[books] Add utility urls to model and scrobbles

Ultimately these should probably be templated

.drone.yml

@@ -14,9 +14,9 @@ steps:
       # Install dependencies
       - cp vrobbler.conf.test vrobbler.conf
       - pip install poetry
-      - poetry install
+      - poetry install --with test
       # Start with a fresh database (which is already running as a service from Drone)
-      - poetry run pytest --cov-report term:skip-covered --cov=vrobbler tests
+      - poetry run pytest -n 5 --cov-report term:skip-covered --cov=vrobbler tests
     environment:
       VROBBLER_DATABASE_URL: sqlite:///test.db
     volumes:
@@ -30,7 +30,7 @@ steps:
         - vrobbler.service
       username: root
       ssh_key:
-        from_secret: ssh_key
+        from_secret: jail_key
       command_timeout: 2m
       script:
         - pip uninstall -y vrobbler
@@ -39,10 +39,10 @@ steps:
         - vrobbler collectstatic --noinput
         - immortalctl restart celery && immortalctl restart vrobbler
     when:
-      branch:
-      - main
+      ref:
+        - refs/tags/*
   - name: build success notification
-    image: parrazam/drone-ntfy
+    image: parrazam/drone-ntfy:0.3-linux-amd64
     when:
         status: [success]
     settings:
@@ -50,11 +50,10 @@ steps:
       topic: drone
       priority: low
       tags:
-        - cd
         - failure
         - vrobbler
   - name: build failure notification
-    image: parrazam/drone-ntfy
+    image: parrazam/drone-ntfy:0.3-linux-amd64
     when:
         status: [failure]
     settings:
@@ -62,7 +61,6 @@ steps:
       topic: drone
       priority: high
       tags:
-        - cd
         - success
         - vrobbler
 volumes:

.github/workflows/django.yml

@@ -0,0 +1,31 @@
+name: Django CI
+
+on:
+  push:
+    branches: [ "develop" ]
+  pull_request:
+    branches: [ "main" ]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    strategy:
+      max-parallel: 4
+      matrix:
+        python-version: [3.9, 3.11, 3.12]
+
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v3
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install Dependencies
+      run: |
+        python -m pip install --upgrade pip
+        python -m pip install poetry
+        poetry install
+    - name: Run Tests
+      run: |
+        pytest

.gitignore

@@ -1,4 +1,4 @@
-db.sqlite3
+db.sqlite3*
 vrobbler.conf
 media/
 dist/

Makefile

@@ -0,0 +1,6 @@
+deploy:
+	ssh vrobbler.service "rm -rf /usr/local/lib/python3.11/site-packages/vrobbler-0.15.4.dist-info/ && pip install git+https://code.unbl.ink/secstate/vrobbler.git@develop && immortalctl restart vrobbler && immortalctl restart vrobbler-celery && vrobbler migrate"
+logs:
+	ssh life.unbl.ink tail -n 100 -f /var/log/vrobbler.json
+test:
+	pytest vrobbler

envrc.sample

@@ -1,4 +1,4 @@
 export ENV_PATH=$(poetry env info --path)
 source "${ENV_PATH}/bin/activate"
 
-export PYPI_PASSWORD="$(pass personal/apikey/pypi)"
+#export PYPI_PASSWORD="$(pass personal/apikey/pypi)"

pyproject.toml

@@ -1,17 +1,18 @@
 [tool.poetry]
 name = "vrobbler"
-version = "0.11.12"
+version = "0.16.1"
 description = ""
 authors = ["Colin Powell <colin@unbl.ink>"]
 
 [tool.poetry.dependencies]
-python = ">=3.9,<4.0"
+python = ">=3.9,<3.12"
 Django = "^4.0.3"
 django-extensions = "^3.1.5"
 python-dateutil = "^2.8.2"
 python-dotenv = "^0.20.0"
 python-json-logger = "^2.0.2"
 colorlog = "^6.6.0"
+httpx = "<=0.27.2"
 djangorestframework = "^3.13.1"
 Markdown = "^3.3.6"
 django-filter = "^21.1"
@@ -38,14 +39,30 @@ honcho = "^1.1.0"
 howlongtobeatpy = "^1.0.5"
 beautifulsoup4 = "^4.11.2"
 django-storages = "^1.13.2"
-boto3 = "^1.26.98"
 stream-sqlite = "^0.0.41"
 ipython = "^8.14.0"
 pendulum = "^2.1.2"
 trafilatura = "^1.6.3"
 django-imagekit = "^5.0.0"
+thefuzz = "^0.22.1"
+dataclass-wizard = "0.22.0"
+webdavclient3 = "^3.14.6"
+boto3 = "^1.35.37"
+urllib3 = "<2"
+django-oauth-toolkit = "^3.0.1"
+meta-yt = "^0.1.9"
+berserk = "^0.13.2"
+poetry-bumpversion = "^0.3.3"
+orgparse = "^0.4.20250520"
+tmdbv3api = "^1.9.0"
+themoviedb = "^1.0.2"
+feedparser = "^6.0.12"
+titlecase = "^2.4.1"
 
-[tool.poetry.dev-dependencies]
+[tool.poetry.group.test]
+optional = true
+
+[tool.poetry.group.test.dependencies]
 Werkzeug = "2.0.3"
 black = "^22.3"
 coverage = "^7.0.5"
@@ -54,10 +71,10 @@ pytest = "^7.1"
 pytest-black = "^0.3.12"
 pytest-cov = "^3.0"
 pytest-django = "^4.5.2"
+pytest-xdist= "^1.0.0"
 pytest-flake8 = "^1.1"
 pytest-isort = "^3.0"
 pytest-runner = "^6.0"
-pytest-selenium = "^2.0.1"
 time-machine = "^2.9.0"
 types-pytz = "^2022.1"
 types-requests = "^2.27"
@@ -65,7 +82,7 @@ bandit = "^1.7.4"
 
 [tool.pytest.ini_options]
 minversion = "6.0"
-addopts = "-ra -q"
+addopts = "-ra -q --reuse-db"
 testpaths = ["tests"]
 DJANGO_SETTINGS_MODULE='vrobbler.settings-testing'
 

tests/podcasts_tests/test_scrapers.py

@@ -1,3 +1,4 @@
+import pytest
 from vrobbler.apps.podcasts.scrapers import scrape_data_from_google_podcasts
 
 expected_desc_snippet = (
@@ -8,6 +9,7 @@ expected_img_url = "https://encrypted-tbn2.gstatic.com/images?q=tbn:ANd9GcR1F0Cf
 expected_google_url = "https://podcasts.google.com/feed/aHR0cHM6Ly9mZWVkcy5ucHIub3JnLzUxMDMxOC9wb2RjYXN0LnhtbA"
 
 
+@pytest.mark.skip("Google Podcasts is gone")
 def test_get_not_allowed_from_mopidy():
     query = "Up First"
     result_dict = scrape_data_from_google_podcasts(query)

tests/scrobbles_tests/conftest.py

@@ -1,19 +1,50 @@
 import json
-import pytest
 
-from rest_framework.authtoken.models import Token
+import pytest
 from django.contrib.auth import get_user_model
+from rest_framework.authtoken.models import Token
+
+from boardgames.models import BoardGame
+from music.models import Track, Artist
+from scrobbles.models import Scrobble
+from people.models import Person
 
 User = get_user_model()
 
 
+@pytest.fixture
+def boardgame_scrobble():
+    first = Person.objects.create(name="First Player")
+    second = Person.objects.create(name="Second Player")
+    return Scrobble.objects.create(
+        board_game=BoardGame.objects.create(title="Test Board Game"),
+        media_type="BoardGame",
+        played_to_completion=True,
+        log={
+            "players": [
+                {"person_id": first.id, "win": True, "score": 30, "color": "Blue"},
+                {"person_id": second.id, "win": False, "score": 28, "color": "Red"}
+            ],
+        },
+    )
+
+
+@pytest.fixture
+def test_track():
+    Track.objects.create(
+        title="Emotion",
+        artist=Artist.objects.create(name="Carly Rae Jepsen"),
+        run_time_seconds=60,
+    )
+
+
 class MopidyRequest:
     name = "Same in the End"
     artist = "Sublime"
     album = "Sublime"
     track_number = 4
     run_time_ticks = 156604
-    run_time = "156"
+    run_time = 60
     playback_time_ticks = 15045
     musicbrainz_track_id = "54214d63-5adf-4909-87cd-c65c37a6d558"
     musicbrainz_album_id = "03b864cd-7761-314c-a892-05a89ddff00d"
@@ -65,8 +96,8 @@ def valid_auth_token():
 
 
 @pytest.fixture
-def mopidy_track_request_data():
-    return MopidyRequest().request_json
+def mopidy_track():
+    return MopidyRequest()
 
 
 @pytest.fixture
@@ -80,4 +111,67 @@ def mopidy_track_diff_album_request_data(**kwargs):
 @pytest.fixture
 def mopidy_podcast_request_data():
     mopidy_uri = "local:podcast:Up%20First/2022-01-01%20Up%20First.mp3"
-    return MopidyRequest(mopidy_uri=mopidy_uri).request_json
+    return MopidyRequest(
+        mopidy_uri=mopidy_uri, artist="NPR", album="Up First"
+    ).request_json
+
+@pytest.fixture
+def mopidy_podcast_https_request_data():
+    mopidy_uri = "podcast+https://feeds.npr.org/510318/podcast.xml#85b9c4c4-ae09-43d9-8853-31ccf43f68e6"
+    return MopidyRequest(
+        mopidy_uri=mopidy_uri, artist="NPR", album="Up First"
+    ).request_json
+
+class JellyfinTrackRequest:
+    name = "Emotion"
+    artist = "Carly Rae Jepsen"
+    album = "Emotion"
+    track_number = 1
+    item_type = "Audio"
+    timestamp = "2024-01-14 12:00:19"
+    run_time_ticks = 156604
+    run_time = "00:00:60"
+    playback_time_ticks = 15045
+    musicbrainz_track_id = "54214d63-5adf-4909-87cd-c65c37a6d558"
+    musicbrainz_album_id = "03b864cd-7761-314c-a892-05a89ddff00d"
+    musicbrainz_artist_id = "95f5b748-d370-47fe-85bd-0af2dc450bc0"
+    status = "resumed"
+
+    def __init__(self, **kwargs):
+        self.request_data = {
+            "Name": kwargs.get("name", self.name),
+            "Artist": kwargs.get("artist", self.artist),
+            "Album": kwargs.get("album", self.album),
+            "TrackNumber": int(kwargs.get("track_number", self.track_number)),
+            "RunTime": kwargs.get("run_time", self.run_time),
+            "ItemType": kwargs.get("item_type", self.item_type),
+            "UtcTimestamp": kwargs.get("timestamp", self.timestamp),
+            "PlaybackPositionTicks": int(
+                kwargs.get("playback_time_ticks", self.playback_time_ticks)
+            ),
+            "Provider_musicbrainztrack": kwargs.get(
+                "musicbrainz_track_id", self.musicbrainz_track_id
+            ),
+            "Provider_musicbrainzalbum": kwargs.get(
+                "musicbrainz_album_id", self.musicbrainz_album_id
+            ),
+            "Provider_musicbrainzartist": kwargs.get(
+                "musicbrainz_artist_id", self.musicbrainz_artist_id
+            ),
+            "Status": kwargs.get("status", self.status),
+        }
+
+    def __eq__(self, other):
+        for key in self.request_data.keys():
+            if self.request_data[key] != getattr(self, key):
+                return False
+        return True
+
+    @property
+    def request_json(self):
+        return json.dumps(self.request_data)
+
+
+@pytest.fixture
+def jellyfin_track():
+    return JellyfinTrackRequest()

tests/scrobbles_tests/test_aggregators.py

@@ -1,6 +1,4 @@
 from datetime import datetime, timedelta
-from unittest import mock
-from unittest.mock import patch
 
 import pytest
 import time_machine
@@ -13,12 +11,13 @@ from profiles.models import UserProfile
 from scrobbles.models import Scrobble
 
 
-def build_scrobbles(client, request_data, num=7, spacing=2):
+def build_scrobbles(client, request_json, num=7, spacing=2):
     url = reverse("scrobbles:mopidy-webhook")
     user = get_user_model().objects.create(username="Test User")
-    UserProfile.objects.create(user=user, timezone="US/Eastern")
+    user.profile.timezone = "US/Eastern"
+    user.profile.save()
     for i in range(num):
-        client.post(url, request_data, content_type="application/json")
+        client.post(url, request_json, content_type="application/json")
         s = Scrobble.objects.last()
         s.user = user
         s.timestamp = timezone.now() - timedelta(days=i * spacing)
@@ -28,8 +27,8 @@ def build_scrobbles(client, request_data, num=7, spacing=2):
 
 @pytest.mark.django_db
 @time_machine.travel(datetime(2022, 3, 4, 1, 24))
-def test_scrobble_counts_data(client, mopidy_track_request_data):
-    build_scrobbles(client, mopidy_track_request_data)
+def test_scrobble_counts_data(client, mopidy_track):
+    build_scrobbles(client, mopidy_track.request_json)
     user = get_user_model().objects.first()
     count_dict = scrobble_counts(user)
     assert count_dict == {
@@ -43,8 +42,8 @@ def test_scrobble_counts_data(client, mopidy_track_request_data):
 
 @pytest.mark.django_db
 @time_machine.travel(datetime(2022, 3, 4, 1, 24))
-def test_live_charts(client, mopidy_track_request_data):
-    build_scrobbles(client, mopidy_track_request_data, 7, 1)
+def test_live_charts(client, mopidy_track):
+    build_scrobbles(client, mopidy_track.request_json, 7, 1)
     user = get_user_model().objects.first()
 
     week = week_of_scrobbles(user)

tests/scrobbles_tests/test_metadata.py

@@ -0,0 +1,44 @@
+import pytest
+
+#from scrobbles.dataclasses import BoardGameLogData, BoardGameScoreLogData
+
+
+@pytest.mark.skip("Need to get local tests running working again")
+@pytest.mark.django_db
+def test_boardgame_log_data(boardgame_scrobble):
+    assert boardgame_scrobble.logdata == BoardGameLogData(
+        players=[
+            BoardGameScoreLogData(
+                person_id=1,
+                bgg_username="",
+                color="Blue",
+                character=None,
+                team=None,
+                score=30,
+                win=True,
+                new=None,
+                rank=None,
+                seat_order=None,
+                role=None
+            ),
+            BoardGameScoreLogData(
+                person_id=2,
+                bgg_username="",
+                color="Red",
+                character=None,
+                team=None,
+                score=28,
+                win=False,
+                new=None,
+                rank=None,
+                seat_order=None,
+                role=None
+            ),
+        ],
+        difficulty=None,
+        solo=None,
+        two_handed=None,
+    )
+    assert len(boardgame_scrobble.logdata.players) == 1
+    assert boardgame_scrobble.logdata.players[0].user.id == 1
+    assert boardgame_scrobble.logdata.players[0].name == "Test"

tests/scrobbles_tests/test_views.py

@@ -1,7 +1,12 @@
+from datetime import datetime, timedelta
+from unittest.mock import patch
+from django.utils import timezone
+
 import pytest
+import time_machine
 from django.urls import reverse
 from music.models import Track
-from podcasts.models import Episode
+from podcasts.models import PodcastEpisode
 from scrobbles.models import Scrobble
 
 
@@ -25,31 +30,28 @@ def test_bad_mopidy_request_data(client, valid_auth_token):
     )
 
 
+@pytest.mark.skip("Need to refactor")
 @pytest.mark.django_db
-def test_scrobble_mopidy_track(
-    client, mopidy_track_request_data, valid_auth_token
-):
-    url = reverse("scrobbles:mopidy-webhook")
-    headers = {"Authorization": f"Token {valid_auth_token}"}
-    response = client.post(
-        url,
-        mopidy_track_request_data,
-        content_type="application/json",
-        headers=headers,
-    )
-    assert response.status_code == 200
-    assert response.data == {"scrobble_id": 1}
-
-    scrobble = Scrobble.objects.get(id=1)
-    assert scrobble.media_obj.__class__ == Track
-    assert scrobble.media_obj.title == "Same in the End"
-
-
-@pytest.mark.skip(reason="API is unstable")
-@pytest.mark.django_db
+@patch("music.utils.lookup_artist_from_mb", return_value={})
+@patch(
+    "music.utils.lookup_album_dict_from_mb",
+    return_value={"year": "1999", "mb_group_id": 1},
+)
+@patch("music.utils.lookup_track_from_mb", return_value={})
+@patch("music.models.lookup_artist_from_tadb", return_value={})
+@patch("music.models.lookup_album_from_tadb", return_value={"year": "1999"})
+@patch("music.models.Album.fetch_artwork", return_value=None)
+@patch("music.models.Album.scrape_allmusic", return_value=None)
 def test_scrobble_mopidy_same_track_different_album(
+    mock_lookup_artist,
+    mock_lookup_album,
+    mock_lookup_track,
+    mock_lookup_artist_tadb,
+    mock_lookup_album_tadb,
+    mock_fetch_artwork,
+    mock_scrape_allmusic,
     client,
-    mopidy_track_request_data,
+    mopidy_track,
     mopidy_track_diff_album_request_data,
     valid_auth_token,
 ):
@@ -57,7 +59,7 @@ def test_scrobble_mopidy_same_track_different_album(
     headers = {"Authorization": f"Token {valid_auth_token}"}
     response = client.post(
         url,
-        mopidy_track_request_data,
+        mopidy_track.request_data,
         content_type="application/json",
         headers=headers,
     )
@@ -76,13 +78,17 @@ def test_scrobble_mopidy_same_track_different_album(
     assert response.data == {"scrobble_id": 2}
     scrobble = Scrobble.objects.last()
     assert scrobble.media_obj.__class__ == Track
-    assert scrobble.media_obj.album.name == "Gold"
+    assert scrobble.media_obj.album.name == "Sublime"
     assert scrobble.media_obj.title == "Same in the End"
 
 
 @pytest.mark.django_db
+@patch(
+    "podcasts.sources.podcastindex.lookup_podcast_from_podcastindex",
+    return_value={},
+)
 def test_scrobble_mopidy_podcast(
-    client, mopidy_podcast_request_data, valid_auth_token
+    mock_lookup_podcast, client, mopidy_podcast_request_data, valid_auth_token
 ):
     url = reverse("scrobbles:mopidy-webhook")
     headers = {"Authorization": f"Token {valid_auth_token}"}
@@ -96,5 +102,151 @@ def test_scrobble_mopidy_podcast(
     assert response.data == {"scrobble_id": 1}
 
     scrobble = Scrobble.objects.get(id=1)
-    assert scrobble.media_obj.__class__ == Episode
+    assert scrobble.media_obj.__class__ == PodcastEpisode
     assert scrobble.media_obj.title == "Up First"
+
+
+@pytest.mark.skip("Need to refactor")
+@pytest.mark.django_db
+@patch("music.utils.lookup_artist_from_mb", return_value={})
+@patch(
+    "music.utils.lookup_album_dict_from_mb",
+    return_value={"year": "1999", "mb_group_id": 1},
+)
+@patch("music.utils.lookup_track_from_mb", return_value={})
+@patch("music.models.lookup_artist_from_tadb", return_value={})
+@patch("music.models.lookup_album_from_tadb", return_value={"year": "1999"})
+@patch("music.models.Album.fetch_artwork", return_value=None)
+@patch("music.models.Album.scrape_allmusic", return_value=None)
+def test_scrobble_jellyfin_track(
+    mock_lookup_artist,
+    mock_lookup_album,
+    mock_lookup_track,
+    mock_lookup_artist_tadb,
+    mock_lookup_album_tadb,
+    mock_fetch_artwork,
+    mock_scrape_allmusic,
+    client,
+    jellyfin_track,
+    valid_auth_token,
+):
+    url = reverse("scrobbles:jellyfin-webhook")
+    headers = {"Authorization": f"Token {valid_auth_token}"}
+
+    with time_machine.travel(datetime(2024, 1, 14, 12, 00, 1)):
+        jellyfin_track.request_data["UtcTimestamp"] = timezone.now().strftime(
+            "%Y-%m-%d %H:%M:%S"
+        )
+        response = client.post(
+            url,
+            jellyfin_track.request_json,
+            content_type="application/json",
+            headers=headers,
+        )
+        assert response.status_code == 200
+        assert response.data == {"scrobble_id": 1}
+
+        scrobble = Scrobble.objects.get(id=1)
+        assert scrobble.media_obj.__class__ == Track
+        assert scrobble.media_obj.title == "Emotion"
+
+
+@pytest.mark.skip("Need to refactor")
+@pytest.mark.django_db
+@patch("music.utils.lookup_artist_from_mb", return_value={})
+@patch(
+    "music.utils.lookup_album_dict_from_mb",
+    return_value={"year": "1999", "mb_group_id": 1},
+)
+@patch("music.utils.lookup_track_from_mb", return_value={})
+@patch("music.models.lookup_artist_from_tadb", return_value={})
+@patch("music.models.lookup_album_from_tadb", return_value={"year": "1999"})
+@patch("music.models.Album.fetch_artwork", return_value=None)
+@patch("music.models.Album.scrape_allmusic", return_value=None)
+def test_scrobble_jellyfin_track_update(
+    mock_lookup_artist,
+    mock_lookup_album,
+    mock_lookup_track,
+    mock_lookup_artist_tadb,
+    mock_lookup_album_tadb,
+    mock_fetch_artwork,
+    mock_scrape_allmusic,
+    test_track,
+    client,
+    jellyfin_track,
+    valid_auth_token,
+):
+    Scrobble.objects.create(
+        timestamp=timezone.now() - timedelta(minutes=0.5),
+        track=Track.objects.first(),
+        user_id=1,
+    )
+    url = reverse("scrobbles:jellyfin-webhook")
+    headers = {"Authorization": f"Token {valid_auth_token}"}
+
+    jellyfin_track.request_data["UtcTimestamp"] = timezone.now().strftime(
+        "%Y-%m-%d %H:%M:%S"
+    )
+    response = client.post(
+        url,
+        jellyfin_track.request_json,
+        content_type="application/json",
+        headers=headers,
+    )
+
+    assert response.status_code == 200
+    assert response.data == {"scrobble_id": 1}
+
+    scrobble = Scrobble.objects.get(id=1)
+    assert scrobble.media_obj.__class__ == Track
+    assert scrobble.media_obj.title == "Emotion"
+
+
+@pytest.mark.skip("Need to refactor")
+@pytest.mark.django_db
+@patch("music.utils.lookup_artist_from_mb", return_value={})
+@patch(
+    "music.utils.lookup_album_dict_from_mb",
+    return_value={"year": "1999", "mb_group_id": 1},
+)
+@patch("music.utils.lookup_track_from_mb", return_value={})
+@patch("music.models.lookup_artist_from_tadb", return_value={})
+@patch("music.models.lookup_album_from_tadb", return_value={"year": "1999"})
+@patch("music.models.Album.fetch_artwork", return_value=None)
+@patch("music.models.Album.scrape_allmusic", return_value=None)
+def test_scrobble_jellyfin_track_create_new(
+    mock_lookup_artist,
+    mock_lookup_album,
+    mock_lookup_track,
+    mock_lookup_artist_tadb,
+    mock_lookup_album_tadb,
+    mock_fetch_artwork,
+    mock_scrape_allmusic,
+    test_track,
+    client,
+    jellyfin_track,
+    valid_auth_token,
+):
+    url = reverse("scrobbles:jellyfin-webhook")
+    headers = {"Authorization": f"Token {valid_auth_token}"}
+    Scrobble.objects.create(
+        timestamp=timezone.now() - timedelta(minutes=1),
+        track=Track.objects.first(),
+        user_id=1,
+    )
+    jellyfin_track.request_data["UtcTimestamp"] = timezone.now().strftime(
+        "%Y-%m-%d %H:%M:%S"
+    )
+    response = client.post(
+        url,
+        jellyfin_track.request_json,
+        content_type="application/json",
+        headers=headers,
+    )
+
+    assert response.status_code == 200
+    assert response.data == {"scrobble_id": 2}
+
+    scrobble = Scrobble.objects.get(id=1)
+    assert scrobble.media_obj.__class__ == Track
+    assert scrobble.media_obj.title == "Emotion"

tests/videos_tests/test_imdb.py

@@ -1,11 +1,6 @@
-import pytest
-
-from videos.imdb import lookup_video_from_imdb
+from videos.sources.imdb import lookup_video_from_imdb
 
