{"id":328,"date":"2008-07-25T21:19:32","date_gmt":"2008-07-25T13:19:32","guid":{"rendered":"http:\/\/www.liangliang.org.cn\/blog\/?p=328"},"modified":"2008-07-25T21:19:32","modified_gmt":"2008-07-25T13:19:32","slug":"%e6%ba%90%e7%a0%81baidu%e4%b8%8b%e8%bd%bd%e5%99%a8%e3%80%82","status":"publish","type":"post","link":"https:\/\/www.liangliang.org.cn\/?p=328","title":{"rendered":"\u6e90\u7801baidu\u4e0b\u8f7d\u5668\u3002"},"content":{"rendered":"

#!\/bin\/bash
\n#Copyright (c) 2006 bones7456 (bones7456@gmail.com)
\n#License: GPLv2
\n#\u975e\u5e38\u611f\u8c22ubuntu\u793e\u533a\u548coneleaf\u8001\u5144
\n#\u5f3a\u70c8\u5efa\u8bae\u5b89\u88c5axel\uff08\u591a\u7ebf\u7a0b\u4e0b\u8f7d\u5de5\u5177\uff09\u548cmid3v2\uff08\u5305\u542b\u5728python-mutagen\u91cc\uff0c\u7528\u4e8e\u4fee\u6539\u6b4c\u66f2\u7684id3\u4fe1\u606f\uff09<\/p>\n

#mp3\u7684\u5730\u5740
\nSOURCE=\"http:\/\/list.mp3.baidu.com\/list\/newhits.html\"
\n#SOURCE=\"http:\/\/list.mp3.baidu.com\/topso\/mp3topsong.html\" \u6539\u6210\u8fd9\u4e2a\u5730\u5740\u53ef\u4ee5\u4e0b\u8f7d\u6b4c\u66f2top500<\/p>\n

