Script to validate URLs

Author: shoumikhin

scripts/check_urls.sh

@@ -7,24 +7,38 @@
 
 set -euo pipefail
 
+status=0
 green='\e[1;32m'; red='\e[1;31m'; cyan='\e[1;36m'; yellow='\e[1;33m'; reset='\e[0m'
-last= rc=0
-while IFS=: read -r f u; do
-  if [ "$f" != "$last" ]; then
-    [ -n "$last" ] && echo
-    printf '%s:\n' "$f"
-    last=$f
+last_filepath=
+
+while IFS=: read -r filepath url; do
+  if [ "$filepath" != "$last_filepath" ]; then
+    printf '\n%s:\n' "$filepath"
+    last_filepath=$filepath
+  fi
+  code=$(curl -gsLm30 -o /dev/null -w "%{http_code}" -I "$url") || code=000
+  if [ "$code" -ge 400 ]; then
+    code=$(curl -gsLm30 -o /dev/null -w "%{http_code}" -r 0-0 -A "Mozilla/5.0" "$url") || code=000
   fi
-  if curl --fail -s -m10 -o /dev/null "$u"; then
-    printf " ${green}[OK]${reset}  ${cyan}%s${reset}\n" "$u"
+  if [ "$code" -ge 200 ] && [ "$code" -lt 400 ]; then
+    printf "${green}%s${reset} ${cyan}%s${reset}\n" "$code" "$url"
   else
-    printf "${red}[FAIL]${reset} ${yellow}%s${reset}\n" "$u"
-    rc=1
+    printf "${red}%s${reset} ${yellow}%s${reset}\n" "$code" "$url" >&2
+    status=1
   fi
 done < <(
-  git --no-pager grep --no-color -I -o -E 'https?://[^[:space:]<>\")\{]+' \
+  git --no-pager grep --no-color -I -o -E \
+    'https?://[^[:space:]<>\")\{\(\$]+' \
     -- '*' \
-    ':(exclude).*' ':(exclude)**/.*' ':(exclude)**/*.lock' ':(exclude)**/third-party/**' \
-  | sed 's/[."\’]$//'
+    ':(exclude).*' \
+    ':(exclude)**/.*' \
+    ':(exclude)**/*.lock' \
+    ':(exclude)**/*.svg' \
+    ':(exclude)**/*.xml' \
+    ':(exclude)**/third-party/**' \
+  | sed 's/[[:punct:]]*$//' \
+  | grep -Ev '://(0\.0\.0\.0|127\.0\.0\.1|localhost)([:/])' \
+  || true
 )
-exit $rc
+
+exit $status