checkUrls.sh

#!/bin/bash

DOMAIN="demo.publicknowledgeproject.org/ojs3/testdrive/index.php"     # Replace with your domain
JOURNAL="testdrive-journal"                                           # Replace with your journal's slug

# Initialize variables
errors=0
valid=0
redirected=0
unknown=0
count=1

# Check if the url is valid or not.
check_url() {
    url=$1
    response_code=$(curl -ks -o /dev/null -w "%{http_code}" "$url")

    case $response_code in
        # Not Found are errors
        404)
            echo "$count --> INVALID - Not Found"
            echo "      $response_code: $url"
            ((errors++))
            ;;
        # Active are valid
        200)
            echo "$count --> VALID - Active"
            echo "      $response_code: $url"
            ((valid++))
            ;;
        # Unauthorized are valid
        403)
            echo "$count --> VALID - Unauthorized "
            echo "      $response_code: $url"
            ((valid++))
            ;;
        # Permanent redirections are valid
        301 | 308)
            echo "$count --> VALID - Permanent redirection"
            echo "      $response_code: $url"
            ((redirected++))
            ((valid++))
            ;;
        # Temporal redirections are valid
        302 | 303 | 307)
            echo "$count --> VALID - Temporal redirection"
            echo "      $response_code: $url"
            ((redirected++))
            ((valid++))
            ;;
        # Anything else is Unknown and are invalid.
        *)
            echo "$count --> UNKNOWN - Need to be checked"
            echo "      $response_code: $url"
            ((unknown++))
            ((errors++))
            ;;
    esac
    ((count++))
}

# Some sample list of URLs need to be adapted to each context.
# Use one of those (setting urlsList variable) or create your own.

# No Restful and multi-tenant installation
listNoRestMulti=(
  "https://$DOMAIN"                                                             # Main page
  "https://$DOMAIN/index"                                                       # OJS site's index
  "https://$DOMAIN/$JOURNAL/about"                                              # Journal's verbs
  "https://$DOMAIN/$JOURNAL/\$\$\$call\$\$\$/page/page/css?name=stylesheet"     # $$$call$$$
  "https://$DOMAIN/$JOURNAL/api/v1/contexts/1"                                  # API in journal
  "https://$DOMAIN/$JOURNAL/oai"                                                # OAI in journal
  "https://$DOMAIN/index/install/install"                                       # Installation
)

# Restful and single-tenant installation (untested list)
listRestSingle=(
  "https://$DOMAIN"                                                             # Main page
  "https://$DOMAIN/index"                                                       # OJS site's index
  "https://$DOMAIN/$JOURNAL/about"                                              # Journal's verbs
  "https://$DOMAIN/$JOURNAL/\$\$\$call\$\$\$/page/page/css?name=stylesheet"     # $$$call$$$
  "https://$DOMAIN/$JOURNAL/api/v1/contexts/1"                                  # API in journal
  "https://$DOMAIN/$JOURNAL/oai"                                                # OAI in journal
  "https://$DOMAIN/index/install/install"                                       # Installation
  "https://$DOMAIN/admin"                                                       # Admin page
  "https://$DOMAIN/api/v1/contexts/1"                                           # API in site
  "https://$DOMAIN/oai"                                                         # OAI in site
)

urlList=''

# Select URLs list based on parameter
if [[ "$1" == "listNoRestMulti" ]]; then
    urlList=("${listNoRestMulti[@]}")
elif [[ "$1" == "listRestSingle" ]]; then
    urlList=("${listRestSingle[@]}")
else
    echo "Invalid parameter."
    echo "Please provide a valid urlList like 'listNoRestMulti', 'listRestSingle'..."
    exit 1
fi

# Iterate the selected list
for url in "${urlList[@]}"; do
    check_url "$url"
done

# Summarize and show results
echo ""
echo "SUMMARY OF YOUR URL's HEALTH:"
echo "- Active: $valid - Those urls are valid."
echo "  - Redirect: $redirected - Redirected url are usually valid, but url destination need to be add to the list and checked too."
echo "- Errors found: $errors - Errors NEED that be fixed, like notFound and other unkown codes."
echo "  - Unkown: $unknown - URLs that returned an unexpected code and need a detailed review. Considered errors."
echo ""

if [ $errors -eq 0 ]; then
  echo "RESULT: Looks like your site looks healthy"
else
  echo "RESULT: Your site fails. There are $errors errors that probably need to be fixed."
fi