 
-@pytest.mark.skip(reason="Need to sort out third party API testing")
-def test_lookup_imdb_bad_id(caplog):
-    data = lookup_video_from_imdb("3409324")
-    assert data is None
-    assert caplog.records[0].levelname == "WARNING"
-    assert caplog.records[0].msg == "IMDB ID should begin with 'tt' 3409324"
+def test_lookup_imdb():
+    metadata = lookup_video_from_imdb("8946378")
+    assert metadata.title == "Knives Out"

tests/videos_tests/test_youtube.py

@@ -0,0 +1,9 @@
+import pytest
+from videos.sources.youtube import lookup_video_from_youtube
+
+
+@pytest.mark.skip(reason="Need to configure Youtube API stuffs in CI")
+@pytest.mark.django_db
+def test_lookup_youtube_id():
+    metadata = lookup_video_from_youtube("RZxs9pAv99Y")
+    assert metadata.title == "No Pun Included's Board Game of the Year 2024"

todos.org

@@ -1,449 +0,0 @@
-#+title: TODOs
-
-A fun way to keep track of things in the project to fix or improve.
-
-* Version 1.0.0
-** TODO What to do with Youtube videos from LastFM and web-scrobbler :bug:source:lastfm:
-** TODO Add a user profile page with ability to change settings :profiles:improvement:
-** DONE [#C] Consider a purge command for duplicated and stuck in-progress scrobbles :utililty:improvement:
-CLOSED: [2023-04-06 Thu 14:09]
-** DONE Add a "stop_timestamp" so we don't rely on content length :improvement:scrobbling:
-CLOSED: [2023-04-02 Sun 23:58]
-
-Essentially, we currently have the timestamp as when the content began
-scrobbling and then calculate the finish time from the length of the content.
-This works pretty well because we know how long most things are.
-
-But in some cases, sports events or long podcasts, we may start mid-way through
-an event or finish halfway through but still want to mark it as done. In these
-cases, knowing the finish time could be useful, especially when interfacing with
-other scrobblers which may have different definitions of when a scrobble
-finishes or started.
-** DONE Fix bug with Various Artist albums being labeled with first artist as album artist :scrobbling:bug:music:
-CLOSED: [2023-03-27 Mon 20:18]
-:LOGBOOK:
-CLOCK: [2023-03-26 Sun 22:01]--[2023-03-27 Mon 01:07] =>  3:06
-:END:
-** DONE Fix bug with weekly aggregator being blank on Sundays :aggregators:music:bug:
-CLOSED: [2023-03-26 Sun 13:52]
-** DONE Fix KoReader scrobbling to use pages rather than time of last read :scrobbling:books:improvement:
-CLOSED: [2023-03-26 Sun 13:51]
-:LOGBOOK:
-CLOCK: [2023-03-26 Sun 13:11]--[2023-03-26 Sun 13:51] =>  0:40
-:END:
-** DONE [#A] Add django-storage to store files on S3 :settings:improvement:
-CLOSED: [2023-03-24 Fri 14:46]
-:LOGBOOK:
-CLOCK: [2023-03-24 Fri 10:47]--[2023-03-24 Fri 14:46] =>  3:59
-CLOCK: [2023-03-24 Fri 10:36]--[2023-03-24 Fri 10:40] =>  0:04
-:END:
-** DONE Fix vrobbler settings not using booleans :settings:bug:
-CLOSED: [2023-03-24 Fri 10:45]
-:LOGBOOK:
-CLOCK: [2023-03-24 Fri 10:40]--[2023-03-24 Fri 10:46] =>  0:06
-:END:
-** DONE Update weekly live chart to be 7-day continuous rather than weekly :views:bug:
-CLOSED: [2023-03-24 Fri 00:31]
-The live view will be blank every Monday, no reason to tie it to a day of the
-week. It should be "the last 7 days"
-** DONE [#B] Implement a detail view for TV shows :improvement:views:
-CLOSED: [2023-03-22 Wed 17:05]
-** DONE [#B] Implement a detail view for Movies :improvement:views:
-CLOSED: [2023-03-22 Wed 17:05]
-** DONE Add "service provider" to TV Series, and use that for source when available :bug:scrobbling:
-CLOSED: [2023-03-22 Wed 17:04]
-** DONE Add view for long-play content (books, video games) to restart them :views:improvement:
-CLOSED: [2023-03-22 Wed 17:01]
-** DONE Add live chart view like Maloja :improvement:views:
-CLOSED: [2023-03-07 Tue 11:13]
-** DONE [#C] Figure out how to add to web-scrobbler :improvement:scrobbling:
-CLOSED: [2023-03-22 Wed 17:06]
-
-An example:
-https://github.com/web-scrobbler/web-scrobbler/blob/master/src/core/background/scrobbler/maloja-scrobbler.js
-
-This is actually going to be moot because we can import from LastFM, and
-web-scrobbler integrates well with LastFM. The only thing to think through here
-now is what to do with all the garbage web-scrobbler sometimes pushes to LastFM
-from Youtube (all videos get pushed, sigh).
-
-* Version 0.11.4
-** DONE Add rudimentary video game scrobbling :improvement:content:videogames:
-CLOSED: [2023-03-07 Tue 11:11]
-** DONE Add ability to scrobble from KOReader statistics files :improvement:books:content:
-CLOSED: [2023-03-07 Tue 11:11]
-
-** DONE [#A] Fix fetching artwork without release group :bug:
-CLOSED: [2023-01-29 Sun 14:27]
-
-When we get artwork from Musicbrianz, and it's not found, we should check for
-release groups as well. This will stop issues with missing artwork because of
-obscure MB release matches.
-
-** DONE [#A] Fix Jellyfin music scrobbling N+1 past 90 completion percent :bug:
-CLOSED: [2023-01-30 Mon 18:31]
-:LOGBOOK:
-CLOCK: [2023-01-30 Mon 18:00]--[2023-01-30 Mon 18:31] =>  0:31
-:END:
-
-If we play music from Jellyfin and the track reaches 90% completion, the
-scrobbling goes crazy and starts creating new scrobbles with every update.
-
-The cause is pretty simple, but the solution is hard. We want to mark a scrobble
-as complete for the following conditions:
-
-- Play stopped and percent played beyond 90%
-- Play completely finished
-
-But if we keep listening beyond 90, we should basically ignore updates (or just
-update the existing scrobble)
-** DONE [#A] Add support for Audioscrobbler tab-separated file uploads :improvement:
-CLOSED: [2023-02-03 Fri 16:52]
-
-An example of the format:
-#+begin_src csv
-,
-#AUDIOSCROBBLER/1.1
-#TZ/UNKNOWN
-#CLIENT/Rockbox sansaclipplus $Revision$
-75 Dollar Bill	I Was Real	I Was Real	4	1015	S	1740494944	64ff5f53-d187-4512-827e-7606c69e66ff
-75 Dollar Bill	I Was Real	I Was Real	4	1015	S	1740494990	64ff5f53-d187-4512-827e-7606c69e66ff
-311	311	Down	1	173	S	1740495003	00476c23-fd9e-464b-9b27-a62d69f3d4f4
-311	311	Down	1	173	L	1740495049	00476c23-fd9e-464b-9b27-a62d69f3d4f4
-311	311	Down	1	173	L	1740495113	00476c23-fd9e-464b-9b27-a62d69f3d4f4
-311	311	Random	2	187	S	1740495190	530c09f3-46fe-4d90-b11f-7b63bcb4b373
-311	311	Random	2	187	L	1740495194	530c09f3-46fe-4d90-b11f-7b63bcb4b373
-311	311	Jackolantern’s Weather	3	204	L	1740495382	cc3b2dec-5d99-47ea-8930-20bf258be4ea
-311	311	All Mixed Up	4	182	L	1740495586	980a78b5-5bdd-4f50-9e3a-e13261e2817b
-311	311	Hive	5	179	L	1740495768	18f6dc98-d3a2-4f81-b967-97359d14c68c
-311	311	Guns (Are for Pussies)	6	137	L	1740495948	5e97ed9f-c8cc-4282-9cbe-f8e17aee5128
-311	311	Misdirected Hostility	7	179	S	1740496085	61ff2c1a-fc9c-44c3-8da1-5e50a44245af
-,
-#+end_src
-** DONE [#B] Allow scrobbling music without MB IDs by grabbing them before scrobble :improvement:
-CLOSED: [2023-02-17 Fri 00:10]
-
-This would allow a few nice flows. One, you'd be able to record the play of an
-entire album by just dropping the muscibrainz_id in. This could be helpful for
-offline listening. It would also mean bad metadata from mopidy would not break
-scrobbling.
-** DONE When updating musicbrainz IDs, clear and run fetch artwrok :improvement:
-CLOSED: [2023-02-17 Fri 00:11]
-** DONE [#A] Add ability to manually scrobble albums or tracks from MB :improvement:
-CLOSED: [2023-03-07 Tue 11:09]
-
-Given a UUID from musicbrainz, we should be able to scrobble an album or
-individual track.
-
-** DONE [#C] Implement keeping track of week/month/year chart-toppers :improvement:
-CLOSED: [2023-03-07 Tue 11:10]
-:LOGBOOK:
-CLOCK: [2023-01-30 Mon 16:30]--[2023-01-30 Mon 18:00] =>  1:30
-:END:
-
-Maloja does this cool thing where artists and tracks get recorded as the top
-track of a given week, month or year. They get gold, silver or bronze stars for
-their place in the time period.
-
-I could see this being implemented as a separate Chart table which gets
-populated at the end of a time period and has a start and end date that defines
-a period, along with a one, two, three instance.
-
-Of course, it could also be a data model without a table, where it runs some fun
-calculations, stores it's values in Redis as a long-term lookup table and just
-has to re-populate when the server restarts.
-* Backlog
-** TODO Add Amazon scraper to look up books when OL fails :books:improvement:
-** TODO [#C] Move to using more robust mopidy-webhooks pacakge form pypi :utility:improvement:
-*** Example payloads from mopidy-webhooks
-**** Podcast playback ended
-#+begin_src json
-{
-    "type": "event",
-    "event": "track_playback_ended",
-    "data": {
-        "tl_track": {
-            "__model__": "TlTrack",
-            "tlid": 13,
-            "track": {
-                "__model__": "Track",
-                "uri": "file:///var/lib/mopidy/media/podcasts/The%20Prince/2022-09-28-Wolf-warriors.mp3",
-                "name": "Wolf warriors",
-                "artists": [
-                    {
-                        "__model__": "Artist",
-                        "name": "The Economist"
-                    }
-                ],
-                "album": {
-                    "__model__": "Album",
-                    "name": "The Prince",
-                    "date": "2022"
-                },
-                "genre": "Blues",
-                "date": "2022",
-                "length": 2437778,
-                "bitrate": 127988
-            }
-        },
-        "time_position": 3290
-    }
-}
-#+end_src
-**** Podcast playback state changes
-#+begin_src json
-{
-    "type": "event",
-    "event": "playback_state_changed",
-    "data": {
-        "old_state": "paused",
-        "new_state": "playing"
-    }
-}
-#+end_src
-
-#+begin_src json
-{
-    "type": "event",
-    "event": "playback_state_changed",
-    "data": {
-        "old_state": "stopped",
-        "new_state": "playing"
-    }
-}
-#+end_src
-**** Podcast playback started
-#+begin_src json
-{
-    "type": "event",
-    "event": "track_playback_started",
-    "data": {
-        "tl_track": {
-            "__model__": "TlTrack",
-            "tlid": 13,
-            "track": {
-                "__model__": "Track",
-                "uri": "file:///var/lib/mopidy/media/podcasts/The%20Prince/2022-09-28-Wolf-warriors.mp3",
-                "name": "Wolf warriors",
-                "artists": [
-                    {
-                        "__model__": "Artist",
-                        "name": "The Economist"
-                    }
-                ],
-                "album": {
-                    "__model__": "Album",
-                    "name": "The Prince",
-                    "date": "2022"
-                },
-                "genre": "Blues",
-                "date": "2022",
-                "length": 2437778,
-                "bitrate": 127988
-            }
-        }
-    }
-}
-#+end_src
-**** Podcast playback paused
-#+begin_src  json
-{
-    "type": "status",
-    "data": {
-        "state": "paused",
-        "current_track": {
-            "__model__": "Track",
-            "uri": "file:///var/lib/mopidy/media/podcasts/The%20Prince/2022-09-28-Wolf-warriors.mp3",
-            "name": "Wolf warriors",
-            "artists": [
-                {
-                    "__model__": "Artist",
-                    "name": "The Economist"
-                }
-            ],
-            "album": {
-                "__model__": "Album",
-                "name": "The Prince",
-                "date": "2022"
-            },
-            "genre": "Blues",
-            "date": "2022",
-            "length": 2437778,
-            "bitrate": 127988
-        },
-        "time_position": 2350
-    }
-}
-
-#+end_src
-**** Track playback started
-#+begin_src json
-{
-    "type": "event",
-    "event": "track_playback_started",
-    "data": {
-        "tl_track": {
-            "__model__": "TlTrack",
-            "tlid": 14,
-            "track": {
-                "__model__": "Track",
-                "uri": "local:track:Various%20Artists%20-%202008%20-%20Twilight%20OST/01-muse-supermassive_black_hole.mp3",
-                "name": "Supermassive Black Hole",
-                "artists": [
-                    {
-                        "__model__": "Artist",
-                        "uri": "local:artist:md5:250dd6551b66a58a6b4897aa697f200c",
-                        "name": "Muse",
-                        "musicbrainz_id": "9c9f1380-2516-4fc9-a3e6-f9f61941d090"
-                    }
-                ],
-                "album": {
-                    "__model__": "Album",
-                    "uri": "local:album:md5:455343d54cdd89cb5a3b5ad537ea99d0",
-                    "name": "Twilight: Original Motion Picture Soundtrack",
-                    "artists": [
-                        {
-                            "__model__": "Artist",
-                            "uri": "local:artist:md5:54e4db2d5624f80b0cc290346e696756",
-                            "name": "Various Artists",
-                            "musicbrainz_id": "89ad4ac3-39f7-470e-963a-56509c546377"
-                        }
-                    ],
-                    "num_tracks": 12,
-                    "num_discs": 1,
-                    "date": "2008-11-04",
-                    "musicbrainz_id": "b4889eaf-d9f4-434c-a68d-69227b12b6a4"
-                },
-                "composers": [
-                    {
-                        "__model__": "Artist",
-                        "uri": "local:artist:md5:4d49cbca0b347e0a89047bb019d2779d",
-                        "name": "Matt Bellamy"
-                    }
-                ],
-                "genre": "Rock",
-                "track_no": 1,
-                "disc_no": 1,
-                "date": "2008-11-04",
-                "length": 211121,
-                "musicbrainz_id": "ff1e3e1a-f6e8-4692-b426-355880383bb6",
-                "last_modified": 1672712949510
-            }
-        }
-    }
-}
-#+end_src
-**** Track playback in progress
-#+begin_src json
-{
-    "type": "status",
-    "data": {
-        "state": "playing",
-        "current_track": {
-            "__model__": "Track",
-            "uri": "local:track:Various%20Artists%20-%202008%20-%20Twilight%20OST/01-muse-supermassive_black_hole.mp3",
-            "name": "Supermassive Black Hole",
-            "artists": [
-                {
-                    "__model__": "Artist",
-                    "uri": "local:artist:md5:250dd6551b66a58a6b4897aa697f200c",
-                    "name": "Muse",
-                    "musicbrainz_id": "9c9f1380-2516-4fc9-a3e6-f9f61941d090"
-                }
-            ],
-            "album": {
-                "__model__": "Album",
-                "uri": "local:album:md5:455343d54cdd89cb5a3b5ad537ea99d0",
-                "name": "Twilight: Original Motion Picture Soundtrack",
-                "artists": [
-                    {
-                        "__model__": "Artist",
-                        "uri": "local:artist:md5:54e4db2d5624f80b0cc290346e696756",
-                        "name": "Various Artists",
-                        "musicbrainz_id": "89ad4ac3-39f7-470e-963a-56509c546377"
-                    }
-                ],
-                "num_tracks": 12,
-                "num_discs": 1,
-                "date": "2008-11-04",
-                "musicbrainz_id": "b4889eaf-d9f4-434c-a68d-69227b12b6a4"
-            },
-            "composers": [
-                {
-                    "__model__": "Artist",
-                    "uri": "local:artist:md5:4d49cbca0b347e0a89047bb019d2779d",
-                    "name": "Matt Bellamy"
-                }
-            ],
-            "genre": "Rock",
-            "track_no": 1,
-            "disc_no": 1,
-            "date": "2008-11-04",
-            "length": 211121,
-            "musicbrainz_id": "ff1e3e1a-f6e8-4692-b426-355880383bb6",
-            "last_modified": 1672712949510
-        },
-        "time_position": 17031
-    }
-}
-#+end_src
-**** Track event playback paused
-#+begin_src json
-{
-    "type": "event",
-    "event": "track_playback_paused",
-    "data": {
-        "tl_track": {
-            "__model__": "TlTrack",
-            "tlid": 14,
-            "track": {
-                "__model__": "Track",
-                "uri": "local:track:Various%20Artists%20-%202008%20-%20Twilight%20OST/01-muse-supermassive_black_hole.mp3",
-                "name": "Supermassive Black Hole",
-                "artists": [
-                    {
-                        "__model__": "Artist",
-                        "uri": "local:artist:md5:250dd6551b66a58a6b4897aa697f200c",
-                        "name": "Muse",
-                        "musicbrainz_id": "9c9f1380-2516-4fc9-a3e6-f9f61941d090"
-                    }
-                ],
-                "album": {
-                    "__model__": "Album",
-                    "uri": "local:album:md5:455343d54cdd89cb5a3b5ad537ea99d0",
-                    "name": "Twilight: Original Motion Picture Soundtrack",
-                    "artists": [
-                        {
-                            "__model__": "Artist",
-                            "uri": "local:artist:md5:54e4db2d5624f80b0cc290346e696756",
-                            "name": "Various Artists",
-                            "musicbrainz_id": "89ad4ac3-39f7-470e-963a-56509c546377"
-                        }
-                    ],
-                    "num_tracks": 12,
-                    "num_discs": 1,
-                    "date": "2008-11-04",
-                    "musicbrainz_id": "b4889eaf-d9f4-434c-a68d-69227b12b6a4"
-                },
-                "composers": [
-                    {
-                        "__model__": "Artist",
-                        "uri": "local:artist:md5:4d49cbca0b347e0a89047bb019d2779d",
-                        "name": "Matt Bellamy"
-                    }
-                ],
-                "genre": "Rock",
-                "track_no": 1,
-                "disc_no": 1,
-                "date": "2008-11-04",
-                "length": 211121,
-                "musicbrainz_id": "ff1e3e1a-f6e8-4692-b426-355880383bb6",
-                "last_modified": 1672712949510
-            }
-        },
-        "time_position": 67578
-    }
-}
-#+end_src
-** TODO Fix bug in Jellyfin scrobbles that spam more scrobbles after completion :scrobbling:videos:bug:
-** TODO Fix bug in podcast scrobbling where a second scrobble is created after completion :scrobbling:podcasts:bug:

vrobbler.conf.example

@@ -20,6 +20,11 @@ VROBBLER_THESPORTSDB_API_KEY="<key>"
 VROBBLER_THEAUDIODB_API_KEY="<key>"
 VROBBLER_IGDB_CLIENT_ID="<id>"
 VROBBLER_IGDB_CLIENT_SECRET="<key>"
+VROBBLER_COMICVINE_API_KEY="<key>"
+VROBBLER_TODOIST_CLIENT_ID="<id>"
+VROBBLER_TODOIST_CLIENT_SECRET="<key>"
+VROBBLER_GOOGLE_API_KEY="<key>"
+VROBBLER_LICHESS_API_KEY = "<key>"
 
 # Storages
 # VROBBLER_DATABASE_URL="postgres://USER:PASSWORD@HOST:PORT/NAME"

vrobbler/apps/beers/admin.py

@@ -0,0 +1,34 @@
+from beers.models import Beer, BeerProducer, BeerStyle
+from django.contrib import admin
+from scrobbles.admin import ScrobbleInline
+
+
+class BeerInline(admin.TabularInline):
+    model = Beer
+    extra = 0
+
+
+@admin.register(BeerStyle)
+class BeerStyle(admin.ModelAdmin):
+    date_hierarchy = "created"
+    search_fields = ("name",)
+
+
+@admin.register(BeerProducer)
+class BeerProducer(admin.ModelAdmin):
+    date_hierarchy = "created"
+    search_fields = ("name",)
+
+
+@admin.register(Beer)
+class BeerAdmin(admin.ModelAdmin):
+    date_hierarchy = "created"
+    list_display = (
+        "uuid",
+        "title",
+    )
+    ordering = ("-created",)
+    search_fields = ("title",)
+    inlines = [
+        ScrobbleInline,
+    ]

vrobbler/apps/beers/apps.py

@@ -0,0 +1,5 @@
+from django.apps import AppConfig
+
+
+class BeersConfig(AppConfig):
+    name = "beers"

vrobbler/apps/beers/migrations/0001_initial.py

@@ -0,0 +1,133 @@
+# Generated by Django 4.2.16 on 2024-10-22 21:26
+
+from django.db import migrations, models
+import django_extensions.db.fields
+import taggit.managers
+import uuid
+
+
+class Migration(migrations.Migration):
+
+    initial = True
+
+    dependencies = [
+        ("scrobbles", "0065_alter_scrobble_log"),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="BeerProducer",
+            fields=[
+                (
+                    "id",
+                    models.BigAutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                (
+                    "created",
+                    django_extensions.db.fields.CreationDateTimeField(
+                        auto_now_add=True, verbose_name="created"
+                    ),
+                ),
+                (
+                    "modified",
+                    django_extensions.db.fields.ModificationDateTimeField(
+                        auto_now=True, verbose_name="modified"
+                    ),
+                ),
+                ("description", models.TextField(blank=True, null=True)),
+                (
+                    "location",
+                    models.CharField(blank=True, max_length=255, null=True),
+                ),
+            ],
+            options={
+                "get_latest_by": "modified",
+                "abstract": False,
+            },
+        ),
+        migrations.CreateModel(
+            name="Beer",
+            fields=[
+                (
+                    "id",
+                    models.BigAutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                (
+                    "created",
+                    django_extensions.db.fields.CreationDateTimeField(
+                        auto_now_add=True, verbose_name="created"
+                    ),
+                ),
+                (
+                    "modified",
+                    django_extensions.db.fields.ModificationDateTimeField(
+                        auto_now=True, verbose_name="modified"
+                    ),
+                ),
+                (
+                    "uuid",
+                    models.UUIDField(
+                        blank=True,
+                        default=uuid.uuid4,
+                        editable=False,
+                        null=True,
+                    ),
+                ),
+                (
+                    "title",
+                    models.CharField(blank=True, max_length=255, null=True),
+                ),
+                (
+                    "run_time_seconds",
+                    models.IntegerField(blank=True, null=True),
+                ),
+                (
+                    "run_time_ticks",
+                    models.PositiveBigIntegerField(blank=True, null=True),
+                ),
+                ("description", models.TextField(blank=True, null=True)),
+                ("ibu", models.SmallIntegerField(blank=True, null=True)),
+                ("abv", models.FloatField(blank=True, null=True)),
+                (
+                    "style",
+                    models.CharField(blank=True, max_length=100, null=True),
+                ),
+                ("non_alcoholic", models.BooleanField(default=False)),
+                (
+                    "beeradvocate_id",
+                    models.CharField(blank=True, max_length=255, null=True),
+                ),
+                (
+                    "beeradvocate_score",
+                    models.SmallIntegerField(blank=True, null=True),
+                ),
+                (
+                    "untappd_id",
+                    models.CharField(blank=True, max_length=255, null=True),
+                ),
+                (
+                    "genre",
+                    taggit.managers.TaggableManager(
+                        blank=True,
+                        help_text="A comma-separated list of tags.",
+                        through="scrobbles.ObjectWithGenres",
+                        to="scrobbles.Genre",
+                        verbose_name="Tags",
+                    ),
+                ),
+            ],
+            options={
+                "abstract": False,
+            },
+        ),
+    ]

vrobbler/apps/beers/migrations/0002_beer_beeradvocate_image_beer_producer_and_more.py

@@ -0,0 +1,36 @@
+# Generated by Django 4.2.16 on 2024-10-22 21:34
+
+from django.db import migrations, models
+import django.db.models.deletion
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("beers", "0001_initial"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="beer",
+            name="beeradvocate_image",
+            field=models.ImageField(
+                blank=True, null=True, upload_to="beers/beeradvcoate/"
+            ),
+        ),
+        migrations.AddField(
+            model_name="beer",
+            name="producer",
+            field=models.ForeignKey(
+                blank=True,
+                null=True,
+                on_delete=django.db.models.deletion.DO_NOTHING,
+                to="beers.beerproducer",
+            ),
+        ),
+        migrations.AddField(
+            model_name="beerproducer",
+            name="beeradvocate_id",
+            field=models.CharField(blank=True, max_length=255, null=True),
+        ),
+    ]

vrobbler/apps/beers/migrations/0003_beerstyle_remove_beer_beeradvocate_image_and_more.py

