我的Shell脚本中的URL URL在空格处断开

Question

#!/bin/sh

scriptname=$0   # $0 is the name of the program
verbose=no
probeonly=no

usage () {
   cat <<EOF
Usage: $scriptname [-o] [-a] [-d] [-c] [-r] [-p] [-h] [-w] movie name
   -a   Lead actor and Actress
   -c   Cast
   -d   Duration
   -h   Help
   -H   History of previous searches by the user
   -o   Overview(Actor,Actress,Ratings,Director and Plot)
   -p   Download the poster
   -r   Rating
   -w   Movies to be released this week

EOF
   exit 0
}
getUrl()
{
    url_first_part="http://www.imdb.com/find?ref_=nv_sr_fn&q="
    url_last_part="&s=all"
    url="${url_first_part}${OPTARG}${url_last_part}"
    echo "${url}"
    content=$(wget ${url} -q -O ~/movie_list) #to save the page source in a local file called movie_list
    count=$(grep -Po -m 1 "(?<=td class=\"primary_photo\"> <a href=\").*?(?=\s*ref_=fn_al_tt_1\")" ~/movie_list|head -1) 
    part_to_be_added="ref_=fn_al_tt_1"
    final_url="www.imdb.com$count$part_to_be_added"
    echo $final_url
    rm ~/movie_list
}
print()
{
    echo "$movie"
}

unset flag #this is to unset the value of flag if it had any value previously
while getopts ":a:c:d:hHo:p:r:w" opt
do
    case $opt in
        a)
          movie="${OPTARG}"
          #echo "-a was triggered, Parameter: $OPTARG" >&2
          getUrl
          flag='1' #we set flag to 1 so as to check if an option was pased or not.Since it skips the getopt part if no option was passed
          ;;
        c)
              getUrl
          #echo "-c was triggered, Parameter: $OPTARG" >&2
          flag='1'
          ;;
            d)
              getUrl
          #echo "-d was triggered, Parameter: $OPTARG" >&2
              flag='1'
          ;;
            h)usage
              flag='1'
          ;;
            H)
              getUrl
          #echo "-H was triggered, Parameter: $OPTARG" >&2
              flag='1'
          ;;
            o)
              getUrl
          #echo "-o was triggered, Parameter: $OPTARG" >&2
              flag='1'
          ;;
            p)
              getUrl
          #echo "-p was triggered, Parameter: $OPTARG" >&2
              flag='1'
          ;;
            r)
              getUrl
          #echo "-r was triggered, Parameter: $OPTARG" >&2
              flag='1'
          ;;
            w)
              getUrl
          echo "-w was triggered, Parameter: $OPTARG" >&2
              flag='1'
          ;;
        \?)
          echo "Invalid option: -$OPTARG" >&2
              flag='1'
          usage
          ;;
        :)
          echo "Option -$OPTARG requires an argument." >&2
              usage
          flag='1'
          ;;
      esac
done
if [ -z "$flag" ] #Here we check if an option was passed or not
then
    echo "No options were passed"
    usage
fi

由于某种原因，每当我输入一个引号中包含多个单词的选项时，我的URL就会拆分。如果我输入了加勒比海盗信息，即使该URL打印为http://www.imdb.com/find？ ref_ = nv_sr_fn＆q = pirates of carribean＆s = all。wget访问的网站是http://www.imdb.com/find?ref_=nv_sr_fn&q=pirates 。 我是unix的新手，请帮忙解决这个问题。我无法调试。

Answer 1

您几乎保护了每个字符串以防空格，但这里没有：

content=$(wget ${url} -q -O ~/movie_list)

应该：

content=$(wget "${url}" -q -O ~/movie_list)

顺便说一句，您宁愿使用/tmp作为临时文件（而不是主目录）

Answer 2

有一些错误。 在脚本级别，您需要在${url}周围加上引号：

content=$(wget "${url}" -q -O ~/movie_list) #to save the page source in a local file called movie_list

这样可以防止空格导致URL作为多个参数发送给wget 。

可以与上述方法结合使用的另一种方法是正确地形成URL。 用+或%20替换这些空格：

url="${url_first_part}$(perl -pe 'chomp;s/ /+/g; s/([^A-Za-z0-9\+-])/sprintf("%%%02X", ord($1))/seg;' <<<"${OPTARG}" )${url_last_part}"