fetchAllGenomesByTaxon.sh

#!/bin/sh

set -u

# usage: fetchAllGenomesByTaxon.sh Daphnia_pulex Lepeophtheirus_salmonis
# either use quotes or underscores
# This is just to show how to define the taxon list inline if you don't want to read taxa from the command line
#TAXLIST=("Daphnia pulex" "Drosophila melanogaster" "Anopheles gambiae" "Pediculus humanus"
#"Ixodes scapularis" "Apis mellifera"  "Bombyx mori")
#TAXLIST=("Strigamia maritima")
WGET_OPTS="-c --random-wait -t 40 -a wget.log"

TAXLIST=$@
for TAX in "${TAXLIST[@]}" ; do
echo getting genome for: $TAX
#mkdir -p "$TAX" # if you want to create a directory
#cd "$TAX"
   GENOME=$(esearch -db genome -query "${TAX}"[Organism:exp] |
       efetch -format docsum | tee "${TAX}.genome.esearch.docsum")
   ACC=`echo $GENOME | xtract -pattern DocumentSummary  -element Assembly_Accession`
   NAME=`echo $GENOME |  xtract -pattern DocumentSummary -element Assembly_Name`
   echo authoritative genome: $ACC $NAME
   RESULT=$(esearch -db assembly -query "$ACC" |
       efetch -format docsum | tee "${TAX}.assembly.esearch.docsum")
   FTPP=`echo $RESULT | xtract -pattern DocumentSummary  -element FtpPath_GenBank`
   TAXID=`echo $RESULT | xtract -pattern DocumentSummary  -element Taxid`
   echo FtpPath: $FTPP
   BASENAME=`basename $FTPP`
   FTPPATHG=$FTPP/$BASENAME'_genomic.fna.gz'
   FTPPATHP=$FTPP/$BASENAME'_protein.faa.gz'
   echo Downloading $FTPPATHG ...

   ## get genome data
   wget $WGET_OPTS $FTPPATHG
   BASENAME=`basename $FTPPATHG`
   gunzip -f $BASENAME
   echo Downloading $FTPPATHP ...
   ## get protein data
   wget $WGET_OPTS $FTPPATHP # this may throw an error
   if [ "$?" -eq "0" ] ; then
     BASENAME=`basename $FTPPATHP`
     gunzip -f $BASENAME
   fi
   # cd ..
done