@@ -0,0 +1,75 @@
+# Generated by Django 4.2.16 on 2024-10-22 21:47
+
+from django.db import migrations, models
+import django_extensions.db.fields
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("beers", "0002_beer_beeradvocate_image_beer_producer_and_more"),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="BeerStyle",
+            fields=[
+                (
+                    "id",
+                    models.BigAutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                (
+                    "created",
+                    django_extensions.db.fields.CreationDateTimeField(
+                        auto_now_add=True, verbose_name="created"
+                    ),
+                ),
+                (
+                    "modified",
+                    django_extensions.db.fields.ModificationDateTimeField(
+                        auto_now=True, verbose_name="modified"
+                    ),
+                ),
+                ("description", models.TextField(blank=True, null=True)),
+            ],
+            options={
+                "get_latest_by": "modified",
+                "abstract": False,
+            },
+        ),
+        migrations.RemoveField(
+            model_name="beer",
+            name="beeradvocate_image",
+        ),
+        migrations.RemoveField(
+            model_name="beer",
+            name="style",
+        ),
+        migrations.AddField(
+            model_name="beer",
+            name="untappd_image",
+            field=models.ImageField(
+                blank=True, null=True, upload_to="beers/untappd/"
+            ),
+        ),
+        migrations.AddField(
+            model_name="beer",
+            name="untappd_rating",
+            field=models.FloatField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name="beerproducer",
+            name="untappd_id",
+            field=models.CharField(blank=True, max_length=255, null=True),
+        ),
+        migrations.AddField(
+            model_name="beer",
+            name="styles",
+            field=models.ManyToManyField(to="beers.beerstyle"),
+        ),
+    ]

vrobbler/apps/beers/migrations/0004_beerproducer_name_beerproducer_uuid_beerstyle_name_and_more.py

@@ -0,0 +1,47 @@
+# Generated by Django 4.2.16 on 2024-10-22 21:52
+
+from django.db import migrations, models
+import uuid
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("beers", "0003_beerstyle_remove_beer_beeradvocate_image_and_more"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="beerproducer",
+            name="name",
+            field=models.CharField(default="Untitled", max_length=255),
+            preserve_default=False,
+        ),
+        migrations.AddField(
+            model_name="beerproducer",
+            name="uuid",
+            field=models.UUIDField(
+                blank=True, default=uuid.uuid4, editable=False, null=True
+            ),
+        ),
+        migrations.AddField(
+            model_name="beerstyle",
+            name="name",
+            field=models.CharField(default="Untitled", max_length=255),
+            preserve_default=False,
+        ),
+        migrations.AddField(
+            model_name="beerstyle",
+            name="uuid",
+            field=models.UUIDField(
+                blank=True, default=uuid.uuid4, editable=False, null=True
+            ),
+        ),
+        migrations.AlterField(
+            model_name="beer",
+            name="styles",
+            field=models.ManyToManyField(
+                related_name="styles", to="beers.beerstyle"
+            ),
+        ),
+    ]

vrobbler/apps/beers/migrations/0005_alter_beer_run_time_seconds.py

@@ -0,0 +1,21 @@
+# Generated by Django 4.2.16 on 2025-01-22 03:55
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        (
+            "beers",
+            "0004_beerproducer_name_beerproducer_uuid_beerstyle_name_and_more",
+        ),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="beer",
+            name="run_time_seconds",
+            field=models.IntegerField(default=900),
+        ),
+    ]

vrobbler/apps/beers/models.py

@@ -0,0 +1,147 @@
+from dataclasses import dataclass
+from typing import Optional
+from uuid import uuid4
+
+from beers.untappd import get_beer_from_untappd_id
+from django.apps import apps
+from django.db import models
+from django.urls import reverse
+from django_extensions.db.models import TimeStampedModel
+from imagekit.models import ImageSpecField
+from imagekit.processors import ResizeToFit
+from scrobbles.dataclasses import BaseLogData
+from scrobbles.mixins import ScrobblableConstants, ScrobblableMixin
+
+BNULL = {"blank": True, "null": True}
+
+
+@dataclass
+class BeerLogData(BaseLogData):
+    rating: Optional[str] = None
+
+
+class BeerStyle(TimeStampedModel):
+    uuid = models.UUIDField(default=uuid4, editable=False, **BNULL)
+    name = models.CharField(max_length=255)
+    description = models.TextField(**BNULL)
+
+    def __str__(self):
+        return self.name
+
+
+class BeerProducer(TimeStampedModel):
+    uuid = models.UUIDField(default=uuid4, editable=False, **BNULL)
+    name = models.CharField(max_length=255)
+    description = models.TextField(**BNULL)
+    location = models.CharField(max_length=255, **BNULL)
+    beeradvocate_id = models.CharField(max_length=255, **BNULL)
+    untappd_id = models.CharField(max_length=255, **BNULL)
+
+    def find_or_create(cls, title: str) -> "BeerProducer":
+        return cls.objects.filter(title=title).first()
+
+    def __str__(self):
+        return self.name
+
+
+class Beer(ScrobblableMixin):
+    description = models.TextField(**BNULL)
+    ibu = models.SmallIntegerField(**BNULL)
+    abv = models.FloatField(**BNULL)
+    styles = models.ManyToManyField(BeerStyle, related_name="styles")
+    non_alcoholic = models.BooleanField(default=False)
+    beeradvocate_id = models.CharField(max_length=255, **BNULL)
+    beeradvocate_score = models.SmallIntegerField(**BNULL)
+    untappd_image = models.ImageField(upload_to="beers/untappd/", **BNULL)
+    untappd_image_small = ImageSpecField(
+        source="untappd_image",
+        processors=[ResizeToFit(100, 100)],
+        format="JPEG",
+        options={"quality": 60},
+    )
+    untappd_image_medium = ImageSpecField(
+        source="untappd_image",
+        processors=[ResizeToFit(300, 300)],
+        format="JPEG",
+        options={"quality": 75},
+    )
+    untappd_id = models.CharField(max_length=255, **BNULL)
+    untappd_rating = models.FloatField(**BNULL)
+    producer = models.ForeignKey(
+        BeerProducer, on_delete=models.DO_NOTHING, **BNULL
+    )
+
+    def get_absolute_url(self) -> str:
+        return reverse("beers:beer_detail", kwargs={"slug": self.uuid})
+
+    def __str__(self):
+        return f"{self.title} by {self.producer}"
+
+    @property
+    def subtitle(self):
+        return self.producer.name
+
+    @property
+    def strings(self) -> ScrobblableConstants:
+        return ScrobblableConstants(verb="Drinking", tags="beer")
+
+    @property
+    def beeradvocate_link(self) -> str:
+        link = ""
+        if self.producer and self.beeradvocate_id:
+            if self.beeradvocate_id:
+                link = f"https://www.beeradvocate.com/beer/profile/{self.producer.beeradvocate_id}/{self.beeradvocate_id}/"
+        return link
+
+    @property
+    def untappd_link(self) -> str:
+        link = ""
+        if self.untappd_id:
+            link = f"https://www.untappd.com/beer/{self.untappd_id}/"
+        return link
+
+    @property
+    def primary_image_url(self) -> str:
+        url = ""
+        if self.untappd_image:
+            url = self.untappd_image.url
+        return url
+
+    @property
+    def logdata_cls(self):
+        return BeerLogData
+
+    @classmethod
+    def find_or_create(cls, untappd_id: str) -> "Beer":
+        beer = cls.objects.filter(untappd_id=untappd_id).first()
+
+        if not beer:
+            beer_dict = get_beer_from_untappd_id(untappd_id)
+            producer_dict = {}
+            style_ids = []
+            for key in list(beer_dict.keys()):
+                if "producer__" in key:
+                    pkey = key.replace("producer__", "")
+                    producer_dict[pkey] = beer_dict.pop(key)
+                if "styles" in key:
+                    for style in beer_dict.pop("styles"):
+                        style_inst, created = BeerStyle.objects.get_or_create(
+                            name=style
+                        )
+                        style_ids.append(style_inst.id)
+
+            producer, _created = BeerProducer.objects.get_or_create(
+                **producer_dict
+            )
+            beer_dict["producer_id"] = producer.id
+            beer = Beer.objects.create(**beer_dict)
+            for style_id in style_ids:
+                beer.styles.add(style_id)
+
+        return beer
+
+    def scrobbles(self, user_id):
+        Scrobble = apps.get_model("scrobbles", "Scrobble")
+        return Scrobble.objects.filter(user_id=user_id, beer=self).order_by(
+            "-timestamp"
+        )

vrobbler/apps/beers/untappd.py

@@ -0,0 +1,142 @@
+import logging
+from typing import Optional
+
+import requests
+from bs4 import BeautifulSoup
+
+logger = logging.getLogger(__name__)
+
+UNTAPPD_URL = "https://untappd.com/beer/{id}"
+
+
+def get_first(key: str, result: dict) -> str:
+    obj = ""
+    if obj_list := result.get(key):
+        obj = obj_list[0]
+    return obj
+
+
+def get_title_from_soup(soup) -> str:
+    title = ""
+    try:
+        title = soup.find("h1").get_text()
+    except AttributeError:
+        pass
+    except ValueError:
+        pass
+    return title
+
+
+def get_description_from_soup(soup) -> str:
+    desc = ""
+    try:
+        desc = (
+            soup.find(class_="beer-descrption-read-less")
+            .get_text()
+            .replace("Show Less", "")
+            .strip()
+        )
+    except AttributeError:
+        pass
+    except ValueError:
+        pass
+    return desc
+
+
+def get_styles_from_soup(soup) -> list[str]:
+    styles = []
+    try:
+        styles = soup.find("p", class_="style").get_text().split(" - ")
+    except AttributeError:
+        pass
+    except ValueError:
+        pass
+    return styles
+
+
+def get_abv_from_soup(soup) -> Optional[float]:
+    abv = None
+    try:
+        abv = soup.find(class_="abv").get_text()
+        if abv:
+            abv = float(abv.strip("\n").strip("% ABV").strip())
+    except AttributeError:
+        pass
+    except ValueError:
+        pass
+    except TypeError:
+        pass
+    return abv
+
+
+def get_ibu_from_soup(soup) -> Optional[int]:
+    ibu = None
+    try:
+        ibu = soup.find(class_="ibu").get_text()
+        if ibu:
+            ibu = int(ibu.strip("\n").strip(" IBU").strip())
+    except AttributeError:
+        pass
+    except ValueError:
+        ibu = None
+    return ibu
+
+
+def get_rating_from_soup(soup) -> str:
+    rating = ""
+    try:
+        rating = float(
+            soup.find(class_="num").get_text().strip("(").strip(")")
+        )
+    except AttributeError:
+        rating = None
+    except ValueError:
+        rating = None
+    return rating
+
+
+def get_producer_id_from_soup(soup) -> str:
+    id = ""
+    try:
+        id = soup.find(class_="brewery").find("a")["href"].strip("/")
+    except ValueError:
+        pass
+    except IndexError:
+        pass
+    return id
+
+
+def get_producer_name_from_soup(soup) -> str:
+    name = ""
+    try:
+        name = soup.find(class_="brewery").find("a").get_text()
+    except AttributeError:
+        pass
+    except ValueError:
+        pass
+    return name
+
+
+def get_beer_from_untappd_id(untappd_id: str) -> dict:
+    beer_url = UNTAPPD_URL.format(id=untappd_id)
+    headers = {"User-Agent": "Vrobbler 0.11.12"}
+    response = requests.get(beer_url, headers=headers)
+    beer_dict = {"untappd_id": untappd_id}
+
+    if response.status_code != 200:
+        logger.warn(
+            "Bad response from untappd.com", extra={"response": response}
+        )
+        return beer_dict
+
+    soup = BeautifulSoup(response.text, "html.parser")
+    beer_dict["title"] = get_title_from_soup(soup)
+    beer_dict["description"] = get_description_from_soup(soup)
+    beer_dict["styles"] = get_styles_from_soup(soup)
+    beer_dict["abv"] = get_abv_from_soup(soup)
+    beer_dict["ibu"] = get_ibu_from_soup(soup)
+    beer_dict["untappd_rating"] = get_rating_from_soup(soup)
+    beer_dict["producer__untappd_id"] = get_producer_id_from_soup(soup)
+    beer_dict["producer__name"] = get_producer_name_from_soup(soup)
+
+    return beer_dict

vrobbler/apps/beers/urls.py

@@ -0,0 +1,14 @@
+from django.urls import path
+from beers import views
+
+app_name = "beers"
+
+
+urlpatterns = [
+    path("beers/", views.BeerListView.as_view(), name="beer_list"),
+    path(
+        "beers/<slug:slug>/",
+        views.BeerDetailView.as_view(),
+        name="beer_detail",
+    ),
+]

vrobbler/apps/beers/views.py

@@ -0,0 +1,11 @@
+from beers.models import Beer
+
+from scrobbles.views import ScrobbleableListView, ScrobbleableDetailView
+
+
+class BeerListView(ScrobbleableListView):
+    model = Beer
+
+
+class BeerDetailView(ScrobbleableDetailView):
+    model = Beer

vrobbler/apps/boardgames/admin.py

@@ -1,6 +1,11 @@
 from django.contrib import admin
 
-from boardgames.models import BoardGame, BoardGamePublisher
+from boardgames.models import (
+    BoardGame,
+    BoardGameLocation,
+    BoardGamePublisher,
+    BoardGameDesigner,
+)
 
 from scrobbles.admin import ScrobbleInline
 
@@ -15,13 +20,34 @@ class BoardGamePublisherAdmin(admin.ModelAdmin):
     ordering = ("-created",)
 
 
+@admin.register(BoardGameDesigner)
+class BoardGameDesignerAdmin(admin.ModelAdmin):
+    date_hierarchy = "created"
+    list_display = (
+        "name",
+        "uuid",
+    )
+    ordering = ("-created",)
+
+
+@admin.register(BoardGameLocation)
+class BoardGameLocationAdmin(admin.ModelAdmin):
+    date_hierarchy = "created"
+    list_display = (
+        "name",
+        "uuid",
+        "geo_location",
+    )
+    ordering = ("-created",)
+
+
 @admin.register(BoardGame)
-class GameAdmin(admin.ModelAdmin):
+class BoardGameAdmin(admin.ModelAdmin):
     date_hierarchy = "created"
     list_display = (
         "bggeek_id",
         "title",
-        "published_date",
+        "published_year",
     )
     search_fields = ("title",)
     ordering = ("-created",)

vrobbler/apps/boardgames/bgg.py

@@ -1,8 +1,15 @@
+import csv
+import json
 import logging
-from typing import Optional
+from typing import TYPE_CHECKING, Optional
 
 import requests
 from bs4 import BeautifulSoup
+from django.contrib.auth import get_user_model
+
+User = get_user_model()
+if TYPE_CHECKING:
+    from scrobbles.models import Scrobble
 
 logger = logging.getLogger(__name__)
 
@@ -90,3 +97,57 @@ def lookup_boardgame_from_bgg(lookup_id: str) -> dict:
         }
 
     return game_dict
+
+
+def push_scrobble_to_bgg(scrobble: "Scrobble", user: User) -> Optional[bool]:
+    bgg_username = "secstate"  # user.profile.bgg_username
+    bgg_password = "yYFCKnfo8AK89lc68q0S"
+
+    if not bgg_username or bgg_password:
+        return
+
+    login_payload = {
+        "credentials": {"username": bgg_username, "password": bgg_password}
+    }
+    headers = {"content-type": "application/json"}
+
+    # TODO Look up past plays for scrobble.media_obj.bggeek_id, and make sure we haven't scrobbled this before
+
+    with requests.Session() as s:
+        p = s.post(
+            "https://boardgamegeek.com/login/api/v1",
+            data=json.dumps(login_payload),
+            headers=headers,
+        )
+        players = []
+        if scrobble.log:
+            for player in scrobble.log.get("players"):
+                player_person = Person.objects.filter(
+                    id=player.get("person_id")
+                ).first()
+                if player_person.get("bgg_username"):
+                    player["username"] = player_person.get("bgg_username")
+                player["name"] = player_person.get("name")
+                player["win"] = player.get("win")
+                # player["role"] = player.get("role")
+                player["new"] = player.get("new")
+                player["score"] = player.get("score")
+                players.append(player)
+
+        play_payload = {
+            "playdate": scrobble.timestamp.date.strftime("%Y-%m-%d"),
+            "length": scrobble.playback_position_seconds / 60,
+            "comments": "Uploaded from Vrobbler",
+            "location": scrobble.log.location or None,
+            "objectid": scrobble.media_obj.bggeek_id,
+            "quantity": "1",
+            "action": "save",
+            "players": players,
+            "objecttype": "thing",
+            "ajax": 1,
+        }
+        r = s.post(
+            "https://boardgamegeek.com/geekplay.php",
+            data=json.dumps(play_payload),
+            headers=headers,
+        )

vrobbler/apps/boardgames/migrations/0007_alter_boardgame_run_time_seconds.py

@@ -0,0 +1,18 @@
+# Generated by Django 4.2.16 on 2025-01-22 03:55
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("boardgames", "0006_alter_boardgame_genre"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="boardgame",
+            name="run_time_seconds",
+            field=models.IntegerField(default=900),
+        ),
+    ]

vrobbler/apps/boardgames/migrations/0008_boardgamedesigner_and_more.py

@@ -0,0 +1,167 @@
+# Generated by Django 4.2.19 on 2025-07-03 01:57
+
+from django.db import migrations, models
+import django.db.models.deletion
+import django_extensions.db.fields
+import uuid
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("locations", "0007_alter_geolocation_run_time_seconds"),
+        ("boardgames", "0007_alter_boardgame_run_time_seconds"),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="BoardGameDesigner",
+            fields=[
+                (
+                    "id",
+                    models.BigAutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                (
+                    "created",
+                    django_extensions.db.fields.CreationDateTimeField(
+                        auto_now_add=True, verbose_name="created"
+                    ),
+                ),
+                (
+                    "modified",
+                    django_extensions.db.fields.ModificationDateTimeField(
+                        auto_now=True, verbose_name="modified"
+                    ),
+                ),
+                ("name", models.CharField(max_length=255)),
+                (
+                    "uuid",
+                    models.UUIDField(
+                        blank=True,
+                        default=uuid.uuid4,
+                        editable=False,
+                        null=True,
+                    ),
+                ),
+                ("bgg_id", models.IntegerField(blank=True, null=True)),
+                ("bio", models.TextField(blank=True, null=True)),
+            ],
+            options={
+                "get_latest_by": "modified",
+                "abstract": False,
+            },
+        ),
+        migrations.RenameField(
+            model_name="boardgamepublisher",
+            old_name="igdb_id",
+            new_name="bgg_id",
+        ),
+        migrations.AddField(
+            model_name="boardgame",
+            name="bgstats_id",
+            field=models.UUIDField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name="boardgame",
+            name="cooperative",
+            field=models.BooleanField(default=False),
+        ),
+        migrations.AddField(
+            model_name="boardgame",
+            name="expansion_for_boardgame",
+            field=models.ForeignKey(
+                blank=True,
+                null=True,
+                on_delete=django.db.models.deletion.DO_NOTHING,
+                to="boardgames.boardgame",
+            ),
+        ),
+        migrations.AddField(
+            model_name="boardgame",
+            name="highest_wins",
+            field=models.BooleanField(default=True),
+        ),
+        migrations.AddField(
+            model_name="boardgame",
+            name="max_play_time",
+            field=models.IntegerField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name="boardgame",
+            name="min_play_time",
+            field=models.IntegerField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name="boardgame",
+            name="no_points",
+            field=models.BooleanField(default=False),
+        ),
+        migrations.AddField(
+            model_name="boardgame",
+            name="uses_teams",
+            field=models.BooleanField(default=False),
+        ),
+        migrations.CreateModel(
+            name="BoardGameLocation",
+            fields=[
+                (
+                    "id",
+                    models.BigAutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                (
+                    "created",
+                    django_extensions.db.fields.CreationDateTimeField(
+                        auto_now_add=True, verbose_name="created"
+                    ),
+                ),
+                (
+                    "modified",
+                    django_extensions.db.fields.ModificationDateTimeField(
+                        auto_now=True, verbose_name="modified"
+                    ),
+                ),
+                ("name", models.CharField(max_length=255)),
+                (
+                    "uuid",
+                    models.UUIDField(
+                        blank=True,
+                        default=uuid.uuid4,
+                        editable=False,
+                        null=True,
+                    ),
+                ),
+                ("bgstats_id", models.UUIDField(blank=True, null=True)),
+                ("description", models.TextField(blank=True, null=True)),
+                (
+                    "geo_location",
+                    models.ForeignKey(
+                        blank=True,
+                        null=True,
+                        on_delete=django.db.models.deletion.DO_NOTHING,
+                        to="locations.geolocation",
+                    ),
+                ),
+            ],
+            options={
+                "get_latest_by": "modified",
+                "abstract": False,
+            },
+        ),
+        migrations.AddField(
+            model_name="boardgame",
+            name="designers",
+            field=models.ManyToManyField(
+                related_name="board_games", to="boardgames.boardgamedesigner"
+            ),
+        ),
+    ]

vrobbler/apps/boardgames/migrations/0009_alter_boardgame_cooperative_and_more.py

@@ -0,0 +1,33 @@
+# Generated by Django 4.2.19 on 2025-07-03 02:21
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("boardgames", "0008_boardgamedesigner_and_more"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="boardgame",
+            name="cooperative",
+            field=models.BooleanField(blank=True, default=False, null=True),
+        ),
+        migrations.AlterField(
+            model_name="boardgame",
+            name="highest_wins",
+            field=models.BooleanField(blank=True, default=True, null=True),
+        ),
+        migrations.AlterField(
+            model_name="boardgame",
+            name="no_points",
+            field=models.BooleanField(blank=True, default=False, null=True),
+        ),
+        migrations.AlterField(
+            model_name="boardgame",
+            name="uses_teams",
+            field=models.BooleanField(blank=True, default=False, null=True),
+        ),
+    ]

vrobbler/apps/boardgames/migrations/0010_boardgame_published_year.py

@@ -0,0 +1,18 @@
+# Generated by Django 4.2.19 on 2025-07-03 04:05
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("boardgames", "0009_alter_boardgame_cooperative_and_more"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="boardgame",
+            name="published_year",
+            field=models.IntegerField(blank=True, null=True),
+        ),
+    ]

vrobbler/apps/boardgames/models.py

@@ -1,8 +1,11 @@
+from functools import cached_property
 import logging
+from dataclasses import dataclass
 from datetime import datetime
 from typing import Optional
 from uuid import uuid4
 
+from django import forms
 import requests
 from boardgames.bgg import lookup_boardgame_from_bgg
 from django.conf import settings
@@ -12,18 +15,120 @@ from django.urls import reverse
 from django_extensions.db.models import TimeStampedModel
 from imagekit.models import ImageSpecField
 from imagekit.processors import ResizeToFit
-from scrobbles.mixins import ScrobblableMixin
-from vrobbler.apps.boardgames.bgg import lookup_boardgame_id_from_bgg
+from locations.models import GeoLocation
+from people.models import Person
+from scrobbles.dataclasses import BaseLogData, LongPlayLogData
+from scrobbles.mixins import ScrobblableConstants, ScrobblableMixin
 
 logger = logging.getLogger(__name__)
 BNULL = {"blank": True, "null": True}
 
 
+@dataclass
+class BoardGameScoreLogData(BaseLogData):
+    person_id: Optional[int] = None
+    bgg_username: Optional[str] = None
+    color: Optional[str] = None
+    character: Optional[str] = None
+    team: Optional[str] = None
+    score: Optional[int] = None
+    win: Optional[bool] = None
+    new: Optional[bool] = None
+    rank: Optional[int] = None
+    seat_order: Optional[int] = None
+    role: Optional[str] = None
+    rank: Optional[int] = None
+    seat_order: Optional[int] = None
+    role: Optional[str] = None
+    lichess_username: Optional[str] = None
+
+    @property
+    def person(self) -> Optional[Person]:
+        return Person.objects.filter(id=self.person_id).first()
+
+    @property
+    def name(self) -> str:
+        name = ""
+        if self.person:
+            name = self.person.name
+        return name
+
+    def __str__(self) -> str:
+        out = self.name
+        if self.score:
+            out += f" {self.score}"
+        if self.color:
+            out += f" ({self.color})"
+        if self.win:
+            out += f" [W]"
+        return out
+
+
+@dataclass
+class BoardGameLogData(BaseLogData, LongPlayLogData):
+    players: Optional[list[BoardGameScoreLogData]] = None
+    location_id: Optional[int] = None
+    difficulty: Optional[int] = None
+    solo: Optional[bool] = None
+    two_handed: Optional[bool] = None
+    expansion_ids: Optional[int] = None
+    moves: Optional[list] = None
+    rated: Optional[str] = None
+    speed: Optional[str] = None
+    variant: Optional[str] = None
+    lichess_id: Optional[int] = None
+    board: Optional[str] = None
+    rounds: Optional[int] = None
+    details: Optional[str] = None
+
+    _excluded_fields = {
+        "lichess_id",
+        "speed",
+        "rated",
+        "moves",
+        "variant",
+    }
+
+    @cached_property
+    def location(self):
+        if not self.location_id:
+            return
+        return BoardGameLocation.objects.filter(id=self.location_id).first()
+
+    @cached_property
+    def player_log(self) -> str:
+        if self.players:
+            return ", ".join(
+                [
+                    BoardGameScoreLogData(**player).__str__()
+                    for player in self.players
+                ]
+            )
+        return ""
+
+    @classmethod
+    def override_fields(cls) -> dict:
+        fields = {}
+        for base in cls.mro()[1:]:
+            if hasattr(base, "override_fields"):
+                base_fields = base.override_fields()
+                fields.update(base_fields)
+        custom_fields = {
+            "location_id": forms.ModelChoiceField(
+                queryset=BoardGameLocation.objects.all(),
+                required=False,
+                widget=forms.Select(),
+            )
+        }
+        fields.update(custom_fields)
+        return fields
+
+
 class BoardGamePublisher(TimeStampedModel):
     name = models.CharField(max_length=255)
     uuid = models.UUIDField(default=uuid4, editable=False, **BNULL)
     logo = models.ImageField(upload_to="games/platform-logos/", **BNULL)
-    igdb_id = models.IntegerField(**BNULL)
+    bgg_id = models.IntegerField(**BNULL)
 
     def __str__(self):
         return self.name
@@ -34,6 +139,39 @@ class BoardGamePublisher(TimeStampedModel):
         )
 