#\u4fdd\u5b58mp3\u7684\u76ee\u5f55
\nSAVE=\"${HOME}\/baidump3\"<\/p>\n

#\u4e0b\u8f7d\u91cd\u8bd5\u6b21\u6570
\nTRYCOUNT=2<\/p>\n

#\u7528axel\u4e0b\u8f7d\u65f6\u7684\u7ebf\u7a0b\u6570
\nAXELNUM=7<\/p>\n

#\u4e34\u65f6\u76ee\u5f55
\nTMP=\"\/tmp\/baidump3-${USER}\"<\/p>\n

#\u662f\u5426\u9700\u8981\u6682\u505c
\nPAUSE=0<\/p>\n

if [ x`which axel` = x\"\" ];then
\nPAUSE=1
\ncat << EOF\n\u60a8\u7684\u7cfb\u7edf\u4e2d\u6ca1\u6709\u5b89\u88c5axel\u591a\u7ebf\u7a0b\u4e0b\u8f7d\u5de5\u5177\uff0c\u8fd9\u5c06\u5bfc\u81f4\u53ea\u80fd\u4f7f\u7528wget\u8fdb\u884c\u5355\u7ebf\u7a0b\u4e0b\u8f7d\uff0c\u5c06\u4f1a\u5f71\u54cd\u4e0b\u8f7d\u901f\u5ea6\u3002\n\u5982\u679c\u662fubuntu\u7528\u6237\uff0c\u53ef\u4ee5\u76f4\u63a5\u4f7f\u7528 sudo apt-get install axel \u8fdb\u884c\u5b89\u88c5\uff0c\u5176\u4ed6\u7cfb\u7edf\u8bf7\u8bbf\u95eeaxel\u4e3b\u9875\uff1ahttp:\/\/wilmer.gaast.net\/main.php\/axel.html \u8fdb\u884c\u4e0b\u8f7d\u3001\u5b89\u88c5\u3002\n\nEOF\nfi\nif [ x`which mid3v2` = x\"\" ];then\nPAUSE=1\ncat << EOF\n\u60a8\u7684\u7cfb\u7edf\u4e2d\u6ca1\u6709\u5b89\u88c5mid3v2\u5de5\u5177\uff0c\u4f7f\u7528\u8be5\u5de5\u5177\u53ef\u4ee5\u4fee\u6539mp3\u6b4c\u66f2\u7684\u6807\u7b7e\u4fe1\u606f(\u5982\u6b4c\u624b\u3001\u6b4c\u540d\u7b49)\uff0c\u5e76\u53bb\u6389\u53ef\u80fd\u5305\u542b\u4e8e\u5176\u4e2d\u7684\u5e7f\u544a\u4fe1\u606f\u3002\n\u5982\u679c\u662fubuntu\u7528\u6237\uff0c\u53ef\u4ee5\u76f4\u63a5\u4f7f\u7528 sudo apt-get install python-mutagen \u8fdb\u884c\u5b89\u88c5\uff0c\u5176\u4ed6\u7cfb\u7edf\u8bf7\u8bbf\u95ee\u5176\u4e3b\u9875\uff1ahttp:\/\/www.sacredchao.net\/quodlibet\/wiki\/Development\/Mutagen \u8fdb\u884c\u4e0b\u8f7d\u3001\u5b89\u88c5\u3002\n\nEOF\nfi\nif [ \"$PAUSE\" = 1 ];then\n\techo \"\u662f\u5426\u7ee7\u7eed(y|n)\uff1f\"\n\tread KEYVAR\n\tcase \"$KEYVAR\" in\n\t\"Y\" | \"y\" )\n\techo \u7565\u8fc7\u3002\n\t;;\n\t* )\n\texit 0\n\t;;\n\tesac\nfi\n\n#\u521b\u5efa\u4e0b\u8f7d\u76ee\u5f55\nif [ ! -d \"${SAVE}\" ];then\n mkdir -p \"${SAVE}\"\nfi\n\n#\u521b\u5efa\u4e34\u65f6\u4e0b\u8f7d\u76ee\u5f55\nif [ -d \"${TMP}\" ];then\n\trm -rf \"${TMP}\"\nfi\n mkdir -p \"${TMP}\"\n\necho \"\u5f00\u59cb\u4e0b\u8f7d\u767e\u5ea6\u6700\u65b0100\u9996\u6b4c\u66f2\u5217\u8868\"\nwget -O ${TMP}\/mp3.html ${SOURCE}\necho \"\u4e0b\u8f7d\u767e\u5ea6\u6700\u65b0100\u9996\u6b4c\u66f2\u5217\u8868\u5b8c\u6210\u3002\"\n\n#\u8f6c\u6362\u7f51\u9875\u7f16\u7801\niconv -f gbk -t utf8 ${TMP}\/mp3.html |\\\n\ngrep \" href=\\\"http:\/\/mp3.baidu.com\/m\" |\\\n\n#\u5c06mp3list.txt\u6240\u6709\u5f00\u5934\u7684\u7a7a\u683c\u53bb\u6389\nsed -e 's\/ *\/\/' |\\\n\n#\u5c06mp3list.txt\u6240\u6709\u5f00\u5934\u7684tab\u53bb\u6389\nsed -e 's\/\\t*\/\/' |\\\n\n#\u5c06mp3list.txt\u6240\u6709\u5168\u89d2\u7a7a\u683c\u53bb\u6389\nsed -e 's\/\u3000\/\/g' |\\\n\n#\u5c06\u6240\u6709\u7684\u56de\u8f66\u7b26\u53bb\u6389\nsed ':a;N;$!ba;s\/\\n\/,\/g' |\\\n\n#\u5728td>,\u540e\u9762\u52a0\u4e0a\u56de\u8f66\u7b26\uff0c\u4e00\u884c\u8868\u793a\u4e00\u4e2amp3\u6587\u4ef6\u3002
\nsed -e 's\/,<\/p>\n,\/td>\\n\/g' |\\<\/p>\n

