Parse URL in shell script

Question

I have url like:

sftp://user@host.net/some/random/path

I want to extract user, host and path from this string. Any part can be random lengt

Answer 1

I did further parsing, expanding the solution given by @Shirkrin:

#!/bin/bash

parse_url() {
    local query1 query2 path1 path2

    # extract the protocol
    proto="$(echo $1 | grep :// | sed -e's,^\(.*://\).*,\1,g')"

    if [[ ! -z $proto ]] ; then
            # remove the protocol
            url="$(echo ${1/$proto/})"

            # extract the user (if any)
            login="$(echo $url | grep @ | cut -d@ -f1)"

            # extract the host
            host="$(echo ${url/$login@/} | cut -d/ -f1)"

            # by request - try to extract the port
            port="$(echo $host | sed -e 's,^.*:,:,g' -e 's,.*:\([0-9]*\).*,\1,g' -e 's,[^0-9],,g')"

            # extract the uri (if any)
            resource="/$(echo $url | grep / | cut -d/ -f2-)"
    else
            url=""
            login=""
            host=""
            port=""
            resource=$1
    fi

    # extract the path (if any)
    path1="$(echo $resource | grep ? | cut -d? -f1 )"
    path2="$(echo $resource | grep \# | cut -d# -f1 )"
    path=$path1
    if [[ -z $path ]] ; then path=$path2 ; fi
    if [[ -z $path ]] ; then path=$resource ; fi

    # extract the query (if any)
    query1="$(echo $resource | grep ? | cut -d? -f2-)"
    query2="$(echo $query1 | grep \# | cut -d\# -f1 )"
    query=$query2
    if [[ -z $query ]] ; then query=$query1 ; fi

    # extract the fragment (if any)
    fragment="$(echo $resource | grep \# | cut -d\# -f2 )"

    echo "url: $url"
    echo "   proto: $proto"
    echo "   login: $login"
    echo "    host: $host"
    echo "    port: $port"
    echo "resource: $resource"
    echo "    path: $path"
    echo "   query: $query"
    echo "fragment: $fragment"
    echo ""
}

parse_url "http://login:password@example.com:8080/one/more/dir/file.exe?a=sth&b=sth#anchor_fragment"
parse_url "https://example.com/one/more/dir/file.exe#anchor_fragment"
parse_url "http://login:password@example.com:8080/one/more/dir/file.exe#anchor_fragment"
parse_url "ftp://user@example.com:8080/one/more/dir/file.exe?a=sth&b=sth"
parse_url "/one/more/dir/file.exe"
parse_url "file.exe"
parse_url "file.exe#anchor"

Answer 2

The above, refined (added password and port parsing), and working in /bin/sh:

# extract the protocol
proto="`echo $DATABASE_URL | grep '://' | sed -e's,^\(.*://\).*,\1,g'`"
# remove the protocol
url=`echo $DATABASE_URL | sed -e s,$proto,,g`

# extract the user and password (if any)
userpass="`echo $url | grep @ | cut -d@ -f1`"
pass=`echo $userpass | grep : | cut -d: -f2`
if [ -n "$pass" ]; then
    user=`echo $userpass | grep : | cut -d: -f1`
else
    user=$userpass
fi

# extract the host -- updated
hostport=`echo $url | sed -e s,$userpass@,,g | cut -d/ -f1`
port=`echo $hostport | grep : | cut -d: -f2`
if [ -n "$port" ]; then
    host=`echo $hostport | grep : | cut -d: -f1`
else
    host=$hostport
fi

# extract the path (if any)
path="`echo $url | grep / | cut -d/ -f2-`"

Posted b/c I needed it, so I wrote it (based on @Shirkin's answer, obviously), and I figured someone else might appreciate it.