github.com/pdfcpu/pdfcpu@v0.11.1/_scripts/extractMetadataDir.sh (about)

     1  #!/bin/sh
     2  
     3  # Copyright 2018 The pdfcpu Authors.
     4  #
     5  # Licensed under the Apache License, Version 2.0 (the "License");
     6  # you may not use this file except in compliance with the License.
     7  # You may obtain a copy of the License at
     8  #
     9  #	http://www.apache.org/licenses/LICENSE-2.0
    10  #
    11  # Unless required by applicable law or agreed to in writing, software
    12  # distributed under the License is distributed on an "AS IS" BASIS,
    13  # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    14  # See the License for the specific language governing permissions and
    15  # limitations under the License.
    16  
    17  # eg: ./extractMetadataDir.sh ~/pdf/big ~/pdf/out
    18  
    19  if [ $# -ne 2 ]; then
    20      echo "usage: ./extractMetadataDir.sh inDir outDir"
    21      echo "extracts XML metadata into corresponding dirs."
    22      exit 1
    23  fi
    24  
    25  out=$2
    26  
    27  for pdf in $1/*.pdf
    28  do
    29  	
    30  	f=${pdf##*/}
    31  	#echo f = $f
    32  	
    33  	f1=${f%.*}
    34  	#echo f1 = $f1
    35  	
    36      mkdir $out/$f1
    37      cp $pdf $out/$f1
    38  
    39      pdfcpu extract -verbose -mode=meta $out/$f1/$f $out/$f1 &> $out/$f1/$f1.log
    40      if [ $? -eq 1 ]; then
    41          echo "metadata extraction error: $pdf -> $out/$f1"
    42          echo
    43  		continue
    44      else
    45          echo "metadata extraction success: $pdf -> $out/$f1"
    46      fi
    47  
    48  done