This is a simpler pure bash/ksh version without the substring logic. Stated differently the other pure shell solutions reparsed the string to get each character (using parameter substitution ${#str} for the lenght and ${str:$i:1} to discover each character). The below method does just one loop over the string to process each character. It is the difference between O(n^2) and O(n). In this answer: https://stackoverflow.com/a/40833433/1344599 Thunderbeef saw ~150x speed improvement on a large text file. This solution is also a shorter oneliner:

while IFS='' read -n 1 c ; do [[ "$c" =~ [A-Za-z0-9.~_-] ]] && printf "$c" || printf '%%%02X' "'$c" ; done

在函数中，你可以使用stdin或形参:

function urlen_stdin {
  while IFS='' read -n 1 c ; do [[ "$c" =~ [A-Za-z0-9.~_-] ]] && printf "$c" || printf '%%%02X' "'$c" ; done
}
function urlen_param {
  printf '%s' "$1" | while IFS='' read -n 1 c ; do [[ "$c" =~ [A-Za-z0-9.~_-] ]] && printf "$c" || printf '%%%02X' "'$c" ; done
}
function urlen_here {
  while IFS='' read -n 1 c ; do [[ "$c" =~ [A-Za-z0-9.~_-] ]] && printf "$c" || printf '%%%02X' "'$c" ; done <<< "$1"
}

#usage: 
echo -n 'hello !@#$%^&*()[]:;{}\/|-_=+.,? world' | urlen_stdin
urlen_param 'hello !@#$%^&*()[]:;{}\/|-_=+.,? world'
urlen_here 'hello !@#$%^&*()[]:;{}\/|-_=+.,? world'
# all methods render:
hello%20%21%40%23%24%25%5E%26%2A%28%29%5B%5D%3A%3B%7B%7D%2F%7C-_%3D%2B.%2C%3F%20world

解释:

IFS= "使空格像普通字符一样 Read -n 1一次读取1个字符 [[=~]]是一个正则表达式比较。如果字符匹配，则遵循&&路径，否则遵循||路径 printf '%%%02X'打印一个%和字符作为零填充长度为2的十六进制代码

我发现在python中可读性更好:

encoded_value=$(python3 -c "import urllib.parse; print urllib.parse.quote('''$value''')")

三重'确保单引号的值不会有伤害。Urllib在标准库中。它的工作，例如这个疯狂的(现实世界)url:

"http://www.rai.it/dl/audio/" "1264165523944Ho servito il re d'Inghilterra - Puntata 7

Uni2ascii非常方便:

$ echo -ne '你好世界' | uni2ascii -aJ
%E4%BD%A0%E5%A5%BD%E4%B8%96%E7%95%8C

Note

这些函数不是用来编码URL的数据，而是用来编码URL。 将url以每行一个的方式放入文件中。

#!/bin/dash

replaceUnicodes () { # $1=input/output file
    if ! mv -f "$1" "$1".tmp 2>/dev/null; then return 1; fi
    output="$1" awk '
    function hexValue(chr) {
        if(chr=="0") return 0; if(chr=="1") return 1; if(chr=="2") return 2; if(chr=="3") return 3; if(chr=="4") return 4; if(chr=="5") return 5;
        if(chr=="6") return 6; if(chr=="7") return 7; if(chr=="8") return 8; if(chr=="9") return 9; if(chr=="A") return 10;
        if(chr=="B") return 11; if(chr=="C") return 12; if(chr=="D") return 13; if(chr=="E") return 14; return 15 }
    function hexToDecimal(str,  value,i,inc) {
        str=toupper(str); value=and(hexValue(substr(str,length(str),1)),15); inc=1;
        for(i=length(str)-1;i>0;i--) {
            value+=lshift(hexValue(substr(str,i,1)),4*inc++)
        } return value }
    function toDecimal(str, value,i) {
        for(i=1;i<=length(str);i++) {
            value=(value*10)+substr(str,i,1)
        } return value }
    function to32BE(high,low) {
        # return 0x10000+((high-0xD800)*0x400)+(low-0xDC00) }
        return lshift((high-0xD800),10)+(low-0xDC00)+0x10000 }
    function toUTF8(value) {
        if(value<0x80) { 
            return sprintf("%%%02X",value)
        } else if(value>0xFFFF) {
            return sprintf("%%%02X%%%02X%%%02X%%%02X",or(0xF0,and(rshift(value,18),0x07)),or(0x80,and(rshift(value,12),0x3F)),or(0x80,and(rshift(value,6),0x3F)),or(0x80,and(rshift(value,0),0x3F)))
        } else if(value>0x07FF) {
            return sprintf("%%%02X%%%02X%%%02X",or(0xE0,and(rshift(value,12),0x0F)),or(0x80,and(rshift(value,6),0x3F)),or(0x80,and(rshift(value,0),0x3F)))
        } else { return sprintf("%%%02X%%%02X",or(0xC0,and(rshift(value,6),0x1F)),or(0x80,and(rshift(value,0),0x3F))) }
    }
    function trap(str) { sub(/^\\+/,"\\",str); return str }
    function esc(str) { gsub(/\\/,"\\\\",str); return str }
    BEGIN { output=ENVIRON["output"] }
    {
        finalStr=""; while(match($0,/[\\]+u[0-9a-fA-F]{4}/)) {
            p=substr($0,RSTART,RLENGTH); num=hexToDecimal(substr(p,RLENGTH-3,4));
            bfrStr=substr($0,1,RSTART-1); $0=substr($0,RSTART+RLENGTH,length($0)-(RSTART+RLENGTH-1));
            if(surrogate) {
                surrogate=0;
                if(RSTART!=1 || num<0xD800 || (num>0xDBFF && num<0xDC00) || num>0xDFFF) {
                    finalStr=sprintf("%s%s%s%s",finalStr,trap(highP),bfrStr,toUTF8(num))
                } else if(num>0xD7FF && num<0xDC00) {
                    surrogate=1; high=num; finalStr=sprintf("%s%s",finalStr,trap(highP))
                } else { finalStr=sprintf("%s%s",finalStr,toUTF8(to32BE(high,num))) }
            } else if(num>0xD7FF && num<0xDC00) {
                surrogate=1; highP=p; high=num; finalStr=sprintf("%s%s",finalStr,bfrStr)
            } else { finalStr=sprintf("%s%s%s",finalStr,bfrStr,toUTF8(num)) }
        } finalStr=sprintf("%s%s",finalStr,$0); $0=finalStr

