get your read shelf from good reads and output an org table.

goodreads.py

#!/usr/bin/env python
"""Grab the books from the current year from goodreads and emit an org mode table.
"""
from __future__ import print_function
import datetime
from email.utils import parsedate
import sys
import time
from xml.dom import minidom

import requests

def get_crap(obj, tag):
    """Grab the firstChild of the first elements with the given tag."""
    elements = obj.getElementsByTagName(tag)
    child = None
    if len(elements) >= 1:
        child = elements[0].firstChild
    return child


def get_year(review):
    "Get the year from the `read_at` node."
    read_at = get_crap(review, 'read_at')
    if read_at is None:
        return "???"
    read_at = read_at.data
    read_at = datetime.datetime.fromtimestamp(time.mktime(parsedate(read_at)))
    return str(read_at.year)


def main(args):
    "uh..main"
    goodreads_key = args[1]

    more_pages = True
    page = 1

    while more_pages:
        # URL =
        url = 'https://www.goodreads.com/review/list'
        params = {
            'key': goodreads_key,
            'v': 2,
            'format': 'xml',
            'id': 1519786,
            'per_page': 200,
            'shelf': 'read',
            'page': page}

        req = requests.get(url, params=params)
        if req.status_code != 200:
            print('Bad request!')
            sys.exit(1)

        xmldoc = minidom.parseString(req.content)

        reviews = xmldoc.getElementsByTagName('reviews')[0]
        end = reviews.getAttribute('end')
        total = reviews.getAttribute('total')

        if end == total:
            # this is the last page
            more_pages = False
        else:
            page = page+1

        for review in reviews.getElementsByTagName('review'):
            authors = review.getElementsByTagName('authors')
            print_data = {
                'year': get_year(review),
                'title': get_crap(review, 'title').data.encode('UTF-8'),
                'link': get_crap(review, 'link').data,
                'rating': get_crap(review, 'rating').data.encode('UTF-8')
            }

            if len(authors) == 1:
                print_data['author'] = get_crap(authors[0], 'name').data.encode('utf-8')
            else:
                print_data['author'] = 'Multiple Authors'

            print('|{year}|[[{link}][{title}]] by {author} ({rating} stars)|'.format(**print_data))

if __name__ == '__main__':
    main(sys.argv)