#\u5220\u9664<\/p>\n\n <\/td>\n\n

sed -e 's\/<\/p>\n\/\/g' |\\
\nsed -e 's\/<\/p>\n\/\/g' |\\
\nsed -e 's\/<\\\/td>\/\/g' |\\
\nsed -e 's\/<\/p>\n

\/\/g' |\\
\nsed -e 's\/<\\\/p>\/\/g' |\\
\nsed -e 's\/\/\/g' |\\<\/p>\n

#\u5220\u9664<\/a>...\"_blank\">
\nsed -e 's\/<\\\/A>\\\/\/\u3001\/g' |\\
\nsed -e 's\/<\\\/A>\/<\\\/a>\/g' |\\
\nsed -e 's\/<\\\/a>.*_blank>\/-\/g' |\\
\n#sed -e 's\/<\\\/a>.*_blank\">\/-\/g' |\\
\n#\u5220\u9664)
\nsed -e 's\/<\\\/a>)\/<\\\/a>\/g' |\\
\n#\u5220\u9664\u6587\u4ef6\u540d\u672b\u5c3e\u7684tab
\nsed -e 's\/\\t<\\\/a>\/<\\\/a>\/g' |\\
\n#\u5220\u9664&
\nsed -e 's\/\\&\\;\/\\\/\/g' >${TMP}\/mp3list.txt<\/p>\n

#\u5f97\u5230\uff1aBaby ,Baby tell me-\u738b\u5fc3\u51cc<\/a><\/p>\n

#\u53d6\u5f97\u884c\u53f7\uff0c\u5faa\u73af
\nline=$(awk 'END{print NR}' ${TMP}\/mp3list.txt)
\ni=1;
\nwhile((i<=line));do\n downed=0;\n mpline=`awk 'NR=='\"$i\"'' ${TMP}\/mp3list.txt`\n url=`echo $mpline | sed -e 's\/\/\/g' | sed -e 's\/.*_blank>\/\/g' | sed -e 's\/<\\\/b>\/\/g' |sed -e 's\/\/\/g' |\\
\n sed -e 's\/<\\\/a>\/\/g' | sed -e 's\/\\\/\/-\/g' | sed -e 's\/:\/-\/g' | sed -e 's\/\"\/'\\''\/g' | cat`
\n title=`echo $name | sed -e 's\/-.*\/\/g'`<\/p>\n

#\u68c0\u67e5\u662f\u5426\u5df2\u7ecf\u4e0b\u8f7d\u8fc7\u8fd9\u9996\u6b4c\uff0c\u5982\u679c\u4e0b\u8f7d\u8fc7\uff0c\u653e\u5f03
\n if [ -e \"${SAVE}\/${name}.mp3\" ] || [ -e \"${SAVE}\/${name}.wma\" ]; then
\n echo -e \"\\e[1;6m\\e[1;31m\u53d1\u73b0 ${name} \u4e0b\u8f7d\u8fc7\uff0c\u5ffd\u7565\uff0c\u7ee7\u7eed\u4e0b\u4e00\u9996\u3002\\e[1;6m\\e[00m\"
\n ((i++))
\n continue;
\n fi<\/p>\n

echo \"\u5f00\u59cb\u901a\u8fc7 $url \u4e0b\u8f7d $name\";
\n wget -O ${TMP}\/down.html $url
\n echo \"\u83b7\u53d6 $name \u4e0b\u8f7d\u5217\u8868\u5b8c\u6210\u3002\";<\/p>\n

#down.txt\u4e3a\u6709\u6548\u7684\u4e0b\u8f7d\u5730\u5740
\n iconv -f gbk -t utf8 -c ${TMP}\/down.html | grep \"onclick=\\\"return ow(event,this)\\\"\" |\\
\n sed -e 's\/.* ${TMP}\/down.txt<\/p>\n

#size.txt\u4e3a\u6709\u6548\u7684\u4e0b\u8f7d\u6587\u4ef6\u5927\u5c0f
\n iconv -f gbk -t utf8 -c ${TMP}\/down.html | grep \"M<\\\/td>\" |\\
\n sed -e 's\/<\/p>\n\/\/g' | sed -e 's\/ M<\\\/td>\/\/g' > ${TMP}\/size.txt<\/p>\n

