From a1fc1ba9508ffe3f495459b0750f1637b28fab57 Mon Sep 17 00:00:00 2001
From: Marc Wrobel <marc.wrobel@gmail.com>
Date: Mon, 1 Aug 2022 19:20:22 +0200
Subject: [PATCH] Initial version of the script

Code copied from https://github.com/marcwrobel/jbanking/blob/2030a902dcd8c396a29520482cf2cbe94d2428a6/bin/check-links.
---
 README.md  |  7 ++++++-
 checklinks | 29 +++++++++++++++++++++++++++++
 2 files changed, 35 insertions(+), 1 deletion(-)
 create mode 100755 checklinks

diff --git a/README.md b/README.md
index ce385c5..409fa48 100644
--- a/README.md
+++ b/README.md
@@ -1,2 +1,7 @@
 # checklinks
-Helps check and fix links in a codebase.
+
+A project codebase often contains a lot of external links. checklinks is an utility that helps checking and fixing those links.
+
+```shell
+path/to/checklinks <directory-to-check>
+```
diff --git a/checklinks b/checklinks
new file mode 100755
index 0000000..2f37c5a
--- /dev/null
+++ b/checklinks
@@ -0,0 +1,29 @@
+#!/usr/bin/env bash
+
+USER_AGENT='Mozilla/5.0 (X11; Linux x86_64; rv:91.0) Gecko/20100101 Firefox/91.0'
+RETRY=1
+RETRY_DELAY=10
+TIMEOUT=3 # seconds
+
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+[ ! -d "$1" ] && echo "'$1'  is not a directory" && exit 1
+
+# Links are processed in a random order to reduce the risk of being blacklisted and temporarily blocked
+for url in $(grep -RioEh 'https?://[^][{} "`<>),*$|\\]*[^][{} "`<>),*$|\\.:'"'"']' | grep -vE 'https?://(localhost|[0-9]+|.+:[0-9]+|example|host|somehost|nohost|link|acme.org|foo.com|application.com|[^/]+.example.com|registry.npmjs.org|apache.org/xml/features|java.sun.com/xml/ns|javax.xml.XMLConstants)' | sort | uniq | sort -R); do
+  # we could use --head, but it is not always supported...
+  status=$(curl -o /dev/null --silent --connect-timeout "$TIMEOUT" --retry $RETRY --retry-delay $RETRY_DELAY --user-agent "$USER_AGENT" --location --write-out '%{http_code}' "$url")
+
+  if [ "$status" = "200" ]; then
+    if [[ $url =~ "http://" ]]; then
+      echo -e "${BLUE}$url ($status)${NC}"
+    else
+      echo -e "${GREEN}$url ($status)${NC}"
+    fi
+  else
+    echo -e "${RED}$url ($status)${NC}"
+  fi
+done