Initial

.gitignore

@@ -0,0 +1,178 @@
+
+# Created by https://www.gitignore.io/api/python,emacs
+
+### Emacs ###
+# -*- mode: gitignore; -*-
+*~
+\#*\#
+/.emacs.desktop
+/.emacs.desktop.lock
+*.elc
+auto-save-list
+tramp
+.\#*
+
+# Org-mode
+.org-id-locations
+*_archive
+
+# flymake-mode
+*_flymake.*
+
+# eshell files
+/eshell/history
+/eshell/lastdir
+
+# elpa packages
+/elpa/
+
+# reftex files
+*.rel
+
+# AUCTeX auto folder
+/auto/
+
+# cask packages
+.cask/
+dist/
+
+# Flycheck
+flycheck_*.el
+
+# server auth directory
+/server/
+
+# projectiles files
+.projectile
+
+# directory configuration
+.dir-locals.el
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+### Python Patch ###
+.venv/
+
+### Python.VirtualEnv Stack ###
+# Virtualenv
+# http://iamzed.com/2009/05/07/a-primer-on-virtualenv/
+[Bb]in
+[Ii]nclude
+[Ll]ib
+[Ll]ib64
+[Ll]ocal
+[Ss]cripts
+pyvenv.cfg
+pip-selfcheck.json
+
+
+# End of https://www.gitignore.io/api/python,emacs

ci.sh

@@ -0,0 +1,10 @@
+#!/bin/bash
+
+cd "$(this_dir)" || exit
+
+. ~/bash_ci
+
+ci_run mypy goodreads
+ci_run pylint -E goodreads
+
+ci_report_errors

goodreads/__init__.py

@@ -0,0 +1,104 @@
+import os
+from xml.dom.minidom import parseString # type: ignore
+
+BPATH = "/L/backups/goodreads"
+
+# TODO might be useful to keep track of updates?...
+# then I need some sort of system to store diffs in generic way...
+# althogh... coud use same mechanism as for filtering
+def get_last() -> str:
+    return max(sorted([os.path.join(BPATH, f) for f in os.listdir(BPATH) if f.endswith('.xmll')]))
+
+_SP = '</review>'
+
+def get_reviews():
+    fname = get_last()
+    xmls = []
+    with open(fname, 'r') as fo:
+        data = fo.read()
+        for xx in data.split(_SP):
+            if len(xx.strip()) == 0:
+                break
+            xmls.append(parseString(xx + _SP))
+    return xmls
+
+def get_books():
+    books = []
+    for review in get_reviews():
+        book_element = review.getElementsByTagName('book')[0]
+        title_element = book_element.getElementsByTagName('title')[0]
+        id_element = book_element.getElementsByTagName('id')[0]
+        isbn_element = book_element.getElementsByTagName('isbn')[0]
+        isbn13_element = book_element.getElementsByTagName('isbn13')[0]
+        date_added = review.getElementsByTagName('date_added')[0]
+        started_at = review.getElementsByTagName('started_at')[0]
+        read_at = review.getElementsByTagName('read_at')[0]
+
+        shelves_element = review.getElementsByTagName('shelves')[0]
+        book_shelves = []
+        for shelf in shelves_element.getElementsByTagName('shelf'):
+            book_shelves.append(shelf.getAttribute('name'))
+
+        book = {
+            'title': title_element.firstChild.data,
+            'id': id_element.firstChild.data,
+            'shelves': book_shelves
+        }
+
+        if isbn_element.getAttribute('nil') != 'true':
+            book['isbn'] = isbn_element.firstChild.data
+        else:
+            book['isbn'] = ''
+
+        if isbn13_element.getAttribute('nil') != 'true':
+            book['isbn13'] = isbn13_element.firstChild.data
+        else:
+            book['isbn13'] = ''
+
+        if started_at.firstChild is not None:
+            book['started_at'] = started_at.firstChild.data
+        else:
+            book['started_at'] = ''
+
+        if read_at.firstChild is not None:
+            book['read_at'] = read_at.firstChild.data
+        else:
+            book['read_at'] = ''
+
+        book['date_added'] = None if date_added.firstChild is None else date_added.firstChild.data
+
+        books.append(book)
+    return books
+
+from typing import List, Dict, NamedTuple
+from datetime import datetime
+
+class Event(NamedTuple):
+    dt: datetime
+    summary: str
+
+
+def _parse_date(s: str) -> datetime:
+    return datetime.strptime(s, "%a %b %d %H:%M:%S %z %Y")
+
+
+def get_events():
+    events = []
+    for b in get_books():
+        added = _parse_date(b['date_added'])
+        title = b['title']
+        events.append(Event(
+            dt=added,
+            summary=f'Added book "{title}"', # TODO shelf?
+        ))
+        # TODO finished? other updates?
+    return sorted(events, key=lambda e: e.dt)
+
+def main():
+    for e in get_events():
+        print(e)
+
+
+if __name__ == '__main__':
+    main()
+

run

@@ -0,0 +1,6 @@
+#!/bin/bash
+set -eu
+
+cd "$(dirname "$0")"
+
+python3 -m goodreads