        while(match($0,/[\\]+U[0-9a-fA-F]{8}/)) {
            str=substr($0,RSTART,RLENGTH); gsub(esc(str),toUTF8(hexToDecimal(substr(str,RLENGTH-7,8))),$0)
        }
        while(match($0,/[\\]*&#[xX][0-9a-fA-F]{1,8};/)) {
            str=substr($0,RSTART,RLENGTH); idx=index(str,"#");
            gsub(esc(str),toUTF8(hexToDecimal(substr(str,idx+2,RLENGTH-idx-2))),$0)
        }
        while(match($0,/[\\]*&#[0-9]{1,10};/)) {
            str=substr($0,RSTART,RLENGTH); idx=index(str,"#");
            gsub(esc(str),toUTF8(toDecimal(substr(str,idx+1,RLENGTH-idx-1))),$0)
        }
        printf("%s\n",$0) > output
    }' "$1".tmp
    rm -f "$1".tmp
}

replaceHtmlEntities () { # $1=input/output file
    if ! mv -f "$1" "$1".tmp 2>/dev/null; then return 1; fi
    sed 's/%3[aA]/:/g; s/%2[fF]/\//g; s/&quot;/%22/g; s/&lt;/%3C/g; s/&gt;/%3E/g; s/&nbsp;/%A0/g; s/&cent;/%A2/g; s/&pound;/%A3/g; s/&yen;/%A5/g; s/&copy;/%A9/g; s/&reg;/%AE/g; s/&amp;/\&/g; s/\\*\//\//g' "$1".tmp > "$1"
    rm -f "$1".tmp
}


# "od -v -A n -t u1 -w99999999"
# "hexdump -v -e \47/1 \42%d \42\47"
# Reminder :: Do not encode (, ), [, and ].
toUTF8Encoded () { # $1=input/output file
    if ! mv -f "$1" "$1".tmp 2>/dev/null; then return 1; fi
    if [ -s "$1".tmp ]; then
        # od -A n -t u1 -w99999999 "$1".tmp | \
        hexdump -v -e '/1 "%d "' "$1".tmp | \
        output="$1" awk 'function hexDigit(chr) { if((chr>47 && chr<58) || (chr>64 && chr<71) || (chr>96 && chr<103)) return 1; return 0 }
        BEGIN { output=ENVIRON["output"] }
        {   for(i=1;i<=NF;i++) {
                flushed=0; c=$(i);
                if(c==13) { if($(i+1)==10) i++; printf("%s\n",url) > output; url=""; flushed=1
                } else if(c==10) { printf("%s\n",url) > output; url=""; flushed=1
                } else if(c==37) {
                    if(hexDigit($(i+1)) && hexDigit($(i+2))) {
                        url=sprintf("%s%%%c%c",url,$(i+1),$(i+2)); i+=2
                    } else { url=sprintf("%s%%25",url) }
                } else if(c>32 && c<127 && c!=34 && c!=39 && c!=96 && c!=60 && c!=62) {
                    url=sprintf("%s%c",url,c)
                } else { url=sprintf("%s%%%02X",url,c) }
            } if(!flushed) printf("%s\n",url) > output
        }'
    fi
    rm -f "$1".tmp
}

调用replacecodes () -> replacemlentities () --> toUTF8Encoded()

使用curl——data-urlencode;来自man curl:

它发布数据，类似于其他——data选项，不同的是它执行url编码。为了与cgi兼容，<data>部分应该以名称开头，后面跟着分隔符和内容规范。

使用示例:

curl \
    --data-urlencode "paramName=value" \
    --data-urlencode "secondParam=value" \
    http://example.com

有关更多信息，请参阅手册页。

这需要curl 7.18.0或更新版本(发布于2008年1月)。使用curl -V来检查您拥有的版本。

你也可以对查询字符串进行编码:

curl --get \
    --data-urlencode "p1=value 1" \
    --data-urlencode "p2=value 2" \
    http://example.com
    # http://example.com?p1=value%201&p2=value%202

这是节点版本:

uriencode() {
  node -p "encodeURIComponent('${1//\'/\\\'}')"
}