 
+class BoardGameDesigner(TimeStampedModel):
+    name = models.CharField(max_length=255)
+    uuid = models.UUIDField(default=uuid4, editable=False, **BNULL)
+    bgg_id = models.IntegerField(**BNULL)
+    bio = models.TextField(**BNULL)
+
+    def __str__(self) -> str:
+        return str(self.name)
+
+    def get_absolute_url(self):
+        return reverse(
+            "boardgames:designer_detail", kwargs={"slug": self.uuid}
+        )
+
+
+class BoardGameLocation(TimeStampedModel):
+    name = models.CharField(max_length=255)
+    uuid = models.UUIDField(default=uuid4, editable=False, **BNULL)
+    bgstats_id = models.UUIDField(**BNULL)
+    description = models.TextField(**BNULL)
+    geo_location = models.ForeignKey(
+        GeoLocation, **BNULL, on_delete=models.DO_NOTHING
+    )
+
+    def __str__(self) -> str:
+        return str(self.name)
+
+    def get_absolute_url(self):
+        return reverse(
+            "boardgames:location_detail", kwargs={"slug": self.uuid}
+        )
+
+
 class BoardGame(ScrobblableMixin):
     COMPLETION_PERCENT = getattr(
         settings, "BOARD_GAME_COMPLETION_PERCENT", 100
@@ -53,6 +191,10 @@ class BoardGame(ScrobblableMixin):
     publisher = models.ForeignKey(
         BoardGamePublisher, **BNULL, on_delete=models.DO_NOTHING
     )
+    designers = models.ManyToManyField(
+        BoardGameDesigner,
+        related_name="board_games",
+    )
     uuid = models.UUIDField(default=uuid4, editable=False, **BNULL)
     description = models.TextField(**BNULL)
     cover = models.ImageField(upload_to="boardgames/covers/", **BNULL)
@@ -85,8 +227,19 @@ class BoardGame(ScrobblableMixin):
     max_players = models.PositiveSmallIntegerField(**BNULL)
     min_players = models.PositiveSmallIntegerField(**BNULL)
     published_date = models.DateField(**BNULL)
+    published_year = models.IntegerField(**BNULL)
     recommended_age = models.PositiveSmallIntegerField(**BNULL)
     bggeek_id = models.CharField(max_length=255, **BNULL)
+    bgstats_id = models.UUIDField(**BNULL)
+    uses_teams = models.BooleanField(default=False, **BNULL)
+    cooperative = models.BooleanField(default=False, **BNULL)
+    highest_wins = models.BooleanField(default=True, **BNULL)
+    no_points = models.BooleanField(default=False, **BNULL)
+    min_play_time = models.IntegerField(**BNULL)
+    max_play_time = models.IntegerField(**BNULL)
+    expansion_for_boardgame = models.ForeignKey(
+        "self", **BNULL, on_delete=models.DO_NOTHING
+    )
 
     def __str__(self):
         return self.title
@@ -96,6 +249,14 @@ class BoardGame(ScrobblableMixin):
             "boardgames:boardgame_detail", kwargs={"slug": self.uuid}
         )
 
+    @property
+    def logdata_cls(self):
+        return BoardGameLogData
+
+    @property
+    def strings(self) -> ScrobblableConstants:
+        return ScrobblableConstants(verb="Playing", tags="game_die")
+
     def primary_image_url(self) -> str:
         url = ""
         if self.cover:
@@ -108,9 +269,6 @@ class BoardGame(ScrobblableMixin):
             link = f"https://boardgamegeek.com/boardgame/{self.bggeek_id}"
         return link
 
-    def get_start_url(self):
-        return reverse("scrobbles:start", kwargs={"uuid": self.uuid})
-
     def fix_metadata(self, data: dict = {}, force_update=False) -> None:
 
         if not self.published_date or force_update:
@@ -123,7 +281,12 @@ class BoardGame(ScrobblableMixin):
             publisher_name = data.pop("publisher_name")
 
             if year:
-                data["published_date"] = datetime(int(year), 1, 1)
+                data["published_year"] = int(year)
+
+            if not data["min_players"]:
+                data.pop("min_players")
+            if not data["min_players"]:
+                data.pop("max_players")
 
             # Fun trick for updating all fields at once
             BoardGame.objects.filter(pk=self.id).update(**data)
@@ -151,12 +314,12 @@ class BoardGame(ScrobblableMixin):
         cls, lookup_id: str, data: Optional[dict] = {}
     ) -> Optional["BoardGame"]:
         """Given a Lookup ID (either BGG or BGA ID), return a board game object"""
-        boardgame = None
+        boardgame = cls.objects.filter(bggeek_id=lookup_id).first()
 
-        if not data:
+        if not data or not boardgame:
             data = lookup_boardgame_from_bgg(lookup_id)
 
-        if data:
+        if data and not boardgame:
             boardgame, created = cls.objects.get_or_create(
                 title=data["title"], bggeek_id=lookup_id
             )

vrobbler/apps/boardgames/sources/lichess.py

@@ -0,0 +1,128 @@
+import berserk
+from boardgames.models import BoardGame
+from django.conf import settings
+from django.contrib.auth import get_user_model
+from scrobbles.models import Scrobble
+from scrobbles.notifications import ScrobbleNtfyNotification
+
+User = get_user_model()
+
+
+def import_chess_games_for_user_id(user_id: int, commit: bool = False) -> dict:
+    user = User.objects.get(id=user_id)
+
+    client = berserk.Client(
+        session=berserk.TokenSession(settings.LICHESS_API_KEY)
+    )
+    games = client.games.export_by_player(user.profile.lichess_username)
+    for game_dict in games:
+        chess, created = BoardGame.objects.get_or_create(title="Chess")
+        if created:
+            chess.run_time_seconds = 1800
+            chess.bggeek_id = 171
+            chess.save(update_fields=["run_time_seconds", "bggeek_id"])
+        scrobble = Scrobble.objects.filter(
+            user_id=user.id,
+            timestamp=game_dict.get("createdAt"),
+            board_game_id=chess.id,
+        ).first()
+
+        if scrobble:
+            continue
+
+        log_data = {
+            "variant": game_dict.get("variant"),
+            "lichess_id": game_dict.get("id"),
+            "rated": game_dict.get("rated"),
+            "speed": game_dict.get("speed"),
+            "moves": game_dict.get("moves"),
+            "players": [],
+        }
+
+        winner = game_dict.get("winner")
+        black_player = game_dict.get("players", {}).get("black", {})
+        white_player = game_dict.get("players", {}).get("white", {})
+
+        user_player = {
+            "user_id": user.id,
+            "lichess_username": user.profile.lichess_username,
+            "bgg_username": user.profile.bgg_username,
+            "color": "",
+            "win": False,
+        }
+        other_player = {"name_str": "", "color": "", "win": False}
+
+        if (
+            black_player.get("user", {}).get("name", "")
+            == user.profile.lichess_username
+        ):
+            user_player["color"] = "black"
+            if "aiLevel" in white_player.keys():
+                other_player["name_str"] = "aiLevel_" + str(
+                    white_player.get("aiLevel", "")
+                )
+            else:
+                other_player["name_str"] = white_player.get("user", {}).get(
+                    "name", ""
+                )
+                other_player["lichess_username"] = other_player["name_str"]
+
+            other_player["color"] = "white"
+            if winner == "black":
+                user_player["win"] = True
+            else:
+                other_player["win"] = True
+        if (
+            white_player.get("user", {}).get("name", "")
+            == user.profile.lichess_username
+        ):
+            user_player["color"] = "white"
+            if "aiLevel" in black_player.keys():
+                other_player["name_str"] = "aiLevel_" + str(
+                    black_player.get("aiLevel", "")
+                )
+            else:
+                other_player["name_str"] = black_player.get("user", {}).get(
+                    "name", ""
+                )
+                other_player["lichess_username"] = other_player["name_str"]
+            other_player["color"] = "black"
+            if winner == "white":
+                user_player["win"] = True
+            else:
+                other_player["win"] = True
+
+        log_data["players"].append(user_player)
+        log_data["players"].append(other_player)
+
+        scrobble_dict = {
+            "media_type": Scrobble.MediaType.BOARD_GAME,
+            "user_id": user.id,
+            "playback_position_seconds": (
+                game_dict.get("lastMoveAt") - game_dict.get("createdAt")
+            ).seconds,
+            "in_progress": False,
+            "played_to_completion": True,
+            "timestamp": game_dict.get("createdAt"),
+            "stop_timestamp": game_dict.get("lastMoveAt"),
+            "board_game_id": chess.id,
+            "source": "Lichess",
+            "timezone": user.profile.timezone,
+            "log": log_data,
+        }
+        if commit:
+            Scrobble.objects.create(**scrobble_dict)
+        return scrobble_dict
+
+
+def import_chess_games_for_all_users():
+    scrobbles_to_create = []
+    for user in User.objects.filter(profile__lichess_username__isnull=False):
+        scrobble_dict = import_chess_games_for_user_id(user.id)
+        scrobbles_to_create.append(Scrobble(**scrobble_dict))
+
+    if scrobbles_to_create:
+        created = Scrobble.objects.bulk_create(scrobbles_to_create)
+        for scrobble in created:
+            ScrobbleNtfyNotification(scrobble).send()
+    return scrobbles_to_create

vrobbler/apps/boardgames/urls.py

@@ -6,10 +6,12 @@ app_name = "boardgames"
 
 urlpatterns = [
     path(
-        "board-game/", views.BoardGameListView.as_view(), name="boardgame_list"
+        "board-games/",
+        views.BoardGameListView.as_view(),
+        name="boardgame_list",
     ),
     path(
-        "board-game/<slug:slug>/",
+        "board-games/<slug:slug>/",
         views.BoardGameDetailView.as_view(),
         name="boardgame_detail",
     ),

vrobbler/apps/boardgames/views.py

@@ -1,15 +1,14 @@
 from django.views import generic
 from boardgames.models import BoardGame, BoardGamePublisher
+from scrobbles.views import ScrobbleableListView, ScrobbleableDetailView
 
 
-class BoardGameListView(generic.ListView):
+class BoardGameListView(ScrobbleableListView):
     model = BoardGame
-    paginate_by = 20
 
 
-class BoardGameDetailView(generic.DetailView):
+class BoardGameDetailView(ScrobbleableDetailView):
     model = BoardGame
-    slug_field = "uuid"
 
 
 class BoardGamePublisherDetailView(generic.DetailView):

vrobbler/apps/books/admin.py

@@ -1,7 +1,5 @@
+from books.models import Author, Book, Paper
 from django.contrib import admin
-
-from books.models import Author, Book, Page
-
 from scrobbles.admin import ScrobbleInline
 
 
@@ -18,22 +16,36 @@ class AuthorAdmin(admin.ModelAdmin):
     search_fields = ("name",)
 
 
-@admin.register(Page)
-class PageAdmin(admin.ModelAdmin):
-    date_hierarchy = "created"
-    list_filter = ("book",)
-    ordering = ("book", "number")
-
-
 @admin.register(Book)
 class BookAdmin(admin.ModelAdmin):
     date_hierarchy = "created"
     list_display = (
         "title",
-        "isbn",
+        "author",
+        "issue_or_volume",
+        "isbn_13",
+        "first_publish_year",
+        "pages",
+    )
+    search_fields = ("name",)
+    ordering = ("-created",)
+    inlines = [
+        ScrobbleInline,
+    ]
+
+    def issue_or_volume(self, obj):
+        return obj.issue_number or obj.volume_number
+
+
+@admin.register(Paper)
+class BookAdmin(admin.ModelAdmin):
+    date_hierarchy = "created"
+    list_display = (
+        "title",
+        "subtitle",
+        "arxiv_id",
         "first_publish_year",
         "pages",
-        "openlibrary_id",
     )
     search_fields = ("name",)
     ordering = ("-created",)

vrobbler/apps/books/amazon.py

@@ -55,9 +55,7 @@ def scrape_data_from_amazon(url) -> dict:
     r = requests.get(url, headers=headers)
     if r.status_code == 200:
         soup = BeautifulSoup(r.text, "html.parser")
-        import pdb
-
-        pdb.set_trace()
+        # TODO Fix this scraper
         data_dict["rating"] = get_rating_from_soup(soup)
         data_dict["review"] = get_review_from_soup(soup)
     return data_dict

vrobbler/apps/books/constants.py

@@ -0,0 +1,9 @@
+#!/usr/bin/env python3
+
+BOOKS_TITLES_TO_IGNORE = [
+    "KOReader Quickstart Guide",
+    "zb2rhkSwygt9vjkAEBj7tP5KVgFqejJqsJ2W3bYsrgiiKK8XL",
+    "zb2rhchGpo7P27mofV9hYjT63d9ZaQnbQ6LSfzmkvsYzvARif",
+]
+
+READCOMICSONLINE_URL = "https://readcomicsonline.ru"

vrobbler/apps/books/koreader.py

@@ -1,22 +1,20 @@
-import codecs
 import logging
-import os
 import re
 import sqlite3
-from datetime import datetime
+from datetime import datetime, timedelta
 from enum import Enum
-from typing import Iterable, List
+from zoneinfo import ZoneInfo
 
-import pytz
 import requests
-from books.models import Author, Book, Page
-from books.openlibrary import get_author_openlibrary_id
-from django.db.models import Sum
-from pylast import httpx, tempfile
-from scrobbles.models import Scrobble
+from books.constants import BOOKS_TITLES_TO_IGNORE
+from django.apps import apps
+from django.contrib.auth import get_user_model
+from scrobbles.notifications import ScrobbleNtfyNotification
 from stream_sqlite import stream_sqlite
+from webdav.client import get_webdav_client
 
 logger = logging.getLogger(__name__)
+User = get_user_model()
 
 
 class KoReaderBookColumn(Enum):
@@ -43,208 +41,374 @@ class KoReaderPageStatColumn(Enum):
 
 
 def _sqlite_bytes(sqlite_url):
-    with httpx.stream("GET", sqlite_url) as r:
-        yield from r.iter_bytes(chunk_size=65_536)
+    with requests.get(sqlite_url, stream=True) as r:
+        yield from r.iter_content(chunk_size=65_536)
 
 
-def get_book_map_from_sqlite(rows: Iterable) -> dict:
+# Grace period between page reads for it to be a new scrobble
+SESSION_GAP_SECONDS = 1800  #  a half hour
+
+
+def get_author_str_from_row(row):
+    """Given a the raw author string from KoReader, convert it to a single line and
+    strip the middle initials, as OpenLibrary lookup usually fails with those.
+    """
+    ko_authors = row[KoReaderBookColumn.AUTHORS.value].replace("\n", ", ")
+    # Strip middle initials, OpenLibrary often fails with these
+    return re.sub(" [A-Z]. ", " ", ko_authors)
+
+
+def lookup_or_create_authors_from_author_str(ko_author_str: str) -> list:
+    """Takes a string of authors from KoReader and returns a list
+    of Authors from our database
+    """
+    from books.models import Author
+
+    author_str_list = ko_author_str.split(", ")
+    author_list = []
+    for author_str in author_str_list:
+        logger.debug(f"Looking up author {author_str}")
+        # KoReader gave us nothing, bail
+        if author_str == "N/A":
+            logger.warn(f"KoReader author string is N/A, no authors to find")
+            continue
+
+        author = Author.objects.filter(name=author_str).first()
+        if not author:
+            author = Author.objects.create(name=author_str)
+            # TODO Move these to async processes after importing
+            # author.fix_metadata()
+            logger.debug(f"Created author {author}")
+        author_list.append(author)
+    return author_list
+
+
+def create_book_from_row(row: list):
+    from books.models import Book
+
+    # No KoReader book yet, create it
+    author_str = get_author_str_from_row(row).replace("\x00", "")
+    total_pages = row[KoReaderBookColumn.PAGES.value]
+    run_time = total_pages * Book.AVG_PAGE_READING_SECONDS
+    book_title = row[KoReaderBookColumn.TITLE.value].replace("\x00", "")
+    if " - " in book_title:
+        split_title = book_title.split(" - ")
+        book_title = split_title[0]
+        if (not author_str or author_str == "N/A") and len(split_title) > 1:
+            author_str = split_title[1].split("_")[0]
+
+    clean_row = []
+    for value in row:
+        if isinstance(value, str):
+            value = value.replace("\x00", "")
+        clean_row.append(value)
+
+    book = Book.objects.create(
+        title=book_title.replace("_", ":"),
+        pages=total_pages,
+        koreader_data_by_hash={
+            str(row[KoReaderBookColumn.MD5.value]): {
+                "title": book_title,
+                "author_str": author_str,
+                "book_id": row[KoReaderBookColumn.ID.value],
+                "raw_row_data": clean_row,
+            }
+        },
+        run_time_seconds=run_time,
+    )
+    # TODO Move these to async processes after importing
+    # book.fix_metadata()
+
+    # Add authors
+    author_list = lookup_or_create_authors_from_author_str(author_str)
+    if author_list:
+        book.authors.add(*author_list)
+
+    # self._lookup_authors
+    return book
+
+
+def build_book_map(rows) -> dict:
     """Given an interable of sqlite rows from the books table, lookup existing
     books, create ones that don't exist, and return a mapping of koreader IDs to
     primary key IDs for page creation.
 
     """
+    from books.models import Book
+
     book_id_map = {}
 
     for book_row in rows:
+
+        if book_row[KoReaderBookColumn.TITLE.value] in BOOKS_TITLES_TO_IGNORE:
+            logger.info(
+                "[build_book_map] Ignoring book title that is likely garbage",
+                extra={"book_row": book_row, "media_type": "Book"},
+            )
+            continue
         book = Book.objects.filter(
-            koreader_md5=book_row[KoReaderBookColumn.MD5.value]
+            koreader_data_by_hash__icontains=book_row[
+                KoReaderBookColumn.MD5.value
+            ]
         ).first()
 
         if not book:
-            book, created = Book.objects.get_or_create(
-                title=book_row[KoReaderBookColumn.TITLE.value]
+            title = (
+                book_row[KoReaderBookColumn.TITLE.value]
+                .split(" - ")[0]
+                .lower()
+                .replace("\x00", "")
             )
+            book = Book.objects.filter(title=title).first()
 
-            if created:
-                total_pages = book_row[KoReaderBookColumn.PAGES.value]
-                run_time = total_pages * book.AVG_PAGE_READING_SECONDS
-                ko_authors = book_row[
-                    KoReaderBookColumn.AUTHORS.value
-                ].replace("\n", ", ")
-                # Strip middle initials, OpenLibrary often fails with these
-                ko_authors = re.sub(" [A-Z]. ", " ", ko_authors)
-                book_dict = {
-                    "title": book_row[KoReaderBookColumn.TITLE.value],
-                    "pages": total_pages,
-                    "koreader_md5": book_row[KoReaderBookColumn.MD5.value],
-                    "koreader_id": int(book_row[KoReaderBookColumn.ID.value]),
-                    "koreader_authors": ko_authors,
-                    "run_time_seconds": run_time,
-                }
-                Book.objects.filter(pk=book.id).update(**book_dict)
-
-                # Add authors
-                authors = ko_authors.split(", ")
-                author_list = []
-                for author_str in authors:
-                    logger.debug(f"Looking up author {author_str}")
-                    if author_str == "N/A":
-                        continue
-
-                    author = Author.objects.filter(name=author_str).first()
-                    if not author:
-                        author = Author.objects.create(
-                            name=author_str,
-                            openlibrary_id=get_author_openlibrary_id(
-                                author_str
-                            ),
-                        )
-                        author.fix_metadata()
-                        logger.debug(f"Created author {author}")
-                    book.authors.add(author)
-
-                # This will try to fix metadata by looking it up on OL
-                book.fix_metadata()
+        if not book:
+            book = create_book_from_row(book_row)
 
         book.refresh_from_db()
         total_seconds = 0
         if book_row[KoReaderBookColumn.TOTAL_READ_TIME.value]:
             total_seconds = book_row[KoReaderBookColumn.TOTAL_READ_TIME.value]
 
-        book_id_map[book_row[KoReaderBookColumn.ID.value]] = (
-            book.id,
-            total_seconds,
-        )
-
+        book_id_map[book_row[KoReaderBookColumn.ID.value]] = {
+            "book_id": book.id,
+            "hash": book_row[KoReaderBookColumn.MD5.value],
+            "total_seconds": total_seconds,
+        }
     return book_id_map
 
 
-def build_scrobbles_from_pages(
-    rows: Iterable, book_id_map: dict, user_id: int
-) -> List[Scrobble]:
-    new_scrobbles = []
+def build_page_data(page_rows: list, book_map: dict, user_tz=None) -> dict:
+    """Given rows of page data from KoReader, parse each row and build
+    scrobbles for our user, loading the page data into the page_data
+    field on the scrobble instance.
+    """
+    book_ids_not_found = []
+    for page_row in page_rows:
+        koreader_book_id = page_row[KoReaderPageStatColumn.ID_BOOK.value]
 
-    new_scrobbles = []
-    pages_found = []
-    book_read_time_map = {}
-    for page_row in rows:
-        koreader_id = page_row[KoReaderPageStatColumn.ID_BOOK.value]
-        if koreader_id not in book_id_map.keys():
+        if koreader_book_id not in book_map.keys():
+            book_ids_not_found.append(koreader_book_id)
             continue
+
+        if "pages" not in book_map[koreader_book_id].keys():
+            book_map[koreader_book_id]["pages"] = {}
+
         page_number = page_row[KoReaderPageStatColumn.PAGE.value]
-        ts = page_row[KoReaderPageStatColumn.START_TIME.value]
-        book_id = book_id_map[koreader_id][0]
-        book_read_time_map[book_id] = book_id_map[koreader_id][1]
+        duration = page_row[KoReaderPageStatColumn.DURATION.value]
+        start_ts = page_row[KoReaderPageStatColumn.START_TIME.value]
 
-        page, page_created = Page.objects.get_or_create(
-            book_id=book_id, number=page_number, user_id=user_id
+        book_map[koreader_book_id]["pages"][page_number] = {
+            "duration": duration,
+            "start_ts": start_ts,
+            "end_ts": start_ts + duration,
+        }
+    if book_ids_not_found:
+        logger.info(
+            f"Found pages for books not in file: {set(book_ids_not_found)}"
         )
-        if page_created:
-            page.start_time = datetime.utcfromtimestamp(ts).replace(
-                tzinfo=pytz.utc
+    return book_map
+
+
+def build_scrobbles_from_book_map(
+    book_map: dict, user: "User"
+) -> list["Scrobble"]:
+    Scrobble = apps.get_model("scrobbles", "Scrobble")
+
+    scrobbles_to_create = []
+
+    pages_not_found = []
+    for koreader_book_id, book_dict in book_map.items():
+        book_id = book_dict["book_id"]
+        if "pages" not in book_dict.keys():
+            pages_not_found.append(book_id)
+            continue
+
+        should_create_scrobble = False
+        scrobble_page_data = {}
+        playback_position_seconds = 0
+        prev_page_stats = {}
+        last_page_number = 0
+
+        pages_processed = 0
+        total_pages_read = len(book_map[koreader_book_id]["pages"])
+        ordered_pages = sorted(
+            book_map[koreader_book_id]["pages"].items(),
+            key=lambda x: x[1]["start_ts"],
+        )
+
+        for cur_page_number, stats in ordered_pages:
+            pages_processed += 1
+
+            seconds_from_last_page = 0
+            if prev_page_stats:
+                seconds_from_last_page = stats.get(
+                    "end_ts"
+                ) - prev_page_stats.get("start_ts")
+
+            playback_position_seconds = playback_position_seconds + stats.get(
+                "duration"
             )
-            page.duration_seconds = page_row[
-                KoReaderPageStatColumn.DURATION.value
-            ]
-            page.save(update_fields=["start_time", "duration_seconds"])
-        pages_found.append(page)
 