#down.txt\u4e0esize.txt\u5408\u5e76\u800c\u5728\u7684down_size.txt\u6587\u4ef6\u4e2d\u5b57\u6bb5\u4e4b\u95f4\u4ee5\"`\"\u4f5c\u4e3a\u5206\u9694\u7b26
\n paste -d '`' ${TMP}\/size.txt ${TMP}\/down.txt > ${TMP}\/down_size.txt<\/p>\n

#\u6392\u5e8f
\n sort -n -r ${TMP}\/down_size.txt > ${TMP}\/down_size_sort.txt<\/p>\n

#\u53bb\u6389\u540e\u9762\u7684\u5c3a\u5bf8
\n sed 's\/.*`\/\/' ${TMP}\/down_size_sort.txt > ${TMP}\/temp.txt<\/p>\n

##### \u6790\u53d6\u51famp3 \u7684\u4e0b\u8f7d\u5730\u5740\u6216 wma\u7684\u4e0b\u8f7d\u5730\u5740 ##############
\n grep -i \"word=mp3\" ${TMP}\/temp.txt | grep \"$title\" > ${TMP}\/down_mp3.txt
\n grep -i \"word=wma\" ${TMP}\/temp.txt | grep \"$title\" > ${TMP}\/down_wma.txt<\/p>\n

downline_mp3=$(awk 'END{print NR}' ${TMP}\/down_mp3.txt);
\n downline_wma=$(awk 'END{print NR}' ${TMP}\/down_wma.txt);
\n echo -e \"\\e[1;6m\\e[1;31m\u53d1\u73b0 ${downline_mp3} \u4e2a\u540d\u4e3a ${name}.mp3 \u4e0b\u8f7d\u5730\u5740\u3002\\e[1;6m\\e[00m\"
\n echo -e \"\\e[1;6m\\e[1;31m\u53d1\u73b0 ${downline_wma} \u4e2a\u540d\u4e3a ${name}.wma \u4e0b\u8f7d\u5730\u5740\u3002\\e[1;6m\\e[00m\"
\n # \u521d\u59cb\u5316\u8ba1\u6570\u5668
\n j=1;
\n # \u4f18\u5148\u4e0b\u8f7dmp3\u683c\u5f0f\u7684\u6b4c\u66f2
\n while((j<=downline_mp3)); do\n mp3=`awk 'NR=='\"$j\"'' ${TMP}\/down_mp3.txt | sed -e 's\/ \/\\\\ \/g'`\n echo -e \"\\e[1;6m\\e[1;31m\u6b63\u5728\u4e0b\u8f7d${name}.mp3\\e[1;6m\\e[00m\"\n #echo -e \"\\e[1;6m\\e[1;31m\u4e2d\u8f6c\u9875\u9762\u5730\u5740\u4e3a${mp3}\\e[1;6m\\e[00m\"\n wget -O \"${TMP}\/transit.html\" \"$mp3\"\n realURL=`iconv -f gbk -t utf8 -c ${TMP}\/transit.html | grep \"\n\n

