SpringerLink CSV to BIB converter

csv2bib.sh

#!/bin/bash
# csv2bib.sh
#
# SpringerLink CSV to BIB
#
# Author: Djalma Jr.
# Site: djalmajr.com
#
# v0.3.0: Updated download link
# v0.2.0: Added command line options
# v0.1.0: First version
#

name=$(basename "$0")

usage="
Usage: $name [OPTIONS]

[OPTIONS]
  -i, --input     The CSV input file
  -o, --output    The BIB output file
  -k, --keep      Keep downloaded files
  -h, --help      Show this help screen
  -V, --version   Show the program version
"

while test -n "$1"; do
  case "$1" in
    -i | --input)
      shift
      csv="$1"
    ;;
    -o | --output)
      shift
      bib="$1"
    ;;
    -k | --keep)
      keep=1
    ;;
    -h | --help)
      echo "$usage"
      exit 0
    ;;
    -V | --version)
      echo -n $(basename "$0")
      # Extracts the version from script header
      grep "^# v" "$0" | head -1 | cut -d : -f 1 | tr -d \#
      exit 0
    ;;
    *)
      if test -n "$1"; then
        echo Invalid option: $1
        exit 1
      fi
    ;;
  esac
  shift # Option processed, remove from queue
done

if [[ -z "$csv" && -z "$bib" ]]; then
  echo "$usage"
  exit 1
fi

if [[ -z "$csv" || -z "$bib" ]]; then
  echo "Missing input or output file"
  exit 1
fi

results=$(cat $csv | grep -Eo "(http|https)://[a-zA-Z0-9./?=_-]*")
total=$(echo "$results" | wc -l)
tmpdir="tmp-${name//\.sh//}"

mkdir -p $tmpdir

echo ">>> Downloading files... ";

while ((i++)); read -r url; do
  # file="${url//\.com\//\.com\/export-citation\/}.bib"
  # code=$(echo "$url" | sed -r -e 's/([sS]?\d[-_.\/]?)+/\1/')
  code=$(echo "$url" | sed -r -e 's/.*(article|chapter|referenceworkentry)\/(.*)/\2/')
  file="https://citation-needed.springer.com/v2/references/$code?format=bibtex&flavour=citation"
  echo "[$i/$total] Downloading $file"
  wget -q -N "$file" -P $tmpdir
done < <(echo "$results")

echo ">>> Creating $bib file..."
cat $tmpdir/* > $bib

if [ -z "$keep" ]; then
  echo ">>> Cleaning up..."
  rm -rf $tmpdir
fi

echo ">>> Done!"