awk的helloworld

两次过滤
awk -F '"' '{print $2}' icon.txt | awk -F ',' '{print $1}'>add.txt

#!/bin/awk -f
BEGIN {
    for(i=0;i<ARGC;i++){
        printf "ARGV[%d]= %s\n",i,ARGV[i];
    }
    exit;
}

# awk -f awktest.sh aaa bbb
ARGV[0]= awk
ARGV[1]= aaa
ARGV[2]= bbb

# ./awktest.sh haha haoning gege
ARGV[0]= awk
ARGV[1]= haha
ARGV[2]= haoning
ARGV[3]= gege\


解析个log

#!/bin/sh
echo "<?xml version=¥"1.0¥" encoding=¥"GBK¥"?>" > /opt/log/local3/pms.xml;
echo "<Root>" >> /opt/log/local3/pms.xml;

grep "pms_z" /opt/log/local3/local3.log |awk '
BEGIN{indx=0;arr[0]=0;}
{
        indx++; 
        arr[indx]= $(NF-1)" "$(NF);
}
END{
        slen=asort(arr,tA);
        tmpentry="";
        if(slen>1){
        for(i=2;i<=slen;i++){
                split(tA[i],mon,"|");
                split(mon[1],monn,":");
                if(tmpentry==mon[1]){ 
                        print "                <QuoteImageID>"mon[7]"</QuoteImageID>";
                }else{
                        if(i>2){
                                print "            </QuoteImages>";
                                print "        </Images>";
                                print "    </ImageInfo>";
                        } 
                        print "    <ImageInfo>¥n        <Page>"; 
                        print "            <PageID>"monn[2]"</PageID>";
                        print "            <PageLink>"mon[2]"</PageLink>";
                        print "            <Title>"mon[3]"</Title>";
                        print "            <PublishTime>"mon[4]"</PublishTime>";
                        print "            <QuoteUser>"mon[5]"</QuoteUser>";
                        print "            <PageMatrix>"mon[6]"</PageMatrix>";
                        print "            <PageKeywords>"mon[8]"</PageKeywords>";
                        print "            <PageDescription>"mon[9]"</PageDescription>";
                        print "        </Page>";
                        print "        <Images>";
                        print "            <QuoteImages>";
                        print "                <QuoteImageID>"mon[7]"</QuoteImageID>";
                };
                tmpentry=mon[1];
        }
        print "            </QuoteImages>";
        print "        </Images>";
        print "    </ImageInfo>";
        }
}' >> /opt/log/local3/pms.xml;

grep "pms_b" /opt/log/local3/local3.log |awk '
BEGIN{
        indx=0;arr[0]=0;
}{
        indx++; 
        arr[indx]= $(NF-1)" "$(NF);
}END{
        slen=asort(arr,tA);
        tmpentry="";
        for(i=2;i<=slen;i++){
                split(tA[i],mon,"|");
                split(mon[1],monn,":");
                split(mon[7],monnn,"/");
                split(mon[7],monnnn,".");
                if(tmpentry==mon[1]){ 
                        print "                <Image>";
                        print "                    <ImageName></ImageName>";
                        print "                    <ImageFormat>"monnn[3]"</ImageFormat>";
                        print "                    <ImagePath>"mon[7]"</ImagePath>";
                        print "                    <ImageSource></ImageSource>";
                        print "                </Image>";
                }else{
                        if(i>2){
                                print "            </ReturnImages>";
                                print "        </Images>";
                                print "    </ImageInfo>";
                        } 
                        print "    <ImageInfo>¥n        <Page>"; 
                        print "            <PageID>"monn[2]"</PageID>";
                        print "            <PageLink>"mon[2]"</PageLink>";
                        print "            <Title>"mon[3]"</Title>";
                        print "            <PublishTime>"mon[4]"</PublishTime>";
                        print "            <QuoteUser>"mon[5]"</QuoteUser>";
                        print "            <PageMatrix>"mon[6]"</PageMatrix>";
                        print "            <PageKeywords>"mon[8]"</PageKeywords>";
                        print "            <PageDescription>"mon[9]"</PageDescription>";
                        print "        </Page>";
                        print "        <Images>";
                        print "            <ReturnImages>";
                        print "                <Image>";
                        print "                    <ImageName>"monnn[3]"</ImageName>";
                        print "                    <ImageFormat>"monnnn[2]"</ImageFormat>";
                        print "                    <ImagePath>"mon[7]"</ImagePath>";
                        print "                    <ImageSource></ImageSource>";
                        print "                </Image>";
                };
                tmpentry=mon[1];
        }
        print "            </ReturnImages>";
        print "        </Images>";
        print "    </ImageInfo>";
}' >> /opt/log/local3/pms.xml;

echo "</Root>" >>/opt/log/local3/pms.xml;