  • \" | sed 's\/.*href=\"\/\/' | sed 's\/\" target=\"_blank\">.*\/\/'`
    \n #echo -e \"\\e[1;6m\\e[1;31m\u771f\u5b9e\u4e0b\u8f7d\u5730\u5740\u4e3a${realURL}\\e[1;6m\\e[00m\"
    \n if [ x`which axel` != x\"\" ];then
    \n\t axel -n $AXELNUM -a -o \"${TMP}\/${name}.mp3\" \"${realURL}\"
    \n\t else
    \n\t #wget\u592a\u6162\u4e86\u3002\u4f46\u662f\u5982\u679c\u6ca1\u6709\u5b89\u88c5axel,\u53ef\u4ee5\u628a\u4e0a\u9762\u4e00\u884c\u6ce8\u91ca\u6389\uff0c\u7528\u4e0b\u9762\u4e00\u884c\u4ee3\u66ff
    \n wget -c --tries=$TRYCOUNT $realURL -O \"${TMP}\/${name}.mp3\"
    \n fi
    \n if [ \"$?\" = 0 ]; then
    \n if [ `file -ib \"${TMP}\/${name}.mp3\" | sed -e 's\/\\\/.*\/\/g'` = \"audio\" ]; then
    \n\t if [ x`which mid3v2` != x\"\" ];then
    \n\t\t\t\ttitle=`echo $name | sed -e 's\/-.*\/\/g'`
    \n\t\t\t\tartist=`echo $name | sed -e 's\/.*-\/\/g' | sed -e 's\/.mp3\/\/g' | sed -e 's\/.wma\/\/g'`
    \n\t\t\t\tmid3v2 -D \"${TMP}\/${name}.mp3\"
    \n\t\t\t\tmid3v2 -t \"${title}\" -a \"${artist}\" \"${TMP}\/${name}.mp3\"
    \n\t\t\t fi
    \n mv \"${TMP}\/${name}.mp3\" \"${SAVE}\/${name}.mp3\"
    \n downed=1;
    \n break;
    \n else
    \n echo -e \"\\e[1;6m\\e[1;31m\u4e0b\u8f7d ${name}.mp3 \u6587\u4ef6\u65e0\u6548\uff0c\u6b63\u5728\u5220\u9664\u91cd\u65b0\u4e0b\u8f7d\\e[1;6m\\e[00m\"
    \n rm \"${TMP}\/${name}.mp3\";
    \n ((j++))
    \n fi
    \n else
    \n echo -e \"\\e[1;6m\\e[1;31m\u4e0b\u8f7d ${name}.mp3 \u6587\u4ef6\u65e0\u6548\uff0c\u6b63\u5728\u5220\u9664\u91cd\u65b0\u4e0b\u8f7d\\e[1;6m\\e[00m\"
    \n rm \"${TMP}\/${name}.mp3\";
    \n ((j++))
    \n fi
    \n done<\/p>\n

    #\u5982\u679c\u4e0b\u8f7d\u6210\u529f\u7ee7\u7eed\u4e0b\u5176\u4f59\u7684\u6b4c
    \n #continue\u7528\u4e8e\u8df3\u8fc7\u5faa\u73af\u4f53\u4e2d\u7684\u540e\u7eed\u547d\u4ee4
    \n if [ \"$downed\" = 1 ] ; then
    \n ((i++))
    \n echo -e \"\\e[1;7m\\e[1;41m\u4e0b\u8f7d $name \u6210\u529f\\e[1;7m\\e[00m\"
    \n continue;
    \n fi<\/p>\n

    # \u5982\u679c\u6ca1\u6709mp3\u683c\u5f0f\u7684\u5219\u4e0b\u8f7dwma\u683c\u5f0f\u7684\u6b4c
    \n j=1;
    \n while((j<=downline_wma)); do\n wma=`awk 'NR=='\"$j\"'' ${TMP}\/down_wma.txt`\n echo -e \"\\e[1;6m\\e[1;31m\u6b63\u5728\u4e0b\u8f7d${name}.wma\\e[1;6m\\e[00m\"\n\n #echo -e \"\\e[1;6m\\e[1;31m\u4e2d\u8f6c\u9875\u9762\u5730\u5740\u4e3a${mp3}\\e[1;6m\\e[00m\"\n wget -O \"${TMP}\/transit.html\" \"$wma\"\n realURL=`iconv -f gbk -t utf8 -c ${TMP}\/transit.html | grep \"\n\n

