「Linux」Linux下根据CET听力文件关键字和lcr时间对mp3进行剪辑分割

 

1. 脚本内容：

#!/bin/bash
# Author: linkscue
# Version: 0.2
# Usage: ./mp3cutsh $input $output
# To use before: sudo apt-get install poc-streamer

if [[ $# != 2 ]]; then
    #statements
    echo 'mp3cutsh $input $output'
    exit 1
fi


# 相关的变量，截取文件名、输出路径
input=${1%.*}
output=${2%/}
input_mp3=${input}.mp3
input_lrc=${input}.lrc

#创建目录
mkdir $output &> /dev/null

# 截取conversation短对话11~18题
keywork1="[bB]egin [wW]ith [tT]he"
keywork2="[cC]onversation [oO]ne"
infomation="8 short conversations"
part_name="conversation"
output_base=$output/$part_name
# 相关计算
start=$(sed -n "/$keywork1/p" $input_lrc | awk '{print substr($0,2,8)}' -)
end=$(sed -n "/$keywork2/p" $input_lrc | awk '{print substr($0,2,8)}' -)
start_t=$(echo $start | sed -e 's/\./+/' - )0
end_t=$(echo $end | sed -e 's/\./+/' - )0
if [[ $start ]]; then #只在非空时执行操作
    #statements
    echo "I: Cutting from [$start] to [$end] -> $output_base.mp3"
    mp3cut -o $output_base.mp3 -t $start_t-$end_t $input_mp3 &> /dev/null
    sed -n "/$start/,/$end/p" $input_lrc > ${output_base}.lrc 
    
fi

# 截取conversation 1
keywork1="[cC]onversation [oO]ne"
keywork2="[cC]onversation [tT]wo"
infomation="conversation one"
part_name="conversation1"
output_base=$output/$part_name
# 相关计算
start=$(sed -n "/$keywork1/p" $input_lrc | awk '{print substr($0,2,8)}' -)
end=$(sed -n "/$keywork2/p" $input_lrc | awk '{print substr($0,2,8)}' -)
start_t=$(echo $start | sed -e 's/\./+/' - )0
end_t=$(echo $end | sed -e 's/\./+/' - )0
if [[ $start ]]; then #只在非空时执行操作
    #statements
    echo "I: Cutting from [$start] to [$end] -> $output_base.mp3"
    mp3cut -o $output_base.mp3 -t $start_t-$end_t $input_mp3 &> /dev/null
    sed -n "/$start/,/$end/p" $input_lrc > ${output_base}.lrc 
    
fi

# 截取conversation 2
keywork1="[cC]onversation [tT]wo"
keywork2="[sS]ection [bB]"
infomation="conversation two"
part_name="conversation2"
output_base=$output/$part_name
# 相关计算
start=$(sed -n "/$keywork1/p" $input_lrc | awk '{print substr($0,2,8)}' -)
end=$(sed -n "/$keywork2/p" $input_lrc | awk '{print substr($0,2,8)}' -)
start_t=$(echo $start | sed -e 's/\./+/' - )0
end_t=$(echo $end | sed -e 's/\./+/' - )0
if [[ $start ]]; then #只在非空时执行操作
    #statements
    echo "I: Cutting from [$start] to [$end] -> $output_base.mp3"
    mp3cut -o $output_base.mp3 -t $start_t-$end_t $input_mp3 &> /dev/null
    sed -n "/$start/,/$end/p" $input_lrc > ${output_base}.lrc 
    
fi

# 截取passage 1
keywork1="[pP]assage [oO]ne"
keywork2="[pP]assage [tT]wo"
infomation="passage one"
part_name="passage1"
output_base=$output/$part_name
# 相关计算
start=$(sed -n "/$keywork1/p" $input_lrc | awk '{print substr($0,2,8)}' -)
end=$(sed -n "/$keywork2/p" $input_lrc | awk '{print substr($0,2,8)}' -)
start_t=$(echo $start | sed -e 's/\./+/' - )0
end_t=$(echo $end | sed -e 's/\./+/' - )0
if [[ $start ]]; then #只在非空时执行操作
    #statements
    echo "I: Cutting from [$start] to [$end] -> $output_base.mp3"
    mp3cut -o $output_base.mp3 -t $start_t-$end_t $input_mp3 &> /dev/null
    sed -n "/$start/,/$end/p" $input_lrc > ${output_base}.lrc
    
