istidy fetches and parses a URL and provides a report on HTML errors and warnings.

istidy

#!/bin/bash

# istidy will use the tidy program to fetch and parse a URL and provide a
# report on errors and warnings found.
#
# Usage: istidy <URL>
# Example: istidy http://google.com/
# 
# This script requires wget and tidy
# (apt-get install wget tidy)

: ${WGET=wget}
: ${TIDY=tidy}

HASERROR=false

red() {
    if [ -t 0 ]; then
        printf "\E[31m" 
    fi
}
op() {
    if [ -t 0 ]; then
        printf "\E[39;49m"
    fi
}

# Assert required programs
assertRequirements() {
    # Detect if wget is available
    which $WGET > /dev/null
    if [ $? -eq 1 ]; then
        red; echo "Error: $WGET not installed. Please install first."; op
        HASERROR=true
    fi

    # Detect if tidy is available
    which $TIDY > /dev/null
    if [ $? -eq 1 ]; then
        red; echo "Error: $TIDY not installed. Please install first."; op
        HASERROR=true
    fi

    if [ $HASERROR == true ]; then
        echo "Goodbye."
        exit 1;
    fi
}

# Print usage
printUsage() {
    echo "Usage: `basename $0` <URL>"
    echo "This will fetch the HTML from the specified URL and display a report of errors from html tidy"
}

# Handle --help arg
if [ -n "$1" -a "$1" == "--help" ]; then
    printUsage
    exit 1
fi

if [ -z $1 ]; then
    printUsage
    exit 2
fi

assertRequirements

$WGET -q -O - "$1" | $TIDY -e 2>&1 | less -FX