-    playback_position_seconds = 0
-    for page in set(pages_found):
-        # Add up page seconds to set the aggregate time of all pages to reading time
-        playback_position_seconds = (
-            playback_position_seconds + page.duration_seconds
-        )
-        if page.is_scrobblable:
-            # Check to see if a scrobble with this timestamp, book and user already exists
-            scrobble = Scrobble.objects.filter(
-                timestamp=page.start_time,
-                book_id=page.book_id,
-                user_id=user_id,
-            ).first()
-            if not scrobble:
-                logger.debug(
-                    f"Queueing scrobble for {page.book}, page {page.number}"
+            end_of_reading = pages_processed == total_pages_read
+            big_jump_to_this_page = (cur_page_number - last_page_number) > 10
+            is_session_gap = seconds_from_last_page > SESSION_GAP_SECONDS
+            if (
+                is_session_gap and not big_jump_to_this_page
+            ) or end_of_reading:
+                should_create_scrobble = True
+
+            if should_create_scrobble:
+                scrobble_page_data = dict(
+                    sorted(
+                        scrobble_page_data.items(),
+                        key=lambda x: x[1]["start_ts"],
+                    )
                 )
-                new_scrobble = Scrobble(
-                    book_id=page.book_id,
-                    user_id=user_id,
-                    source="KOReader",
-                    media_type=Scrobble.MediaType.BOOK,
-                    timestamp=page.start_time,
-                    played_to_completion=True,
-                    playback_position_seconds=playback_position_seconds,
-                    in_progress=False,
-                    book_pages_read=page.number,
-                    long_play_complete=False,
+                try:
+                    first_page = scrobble_page_data.get(
+                        list(scrobble_page_data.keys())[0]
+                    )
+                    last_page = scrobble_page_data.get(
+                        list(scrobble_page_data.keys())[-1]
+                    )
+                except IndexError:
+                    logger.error(
+                        "Could not process book, no page data found",
+                        extra={"scrobble_page_data": scrobble_page_data},
+                    )
+                    continue
+
+                timestamp = user.profile.get_timestamp_with_tz(
+                    datetime.fromtimestamp(int(first_page.get("start_ts")))
                 )
-                new_scrobbles.append(new_scrobble)
-            # After setting a scrobblable page, reset our accumulator
-            playback_position_seconds = 0
-    return new_scrobbles
+                stop_timestamp = user.profile.get_timestamp_with_tz(
+                    datetime.fromtimestamp(int(last_page.get("end_ts")))
+                )
+
+                # Adjust for Daylight Saving Time
+                if timestamp.dst() == timedelta(
+                    0
+                ) or stop_timestamp.dst() == timedelta(0):
+                    timestamp = timestamp - timedelta(hours=1)
+                    stop_timestamp = stop_timestamp - timedelta(hours=1)
+
+                scrobble = Scrobble.objects.filter(
+                    timestamp=timestamp,
+                    book_id=book_id,
+                    user_id=user.id,
+                ).first()
+
+                if not scrobble:
+                    logger.info(
+                        f"Queueing scrobble for {book_id}, page {cur_page_number}"
+                    )
+                    log_data = {
+                        "koreader_hash": book_dict.get("hash"),
+                        "page_data": scrobble_page_data,
+                        "pages_read": len(scrobble_page_data.keys()),
+                    }
+                    scrobbles_to_create.append(
+                        Scrobble(
+                            book_id=book_id,
+                            user_id=user.id,
+                            source="KOReader",
+                            media_type=Scrobble.MediaType.BOOK,
+                            timestamp=timestamp,
+                            log=log_data,
+                            stop_timestamp=stop_timestamp,
+                            playback_position_seconds=playback_position_seconds,
+                            in_progress=False,
+                            played_to_completion=True,
+                            long_play_complete=False,
+                            timezone=timestamp.tzinfo.name,
+                        )
+                    )
+                # Then start over
+                should_create_scrobble = False
+                playback_position_seconds = 0
+                scrobble_page_data = {}
+
+            # We accumulate pages for the scrobble until we should create a new one
+            scrobble_page_data[cur_page_number] = stats
+
+            last_page_number = cur_page_number
+            prev_page_stats = stats
+    if pages_not_found:
+        logger.info(f"Pages not found for books: {set(pages_not_found)}")
+    return scrobbles_to_create
 
 
-def enrich_koreader_scrobbles(scrobbles: list) -> None:
+def fix_long_play_stats_for_scrobbles(scrobbles: list) -> None:
     """Given a list of scrobbles, update pages read, long play seconds and check
     for media completion"""
 
     for scrobble in scrobbles:
-        scrobble.book_pages_read = scrobble.book.page_set.last().number
         # But if there's a next scrobble, set pages read to their starting page
-        #
-        if scrobble.next:
-            scrobble.book_pages_read = scrobble.next.book_pages_read - 1
-        scrobble.long_play_seconds = scrobble.book.page_set.filter(
-            number__lte=scrobble.book_pages_read
-        ).aggregate(Sum("duration_seconds"))["duration_seconds__sum"]
-
-        scrobble.save(update_fields=["book_pages_read", "long_play_seconds"])
-
-
-def process_koreader_sqlite_url(file_url, user_id) -> list:
-    book_id_map = {}
-    new_scrobbles = []
-
-    for table_name, pragma_table_info, rows in stream_sqlite(
-        _sqlite_bytes(file_url), max_buffer_size=1_048_576
-    ):
-        logger.debug(f"Found table {table_name} - processing")
-        if table_name == "book":
-            book_id_map = get_book_map_from_sqlite(rows)
-
-        if table_name == "page_stat_data":
-            new_scrobbles = build_scrobbles_from_pages(
-                rows, book_id_map, user_id
+        if scrobble.previous and not scrobble.previous.long_play_complete:
+            scrobble.long_play_seconds = scrobble.playback_position_seconds + (
+                scrobble.previous.long_play_seconds or 0
             )
-            logger.debug(f"Creating {len(new_scrobbles)} new scrobbles")
+        else:
+            scrobble.long_play_seconds = scrobble.playback_position_seconds
+        scrobble.log["book_pages_read"] = scrobble.calc_pages_read()
 
-    created = []
-    if new_scrobbles:
-        created = Scrobble.objects.bulk_create(new_scrobbles)
-        enrich_koreader_scrobbles(created)
-        logger.info(
-            f"Created {len(created)} scrobbles",
-            extra={"created_scrobbles": created},
-        )
-    return created
+        scrobble.save(update_fields=["log", "long_play_seconds"])
 
 
 def process_koreader_sqlite_file(file_path, user_id) -> list:
     """Given a sqlite file from KoReader, open the book table, iterate
     over rows creating scrobbles from each book found"""
-    # Create a SQL connection to our SQLite database
-    con = sqlite3.connect(file_path)
-    cur = con.cursor()
+    Scrobble = apps.get_model("scrobbles", "Scrobble")
 
-    book_id_map = get_book_map_from_sqlite(cur.execute("SELECT * FROM book"))
-    new_scrobbles = build_scrobbles_from_pages(
-        cur.execute("SELECT * from page_stat_data"), book_id_map, user_id
-    )
+    new_scrobbles = []
+    user = User.objects.filter(id=user_id).first()
+    tz = ZoneInfo("UTC")
+    if user:
+        tz = user.profile.tzinfo
 
+    is_os_file = "https://" not in file_path
+    if is_os_file:
+        # Loading sqlite file from local filesystem
+        con = sqlite3.connect(file_path)
+        cur = con.cursor()
+        try:
+            book_map = build_book_map(cur.execute("SELECT * FROM book"))
+        except sqlite3.OperationalError:
+            logger.warning("KOReader sqlite file had not table: book")
+            return new_scrobbles
+
+        book_map = build_page_data(
+            cur.execute(
+                "SELECT * from page_stat_data ORDER BY id_book, start_time"
+            ),
+            book_map,
+            tz,
+        )
+        new_scrobbles = build_scrobbles_from_book_map(book_map, user)
+    else:
+        # Streaming the sqlite file off S3
+        book_map = {}
+        for table_name, pragma_table_info, rows in stream_sqlite(
+            _sqlite_bytes(file_path), max_buffer_size=1_048_576
+        ):
+            logger.debug(f"Found table {table_name} - processing")
+            if table_name == "book":
+                book_map = build_book_map(rows)
+
+        for table_name, pragma_table_info, rows in stream_sqlite(
+            _sqlite_bytes(file_path), max_buffer_size=1_048_576
+        ):
+            if table_name == "page_stat_data":
+                book_map = build_page_data(rows, book_map, tz)
+                new_scrobbles = build_scrobbles_from_book_map(book_map, user)
+
+    logger.info(f"Creating {len(new_scrobbles)} new scrobbles")
     created = []
     if new_scrobbles:
         created = Scrobble.objects.bulk_create(new_scrobbles)
-        enrich_koreader_scrobbles(created)
+        if created:
+            ScrobbleNtfyNotification(created[-1]).send()
+        fix_long_play_stats_for_scrobbles(created)
         logger.info(
             f"Created {len(created)} scrobbles",
             extra={"created_scrobbles": created},
@@ -252,11 +416,17 @@ def process_koreader_sqlite_file(file_path, user_id) -> list:
     return created
 
 
-def process_koreader_sqlite(file_path: str, user_id: int) -> list:
-    is_os_file = "https://" not in file_path
+def fetch_file_from_webdav(user_id: int) -> str:
+    file_path = f"/tmp/{user_id}-koreader-import.sqlite3"
+    client = get_webdav_client(user_id)
 
-    if is_os_file:
-        created = process_koreader_sqlite_file(file_path, user_id)
-    else:
-        created = process_koreader_sqlite_url(file_path, user_id)
-    return created
+    if not client:
+        logger.warning("could not get webdav client for user")
+        # TODO maybe we raise an exception here?
+        return ""
+
+    client.download_sync(
+        remote_path="var/koreader/statistics.sqlite3",
+        local_path=file_path,
+    )
+    return file_path

vrobbler/apps/books/locg.py

@@ -1,6 +1,5 @@
 #!/usr/bin/env python3
 
-from enum import Enum
 from typing import Optional
 from bs4 import BeautifulSoup
 import requests

vrobbler/apps/books/management/commands/cleanup_book_scrobble_times.py

@@ -0,0 +1,42 @@
+#!/usr/bin/env python3
+import logging
+import pytz
+from datetime import datetime, timedelta
+from books.models import Book
+from django.core.management.base import BaseCommand
+from scrobbles.models import Scrobble
+from vrobbler.apps.books.koreader import fix_long_play_stats_for_scrobbles
+from vrobbler.apps.scrobbles.utils import timestamp_user_tz_to_utc
+
+
+logger = logging.getLogger(__name__)
+
+# Grace period between page reads for it to be a new scrobble
+SESSION_GAP_SECONDS = 1800  #  a half hour
+
+def update_scrobble_from_page_data(scrobble, commit=True):
+    page_list = list(scrobble.book_page_data.items())
+    first_page_start_ts = datetime.fromtimestamp(page_list[0][1]["start_ts"])
+    last_page_end_ts = datetime.fromtimestamp(page_list[-1][1]["end_ts"])
+
+    if (
+        datetime(2023, 10, 15) <= first_page_start_ts <= datetime(2023, 12, 15)
+    ):
+        first_page_start_ts.replace(tzinfo=pytz.timezone("Europe/Paris"))
+        last_page_end_ts.replace(tzinfo=pytz.timezone("Europe/Paris"))
+    else:
+        first_page_start_ts.replace(tzinfo=pytz.timezone("US/Eastern"))
+        last_page_end_ts.replace(tzinfo=pytz.timezone("US/Eastern"))
+
+    scrobble.timestamp = first_page_start_ts
+    scrobble.stop_timestamp = last_page_end_ts
+    if commit:
+        scrobble.save(update_fields=["timestamp", "stop_timestamp"])
+
+
+class Command(BaseCommand):
+    def handle(self, *args, **options):
+        scrobbles_to_create = []
+
+        for scrobble in Scrobble.objects.filter(media_type="Book", source="KOReader"):
+            update_scrobble_from_page_data(scrobble)

vrobbler/apps/books/management/commands/migrate_koreader_data_to_json.py

@@ -0,0 +1,160 @@
+import logging
+import pytz
+from datetime import datetime, timedelta
+from books.models import Book
+from django.core.management.base import BaseCommand
+from scrobbles.models import Scrobble
+from vrobbler.apps.books.koreader import fix_long_play_stats_for_scrobbles
+from vrobbler.apps.scrobbles.utils import timestamp_user_tz_to_utc
+
+
+logger = logging.getLogger(__name__)
+
+# Grace period between page reads for it to be a new scrobble
+SESSION_GAP_SECONDS = 1800  #  a half hour
+
+
+class Command(BaseCommand):
+    def handle(self, *args, **options):
+        scrobbles_to_create = []
+
+        for book in Book.objects.filter(koreader_id__isnull=False):
+            book.scrobble_set.all().delete()
+
+            koreader_data = book.koreader_data_by_hash or {}
+            if book.koreader_md5:
+                koreader_data[book.koreader_md5] = {
+                    "title": book.title,
+                    "book_id": book.koreader_id,
+                    "author_str": book.koreader_authors,
+                    "pages": book.pages,
+                }
+            book.koreader_data_by_hash = koreader_data
+            book.save(update_fields=["koreader_data_by_hash"])
+
+            # Next parse all this book's pages into new scrobbles
+            should_create_scrobble = False
+            scrobble_page_data = {}
+            playback_position_seconds = 0
+            prev_page = None
+
+            pages_processed = 0
+            total_pages = book.pages
+            for page in book.page_set.order_by("number"):
+                user = page.user
+                book_id = page.book.id
+                pages_processed += 1
+                scrobble_page_data[page.number] = {
+                    "duration": page.duration_seconds,
+                    "start_ts": page.start_time.timestamp(),
+                    "end_ts": page.end_time.timestamp(),
+                }
+                seconds_from_last_page = 0
+                if prev_page:
+                    seconds_from_last_page = (
+                        page.end_time.timestamp()
+                        - prev_page.start_time.timestamp()
+                    )
+                playback_position_seconds = (
+                    playback_position_seconds + page.duration_seconds
+                )
+
+                end_of_reading = pages_processed == total_pages
+                big_jump_to_this_page = False
+                if prev_page:
+                    big_jump_to_this_page = (
+                        page.number - prev_page.number
+                    ) > 10
+                if (
+                    seconds_from_last_page > SESSION_GAP_SECONDS
+                    and not big_jump_to_this_page
+                ):
+                    should_create_scrobble = True
+
+                if should_create_scrobble:
+                    first_page = scrobble_page_data.get(
+                        list(scrobble_page_data.keys())[0]
+                    )
+                    last_page = scrobble_page_data.get(
+                        list(scrobble_page_data.keys())[-1]
+                    )
+                    start_ts = int(first_page.get("start_ts"))
+                    end_ts = start_ts + playback_position_seconds
+
+                    timestamp = datetime.fromtimestamp(start_ts).replace(
+                        tzinfo=user.profile.tzinfo
+                    )
+                    stop_timestamp = datetime.fromtimestamp(end_ts).replace(
+                        tzinfo=user.profile.tzinfo
+                    )
+                    # Add a shim here temporarily to fix imports while we were in France
+                    # if date is between 10/15 and 12/15, cast it to Europe/Central
+                    if (
+                        datetime(2023, 10, 15).replace(
+                            tzinfo=pytz.timezone("Europe/Paris")
+                        )
+                        <= timestamp
+                        <= datetime(2023, 12, 15).replace(
+                            tzinfo=pytz.timezone("Europe/Paris")
+                        )
+                    ):
+                        timestamp.replace(tzinfo=pytz.timezone("Europe/Paris"))
+
+                    elif (
+                        timestamp.tzinfo._dst.seconds == 0
+                        or stop_timestamp.tzinfo._dst.seconds == 0
+                    ):
+                        timestamp = timestamp - timedelta(hours=1)
+                        stop_timestamp = stop_timestamp - timedelta(hours=1)
+
+                    scrobble = Scrobble.objects.filter(
+                        timestamp=timestamp,
+                        book_id=book_id,
+                        user_id=user.id,
+                    ).first()
+                    if scrobble:
+                        logger.info(
+                            f"Found existing scrobble {scrobble}, updating"
+                        )
+                        scrobble.book_page_data = scrobble_page_data
+                        scrobble.playback_position_seconds = (
+                            scrobble.calc_reading_duration()
+                        )
+                        scrobble.save(
+                            update_fields=[
+                                "book_page_data",
+                                "playback_position_seconds",
+                            ]
+                        )
+                    if not scrobble:
+                        logger.info(
+                            f"Queueing scrobble for {book_id}, page {page.number}"
+                        )
+                        scrobbles_to_create.append(
+                            Scrobble(
+                                book_id=book_id,
+                                user_id=user.id,
+                                source="KOReader",
+                                media_type=Scrobble.MediaType.BOOK,
+                                timestamp=timestamp,
+                                stop_timestamp=stop_timestamp,
+                                playback_position_seconds=playback_position_seconds,
+                                book_koreader_hash=list(
+                                    book.koreader_data_by_hash.keys()
+                                )[0],
+                                book_page_data=scrobble_page_data,
+                                book_pages_read=page.number,
+                                in_progress=False,
+                                played_to_completion=True,
+                                long_play_complete=False,
+                            )
+                        )
+                        # Then start over
+                        should_create_scrobble = False
+                        playback_position_seconds = 0
+                        scrobble_page_data = {}
+
+                prev_page = page
+
+        created = Scrobble.objects.bulk_create(scrobbles_to_create)
+        fix_long_play_stats_for_scrobbles(created)

vrobbler/apps/books/management/commands/migrate_koreader_data_to_log_json.py

@@ -0,0 +1,29 @@
+import logging
+import pytz
+from datetime import datetime, timedelta
+from books.models import Book
+from django.core.management.base import BaseCommand
+from scrobbles.models import Scrobble
+from vrobbler.apps.books.koreader import fix_long_play_stats_for_scrobbles
+from vrobbler.apps.scrobbles.utils import timestamp_user_tz_to_utc
+
+
+logger = logging.getLogger(__name__)
+
+
+class Command(BaseCommand):
+    def handle(self, *args, **options):
+        total_books = Book.objects.all().count()
+        processed_books = 0
+
+        for book in Book.objects.all():
+            for scrobble in book.scrobble_set.all():
+                log_data = {
+                    "koreader_hash": scrobble.book_koreader_hash,
+                    "page_data": scrobble.book_page_data,
+                    "pages_read": scrobble.book_pages_read,
+                }
+                scrobble.log = log_data
+                scrobble.save(update_fields=["log"])
+            processed_books += 1
+            logger.info(f"Processed book {processed_books} of {total_books}")

vrobbler/apps/books/metadata.py

@@ -0,0 +1,40 @@
+from enum import Enum
+from typing import Optional
+
+import pendulum
+
+YOUTUBE_VIDEO_URL = "https://www.youtube.com/watch?v="
+IMDB_VIDEO_URL = "https://www.imdb.com/title/tt"
+
+
+class BookType:
+    ...
+
+
+class BookMetadata:
+    title: str
+    run_time_seconds: Optional[int]
+    authors = Optional[str]
+    goodreads_id = Optional[str]
+    koreader_data_by_hash = Optional[dict]
+    isbn = Optional[str]
+    # isbn_13 = Optional[str]
+    # isbn_10 = Optional[str]
+    pages = Optional[int]
+    language = Optional[str]
+    first_publish_year = Optional[int]
+    summary = Optional[str]
+
+    # General
+    cover_url: Optional[str]
+    genres: list[str]
+
+    def __init__(self, title: Optional[str] = ""):
+        self.title = title
+
+    def as_dict_with_authors_cover_and_genres(self) -> tuple:
+        book_dict = vars(self)
+        authors = book_dict.pop("authors")
+        cover = book_dict.pop("cover_url")
+        genres = book_dict.pop("genres")
+        return book_dict, authors, cover, genres

vrobbler/apps/books/migrations/0020_author_comicvine_data_book_comicvine_data_and_more.py

@@ -0,0 +1,28 @@
+# Generated by Django 4.2.9 on 2024-01-29 05:55
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("books", "0019_alter_book_authors"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="author",
+            name="comicvine_data",
+            field=models.JSONField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name="book",
+            name="comicvine_data",
+            field=models.JSONField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name="book",
+            name="koreader_data_by_hash",
+            field=models.JSONField(blank=True, null=True),
+        ),
+    ]

vrobbler/apps/books/migrations/0021_remove_book_koreader_authors_remove_book_koreader_id_and_more.py

@@ -0,0 +1,25 @@
+# Generated by Django 4.2.16 on 2024-10-17 20:08
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("books", "0020_author_comicvine_data_book_comicvine_data_and_more"),
+    ]
+
+    operations = [
+        migrations.RemoveField(
+            model_name="book",
+            name="koreader_authors",
+        ),
+        migrations.RemoveField(
+            model_name="book",
+            name="koreader_id",
+        ),
+        migrations.RemoveField(
+            model_name="book",
+            name="koreader_md5",
+        ),
+    ]

vrobbler/apps/books/migrations/0022_alter_book_run_time_seconds.py

@@ -0,0 +1,21 @@
+# Generated by Django 4.2.16 on 2025-01-22 03:55
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        (
+            "books",
+            "0021_remove_book_koreader_authors_remove_book_koreader_id_and_more",
+        ),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="book",
+            name="run_time_seconds",
+            field=models.IntegerField(default=900),
+        ),
+    ]

vrobbler/apps/books/migrations/0023_rename_isbn_book_isbn_13_remove_book_comicvine_data_and_more.py

@@ -0,0 +1,40 @@
+# Generated by Django 4.2.18 on 2025-01-27 04:20
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("books", "0022_alter_book_run_time_seconds"),
+    ]
+
+    operations = [
+        migrations.RenameField(
+            model_name="book",
+            old_name="isbn",
+            new_name="isbn_13",
+        ),
+        migrations.RemoveField(
+            model_name="book",
+            name="comicvine_data",
+        ),
+        migrations.RemoveField(
+            model_name="book",
+            name="goodreads_id",
+        ),
+        migrations.RemoveField(
+            model_name="book",
+            name="locg_slug",
+        ),
+        migrations.AddField(
+            model_name="book",
+            name="isbn_10",
+            field=models.CharField(blank=True, max_length=255, null=True),
+        ),
+        migrations.AddField(
+            model_name="book",
+            name="publish_date",
+            field=models.DateField(blank=True, null=True),
+        ),
+    ]

vrobbler/apps/books/migrations/0024_book_publisher.py

@@ -0,0 +1,21 @@
+# Generated by Django 4.2.18 on 2025-01-27 04:31
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        (
+            "books",
+            "0023_rename_isbn_book_isbn_13_remove_book_comicvine_data_and_more",
+        ),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="book",
+            name="publisher",
+            field=models.CharField(blank=True, max_length=255, null=True),
+        ),
+    ]

vrobbler/apps/books/migrations/0025_remove_author_amazon_id_and_more.py

@@ -0,0 +1,136 @@
+# Generated by Django 4.2.19 on 2025-02-18 05:11
+
+from django.db import migrations, models
+import django_extensions.db.fields
+import taggit.managers
+import uuid
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("scrobbles", "0067_scrobble_food_alter_scrobble_media_type"),
+        ("books", "0024_book_publisher"),
+    ]
+
+    operations = [
+        migrations.RemoveField(
+            model_name="author",
+            name="amazon_id",
+        ),
+        migrations.RemoveField(
+            model_name="author",
+            name="librarything_id",
+        ),
+        migrations.RemoveField(
+            model_name="author",
+            name="locg_slug",
+        ),
+        migrations.AddField(
+            model_name="author",
+            name="semantic_id",
+            field=models.CharField(blank=True, max_length=50, null=True),
+        ),
+        migrations.CreateModel(
+            name="Paper",
+            fields=[
+                (
+                    "id",
+                    models.BigAutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                (
+                    "created",
+                    django_extensions.db.fields.CreationDateTimeField(
+                        auto_now_add=True, verbose_name="created"
+                    ),
+                ),
+                (
+                    "modified",
+                    django_extensions.db.fields.ModificationDateTimeField(
+                        auto_now=True, verbose_name="modified"
+                    ),
+                ),
+                (
+                    "uuid",
+                    models.UUIDField(
+                        blank=True,
+                        default=uuid.uuid4,
+                        editable=False,
+                        null=True,
+                    ),
+                ),
+                ("run_time_seconds", models.IntegerField(default=900)),
+                (
+                    "run_time_ticks",
+                    models.PositiveBigIntegerField(blank=True, null=True),
+                ),
+                ("title", models.CharField(max_length=255)),
+                ("semantic_title", models.CharField(max_length=255)),
+                (
+                    "koreader_data_by_hash",
+                    models.JSONField(blank=True, null=True),
+                ),
+                (
+                    "semantic_id",
+                    models.CharField(blank=True, max_length=50, null=True),
+                ),
+                (
+                    "arxiv_id",
+                    models.CharField(blank=True, max_length=50, null=True),
+                ),
+                (
+                    "corpus_id",
+                    models.CharField(blank=True, max_length=50, null=True),
+                ),
+                (
+                    "doi_id",
+                    models.CharField(blank=True, max_length=50, null=True),
+                ),
+                ("pages", models.IntegerField(blank=True, null=True)),
+                (
+                    "language",
+                    models.CharField(blank=True, max_length=4, null=True),
+                ),
+                (
+                    "first_publish_year",
+                    models.IntegerField(blank=True, null=True),
+                ),
+                ("publish_date", models.DateField(blank=True, null=True)),
+                (
+                    "journal",
+                    models.CharField(blank=True, max_length=255, null=True),
+                ),
+                (
+                    "journal_volume",
+                    models.CharField(blank=True, max_length=50, null=True),
+                ),
+                ("abstract", models.TextField(blank=True, null=True)),
+                ("num_citations", models.IntegerField(blank=True, null=True)),
+                (
+                    "openaccess_pdf_url",
+                    models.CharField(blank=True, max_length=255, null=True),
+                ),
+                (
+                    "authors",
+                    models.ManyToManyField(blank=True, to="books.author"),
+                ),
+                (
+                    "genre",
+                    taggit.managers.TaggableManager(
+                        help_text="A comma-separated list of tags.",
+                        through="scrobbles.ObjectWithGenres",
+                        to="scrobbles.Genre",
+                        verbose_name="Tags",
+                    ),
+                ),
+            ],
+            options={
+                "abstract": False,
+            },
+        ),
+    ]

vrobbler/apps/books/migrations/0026_alter_paper_semantic_title.py

@@ -0,0 +1,18 @@
+# Generated by Django 4.2.19 on 2025-02-18 05:28
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("books", "0025_remove_author_amazon_id_and_more"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="paper",
+            name="semantic_title",
+            field=models.CharField(blank=True, max_length=255, null=True),
+        ),
+    ]

vrobbler/apps/books/migrations/0027_remove_paper_num_citations_paper_tldr.py

@@ -0,0 +1,22 @@
+# Generated by Django 4.2.19 on 2025-02-18 05:33
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("books", "0026_alter_paper_semantic_title"),
+    ]
+
+    operations = [
+        migrations.RemoveField(
+            model_name="paper",
+            name="num_citations",
+        ),
+        migrations.AddField(
+            model_name="paper",
+            name="tldr",
+            field=models.CharField(blank=True, max_length=255, null=True),
+        ),
+    ]

vrobbler/apps/books/migrations/0028_delete_page.py

@@ -0,0 +1,16 @@
+# Generated by Django 4.2.19 on 2025-04-07 17:16
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("books", "0027_remove_paper_num_citations_paper_tldr"),
+    ]
+
+    operations = [
+        migrations.DeleteModel(
+            name="Page",
+        ),
+    ]

vrobbler/apps/books/migrations/0029_book_comicvine_id_book_issue_number_and_more.py

