goodreads-cli.py

#!/usr/bin/env python
# -*- coding: utf8 -*-

import oauth2 as oauth
import urlparse
import os
import urllib
import sys
import json
from pprint import pprint
import xml.etree.ElementTree as ET

directory_name = os.path.dirname(os.path.realpath(__file__))
token_fn = os.path.join(directory_name, 'goodreads_tokens')

# look for tokens file. dev token is required
# if oauth token is not already in file, we'll fetch it
try:
    json_data = open(token_fn)
    goodreads_tokens = json.load(json_data)
    json_data.close()
except IOError:
    print "WOOPS: Can't open required file '%s'" % token_fn
    sys.exit()

url = 'http://www.goodreads.com'
request_token_url = '%s/oauth/request_token' % url
authorize_url = '%s/oauth/authorize/' % url
access_token_url = '%s/oauth/access_token' % url

consumer = oauth.Consumer(key=goodreads_tokens['dev_key'],
                          secret=goodreads_tokens['dev_secret'])

client = oauth.Client(consumer)

if not 'oauth_token' in goodreads_tokens and not 'oauth_token_secret' in goodreads_tokens:
    response, content = client.request(request_token_url, 'GET')
    if response['status'] != '200':
        raise Exception('Invalid response: %s' % response['status'])

    request_token = dict(urlparse.parse_qsl(content))

    authorize_link = '%s?oauth_token=%s' % (authorize_url,
                                            request_token['oauth_token'])
    print authorize_link
    accepted = 'n'
    while accepted.lower() == 'n':
        # you need to access the authorize_link via a browser,
        # and proceed to manually authorize the consumer
        accepted = raw_input('Have you authorized me? (y/n) ')

    token = oauth.Token(request_token['oauth_token'],
                        request_token['oauth_token_secret'])

    client = oauth.Client(consumer, token)
    response, content = client.request(access_token_url, 'POST')
    if response['status'] != '200':
        raise Exception('Invalid response: %s' % response['status'])

    access_token = dict(urlparse.parse_qsl(content))

    goodreads_tokens['oauth_token'] = access_token['oauth_token']
    goodreads_tokens['oauth_token_secret'] = access_token['oauth_token_secret']

    # write the access token to file
    try:
        f = open(token_fn, 'w')
        f.write(json.JSONEncoder().encode(goodreads_tokens))
        f.close()
    except IOError:
        print "WOOPS: Can't write tokens to file: '%s'" % token_fn
        sys.exit()

token = oauth.Token(goodreads_tokens['oauth_token'],
                    goodreads_tokens['oauth_token_secret'])

client = oauth.Client(consumer, token)

headers = {'content-type': 'application/x-www-form-urlencoded'}

lookup_successes = []
lookup_failures = []

print "Querying IDs from Goodreads.com ..."

book_file = open('/home/ben/Dropbox/Read.txt')

# loop through and find the id numbers
for line in book_file:
    date, title_author = line.strip().split('\t')
    book = {}
    try:
        title, author = title_author.split(' -- ')
    except ValueError:
        book = {'date': date, 'title': title}
        body = urllib.urlencode({'title': title})
    else:
        book = {'date': date, 'title': title, 'author': author}
        body = urllib.urlencode({'author': author, 'title': title})

    response, content = client.request('%s/book/title.xml' % url, 'GET', body, headers)
    if response['status'] != '200':
        lookup_failures.append(book)
        print 'Error locating "%s" response code %s' % (title, response['status'])
    else:
        # print "Found! '%s'" % book['title']

        root = ET.fromstring(content)
        book['id'] = root.findall('book')[0].findall('id')[0].text
        lookup_successes.append(book)

book_file.close()

print """\n\nSEARCH QUERIES:
    Successes found:    %d
    Failures            %d
    Total Queries:      %d\n\n""" % (len(lookup_successes), len(lookup_failures), len(lookup_successes) + len(lookup_failures))

add_successes = 0
add_failures = []

print "Adding books to Goodreads.com ..."

# # try adding the books to the 'read' shelf
for book in lookup_successes:
    body = urllib.urlencode({'book_id': book['id'], 'shelf': 'read', 'review[read_at]': book['date']})
    response, content = client.request('%s/review.xml' % url, 'POST', body, headers)

    if response['status'] != '201':
        add_failures.append(book)
        print 'Error adding "%s" response code %s' % (book['title'], response['status'])
    else:
        add_successes += 1
        print "Added: '%s'" % book['title']

print """\n\nADD QUERIES:
    Successfully Added      %d
    Failures                %d""" % (add_successes, len(add_failures))

pprint(add_failures)

TODO:

1. more command line options, like scan latest entries of Read.txt and add, instead of whole list
2. Other shelves: to-read, etc
3. Sync down from goodreads for Read.txt and To-read.txt