fi

# 截取passage 2
keywork1="[pP]assage [tT]wo"
keywork2="Passage [tT]hree"
infomation="passage two"
part_name="passage2"
output_base=$output/$part_name
# 相关计算
start=$(sed -n "/$keywork1/p" $input_lrc | awk '{print substr($0,2,8)}' -)
end=$(sed -n "/$keywork2/p" $input_lrc | awk '{print substr($0,2,8)}' -)
start_t=$(echo $start | sed -e 's/\./+/' - )0
end_t=$(echo $end | sed -e 's/\./+/' - )0
if [[ $start ]]; then #只在非空时执行操作
    #statements
    echo "I: Cutting from [$start] to [$end] -> $output_base.mp3"
    mp3cut -o $output_base.mp3 -t $start_t-$end_t $input_mp3  &> /dev/null
    sed -n "/$start/,/$end/p" $input_lrc > ${output_base}.lrc
    
fi

# 截取passage 3
keywork1="Passage [tT]hree"
keywork2="[sS]ection [cC]"
infomation="passage three"
part_name="passage3"
output_base=$output/$part_name
# 相关计算
start=$(sed -n "/$keywork1/p" $input_lrc | awk '{print substr($0,2,8)}' -)
end=$(sed -n "/$keywork2/p" $input_lrc | awk '{print substr($0,2,8)}' -)
start_t=$(echo $start | sed -e 's/\./+/' - )0
end_t=$(echo $end | sed -e 's/\./+/' - )0
if [[ $start ]]; then #只在非空时执行操作
    #statements
    echo "I: Cutting from [$start] to [$end] -> $output_base.mp3"
    mp3cut -o $output_base.mp3 -t $start_t-$end_t $input_mp3 &> /dev/null
    sed -n "/$start/,/$end/p" $input_lrc > ${output_base}.lrc
    
fi

# 截取听写部分
keywork1="[nN]ow [lL]isten [tT]o [tT]he [pP]assage"
keywork2="[tT]his [iI]s [tT]he [eE]nd"
infomation="Section C"
part_name="sectionc"
output_base=$output/$part_name
# 相关计算
start=$(sed -n "/$keywork1/p" $input_lrc | awk '{print substr($0,2,8)}' -)
end=$(sed -n "/$keywork2/p" $input_lrc | awk '{print substr($0,2,8)}' -)
start_t=$(echo $start | sed -e 's/\./+/' - )0
end_t=$(echo $end | sed -e 's/\./+/' - )0
if [[ $start ]]; then #只在非空时执行操作
    #statements
    echo "I: Cutting from [$start] to [$end] -> $output_base.mp3"
    mp3cut -o $output_base.mp3 -t $start_t-$end_t $input_mp3 &> /dev/null
    sed -n "/$start/,/$end/p" $input_lrc > ${output_base}.lrc
    
fi

echo "I: All Done!"

# this is the old version code
#output_mp3=$1.mp3
#output_lrc=$1.lrc
#start=$(echo $2 | sed -e 's/\./+/' - )0
#end=$(echo $3 | sed -e 's/\./+/' - )0
#input_mp3=$4.mp3
#input_lrc=$4.lrc
#mp3cut -o $output_mp3 -t $start-$end $input_mp3
#sed -n "/$2/,/$3/p" $input_lrc > $output_lrc
# 转换文本的编码格式
#iconv -f gb18030 -t utf-8 $output_lrc $output_lrc
# cat $output_lrc

2. 输出结果展示

scue@Link:cet$ ./mp3cutsh 2012年6月.mp3 cet2012
I: Cutting from [02:51.74] to [07:37.54] -> cet2012/conversation.mp3
I: Cutting from [07:37.54] to [10:39.12] -> cet2012/conversation1.mp3
I: Cutting from [10:39.12] to [13:35.27] -> cet2012/conversation2.mp3
I: Cutting from [14:08.62] to [16:54.10] -> cet2012/passage1.mp3
I: Cutting from [16:54.10] to [19:33.92] -> cet2012/passage2.mp3
I: Cutting from [19:33.92] to [22:57.88] -> cet2012/passage3.mp3
I: Cutting from [23:50.05] to [32:27.48] -> cet2012/sectionc.mp3
I: All Done