@@ -0,0 +1,33 @@
+# Generated by Django 4.2.19 on 2025-10-20 18:35
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('books', '0028_delete_page'),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name='book',
+            name='comicvine_id',
+            field=models.CharField(blank=True, max_length=255, null=True),
+        ),
+        migrations.AddField(
+            model_name='book',
+            name='issue_number',
+            field=models.IntegerField(blank=True, max_length=5, null=True),
+        ),
+        migrations.AddField(
+            model_name='book',
+            name='original_title',
+            field=models.CharField(blank=True, max_length=255, null=True),
+        ),
+        migrations.AddField(
+            model_name='book',
+            name='volume_number',
+            field=models.IntegerField(blank=True, max_length=5, null=True),
+        ),
+    ]

vrobbler/apps/books/migrations/0030_book_readcomics_url.py

@@ -0,0 +1,18 @@
+# Generated by Django 4.2.19 on 2025-10-22 16:29
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('books', '0029_book_comicvine_id_book_issue_number_and_more'),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name='book',
+            name='readcomics_url',
+            field=models.CharField(blank=True, max_length=255, null=True),
+        ),
+    ]

vrobbler/apps/books/migrations/0031_book_next_readcomics_url.py

@@ -0,0 +1,18 @@
+# Generated by Django 4.2.19 on 2025-10-22 17:42
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('books', '0030_book_readcomics_url'),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name='book',
+            name='next_readcomics_url',
+            field=models.CharField(blank=True, max_length=255, null=True),
+        ),
+    ]

vrobbler/apps/books/models.py

@@ -1,12 +1,19 @@
 import logging
-from datetime import timedelta
+from collections import OrderedDict
+from dataclasses import dataclass
+from datetime import datetime
+from typing import Optional
 from uuid import uuid4
 
 import requests
+from books.constants import READCOMICSONLINE_URL
 from books.openlibrary import (
     lookup_author_from_openlibrary,
     lookup_book_from_openlibrary,
 )
+from books.sources.google import lookup_book_from_google
+from books.sources.semantic import lookup_paper_from_semantic
+from books.utils import get_comic_issue_url
 from django.conf import settings
 from django.contrib.auth import get_user_model
 from django.core.files.base import ContentFile
@@ -15,25 +22,61 @@ from django.urls import reverse
 from django_extensions.db.models import TimeStampedModel
 from imagekit.models import ImageSpecField
 from imagekit.processors import ResizeToFit
+from scrobbles.dataclasses import BaseLogData, LongPlayLogData
 from scrobbles.mixins import (
     LongPlayScrobblableMixin,
     ObjectWithGenres,
-    ScrobblableMixin,
+    ScrobblableConstants,
 )
-from scrobbles.utils import get_scrobbles_for_media
+from scrobbles.utils import get_scrobbles_for_media, next_url_if_exists
 from taggit.managers import TaggableManager
+from thefuzz import fuzz
 
 from vrobbler.apps.books.locg import (
     lookup_comic_by_locg_slug,
     lookup_comic_from_locg,
     lookup_comic_writer_by_locg_slug,
 )
+from vrobbler.apps.books.sources.comicvine import (
+    ComicVineClient,
+    lookup_comic_from_comicvine,
+)
+
+COMICVINE_API_KEY = getattr(settings, "COMICVINE_API_KEY", "")
 
 logger = logging.getLogger(__name__)
 User = get_user_model()
 BNULL = {"blank": True, "null": True}
 
 
+@dataclass
+class BookPageLogData(BaseLogData):
+    page_number: Optional[int] = None
+    end_ts: Optional[int] = None
+    start_ts: Optional[int] = None
+    duration: Optional[int] = None
+
+
+@dataclass
+class BookLogData(BaseLogData, LongPlayLogData):
+    koreader_hash: Optional[str] = None
+    page_data: Optional[dict[int, BookPageLogData]] = None
+    pages_read: Optional[int] = None
+    page_start: Optional[int] = None
+    page_end: Optional[int] = None
+    resume_url: Optional[str] = None
+
+    _excluded_fields = {"koreader_hash", "page_data"}
+
+    def avg_seconds_per_page(self):
+        if self.page_data:
+            total_duration = 0
+            for page_num, stats in self.page_data.items():
+                total_duration += stats.get("duration", 0)
+            if total_duration:
+                return int(total_duration / len(self.page_data))
+
+
 class Author(TimeStampedModel):
     name = models.CharField(max_length=255)
     uuid = models.UUIDField(default=uuid4, editable=False, **BNULL)
@@ -53,21 +96,27 @@ class Author(TimeStampedModel):
     )
     bio = models.TextField(**BNULL)
     wikipedia_url = models.CharField(max_length=255, **BNULL)
-    isni = models.CharField(max_length=255, **BNULL)
-    locg_slug = models.CharField(max_length=255, **BNULL)
     wikidata_id = models.CharField(max_length=255, **BNULL)
+    isni = models.CharField(max_length=255, **BNULL)
     goodreads_id = models.CharField(max_length=255, **BNULL)
-    librarything_id = models.CharField(max_length=255, **BNULL)
-    amazon_id = models.CharField(max_length=255, **BNULL)
+    comicvine_data = models.JSONField(**BNULL)
+
+    semantic_id = models.CharField(max_length=50, **BNULL)
 
     def __str__(self):
         return f"{self.name}"
 
-    def fix_metadata(self, data_dict: dict = {}):
-        if not data_dict and self.openlibrary_id:
-            data_dict = lookup_author_from_openlibrary(self.openlibrary_id)
+    def enrich_from_semantic(self, overwrite=False):
+        ...
+
+    def enrich_from_google_books(self, overwrite=False):
+        ...
+
+    def enrich_from_openlibrary(self, overwrite=False):
+        data_dict = lookup_author_from_openlibrary(self.openlibrary_id)
 
         if not data_dict or not data_dict.get("name"):
+            logger.warning("Could not find author on openlibrary")
             return
 
         headshot_url = data_dict.pop("author_headshot_url", "")
@@ -89,18 +138,25 @@ class Book(LongPlayScrobblableMixin):
     )
 
     title = models.CharField(max_length=255)
+    original_title = models.CharField(max_length=255, **BNULL)
     authors = models.ManyToManyField(Author, blank=True)
-    goodreads_id = models.CharField(max_length=255, **BNULL)
-    koreader_id = models.IntegerField(**BNULL)
-    koreader_authors = models.CharField(max_length=255, **BNULL)
-    koreader_md5 = models.CharField(max_length=255, **BNULL)
-    isbn = models.CharField(max_length=255, **BNULL)
+    koreader_data_by_hash = models.JSONField(**BNULL)
+    isbn_13 = models.CharField(max_length=255, **BNULL)
+    isbn_10 = models.CharField(max_length=255, **BNULL)
     pages = models.IntegerField(**BNULL)
     language = models.CharField(max_length=4, **BNULL)
     first_publish_year = models.IntegerField(**BNULL)
+    publish_date = models.DateField(**BNULL)
+    publisher = models.CharField(max_length=255, **BNULL)
     first_sentence = models.TextField(**BNULL)
+    # ComicVine
+    comicvine_id = models.CharField(max_length=255, **BNULL)
+    readcomics_url = models.CharField(max_length=255, **BNULL)
+    next_readcomics_url = models.CharField(max_length=255, **BNULL)
+    issue_number = models.IntegerField(max_length=5, **BNULL)
+    volume_number = models.IntegerField(max_length=5, **BNULL)
+    # OpenLibrary
     openlibrary_id = models.CharField(max_length=255, **BNULL)
-    locg_slug = models.CharField(max_length=255, **BNULL)
     cover = models.ImageField(upload_to="books/covers/", **BNULL)
     cover_small = ImageSpecField(
         source="cover",
@@ -118,13 +174,25 @@ class Book(LongPlayScrobblableMixin):
 
     genre = TaggableManager(through=ObjectWithGenres)
 
-    def __str__(self):
+    def __str__(self) -> str:
+        if self.issue_number and "Issue" not in str(self.title):
+            return f"{self.title} - Issue {self.issue_number}"
+        if self.volume_number and "Volume" not in str(self.title):
+            return f"{self.title} - Volume {self.volume_number}"
         return f"{self.title}"
 
     @property
     def subtitle(self):
         return f" by {self.author}"
 
+    @property
+    def strings(self) -> ScrobblableConstants:
+        return ScrobblableConstants(verb="Reading", tags="book")
+
+    @property
+    def logdata_cls(self):
+        return BookLogData
+
     @property
     def primary_image_url(self) -> str:
         url = ""
@@ -132,39 +200,153 @@ class Book(LongPlayScrobblableMixin):
             url = self.cover_medium.url
         return url
 
-    def get_start_url(self):
-        return reverse("scrobbles:start", kwargs={"uuid": self.uuid})
-
     def get_absolute_url(self):
         return reverse("books:book_detail", kwargs={"slug": self.uuid})
 
+    @classmethod
+    def get_from_comicvine(cls, title: str, overwrite: bool = False, force_new: bool =False) -> "Book":
+        book, created = cls.objects.get_or_create(title=title)
+
+        if not created:
+            return book
+
+        book_dict = lookup_comic_from_comicvine(title)
+
+        if created or overwrite:
+            author_list = []
+            author_dicts = book_dict.pop("author_dicts")
+            if author_dicts:
+                for author_dict in author_dicts:
+                    if author_dict.get("authorId"):
+                        author, a_created = Author.objects.get_or_create(
+                            semantic_id=author_dict.get("authorId")
+                        )
+                        author_list.append(author)
+                        if a_created:
+                            author.name = author_dict.get("name")
+                            author.save()
+                            # TODO enrich author?
+                            ...
+
+            for k, v in book_dict.items():
+                setattr(book, k, v)
+            book.save()
+
+            if author_list:
+                book.authors.add(*author_list)
+            genres = book_dict.pop("genres", [])
+            if genres:
+                book.genre.add(*genres)
+        return book
+
+    @classmethod
+    def find_or_create(
+            cls, title: str, url: str = "", enrich: bool = False, commit: bool = True
+    ):
+        """Given a title, get a Book instance.
+
+        If the book is not already in our database, or overwrite is True,
+        this method will enrich the Book with data from Google.
+
+        By default this method will also save the data back to the model. If you'd
+        like to batch create, use commit=False and you'll get an unsaved but enriched
+        instance back which you can then save at your convenience."""
+        # TODO use either a Google Books id identifier or author name like for tracks
+        book, created = cls.objects.get_or_create(original_title=title)
+        if not created:
+            logger.info(
+                "Found exact match for book by title", extra={"title": title}
+            )
+
+        if not enrich:
+            logger.info(
+                "Found book by title, but not enriching",
+                extra={"title": title},
+            )
+            return book
+
+        book_dict = None
+        if READCOMICSONLINE_URL in url:
+            book_dict = lookup_comic_from_comicvine(title)
+            book_dict["readcomics_url"] = get_comic_issue_url(url)
+            book_dict["next_readcomics_url"] = next_url_if_exists(book_dict["readcomics_url"])
+
+        if not book_dict:
+            book_dict = lookup_book_from_google(title)
+
+        if not book_dict:
+            logger.warning("No book found in any source, using data as is", extra={"title": title})
+
+        author_list = []
+        authors = book_dict.pop("authors", [])
+        cover_url = book_dict.pop("cover_url", "")
+        genres = book_dict.pop("generes", [])
+
+        if authors:
+            for author_str in authors:
+                if author_str:
+                    author, a_created = Author.objects.get_or_create(
+                        name=author_str
+                    )
+                    author_list.append(author)
+                    if a_created:
+                        # TODO enrich author
+                        ...
+
+        for k, v in book_dict.items():
+            setattr(book, k, v)
+
+        if commit:
+            book.save()
+
+            book.save_image_from_url(cover_url)
+            book.genre.add(*genres)
+            book.authors.add(*author_list)
+
+        return book
+
+    def save_image_from_url(self, url: str, force_update: bool = False):
+        if url and (not self.cover or force_update):
+            r = requests.get(url)
+            if r.status_code == 200:
+                fname = f"{self.title}_{self.uuid}.jpg"
+                self.cover.save(fname, ContentFile(r.content), save=True)
+
     def fix_metadata(self, data: dict = {}, force_update=False):
         if (not self.openlibrary_id or not self.locg_slug) or force_update:
             author_name = ""
             if self.author:
                 author_name = self.author.name
 
+            if not data:
+                logger.warn(f"Checking openlibrary for {self.title}")
+                if self.openlibrary_id and force_update:
+                    data = lookup_book_from_openlibrary(
+                        str(self.openlibrary_id)
+                    )
+                else:
+                    data = lookup_book_from_openlibrary(
+                        str(self.title), author_name
+                    )
+
             if not data:
                 if self.locg_slug:
+                    logger.warn(
+                        f"Checking LOCG for {self.title} with slug {self.locg_slug}"
+                    )
                     data = lookup_comic_by_locg_slug(str(self.locg_slug))
                 else:
+                    logger.warn(f"Checking LOCG for {self.title}")
                     data = lookup_comic_from_locg(str(self.title))
 
-                if not data:
-                    logger.warn(
-                        f"Book not found on LOCG, checking OL {self.title}"
-                    )
-                    if self.openlibrary_id and force_update:
-                        data = lookup_book_from_openlibrary(
-                            str(self.openlibrary_id)
-                        )
-                    else:
-                        data = lookup_book_from_openlibrary(
-                            str(self.title), author_name
-                        )
-                if not data:
-                    logger.warn(f"Book not found in OL {self.title}")
-                    return
+            if not data and COMICVINE_API_KEY:
+                logger.warn(f"Checking ComicVine for {self.title}")
+                cv_client = ComicVineClient(api_key=COMICVINE_API_KEY)
+                data = lookup_comic_from_comicvine(str(self.title))
+
+            if not data:
+                logger.warn(f"Book not found in any sources: {self.title}")
+                return
 
             # We can discard the author name from OL for now, we'll lookup details below
             data.pop("ol_author_name", "")
@@ -174,15 +356,31 @@ class Book(LongPlayScrobblableMixin):
                 self.get_author_from_locg(data.pop("locg_writer_slug", ""))
 
             ol_title = data.get("title", "")
+            data.pop("ol_author_id", "")
 
             # Kick out a little warning if we're about to change KoReader's title
-            if ol_title.lower() != str(self.title).lower():
+            if (
+                fuzz.ratio(ol_title.lower(), str(self.title).lower()) < 80
+                and not force_update
+            ):
                 logger.warn(
-                    f"OL and KoReader disagree on this book title {self.title} != {ol_title}"
+                    f"OL and KoReader disagree on this book title {self.title} != {ol_title}, check manually"
                 )
+                self.openlibrary_id = data.get("openlibrary_id")
+                self.save(update_fields=["openlibrary_id"])
+                return
 
             # If we don't know pages, don't overwrite existing with None
-            if data.get("pages") == None:
+            if "pages" in data.keys() and data.get("pages") == None:
+                data.pop("pages")
+
+            if (
+                not isinstance(data.get("pages"), int)
+                and "pages" in data.keys()
+            ):
+                logger.info(
+                    f"Pages for {self} from OL expected to be int, but got {data.get('pages')}"
+                )
                 data.pop("pages")
 
             # Pop this, so we can look it up later
@@ -242,6 +440,27 @@ class Book(LongPlayScrobblableMixin):
                 author.headshot.save(fname, ContentFile(r.content), save=True)
         self.authors.add(author)
 
+    def page_data_for_user(
+        self, user_id: int, convert_timestamps: bool = True
+    ) -> dict:
+        scrobbles = self.scrobble_set.filter(user=user_id)
+
+        pages = {}
+        for scrobble in scrobbles:
+            if scrobble.logdata.page_data:
+                for page, data in scrobble.logdata.page_data.items():
+                    if convert_timestamps:
+                        data["start_ts"] = datetime.fromtimestamp(
+                            data["start_ts"]
+                        )
+                        data["end_ts"] = datetime.fromtimestamp(data["end_ts"])
+                    pages[page] = data
+        sorted_pages = OrderedDict(
+            sorted(pages.items(), key=lambda x: x[1]["start_ts"])
+        )
+
+        return sorted_pages
+
     @property
     def author(self):
         return self.authors.first()
@@ -264,114 +483,70 @@ class Book(LongPlayScrobblableMixin):
         last_scrobble = get_scrobbles_for_media(self, user).last()
         progress = 0
         if last_scrobble:
-            progress = int((last_scrobble.book_pages_read / self.pages) * 100)
+            progress = int((last_scrobble.last_page_read / self.pages) * 100)
         return progress
 
+
+class Paper(LongPlayScrobblableMixin):
+    """Keeps track of Academic Papers"""
+
+    COMPLETION_PERCENT = getattr(settings, "PAPER_COMPLETION_PERCENT", 60)
+    AVG_PAGE_READING_SECONDS = getattr(
+        settings, "AVERAGE_PAGE_READING_SECONDS", 60
+    )
+
+    title = models.CharField(max_length=255)
+    semantic_title = models.CharField(max_length=255, **BNULL)
+    authors = models.ManyToManyField(Author, blank=True)
+    koreader_data_by_hash = models.JSONField(**BNULL)
+    arxiv_id = models.CharField(max_length=50, **BNULL)
+    semantic_id = models.CharField(max_length=50, **BNULL)
+    arxiv_id = models.CharField(max_length=50, **BNULL)
+    corpus_id = models.CharField(max_length=50, **BNULL)
+    doi_id = models.CharField(max_length=50, **BNULL)
+    pages = models.IntegerField(**BNULL)
+    language = models.CharField(max_length=4, **BNULL)
+    first_publish_year = models.IntegerField(**BNULL)
+    publish_date = models.DateField(**BNULL)
+    journal = models.CharField(max_length=255, **BNULL)
+    journal_volume = models.CharField(max_length=50, **BNULL)
+    abstract = models.TextField(**BNULL)
+    tldr = models.CharField(max_length=255, **BNULL)
+    openaccess_pdf_url = models.CharField(max_length=255, **BNULL)
+
+    genre = TaggableManager(through=ObjectWithGenres)
+
     @classmethod
-    def find_or_create(cls, lookup_id: str, author: str = "") -> "Book":
-        data = lookup_book_from_openlibrary(lookup_id, author)
+    def get_from_semantic(cls, title: str, overwrite: bool = False) -> "Paper":
+        paper, created = cls.objects.get_or_create(title=title)
+        if not created and not overwrite:
+            return paper
 
-        book, book_created = cls.objects.get_or_create(isbn=data["isbn"])
-        if book_created:
-            book.fix_metadata(data=data)
+        paper_dict = lookup_paper_from_semantic(title)
 
-        return book
+        if created or overwrite:
+            author_list = []
+            author_dicts = paper_dict.pop("author_dicts")
+            if author_dicts:
+                for author_dict in author_dicts:
+                    if author_dict.get("authorId"):
+                        author, a_created = Author.objects.get_or_create(
+                            semantic_id=author_dict.get("authorId")
+                        )
+                        author_list.append(author)
+                        if a_created:
+                            author.name = author_dict.get("name")
+                            author.save()
+                            # TODO enrich author?
+                            ...
 
-    def save(self, *args, **kwargs):
-        if (
-            (not self.isbn and not self.cover)
-            and (self.locg_slug or self.openlibrary_id)
-            and self.id
-        ):
-            self.fix_metadata(force_update=True)
+            for k, v in paper_dict.items():
+                setattr(paper, k, v)
+            paper.save()
 
-        return super(Book, self).save(*args, **kwargs)
-
-
-class Page(TimeStampedModel):
-    user = models.ForeignKey(User, on_delete=models.CASCADE)
-    book = models.ForeignKey(Book, on_delete=models.CASCADE)
-    number = models.IntegerField()
-    start_time = models.DateTimeField(**BNULL)
-    end_time = models.DateTimeField(**BNULL)
-    duration_seconds = models.IntegerField(**BNULL)
-
-    class Meta:
-        unique_together = (
-            "book",
-            "number",
-        )
-
-    def __str__(self):
-        return f"Page {self.number} of {self.book.pages} in {self.book.title}"
-
-    def save(self, *args, **kwargs):
-        if not self.end_time and self.duration_seconds:
-            self._set_end_time()
-
-        return super(Page, self).save(*args, **kwargs)
-
-    @property
-    def next(self):
-        page = self.book.page_set.filter(number=self.number + 1).first()
-        if not page:
-            page = (
-                self.book.page_set.filter(created__gt=self.created)
-                .order_by("created")
-                .first()
-            )
-        return page
-
-    @property
-    def previous(self):
-        page = self.book.page_set.filter(number=self.number - 1).first()
-        if not page:
-            page = (
-                self.book.page_set.filter(created__lt=self.created)
-                .order_by("-created")
-                .first()
-            )
-        return page
-
-    @property
-    def seconds_to_next_page(self) -> int:
-        seconds = 999999  # Effectively infnity time as we have no next
-        if not self.end_time:
-            self._set_end_time()
-        if self.next:
-            seconds = (self.next.start_time - self.end_time).seconds
-        return seconds
-
-    @property
-    def is_scrobblable(self) -> bool:
-        """A page defines the start of a scrobble if the seconds to next page
-        are greater than an hour, or 3600 seconds, and it's not a single page,
-        so the next seconds to next_page is less than an hour as well.
-
-        As a special case, the first recorded page is a scrobble, so we establish
-        when the book was started.
-
-        """
-        is_scrobblable = False
-        over_an_hour_since_last_page = False
-        if not self.previous:
-            is_scrobblable = True
-
-        if self.previous:
-            over_an_hour_since_last_page = (
-                self.previous.seconds_to_next_page >= 3600
-            )
-        blip = self.seconds_to_next_page >= 3600
-
-        if over_an_hour_since_last_page and not blip:
-            is_scrobblable = True
-        return is_scrobblable
-
-    def _set_end_time(self) -> None:
-        if self.end_time:
-            return
-
-        self.end_time = self.start_time + timedelta(
-            seconds=self.duration_seconds
-        )
-        self.save(update_fields=["end_time"])
+            if author_list:
+                paper.authors.add(*author_list)
+            genres = paper_dict.pop("genres", [])
+            if genres:
+                paper.genre.add(*genres)
+        return paper

vrobbler/apps/books/openlibrary.py

@@ -5,6 +5,8 @@ import urllib
 
 import requests
 
+from thefuzz import fuzz
+
 logger = logging.getLogger(__name__)
 
 ISBN_URL = "https://openlibrary.org/isbn/{isbn}.json"
@@ -36,8 +38,11 @@ def get_author_openlibrary_id(name: str) -> str:
         logger.warn(f"No author results found from search for {name}")
         return ""
 
-    result = results.get("docs", [])
-    return result[0].get("key")
+    try:
+        result = results.get("docs", [])[0]
+    except IndexError:
+        result = {"key": ""}
+    return result.get("key")
 
 
 def lookup_author_from_openlibrary(olid: str) -> dict:
@@ -99,11 +104,22 @@ def lookup_book_from_openlibrary(
 
     top = None
     for result in results.get("docs"):
-        # These Summary things suck and ruin our one-shot search
-        if "Summary of" not in result.get("title"):
+        if fuzz.ratio(title.lower(), result.get("title", "").lower()) > 90:
             top = result
             break
 
