COLOR_RESET}${COLOR_CYAN}Nothing found on: "$line"${COLOR_RESET}
+  fi
+done < log.txt
+kill -9 $SPIN_PID