#/usr/bin/rsync -av --password-file=/etc/rsyncd.secrets.nieting /opt/log/local3/pms.xml  [email protected]::testpmsxml

时隔3年多，又整了一下
[code="java"]
# cat my.sh
#!/bin/sh
if [ -z "$1" ];
then
echo "please input crawl file name";
exit;
fi
grep "BigPicImg" $1 >tmp_BigPicImg.txt
awk '
BEGIN{indx=0;arr[0]=0;}
{
indx++;
arr[indx]= $0;
}
END{
for(j=1;j<length(arr);j++){
split(arr[j],monn,"\"");
split(monn[2],thisarray,",");
slen = length(thisarray);
tmpname=thisarray[1];
print "mkdir "tmpname;
for(i=2;i<=slen;i++){
print "wget -O "tmpname"/"tmpname"_big_"i-1".jpg '\''"thisarray[i]"'\''";
}
}
}' tmp_BigPicImg.txt >exe_wget.sh
rm tmp_BigPicImg.txt
#----------------------
grep "SmallPicImg" $1 >tmp_SmallPicImg.txt
awk '
BEGIN{indx=0;arr[0]=0;}
{
indx++;
arr[indx]= $0;
}
END{
for(j=1;j<length(arr);j++){
split(arr[j],monn,"\"");
split(monn[2],thisarray,",");
slen = length(thisarray);
tmpname=thisarray[1];
print "mkdir "tmpname;
for(i=2;i<=slen;i++){
print "wget -O "tmpname"/"tmpname"_small_"i-1".jpg '\''"thisarray[i]"'\''";
}
}
}' tmp_SmallPicImg.txt >>exe_wget.sh
rm tmp_SmallPicImg.txt
#--------------
grep "Download" $1 >tmp_Download.txt
awk '
BEGIN{indx=0;arr[0]=0;}
{
indx++;
arr[indx]= $0;
}
END{
for(j=1;j<length(arr);j++){
split(arr[j],monn,"\"");
split(monn[2],thisarray,",");
slen = length(thisarray);
tmpname=thisarray[1];
print "mkdir "tmpname;
for(i=2;i<=slen;i++){
print "wget -O "tmpname"/"tmpname"_apk.apk '\''"thisarray[i]"'\''";
}
}
}' tmp_Download.txt >>exe_wget.sh
rm tmp_Download.txt
chmod 700 exe_wget.sh
./exe_wget.sh >a.log
#
[/code]


[code="java"]
# cat new.sh
#!/bin/sh
if [ -z "$1" ];
then
echo "please input crawl file name";
exit;
fi
grep "IconImg" $1 >tmp_IconImg.txt
awk '
BEGIN{indx=0;arr[0]=0;}
{
indx++;
arr[indx]= $0;
}
END{
for(j=1;j<length(arr);j++){
split(arr[j],monn,"\"");
split(monn[4],thisarray,",");
slen = length(thisarray);
tmpname=thisarray[1];
tmpvarsion=thisarray[2];
tmppath="/home/7po/"tmpname"/"tmpvarsion;
print "mkdir -p "tmppath;
for(i=3;i<=slen;i++){
print "wget -P "tmppath" '\''"thisarray[i]"'\''";
}
}
}' tmp_IconImg.txt >7po_wget.sh
rm tmp_IconImg.txt
#---------------------------------
grep "PicImg" $1 >tmp_PicImg.txt
awk '
BEGIN{indx=0;arr[0]=0;}
{
indx++;
arr[indx]= $0;
}
END{
for(j=1;j<length(arr);j++){
split(arr[j],monn,"\"");
split(monn[4],thisarray,",");
slen = length(thisarray);
tmpname=thisarray[1];
tmpvarsion=thisarray[2];
tmppath="/home/7po/"tmpname"/"tmpvarsion;
print "mkdir -p "tmppath;
for(i=3;i<=slen;i++){
split(thisarray[i],thisurl,"?");
print "wget -P "tmppath" '\''"thisurl[1]"'\''";
}
}
}' tmp_PicImg.txt >>7po_wget.sh
rm tmp_PicImg.txt
#--------------------
grep "Download" $1 >tmp_Download.txt
awk '
BEGIN{indx=0;arr[0]=0;}
{
indx++;
arr[indx]= $0;
}
END{
for(j=1;j<length(arr);j++){
split(arr[j],monn,"\"");
split(monn[4],thisarray,",");
slen = length(thisarray);
tmpname=thisarray[1];
tmpvarsion=thisarray[2];
tmppath="/home/7po/"tmpname"/"tmpvarsion;
print "mkdir -p "tmppath;
for(i=3;i<=slen;i++){
print "wget -O "tmppath"/"tmpname".apk '\''"thisarray[i]"'\''";
}
}
}' tmp_Download.txt >>7po_wget.sh
rm tmp_Download.txt
#
[/code]