  • \" | sed 's\/.*href=\"\/\/' | sed 's\/\" target=\"_blank\">.*\/\/'`
    \n #echo -e \"\\e[1;6m\\e[1;31m\u771f\u5b9e\u4e0b\u8f7d\u5730\u5740\u4e3a${realURL}\\e[1;6m\\e[00m\"
    \n if [ x`which axel` != x\"\" ];then
    \n\t axel -n $AXELNUM -a -o \"${TMP}\/${name}.wma\" \"${realURL}\"
    \n\t else
    \n\t #wget\u592a\u6162\u4e86\u3002\u4f46\u662f\u5982\u679c\u6ca1\u6709\u5b89\u88c5axel,\u53ef\u4ee5\u628a\u4e0a\u9762\u4e00\u884c\u6ce8\u91ca\u6389\uff0c\u7528\u4e0b\u9762\u4e00\u884c\u4ee3\u66ff
    \n wget -c --tries=$TRYCOUNT $realURL -O \"${TMP}\/${name}.wma\"
    \n fi
    \n if [ \"$?\" = 0 ]; then
    \n if [ `file -ib \"${TMP}\/${name}.wma\" | sed -e 's\/\\\/.*\/\/g'` = \"application\" ]; then
    \n\t\t\t#title=`echo $name | sed -e 's\/-.*\/\/g'`
    \n\t\t\t#artist=`echo $name | sed -e 's\/.*-\/\/g' | sed -e 's\/.mp3\/\/g' | sed -e 's\/.wma\/\/g'`
    \n\t\t\t#mid3v2 -D \"${TMP}\/${name}.wma\"
    \n\t\t\t#mid3v2 -t \"${title}\" -a \"${artist}\" \"${TMP}\/${name}.wma\"
    \n mv \"${TMP}\/${name}.wma\" \"${SAVE}\/${name}.wma\"
    \n downed=1;
    \n break;
    \n else
    \n echo -e \"\\e[1;6m\\e[1;31m\u4e0b\u8f7d ${name}.wma \u6587\u4ef6\u65e0\u6548\uff0c\u6b63\u5728\u5220\u9664\u91cd\u65b0\u4e0b\u8f7d\\e[1;6m\\e[00m\"
    \n rm \"${TMP}\/${name}.wma\";
    \n ((j++))
    \n fi
    \n else
    \n echo -e \"\\e[1;6m\\e[1;31m\u4e0b\u8f7d ${name}.wma \u6587\u4ef6\u65e0\u6548\uff0c\u6b63\u5728\u5220\u9664\u91cd\u65b0\u4e0b\u8f7d\\e[1;6m\\e[00m\"
    \n rm \"${TMP}\/${name}.wma\";
    \n ((j++))
    \n fi
    \n done<\/p>\n

    ((i++))
    \n if [ \"$downed\" = 1 ] ; then
    \n echo -e \"\\e[1;7m\\e[1;41m\u4e0b\u8f7d $name \u6210\u529f\\e[1;7m\\e[00m\"
    \n else
    \n echo -e \"\\e[1;7m\\e[1;41m\u4e0b\u8f7d $name \u5931\u8d25\\e[1;7m\\e[00m\"
    \n fi
    \ndone
    \nrm -fr ${TMP}
    \nexit 0 <\/p>\n","protected":false},"excerpt":{"rendered":"

    #!\/bin\/bash #Copyright (c) 2006 bones7456 (bones7456@gmail.com) #License: GPLv2 #\u975e\u5e38\u611f\u8c22ubuntu\u793e\u533a\u548conelea...<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[35],"tags":[],"class_list":["post-328","post","type-post","status-publish","format-standard","hentry","category-35"],"jetpack_featured_media_url":"","_links":{"self":[{"href":"https:\/\/www.liangliang.org.cn\/index.php?rest_route=\/wp\/v2\/posts\/328","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.liangliang.org.cn\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.liangliang.org.cn\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.liangliang.org.cn\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.liangliang.org.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=328"}],"version-history":[{"count":0,"href":"https:\/\/www.liangliang.org.cn\/index.php?rest_route=\/wp\/v2\/posts\/328\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.liangliang.org.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=328"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.liangliang.org.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=328"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.liangliang.org.cn\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=328"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}