+    if not top:
+        for result in results.get("docs"):
+            # These Summary things suck and ruin our one-shot search
+            if "Summary of" in result.get("title"):
+                continue
+
+            if title.lower() in result.get("title", "").lower():
+                top = result
+
+    if not top and len(results.get("docs")) > 0:
+        top = results.get("docs")[0]
+
     if not top:
         logger.warn(f"No book found for query {query}")
         return {}

vrobbler/apps/books/sources/comicvine.py

@@ -0,0 +1,270 @@
+"""
+ComicVine API Information & Documentation:
+https://comicvine.gamespot.com/api/
+https://comicvine.gamespot.com/api/documentation
+"""
+import logging
+from django.conf import settings
+
+import requests
+
+logger = logging.getLogger(__name__)
+
+
+class ComicVineClient(object):
+    """
+    Interacts with the ``search`` resource of the ComicVine API. Requires an
+    account on https://comicvine.gamespot.com/ in order to obtain an API key.
+    """
+
+    # All API requests made by this client will be made to this URL.
+    API_URL = "https://www.comicvine.com/api/search/"
+
+    # A valid User-Agent header must be set in order for our API requests to
+    # be accepted, otherwise our request will be rejected with a
+    # **403 - Forbidden** error.
+    HEADERS = {
+        "User-Agent": "Mozilla/5.0 (X11; Linux x86_64; rv:7.0) "
+        "Gecko/20130825 Firefox/36.0"
+    }
+
+    # A set of valid resource types to return in results.
+    RESOURCE_TYPES = {
+        "character",
+        "issue",
+        "location",
+        "object",
+        "person",
+        "publisher",
+        "story_arc",
+        "team",
+        "volume",
+    }
+
+    def __init__(self, api_key, expire_after=300):
+        """
+        Store the API key in a class variable, and install the requests cache,
+        configuring it using the ``expire_after`` parameter.
+
+        :param api_key: Your personal ComicVine API key.
+        :type  api_key: str
+        :param expire_after: The number of seconds to retain an entry in cache.
+        :type  expire_after: int or None
+        """
+
+        self.api_key = api_key
+
+    def search(self, query, offset=0, limit=10, resources=None):
+        """
+        Perform a search against the API, using the provided query term. If
+        required, a list of resource types to filter search results to can
+        be included.
+
+        Take the JSON contained in the response and provide it to the custom
+        ``Response`` object's constructor. Return the ``Response`` object.
+
+        :param query: The search query with which to make the request.
+        :type  query: str
+        :param offset: The index of the first record returned.
+        :type  offset: int or None
+        :param limit: How many records to return **(max 10)**
+        :type  limit: int or None
+        :param resources: A list of resources to include in the search results.
+        :type  resources: list or None
+        :type  use_cache: bool
+
+        :return: The response object containing the results of the search
+                 query.
+        :rtype:  comicvine_search.response.Response
+        """
+
+        params = self._request_params(query, offset, limit, resources)
+        json_data = self._query_api(params)
+
+        return json_data
+
+    def _request_params(self, query, offset, limit, resources):
+        """
+        Construct a dict containing the required key-value pairs of parameters
+        required in order to make the API request.
+
+        The documentation for the ``search`` resource can be found at
+        https://comicvine.gamespot.com/api/documentation#toc-0-30.
+
+        Regarding 'limit', as per the documentation:
+
+            The number of results to display per page. This value defaults to
+            10 and can not exceed this number.
+
+        :param query: The search query with which to make the request.
+        :type  query: str
+        :param offset: The index of the first record returned.
+        :type  offset: int
+        :param limit: How many records to return **(max 10)**
+        :type  limit: int
+        :param resources: A list of resources to include in the search results.
+        :type  resources: list or None
+
+        :return: A dictionary of request parameters.
+        :rtype:  dict
+        """
+
+        return {
+            "api_key": self.api_key,
+            "format": "json",
+            "limit": min(10, limit),  # hard limit of 10
+            "offset": max(0, offset),  # cannot provide negative offset
+            "query": query,
+            "resources": self._validate_resources(resources),
+        }
+
+    def _validate_resources(self, resources):
+        """
+        Provided a list of resources, first convert it to a set and perform an
+        intersection with the set of valid resource types, ``RESOURCE_TYPES``.
+        Return a comma-separted string of the remaining valid resources, or
+        None if the set is empty.
+
+        :param resources: A list of resources to include in the search results.
+        :type  resources: list or None
+
+        :return: A comma-separated string of valid resources.
+        :rtype:  str or None
+        """
+
+        if not resources:
+            return None
+
+        valid_resources = self.RESOURCE_TYPES & set(resources)
+        return ",".join(valid_resources) if valid_resources else None
+
+    def _query_api(self, params):
+        """
+        Query the ComicVine API's ``search`` resource, providing the required
+        headers and parameters with the request. Optionally allow the caller
+        of the function to disable the request cache.
+
+        If an error occurs during the request, handle it accordingly. Upon
+        success, return the JSON from the response.
+
+        :param params: Parameters to include with the request.
+        :type  params: dict
+        :param use_cache: Toggle the use of requests_cache.
+        :type  use_cache: bool
+
+        :return: The JSON contained in the response.
+        :rtype:  dict
+        """
+
+        # Since we're performing the identical action regardless of whether
+        # or not the request cache is to be used, store the procedure in a
+        # local function to avoid repetition.
+        def __httpget():
+            response = requests.get(
+                self.API_URL, headers=self.HEADERS, params=params
+            )
+
+            if not response.ok:
+                self._handle_http_error(response)
+
+            return response.json()
+
+        return __httpget()
+
+    def _handle_http_error(self, response):
+        """
+        Provided a ``requests.Response`` object, if the status code is
+        anything other than **200**, we will treat it as an error.
+
+        Using the response's status code, determine which type of exception to
+        raise. Construct an exception message from the response's status code
+        and reason properties before raising the exception.
+
+        :param response: The requests.Response object returned by the HTTP
+                         request.
+        :type  response: requests.Response
+
+        :raises ComicVineUnauthorizedException: if no API key provided.
+        :raises ComicVineForbiddenException: if no User-Agent header provided.
+        :raises ComicVineApiException: if an unidentified error occurs.
+        """
+
+        exception = {
+            401: Exception,
+            403: Exception,
+        }.get(response.status_code, Exception)
+        message = f"{response.status_code} {response.reason}"
+
+        raise exception(message)
+
+
+def lookup_comic_from_comicvine(title: str) -> dict:
+    original_title = title
+
+    issue_number = None
+    volume_nubmer = None
+    resource_type = "issue"
+    if "Issue " in title:
+        resource_type = "issue"
+        issue_number = title.split("Issue ")[1]
+    volume_number = None
+    if "Volume " in title:
+        resource_type = "volume"
+        volume_number = title.split("Volume ")[1]
+
+    api_key = getattr(settings, "COMICVINE_API_KEY", "")
+    if not api_key:
+        logger.warning("No ComicVine API key configured, not looking anything up")
+        return {}
+
+    client = ComicVineClient(
+        api_key=getattr(settings, "COMICVINE_API_KEY", None)
+    )
+
+    raw_results = client.search(title).get("results")
+    results = [
+        r
+        for r in raw_results
+        if r.get("resource_type") == resource_type
+    ]
+    if not results:
+        logger.warning("No comic found on ComicVine")
+        return {}
+
+    found_result = None
+    for result in results:
+        if result.get("issue_number") == str(issue_number):
+            found_result = result
+            break
+        if result.get("volume_number") == str(volume_number):
+            found_result = result
+            break
+
+    if not found_result:
+        found_result = results[0]
+
+    logger.info("ComicVine results", extra={"results": results})
+
+    if not found_result:
+        logger.warning("No matches found on ComicVine")
+        return {}
+
+    title = found_result.get("name")
+
+    if found_result.get("volume"):
+        title = found_result.get("volume").get("name")
+
+    data_dict = {
+        "title": title,
+        "original_title": original_title,
+        "issue_number": found_result.get("issue_number"),
+        "volume_number": found_result.get("volume_number"),
+        "cover_url": found_result.get("image").get("original_url"),
+        "comicvine_id": found_result.get("id"),
+        "comicvine_data": found_result,
+        "summary": found_result.get("description"),
+        "publish_date": found_result.get("cover_date"),
+        "first_publish_year": found_result.get("cover_date", "")[:4]
+    }
+
+    return data_dict

vrobbler/apps/books/sources/google.py

@@ -0,0 +1,76 @@
+import json
+import logging
+
+import pendulum
+import requests
+from django.conf import settings
+
+API_KEY = settings.GOOGLE_API_KEY
+GOOGLE_BOOKS_URL = (
+    "https://www.googleapis.com/books/v1/volumes?q=\"{title}\"&key={key}"
+)
+
+logger = logging.getLogger(__name__)
+
+
+def lookup_book_from_google(title: str) -> dict:
+    book_dict = {"title": title}
+
+    url = GOOGLE_BOOKS_URL.format(title=title, key=API_KEY)
+    headers = {"User-Agent": "Vrobbler 0.11.12"}
+    response = requests.get(url, headers=headers)
+
+    if response.status_code != 200:
+        logger.warning(
+            "Bad response from Google", extra={"response": response}
+        )
+        return book_dict
+
+    google_result = (
+        json.loads(response.content).get("items", [{}])[0].get("volumeInfo")
+    )
+    if not google_result:
+        return {}
+
+    publish_date = pendulum.parse(google_result.get("publishedDate"))
+
+    isbn_13 = ""
+    isbn_10 = ""
+    for ident in google_result.get("industryIdentifiers", []):
+        if ident.get("type") == "ISBN_13":
+            isbn_13 = ident.get("identifier")
+        if ident.get("type") == "ISBN_10":
+            isbn_10 = ident.get("identifier")
+    # TODO this may lead to issues with the first get if Google changes our title
+    # book_metadata.title = google_result.get("title")
+    # if google_result.get("subtitle"):
+    #    book_metadata["title"] = ": ".join(
+    #        [google_result.get("title"), google_result.get("subtitle")]
+    #    )
+    # book_dict["subtitle"] = google_result.get("subtitle")
+    book_dict["authors"] = google_result.get("authors")
+    book_dict["publisher"] = google_result.get("publisher")
+    book_dict["first_publish_year"] = publish_date.year
+    book_dict["pages"] = google_result.get("pageCount")
+    book_dict["isbn_13"] = isbn_13
+    book_dict["isbn_10"] = isbn_10
+    book_dict["publish_date"] = google_result.get("publishedDate")
+    if len(book_dict["publish_date"]) == 4:
+        book_dict["publish_date"] = f"{book_dict['publish_date']}-1-1"
+    book_dict["language"] = google_result.get("language")
+    book_dict["summary"] = google_result.get("description")
+    book_dict["genres"] = google_result.get("categories")
+    book_dict["cover_url"] = (
+        google_result.get("imageLinks", {})
+        .get("thumbnail", "")
+        .replace("zoom=1", "zoom=15")
+        .replace("&edge=curl", "")
+    )
+
+    book_dict["run_time_seconds"] = 3600
+    if book_dict.get("pages"):
+        book_dict["run_time_seconds"] = book_dict.get("pages", 10) * getattr(
+            settings, "AVERAGE_PAGE_READING_SECONDS", 60
+        )
+
+    return book_dict

vrobbler/apps/books/sources/semantic.py

@@ -0,0 +1,76 @@
+import json
+import logging
+from datetime import datetime
+
+import requests
+from django.conf import settings
+
+PAPER_SEARCH_URL = (
+    "https://api.semanticscholar.org/graph/v1/paper/search/match?query={}"
+)
+PAPER_DETAIL_URL = "https://api.semanticscholar.org/graph/v1/paper/{}?fields=title,authors,url,year,abstract,externalIds,citationCount,referenceCount,journal,fieldsOfStudy,publicationDate,openAccessPdf"
+
+logger = logging.getLogger(__name__)
+
+
+def get_api_result(url):
+    headers = {"User-Agent": "Vrobbler 0.11.12"}
+    response = requests.get(url, headers=headers)
+
+    if response.status_code != 200:
+        logger.warning(
+            "Bad response from Semantic", extra={"response": response}
+        )
+        return None
+
+    return response
+
+
+def lookup_paper_from_semantic(title: str) -> dict:
+    paper_dict = {"title": title}
+
+    response = get_api_result(PAPER_SEARCH_URL.format(title))
+    if not response:
+        return paper_dict
+
+    semantic_id = json.loads(response.content).get("data")[0].get("paperId")
+    response = get_api_result(PAPER_DETAIL_URL.format(semantic_id))
+
+    result = json.loads(response.content)
+
+    if not result:
+        return paper_dict
+
+    page_str = result.get("journal", {}).get("pages")
+    if page_str:
+        try:
+            start_page = page_str.split(" - ")[0]
+            end_page = page_str.split(" - ")[1]
+            paper_dict["pages"] = int(end_page) - int(start_page)
+        except IndexError:
+            pass
+
+    paper_dict["semantic_id"] = result.get("paperId")
+    paper_dict["doi_id"] = result.get("externalIds", {}).get("DOI")
+    paper_dict["arxiv_id"] = result.get("externalIds", {}).get("ArXiv")
+    paper_dict["pubmed_id"] = result.get("externalIds", {}).get("PubMed")
+    paper_dict["corpus_id"] = result.get("externalIds", {}).get("CorpusId")
+    paper_dict["semantic_title"] = result.get("title")
+    paper_dict["first_publish_year"] = result.get("year")
+    paper_dict["publish_date"] = datetime.strptime(
+        result.get("publicationDate", "1950-01-01"), "%Y-%m-%d"
+    )
+    paper_dict["abstract"] = result.get("abstract")
+    paper_dict["tldr"] = result.get("bib", {}).get("abstract")
+    paper_dict["journal"] = result.get("journal", {}).get("name")
+    paper_dict["journal_volume"] = result.get("journal", {}).get("volume")
+    paper_dict["openaccess_pdf_url"] = result.get("openAccessPdf", {}).get(
+        "url"
+    )
+    paper_dict["run_time_seconds"] = paper_dict.get("pages", 10) * getattr(
+        settings, "AVERAGE_PAGE_READING_SECONDS", 60
+    )
+    paper_dict["author_dicts"] = result.get("authors")
+    paper_dict["genres"] = result.get("fieldsOfStudy")
+
+    return paper_dict

vrobbler/apps/books/tests/conftest.py

@@ -0,0 +1,123 @@
+import hashlib
+import random
+
+import pytest
+from django.contrib.auth import get_user_model
+
+from vrobbler.apps.books.koreader import KoReaderBookColumn
+
+User = get_user_model()
+
+ordinal = lambda n: "%d%s" % (
+    n,
+    "tsnrhtdd"[(n // 10 % 10 != 1) * (n % 10 < 4) * n % 10 :: 4],
+)
+AVERAGE_PAGE_READING_SECONDS = 60
+
+
+class DummyResponse:
+    status_code = 200
+
+    def status_code(self):
+        return self.status_code
+
+
+@pytest.fixture
+def valid_response():
+    return DummyResponse()
+
+
+class KoReaderBookRows:
+    id = 1
+    DEFAULT_STR = "N/A"
+    DEFAULT_INT = 0
+    DEFAULT_TIME = 1703800469
+    BOOK_ROWS = []
+    PAGE_STATS_ROWS = []
+
+    def _gen_random_row(self, i):
+        wiggle = random.randrange(15)
+        title = f"Memoirs, Volume {i}"
+        return [
+            i,
+            title,
+            f"Lord Beaverbrook the {ordinal(i)}",
+            self.DEFAULT_INT + wiggle / 10,
+            self.DEFAULT_TIME + i * wiggle,
+            0,
+            300 + wiggle,
+            self.DEFAULT_STR,
+            self.DEFAULT_STR,
+            hashlib.md5(title.encode()).hexdigest(),
+            i * wiggle * 20,
+            120,
+        ]
+
+    def _generate_random_book_rows(self, book_count):
+        if book_count > 0:
+            for i in range(1, book_count + 1):
+                self.BOOK_ROWS.append(self._gen_random_row(i))
+
+    def _generate_custom_book_row(self, **kwargs):
+        title = kwargs.get("title", self.DEFAULT_STR)
+        if title and title != "N/A":
+            self.BOOK_ROWS.append(
+                [
+                    kwargs.get("id", self.id),
+                    kwargs.get("title", self.DEFAULT_STR),
+                    kwargs.get("authors", self.DEFAULT_STR),
+                    kwargs.get("notes", self.DEFAULT_INT),
+                    kwargs.get("last_open", self.DEFAULT_TIME),
+                    kwargs.get("highlights", self.DEFAULT_INT),
+                    kwargs.get("pages", self.DEFAULT_INT),
+                    kwargs.get("series", self.DEFAULT_STR),
+                    kwargs.get("language", self.DEFAULT_STR),
+                    hashlib.md5(title.encode()),
+                    kwargs.get("total_read_time", self.DEFAULT_INT),
+                    kwargs.get("total_read_pages", self.DEFAULT_INT),
+                ]
+            )
+
+    def _generate_random_page_stats_rows(self):
+        for book in self.BOOK_ROWS:
+            pages = book[KoReaderBookColumn.PAGES.value]
+            pages_per_session = 20
+
+            start_time = book[KoReaderBookColumn.LAST_OPEN.value]
+            end_session = False
+            for page_num in range(
+                1, book[KoReaderBookColumn.TOTAL_READ_PAGES.value] + 1
+            ):
+                wiggle = random.randrange(5)
+                self.PAGE_STATS_ROWS.append(
+                    [
+                        book[KoReaderBookColumn.ID.value],
+                        page_num,
+                        start_time,
+                        AVERAGE_PAGE_READING_SECONDS + wiggle,
+                        pages,
+                    ]
+                )
+                if end_session:
+                    start_time += 3600  # one second over an hour, marking a new reading session
+                    end_session = False
+                else:
+                    start_time += AVERAGE_PAGE_READING_SECONDS
+
+                if page_num % pages_per_session == 0:
+                    end_session = True
+
+    def __init__(self, book_count=0, **kwargs):
+        self._generate_random_book_rows(book_count)
+        self._generate_custom_book_row(**kwargs)
+        self._generate_random_page_stats_rows()
+
+
+@pytest.fixture
+def koreader_rows():
+    return KoReaderBookRows(book_count=1)
+
+
+@pytest.fixture
+def demo_user():
+    return User.objects.create(email="demo@example.com")

vrobbler/apps/books/tests/test_koreader.py

@@ -0,0 +1,54 @@
+import pytest
+from unittest import mock
+
+from books.koreader import (
+    KoReaderBookColumn,
+    build_book_map,
+    build_page_data,
+    build_scrobbles_from_book_map,
+)
+
+
+@pytest.mark.django_db
+@mock.patch("requests.get")
+def test_build_book_map(get_mock, koreader_rows, valid_response):
+    get_mock.return_value = valid_response
+    book_map = build_book_map(koreader_rows.BOOK_ROWS)
+    assert len(book_map) == 1
+
+
+@pytest.mark.django_db
+@mock.patch("requests.get")
+def test_load_page_data_to_map(get_mock, koreader_rows, valid_response):
+    get_mock.return_value = valid_response
+    book_map = build_page_data(
+        koreader_rows.PAGE_STATS_ROWS,
+        build_book_map(koreader_rows.BOOK_ROWS),
+    )
+    assert (
+        len(book_map[1]["pages"])
+        == koreader_rows.BOOK_ROWS[0][
+            KoReaderBookColumn.TOTAL_READ_PAGES.value
+        ]
+    )
+
+
+@pytest.mark.django_db
+@mock.patch("requests.get")
+def test_build_scrobbles_from_pages(
+    get_mock, koreader_rows, demo_user, valid_response
+):
+    get_mock.return_value = valid_response
+    book_map = build_book_map(koreader_rows.BOOK_ROWS)
+    book_map = build_page_data(koreader_rows.PAGE_STATS_ROWS, book_map)
+
+    scrobbles = build_scrobbles_from_book_map(book_map, demo_user)
+    # Corresponds to number of sessions per book ( 20 pages per session, 120 +/- 15 pages read )
+    expected_scrobbles = 6 * len(book_map.keys())
+    assert len(scrobbles) == expected_scrobbles
+    assert len(scrobbles[0].logdata.page_data.keys()) == 21
+    assert len(scrobbles[1].logdata.page_data.keys()) == 20
+    assert len(scrobbles[2].logdata.page_data.keys()) == 20
+    assert len(scrobbles[3].logdata.page_data.keys()) == 20
+    assert len(scrobbles[4].logdata.page_data.keys()) == 20
+    assert len(scrobbles[5].logdata.page_data.keys()) == 18

vrobbler/apps/books/tests/test_openlibrary.py

@@ -0,0 +1,39 @@
+from unittest import skip
+
+import pytest
+
+from books.openlibrary import lookup_book_from_openlibrary
+
+
+@pytest.mark.skip()
+def test_lookup_modern_book():
+    book = lookup_book_from_openlibrary("Matrix", "Lauren Groff")
+    assert book.get("title") == "Matrix"
+    assert book.get("openlibrary_id") == "OL32170218M"
+    assert book.get("ol_author_id") == "OL3675729A"
+
+
+@pytest.mark.skip()
+def test_lookup_classic_book():
+    book = lookup_book_from_openlibrary(
+        "The Life of Castruccio Castracani", "Machiavelli"
+    )
+    assert book.get("title") == "The Life of Castruccio Castracani of Lucca"
+    assert book.get("openlibrary_id") == "OL8950869M"
+    assert book.get("ol_author_id") == "OL23135A"
+
+
+@pytest.mark.skip()
+def test_lookup_foreign_book():
+    book = lookup_book_from_openlibrary("Ravagé", "René Barjavel")
+    assert book.get("title") == "Ravage"
+    assert book.get("openlibrary_id") == "OL8837839M"
+    assert book.get("ol_author_id") == "OL152472A"
+
+
+@skip("This is rotten in OL, updated but waiting for it to update")
+def test_lookup_book():
+    book = lookup_book_from_openlibrary("Hark! A Vagrant")
+    assert book.get("title") == "Hark! A Vagrant"
+    assert book.get("openlibrary_id") == "OL8837839M"
+    assert book.get("ol_author_id") == "OL152472A"

vrobbler/apps/books/urls.py

@@ -5,14 +5,14 @@ app_name = "books"
 
 
 urlpatterns = [
-    path("book/", views.BookListView.as_view(), name="book_list"),
+    path("books/", views.BookListView.as_view(), name="book_list"),
     path(
-        "book/<slug:slug>/",
+        "books/<slug:slug>/",
         views.BookDetailView.as_view(),
         name="book_detail",
     ),
     path(
-        "author/<slug:slug>/",
+        "authors/<slug:slug>/",
         views.AuthorDetailView.as_view(),
         name="author_detail",
     ),

vrobbler/apps/books/utils.py

@@ -0,0 +1,59 @@
+import re
+from urllib.parse import urlparse, urlunparse
+
+from titlecase import titlecase
+
+
+def parse_readcomicsonline_uri(uri: str) -> tuple:
+    try:
+        path = uri.split("comic/")[1]
+    except IndexError:
+        return "", "", ""
+
+    parts = path.split('/')
+    title = ""
+    volume = 1
+    page = 1
+    if len(parts) == 2:
+        title = titlecase(parts[0].replace("-", " "))
+        volume = parts[1]
+    if len(parts) == 3:
+        title = titlecase(parts[0].replace("-", " "))
+        volume = parts[1]
+        page = parts[2]
+
+    return title, volume, page
+
+
+def get_comic_issue_url(url: str) -> str:
+    parsed = urlparse(url)
+    parts = [p for p in parsed.path.strip('/').split('/') if p]
+
+    # Find the index of "comic"
+    try:
+        comic_index = parts.index("comic")
+    except ValueError:
+        raise ValueError("URL does not contain '/comic/' segment")
+
+    # Extract title (next part after 'comic')
+    if len(parts) <= comic_index + 1:
+        raise ValueError("No comic title found after '/comic/'")
+    title = parts[comic_index + 1]
+
+    # Look for the first numeric segment after the title
+    number = None
+    for segment in parts[comic_index + 2:]:
+        if segment.isdigit():
+            number = segment
+            break
+
+    # Build normalized path
+    new_parts = ["comic", title]
+    if number:
+        new_parts.append(number)
+
+    normalized_path = "/" + "/".join(new_parts)
+
+    # Rebuild full URL (same scheme and host)
+    simplified_url = urlunparse(parsed._replace(path=normalized_path, query='', fragment=''))
+    return simplified_url

vrobbler/apps/books/views.py

@@ -1,15 +1,15 @@
 from django.views import generic
 from books.models import Book, Author
 
+from scrobbles.views import ScrobbleableListView, ScrobbleableDetailView
 
-class BookListView(generic.ListView):
+
+class BookListView(ScrobbleableListView):
     model = Book
-    paginate_by = 20
 
