import_goodreads.py

#!/usr/bin/env python3
#
# Get CSV from https://www.goodreads.com/review/import

import csv
import os

# change these to match your setup
outputdir = 'YOUROUTPUTDIRECTORY'
goodreadsfile = '~/Downloads/goodreads_library_export.csv'

goodreadsdict = csv.DictReader(open(goodreadsfile))
for row in goodreadsdict:
  pub_year = row['Year Published']
  if row['Original Publication Year']:
    pub_year = row['Original Publication Year']
  outfilename = '-'.join([pub_year, row['Author l-f'], row['Title']])
  sanitizedname = ''.join([c for c in outfilename if c.isalpha() or c.isdigit() or c in '.-_ ']).strip()
  outfilepath = outputdir + sanitizedname + '.md'
  print(outfilepath)
  # Set tags based on shelves and author lastname
  tags = []
  for v in [row.pop('Exclusive Shelf'), row.pop('Bookshelves')]:
    tags += v.replace(',', '').split()
  # tagging author last name is too noisy
  #tags.append(row.pop('Author l-f').split(',')[0])
  content = '''---
created: {}
---
https://www.goodreads.com/book/show/{}

Title: {}

Author: {}

Date Read: {}

Tags: {}

'''.format(row.pop('Date Added').replace('/', '-'),
           row.pop('Book Id'),
           row.pop('Title'),
           row.pop('Author'),
           row.pop('Date Read').replace('/', '-'),
           ' '.join(set(['#{}'.format(x) for x in tags])))
  for k,v in row.items():
    if v:
      if k == 'Bookshelves with positions':
        content += '{0}: {1}\n\n'.format(k,v.replace('#', ''))
      else:
        content += '{0}: {1}\n\n'.format(k,v)
  outfile = open(outfilepath, 'w')
  outfile.write(content.strip())
  outfile.close()
  #break