obsmirror: add logging

1 files changed, 58 insertions, 48 deletions

diff --git a/obsmirror.sh/obsmirror.sh b/obsmirror.sh/obsmirror.sh
index 3f5539c..fc69b4a 100755
--- a/obsmirror.sh/obsmirror.sh
+++ b/obsmirror.sh/obsmirror.sh
@@ -24,57 +24,67 @@
 #    binaries: curl httrack grep head tr sed awk chmod chown find rm ln
 #    user: obsmirror
 
-# learn site
-inurl="http://download.opensuse.org/repositories/home:/bgstack15/Debian_Unstable"
-workdir=/tmp/obs-stage
-outdir=/var/www/mirror/obs
-thisuser=obsmirror
+logfile="/var/log/obsmirror/obsmirror.$( date "+%FT%H%M%S" ).log"
+{
+   test "${DEBUG:-NONE}" = "FULL" && set -x
+   inurl="http://download.opensuse.org/repositories/home:/bgstack15/Debian_Unstable"
+   workdir=/tmp/obs-stage
+   outdir=/var/www/mirror/obs
+   thisuser=obsmirror
+   echo "logfile=${logfile}"
 
-mkdir -p "${workdir}" ; chmod "0711" "${workdir}" ; chown "${thisuser}:$( id -Gn obsmirror )" "${workdir}" 
-cd "${workdir}"
-# get page contents
-step1="$( curl -s -L "${inurl}/all" )"
-# get first listed package
-step2="$( echo "${step1}" | grep --color=always -oE 'href="[a-zA-Z0-9_.+\-]+\.deb"' | head -n1 | grep -oE '".*"' | tr -d '"' )"
-# get full url to a package
-step3="$( curl -s -I "${inurl}/all/${step2}" | awk '/Location:/ {print $2}' )"
-# get directory of the mirror to save down
-step4="$( echo "${step3}" | sed -r -e "s/all\/${step2}//;" -e 's/\s*$//;' )"
-echo "TARGET URL: ${step4}"
-test -z "${DRYRUN}" && {
-   # have to skip the orig.tar.gz files because they are large and slow down the sync process significantly.
-   echo su "${thisuser}" -c "httrack \"${step4}\" -*.orig.t* --mirror --update -s0 -r3 -%e0 \"${workdir}\""
-   time su "${thisuser}" -c "httrack ${step4} -*.orig.t* --mirror --update -s0 -r3 -%e0 ${workdir}"
-}
-# -s0 ignore robots.txt
-# -r3 only go down 3 links
-# -%e0 follow 0 links to external sites
+   mkdir -p "${workdir}" ; chmod "0711" "${workdir}" ; chown "${thisuser}:$( id -Gn obsmirror )" "${workdir}" 
+   cd "${workdir}"
+   # get page contents
+   step1="$( curl -s -L "${inurl}/all" )"
+   # get first listed package
+   step2="$( echo "${step1}" | grep --color=always -oE 'href="[a-zA-Z0-9_.+\-]+\.deb"' | head -n1 | grep -oE '".*"' | tr -d '"' )"
+   # get full url to a package
+   step3="$( curl -s -I "${inurl}/all/${step2}" | awk '/Location:/ {print $2}' )"
+   # get directory of the mirror to save down
+   step4="$( echo "${step3}" | sed -r -e "s/all\/${step2}//;" -e 's/\s*$//;' )"
+   # get domain of full url
+   domainname="$( echo "${step3}" | grep -oE '(ht|f)tps?:\/\/[^\/]+\/' | cut -d'/' -f3 )"
+   echo "TARGET URL: ${step4}"
+   test -z "${DRYRUN}" && {
+      # clean workdir of specific domain name in use right now.
+      echo su "${thisuser}" -c "rm -rf \"${workdir:-SOMETHING}/${domainname:-SOMETHING}\""
+      su "${thisuser}" -c "rm -rf \"${workdir:-SOMETHING}/${domainname:-SOMETHING}\"*"
+      # have to skip the orig.tar.gz files because they are large and slow down the sync process significantly.
+      echo su "${thisuser}" -c "httrack \"${step4}\" -*.orig.t* -v --mirror --update -s0 -r3 -%e0 \"${workdir}\""
+      time su "${thisuser}" -c "httrack ${step4} -*.orig.t* -v --mirror --update -s0 -r3 -%e0 ${workdir}"
+   }
+   # -s0 ignore robots.txt
+   # -r3 only go down 3 links
+   # -%e0 follow 0 links to external sites
 
-# find most recent directory of that level
-levelcount="$(( $( printf "%s" "${inurl}" | tr -dc '/' | wc -c ) - 1 ))"
-subdir="$( find "${workdir}" -mindepth "${levelcount}" -maxdepth "${levelcount}" -type d -name 'Debian_Unstable' -printf '%T@ %p\n' | sort -n -k1 | head -n1 | awk '{print $2}' )"
+   # find most recent directory of that level
+   levelcount="$(( $( printf "%s" "${inurl}" | tr -dc '/' | wc -c ) - 1 ))"
+   subdir="$( find "${workdir}" -mindepth "${levelcount}" -maxdepth "${levelcount}" -type d -name 'Debian_Unstable' -printf '%T@ %p\n' | sort -n -k1 | head -n1 | awk '{print $2}' )"
 
-# if the work directory actually synced
-if test -n "${subdir}" ;
-then
-   printf "%s " "DIRECTORY SIZE:"
-   du -sxBM "${subdir:-.}"
-   mkdir -p "$( dirname "${outdir}" )"
-   # get current target of symlink
-   current_target="$( find "${outdir}" -maxdepth 0 -type l -printf '%l\n' )"
-
-   # if the current link is pointing to a different directory than this subdir
-   if test "${current_target}" != "${subdir}" ;
+   # if the work directory actually synced
+   if test -n "${subdir}" ;
    then
-      # then replace it with a link to this one
-      test -L "${outdir}" && unlink "${outdir}"
-      echo ln -sf "${subdir}" "${outdir}"
-      ln -sf "${subdir}" "${outdir}"
+
+      printf "%s " "DIRECTORY SIZE:"
+      du -sxBM "${subdir:-.}"
+      mkdir -p "$( dirname "${outdir}" )"
+      # get current target of symlink
+      current_target="$( find "${outdir}" -maxdepth 0 -type l -printf '%l\n' )"
+
+      # if the current link is pointing to a different directory than this subdir
+      if test "${current_target}" != "${subdir}" ;
+      then
+         # then replace it with a link to this one
+         test -L "${outdir}" && unlink "${outdir}"
+         echo ln -sf "${subdir}" "${outdir}"
+         ln -sf "${subdir}" "${outdir}"
+      fi
+
+   else
+      echo "ERROR: No subdir found, so cannot update the symlink."
    fi
-   
-else
-   echo "ERROR: No subdir found, so cannot update the symlink."
-fi
 
-# disable the index.html with all the httrack comments and original site links
-find "${workdir}" -iname '*index.html' -exec rm {} +
+   # disable the index.html with all the httrack comments and original site links
+   find "${workdir}" -iname '*index.html' -exec rm {} +
+} 2>&1 | tee -a "${logfile}"