Code
2023-09-09 06:00:02

如何为curl命令urlencode数据?

我试图写一个bash脚本测试，需要一个参数，并通过curl发送到网站。我需要url编码的值，以确保特殊字符被正确处理。最好的方法是什么?

这是我到目前为止的基本脚本:

#!/bin/bash
host=${1:?'bad host'}
value=$2
shift
shift
curl -v -d "param=${value}" http://${host}/somepath $@

当前回答

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()

2021-05-08 15:02:38

其他回答

有什么能比javascript更好地解析url呢?

node -p "encodeURIComponent('$url')"
2017-04-12 17:42:15

Ruby，为了完整性

value="$(ruby -r cgi -e 'puts CGI.escape(ARGV[0])' "$2")"
2012-06-19 23:45:26 
url=$(echo "$1" | sed -e 's/%/%25/g' -e 's/ /%20/g' -e 's/!/%21/g' -e 's/"/%22/g' -e 's/#/%23/g' -e 's/\$/%24/g' -e 's/\&/%26/g' -e 's/'\''/%27/g' -e 's/(/%28/g' -e 's/)/%29/g' -e 's/\*/%2a/g' -e 's/+/%2b/g' -e 's/,/%2c/g' -e 's/-/%2d/g' -e 's/\./%2e/g' -e 's/\//%2f/g' -e 's/:/%3a/g' -e 's/;/%3b/g' -e 's//%3e/g' -e 's/?/%3f/g' -e 's/@/%40/g' -e 's/\[/%5b/g' -e 's/\\/%5c/g' -e 's/\]/%5d/g' -e 's/\^/%5e/g' -e 's/_/%5f/g' -e 's/`/%60/g' -e 's/{/%7b/g' -e 's/|/%7c/g' -e 's/}/%7d/g' -e 's/~/%7e/g')

这将对$1中的字符串进行编码，并将其输出到$url中。尽管你不需要把它放在var中。顺便说一句，没有包括sed for选项卡，认为它会把它变成空格

2011-01-11 12:51:29

如果不想依赖Perl，也可以使用sed。这有点混乱，因为每个角色都必须单独转义。用以下内容创建一个文件，并将其命名为urlencode.sed

s/%/%25/g
s/ /%20/g
s/ /%09/g
s/!/%21/g
s/"/%22/g
s/#/%23/g
s/\$/%24/g
s/\&/%26/g
s/'\''/%27/g
s/(/%28/g
s/)/%29/g
s/\*/%2a/g
s/+/%2b/g
s/,/%2c/g
s/-/%2d/g
s/\./%2e/g
s/\//%2f/g
s/:/%3a/g
s/;/%3b/g
s//%3e/g
s/?/%3f/g
s/@/%40/g
s/\[/%5b/g
s/\\/%5c/g
s/\]/%5d/g
s/\^/%5e/g
s/_/%5f/g
s/`/%60/g
s/{/%7b/g
s/|/%7c/g
s/}/%7d/g
s/~/%7e/g
s/      /%09/g

要使用它，请执行以下操作。

STR1=$(echo "https://www.example.com/change&$ ^this to?%checkthe@-functionality" | cut -d\? -f1)
STR2=$(echo "https://www.example.com/change&$ ^this to?%checkthe@-functionality" | cut -d\? -f2)
OUT2=$(echo "$STR2" | sed -f urlencode.sed)
echo "$STR1?$OUT2"

这将把字符串分成需要编码的部分，而没问题的部分，编码需要它的部分，然后缝合在一起。

为了方便起见，你可以把它放在sh脚本中，也许让它带一个参数来编码，把它放在你的路径上，然后你可以调用:

urlencode https://www.exxample.com?isThisFun=HellNo

源

2008-11-17 19:42:51

以下是基于奥威尔的回答，但解决了多字节 通过设置LC_ALL=C (vte.sh的一个技巧)在评论中提到的错误。 我把它写成了函数PROMPT_COMMAND的形式，因为 我就是这么用的。

print_path_url() {
  local LC_ALL=C
  local string="$PWD"
  local strlen=${#string}
  local encoded=""
  local pos c o

  for (( pos=0 ; pos<strlen ; pos++ )); do
     c=${string:$pos:1}
     case "$c" in
        [-_.~a-zA-Z0-9/] ) o="${c}" ;;
        * )               printf -v o '%%%02x' "'$c"
     esac
     encoded+="${o}"
  done
  printf "\033]7;file://%s%s\007" "${HOSTNAME:-}" "${encoded}"
}
2018-01-03 04:56:48

推荐文章

aliyun

最新文章

标签

2024 code 京ICP备15047053号-1