 
-class BookDetailView(generic.DetailView):
+class BookDetailView(ScrobbleableDetailView):
     model = Book
-    slug_field = "uuid"
 
 
 class AuthorDetailView(generic.DetailView):

vrobbler/apps/bricksets/admin.py

@@ -0,0 +1,23 @@
+from django.contrib import admin
+
+from bricksets.models import BrickSet
+from scrobbles.admin import ScrobbleInline
+
+
+class BrickSetInline(admin.TabularInline):
+    model = BrickSet
+    extra = 0
+
+
+@admin.register(BrickSet)
+class BrickSetAdmin(admin.ModelAdmin):
+    date_hierarchy = "created"
+    list_display = (
+        "uuid",
+        "title",
+    )
+    ordering = ("-created",)
+    search_fields = ("title",)
+    inlines = [
+        ScrobbleInline,
+    ]

vrobbler/apps/bricksets/apps.py

@@ -0,0 +1,5 @@
+from django.apps import AppConfig
+
+
+class BrickSetsConfig(AppConfig):
+    name = "bricksets"

vrobbler/apps/bricksets/migrations/0001_initial.py

@@ -0,0 +1,106 @@
+# Generated by Django 4.2.15 on 2024-09-07 05:38
+
+from django.db import migrations, models
+import django_extensions.db.fields
+import taggit.managers
+import uuid
+
+
+class Migration(migrations.Migration):
+
+    initial = True
+
+    dependencies = [
+        ("scrobbles", "0059_remove_scrobble_book_koreader_hash_and_more"),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="BrickSet",
+            fields=[
+                (
+                    "id",
+                    models.BigAutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                (
+                    "created",
+                    django_extensions.db.fields.CreationDateTimeField(
+                        auto_now_add=True, verbose_name="created"
+                    ),
+                ),
+                (
+                    "modified",
+                    django_extensions.db.fields.ModificationDateTimeField(
+                        auto_now=True, verbose_name="modified"
+                    ),
+                ),
+                (
+                    "uuid",
+                    models.UUIDField(
+                        blank=True,
+                        default=uuid.uuid4,
+                        editable=False,
+                        null=True,
+                    ),
+                ),
+                (
+                    "title",
+                    models.CharField(blank=True, max_length=255, null=True),
+                ),
+                (
+                    "run_time_seconds",
+                    models.IntegerField(blank=True, null=True),
+                ),
+                (
+                    "run_time_ticks",
+                    models.PositiveBigIntegerField(blank=True, null=True),
+                ),
+                (
+                    "number",
+                    models.CharField(blank=True, max_length=10, null=True),
+                ),
+                ("release_year", models.IntegerField(blank=True, null=True)),
+                ("piece_count", models.IntegerField(blank=True, null=True)),
+                (
+                    "brickset_rating",
+                    models.DecimalField(
+                        blank=True, decimal_places=1, max_digits=3, null=True
+                    ),
+                ),
+                (
+                    "lego_item_number",
+                    models.CharField(blank=True, max_length=10, null=True),
+                ),
+                (
+                    "box_image",
+                    models.ImageField(
+                        blank=True, null=True, upload_to="brickset/boxes/"
+                    ),
+                ),
+                (
+                    "set_image",
+                    models.ImageField(
+                        blank=True, null=True, upload_to="brickset/sets/"
+                    ),
+                ),
+                (
+                    "genre",
+                    taggit.managers.TaggableManager(
+                        blank=True,
+                        help_text="A comma-separated list of tags.",
+                        through="scrobbles.ObjectWithGenres",
+                        to="scrobbles.Genre",
+                        verbose_name="Tags",
+                    ),
+                ),
+            ],
+            options={
+                "abstract": False,
+            },
+        ),
+    ]

vrobbler/apps/bricksets/migrations/0002_alter_brickset_run_time_seconds.py

@@ -0,0 +1,18 @@
+# Generated by Django 4.2.16 on 2025-01-22 03:55
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("bricksets", "0001_initial"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="brickset",
+            name="run_time_seconds",
+            field=models.IntegerField(default=900),
+        ),
+    ]

vrobbler/apps/bricksets/models.py

@@ -0,0 +1,85 @@
+from dataclasses import dataclass
+
+from django.db import models
+from django.urls import reverse
+from imagekit.models import ImageSpecField
+from imagekit.processors import ResizeToFit
+from scrobbles.mixins import LongPlayScrobblableMixin
+
+from vrobbler.apps.scrobbles.dataclasses import (
+    BaseLogData,
+    LongPlayLogData,
+    WithPeopleLogData,
+)
+
+BNULL = {"blank": True, "null": True}
+
+
+@dataclass
+class BrickSetLogData(BaseLogData, WithPeopleLogData, LongPlayLogData):
+    pass
+
+
+class BrickSet(LongPlayScrobblableMixin):
+    """"""
+
+    number = models.CharField(max_length=10, **BNULL)
+    release_year = models.IntegerField(**BNULL)
+    piece_count = models.IntegerField(**BNULL)
+    brickset_rating = models.DecimalField(
+        max_digits=3, decimal_places=1, **BNULL
+    )
+    lego_item_number = models.CharField(max_length=10, **BNULL)
+    box_image = models.ImageField(upload_to="brickset/boxes/", **BNULL)
+    box_image_small = ImageSpecField(
+        source="box_image",
+        processors=[ResizeToFit(100, 100)],
+        format="JPEG",
+        options={"quality": 60},
+    )
+    box_image_medium = ImageSpecField(
+        source="box_image",
+        processors=[ResizeToFit(300, 300)],
+        format="JPEG",
+        options={"quality": 75},
+    )
+    set_image = models.ImageField(upload_to="brickset/sets/", **BNULL)
+    set_image_small = ImageSpecField(
+        source="set_image",
+        processors=[ResizeToFit(100, 100)],
+        format="JPEG",
+        options={"quality": 60},
+    )
+    set_image_medium = ImageSpecField(
+        source="set_image",
+        processors=[ResizeToFit(300, 300)],
+        format="JPEG",
+        options={"quality": 75},
+    )
+
+    def get_absolute_url(self):
+        return reverse("bricksets:brickset_detail", kwargs={"slug": self.uuid})
+
+    def __str__(self) -> str:
+        name = str(self.title)
+        if not self.title:
+            name = str(self.number)
+        return name
+
+    @property
+    def logdata_cls(self):
+        return BrickSetLogData
+
+    @classmethod
+    def find_or_create(cls, brickset_id: str) -> "BrickSet":
+        brickset = cls.objects.filter(number=brickset_id).first()
+        if not brickset:
+            # TODO: enrich this from the website
+            brickset = cls.objects.create(number=brickset_id)
+        return brickset
+
+    @property
+    def primary_image_url(self) -> str:
+        if self.box_image:
+            return self.box_image.url
+        return ""

vrobbler/apps/bricksets/urls.py

@@ -0,0 +1,14 @@
+from django.urls import path
+from bricksets import views
+
+app_name = "bricksets"
+
+
+urlpatterns = [
+    path("bricksets/", views.BrickSetListView.as_view(), name="brickset_list"),
+    path(
+        "bricksets/<slug:slug>/",
+        views.BrickSetDetailView.as_view(),
+        name="brickset_detail",
+    ),
+]

vrobbler/apps/bricksets/views.py

@@ -0,0 +1,10 @@
+from bricksets.models import BrickSet
+from scrobbles.views import ScrobbleableListView, ScrobbleableDetailView
+
+
+class BrickSetListView(ScrobbleableListView):
+    model = BrickSet
+
+
+class BrickSetDetailView(ScrobbleableDetailView):
+    model = BrickSet

vrobbler/apps/foods/admin.py

@@ -0,0 +1,28 @@
+from foods.models import Food, FoodCategory
+from django.contrib import admin
+from scrobbles.admin import ScrobbleInline
+
+
+class FoodInline(admin.TabularInline):
+    model = Food
+    extra = 0
+
+
+@admin.register(FoodCategory)
+class FoodCategoryAdmin(admin.ModelAdmin):
+    date_hierarchy = "created"
+    search_fields = ("name",)
+
+
+@admin.register(Food)
+class FoodAdmin(admin.ModelAdmin):
+    date_hierarchy = "created"
+    list_display = (
+        "uuid",
+        "title",
+    )
+    ordering = ("-created",)
+    search_fields = ("title",)
+    inlines = [
+        ScrobbleInline,
+    ]

vrobbler/apps/foods/allrecipe.py

@@ -0,0 +1,143 @@
+import json
+import logging
+import urllib
+from typing import Optional
+
+import requests
+from bs4 import BeautifulSoup
+
+logger = logging.getLogger(__name__)
+
+ALLRECIPE_URL = "https://allrecipe.com/{id}"
+
+
+def get_first(key: str, result: dict) -> str:
+    obj = ""
+    if obj_list := result.get(key):
+        obj = obj_list[0]
+    return obj
+
+
+def get_title_from_soup(soup) -> str:
+    title = ""
+    try:
+        title = soup.find("h1").get_text()
+    except AttributeError:
+        pass
+    except ValueError:
+        pass
+    return title
+
+
+def get_description_from_soup(soup) -> str:
+    desc = ""
+    try:
+        desc = (
+            soup.find(class_="beer-descrption-read-less")
+            .get_text()
+            .replace("Show Less", "")
+            .strip()
+        )
+    except AttributeError:
+        pass
+    except ValueError:
+        pass
+    return desc
+
+
+def get_styles_from_soup(soup) -> list[str]:
+    styles = []
+    try:
+        styles = soup.find("p", class_="style").get_text().split(" - ")
+    except AttributeError:
+        pass
+    except ValueError:
+        pass
+    return styles
+
+
+def get_abv_from_soup(soup) -> Optional[float]:
+    abv = None
+    try:
+        abv = soup.find(class_="abv").get_text()
+        if abv:
+            abv = float(abv.strip("\n").strip("% ABV").strip())
+    except AttributeError:
+        pass
+    except ValueError:
+        pass
+    except TypeError:
+        pass
+    return abv
+
+
+def get_ibu_from_soup(soup) -> Optional[int]:
+    ibu = None
+    try:
+        ibu = soup.find(class_="ibu").get_text()
+        if ibu:
+            ibu = int(ibu.strip("\n").strip(" IBU").strip())
+    except AttributeError:
+        pass
+    except ValueError:
+        ibu = None
+    return ibu
+
+
+def get_rating_from_soup(soup) -> str:
+    rating = ""
+    try:
+        rating = float(
+            soup.find(class_="num").get_text().strip("(").strip(")")
+        )
+    except AttributeError:
+        rating = None
+    except ValueError:
+        rating = None
+    return rating
+
+
+def get_producer_id_from_soup(soup) -> str:
+    id = ""
+    try:
+        id = soup.find(class_="brewery").find("a")["href"].strip("/")
+    except ValueError:
+        pass
+    except IndexError:
+        pass
+    return id
+
+
+def get_producer_name_from_soup(soup) -> str:
+    name = ""
+    try:
+        name = soup.find(class_="brewery").find("a").get_text()
+    except AttributeError:
+        pass
+    except ValueError:
+        pass
+    return name
+
+
+def get_food_from_allrecipe_id(allrecipe_id: str) -> dict:
+    url = ALLRECIPE_URL.format(id=allrecipe_id)
+    headers = {"User-Agent": "Vrobbler 0.11.12"}
+    response = requests.get(url, headers=headers)
+
+    food_dict = {"allrecipe_id": allrecipe_id}
+
+    if response.status_code != 200:
+        logger.warn(
+            "Bad response from allrecipe", extra={"response": response}
+        )
+        return food_dict
+
+    import pdb
+
+    pdb.set_trace()
+    soup = BeautifulSoup(response.text, "html.parser")
+    food_dict["title"] = get_title_from_soup(soup)
+    food_dict["description"] = get_description_from_soup(soup)
+    food_dict["allrecipe_rating"] = get_rating_from_soup(soup)
+
+    return food_dict

vrobbler/apps/foods/apps.py

@@ -0,0 +1,5 @@
+from django.apps import AppConfig
+
+
+class FoodsConfig(AppConfig):
+    name = "foods"

vrobbler/apps/foods/migrations/0001_initial.py

@@ -0,0 +1,151 @@
+# Generated by Django 4.2.16 on 2024-11-24 14:45
+
+from django.db import migrations, models
+import django.db.models.deletion
+import django_extensions.db.fields
+import taggit.managers
+import uuid
+
+
+class Migration(migrations.Migration):
+
+    initial = True
+
+    dependencies = [
+        ("scrobbles", "0066_scrobble_beer_alter_scrobble_media_type"),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="FoodCategory",
+            fields=[
+                (
+                    "id",
+                    models.BigAutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                (
+                    "created",
+                    django_extensions.db.fields.CreationDateTimeField(
+                        auto_now_add=True, verbose_name="created"
+                    ),
+                ),
+                (
+                    "modified",
+                    django_extensions.db.fields.ModificationDateTimeField(
+                        auto_now=True, verbose_name="modified"
+                    ),
+                ),
+                (
+                    "uuid",
+                    models.UUIDField(
+                        blank=True,
+                        default=uuid.uuid4,
+                        editable=False,
+                        null=True,
+                    ),
+                ),
+                ("name", models.CharField(max_length=255)),
+                (
+                    "allrecipe_image",
+                    models.ImageField(
+                        blank=True, null=True, upload_to="food/recipe/"
+                    ),
+                ),
+                (
+                    "allrecipe_id",
+                    models.CharField(blank=True, max_length=255, null=True),
+                ),
+                ("description", models.TextField(blank=True, null=True)),
+            ],
+            options={
+                "get_latest_by": "modified",
+                "abstract": False,
+            },
+        ),
+        migrations.CreateModel(
+            name="Food",
+            fields=[
+                (
+                    "id",
+                    models.BigAutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                (
+                    "created",
+                    django_extensions.db.fields.CreationDateTimeField(
+                        auto_now_add=True, verbose_name="created"
+                    ),
+                ),
+                (
+                    "modified",
+                    django_extensions.db.fields.ModificationDateTimeField(
+                        auto_now=True, verbose_name="modified"
+                    ),
+                ),
+                (
+                    "uuid",
+                    models.UUIDField(
+                        blank=True,
+                        default=uuid.uuid4,
+                        editable=False,
+                        null=True,
+                    ),
+                ),
+                (
+                    "title",
+                    models.CharField(blank=True, max_length=255, null=True),
+                ),
+                (
+                    "run_time_seconds",
+                    models.IntegerField(blank=True, null=True),
+                ),
+                (
+                    "run_time_ticks",
+                    models.PositiveBigIntegerField(blank=True, null=True),
+                ),
+                ("description", models.TextField(blank=True, null=True)),
+                (
+                    "allrecipe_image",
+                    models.ImageField(
+                        blank=True, null=True, upload_to="food/recipe/"
+                    ),
+                ),
+                (
+                    "allrecipe_id",
+                    models.CharField(blank=True, max_length=255, null=True),
+                ),
+                ("allrecipe_rating", models.FloatField(blank=True, null=True)),
+                (
+                    "category",
+                    models.ForeignKey(
+                        blank=True,
+                        null=True,
+                        on_delete=django.db.models.deletion.DO_NOTHING,
+                        to="foods.foodcategory",
+                    ),
+                ),
+                (
+                    "genre",
+                    taggit.managers.TaggableManager(
+                        blank=True,
+                        help_text="A comma-separated list of tags.",
+                        through="scrobbles.ObjectWithGenres",
+                        to="scrobbles.Genre",
+                        verbose_name="Tags",
+                    ),
+                ),
+            ],
+            options={
+                "abstract": False,
+            },
+        ),
+    ]

vrobbler/apps/foods/migrations/0002_alter_food_run_time_seconds.py

@@ -0,0 +1,18 @@
+# Generated by Django 4.2.16 on 2025-01-22 03:55
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("foods", "0001_initial"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="food",
+            name="run_time_seconds",
+            field=models.IntegerField(default=900),
+        ),
+    ]

vrobbler/apps/foods/migrations/0003_food_calories.py

@@ -0,0 +1,18 @@
+# Generated by Django 4.2.19 on 2025-09-11 13:35
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('foods', '0002_alter_food_run_time_seconds'),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name='food',
+            name='calories',
+            field=models.IntegerField(blank=True, null=True),
+        ),
+    ]

vrobbler/apps/foods/models.py

@@ -0,0 +1,124 @@
+from dataclasses import dataclass
+from typing import Optional
+from uuid import uuid4
+
+from django.apps import apps
+from django.db import models
+from django.urls import reverse
+from django_extensions.db.models import TimeStampedModel
+from imagekit.models import ImageSpecField
+from imagekit.processors import ResizeToFit
+from scrobbles.dataclasses import BaseLogData, WithPeopleLogData
+from scrobbles.mixins import ScrobblableConstants, ScrobblableMixin
+
+BNULL = {"blank": True, "null": True}
+
+
+@dataclass
+class FoodLogData(BaseLogData, WithPeopleLogData):
+    calories: Optional[int] = None
+    meal: Optional[str] = None
+    rating: Optional[str] = None
+
+
+class FoodCategory(TimeStampedModel):
+    uuid = models.UUIDField(default=uuid4, editable=False, **BNULL)
+    name = models.CharField(max_length=255)
+    allrecipe_image = models.ImageField(upload_to="food/recipe/", **BNULL)
+    allrecipe_image_small = ImageSpecField(
+        source="recipe_image",
+        processors=[ResizeToFit(100, 100)],
+        format="JPEG",
+        options={"quality": 60},
+    )
+    allrecipe_image_medium = ImageSpecField(
+        source="recipe_image",
+        processors=[ResizeToFit(300, 300)],
+        format="JPEG",
+        options={"quality": 75},
+    )
+    allrecipe_id = models.CharField(max_length=255, **BNULL)
+    description = models.TextField(**BNULL)
+
+    def find_or_create(cls, title: str) -> "FoodCategory":
+        return cls.objects.filter(title=title).first()
+
+    def __str__(self):
+        return self.name
+
+
+class Food(ScrobblableMixin):
+    description = models.TextField(**BNULL)
+    calories = models.IntegerField(**BNULL)
+    allrecipe_image = models.ImageField(upload_to="food/recipe/", **BNULL)
+    allrecipe_image_small = ImageSpecField(
+        source="allrecipe_image",
+        processors=[ResizeToFit(100, 100)],
+        format="JPEG",
+        options={"quality": 60},
+    )
+    allrecipe_image_medium = ImageSpecField(
+        source="allrecipe_image",
+        processors=[ResizeToFit(300, 300)],
+        format="JPEG",
+        options={"quality": 75},
+    )
+    allrecipe_id = models.CharField(max_length=255, **BNULL)
+    allrecipe_rating = models.FloatField(**BNULL)
+    category = models.ForeignKey(
+        FoodCategory, on_delete=models.DO_NOTHING, **BNULL
+    )
+
+    def get_absolute_url(self) -> str:
+        return reverse("foods:food_detail", kwargs={"slug": self.uuid})
+
+    @property
+    def subtitle(self):
+        if self.category:
+            return self.category.name
+
+    @property
+    def strings(self) -> ScrobblableConstants:
+        return ScrobblableConstants(verb="Eating", tags="food")
+
+    @property
+    def allrecipe_link(self) -> str:
+        link = ""
+        if self.producer and self.allrecipe_id:
+            if self.allrecipe_id:
+                link = f"https://www.allrecipe.com/{self.allrecipe_id}/"
+        return link
+
+    @property
+    def primary_image_url(self) -> str:
+        url = ""
+        if self.allrecipe_image:
+            url = self.allrecipe_image.url
+        return url
+
+    @property
+    def logdata_cls(self):
+        return FoodLogData
+
+    @classmethod
+    def find_or_create(cls, allrecipe_id: str) -> "Food":
+        food = cls.objects.filter(allrecipe_id=allrecipe_id).first()
+
+        if not food:
+            food_dict = get_food_from_allrecipe_id(allrecipe_id)
+            # category_dict = {}
+
+            # category, _created = FoodCategory.objects.get_or_create(
+            #    **category_dict
+            # )
+            food = Food.objects.create(**food_dict)
+            # for category_id in category_ids:
+            #    food.category.add(category_id)
+
+        return food
+
+    def scrobbles(self, user_id):
+        Scrobble = apps.get_model("scrobbles", "Scrobble")
+        return Scrobble.objects.filter(user_id=user_id, food=self).order_by(
+            "-timestamp"
+        )

vrobbler/apps/foods/urls.py

@@ -0,0 +1,14 @@
+from django.urls import path
+from foods import views
+
+app_name = "foods"
+
+
+urlpatterns = [
+    path("foods/", views.FoodListView.as_view(), name="food_list"),
+    path(
+        "foods/<slug:slug>/",
+        views.FoodDetailView.as_view(),
+        name="food_detail",
+    ),
+]

vrobbler/apps/foods/views.py

@@ -0,0 +1,11 @@
+from foods.models import Food
+
+from scrobbles.views import ScrobbleableListView, ScrobbleableDetailView
+
+
+class FoodListView(ScrobbleableListView):
+    model = Food
+
+
+class FoodDetailView(ScrobbleableDetailView):
+    model = Food

vrobbler/apps/lifeevents/admin.py

@@ -0,0 +1,16 @@
+from django.contrib import admin
+
+from lifeevents.models import LifeEvent
+
+from scrobbles.admin import ScrobbleInline
+
+
+@admin.register(LifeEvent)
+class EventAdmin(admin.ModelAdmin):
+    date_hierarchy = "created"
+    list_display = ("title",)
+    search_fields = ("title",)
+    ordering = ("-created",)
+    inlines = [
+        ScrobbleInline,
+    ]

vrobbler/apps/lifeevents/migrations/0001_initial.py

@@ -0,0 +1,79 @@
+# Generated by Django 4.2.11 on 2024-05-07 13:37
+
+from django.db import migrations, models
+import django_extensions.db.fields
+import taggit.managers
+import uuid
+
+
+class Migration(migrations.Migration):
+
+    initial = True
+
+    dependencies = [
+        ("scrobbles", "0055_rename_scrobble_log_scrobble_log"),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="LifeEvent",
+            fields=[
+                (
+                    "id",
+                    models.BigAutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                (
+                    "created",
+                    django_extensions.db.fields.CreationDateTimeField(
+                        auto_now_add=True, verbose_name="created"
+                    ),
+                ),
+                (
+                    "modified",
+                    django_extensions.db.fields.ModificationDateTimeField(
+                        auto_now=True, verbose_name="modified"
+                    ),
+                ),
+                (
+                    "uuid",
+                    models.UUIDField(
+                        blank=True,
+                        default=uuid.uuid4,
+                        editable=False,
+                        null=True,
+                    ),
+                ),
+                (
+                    "title",
+                    models.CharField(blank=True, max_length=255, null=True),
+                ),
+                (
+                    "run_time_seconds",
+                    models.IntegerField(blank=True, null=True),
+                ),
+                (
+                    "run_time_ticks",
+                    models.PositiveBigIntegerField(blank=True, null=True),
+                ),
+                ("description", models.TextField(blank=True, null=True)),
+                (
+                    "genre",
+                    taggit.managers.TaggableManager(
+                        blank=True,
+                        help_text="A comma-separated list of tags.",
+                        through="scrobbles.ObjectWithGenres",
+                        to="scrobbles.Genre",
+                        verbose_name="Tags",
+                    ),
+                ),
+            ],
+            options={
+                "abstract": False,
+            },
+        ),
+    ]

vrobbler/apps/lifeevents/migrations/0002_alter_lifeevent_run_time_seconds.py

@@ -0,0 +1,18 @@
+# Generated by Django 4.2.16 on 2025-01-22 03:55
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("lifeevents", "0001_initial"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="lifeevent",
+            name="run_time_seconds",
+            field=models.IntegerField(default=900),
+        ),
+    ]

vrobbler/apps/lifeevents/models.py

@@ -0,0 +1,43 @@
+from dataclasses import dataclass
+from django.apps import apps
+from django.db import models
+from django.urls import reverse
+from scrobbles.dataclasses import BaseLogData, WithPeopleLogData
+from scrobbles.mixins import ScrobblableConstants, ScrobblableMixin
+
+BNULL = {"blank": True, "null": True}
+
+
+@dataclass
+class LifeEventLogData(BaseLogData, WithPeopleLogData):
+    pass
+
+
+class LifeEvent(ScrobblableMixin):
+    description = models.TextField(**BNULL)
+
+    def __str__(self):
+        return self.title
+
+    def get_absolute_url(self):
+        return reverse(
+            "life-events:life-event_detail", kwargs={"slug": self.uuid}
+        )
+
+    @property
+    def logdata_cls(self):
+        return LifeEventLogData
+
+    @property
+    def strings(self) -> ScrobblableConstants:
+        return ScrobblableConstants(verb="Experiencing", tags="camping")
+
+    @classmethod
+    def find_or_create(cls, title: str) -> "LifeEvent":
+        return cls.objects.filter(title=title).first()
+
+    def scrobbles(self, user_id):
+        Scrobble = apps.get_model("scrobbles", "Scrobble")
+        return Scrobble.objects.filter(
+            user_id=user_id, life_event=self
+        ).order_by("-timestamp")

vrobbler/apps/lifeevents/urls.py

@@ -0,0 +1,16 @@
+from django.urls import path
+from lifeevents import views
+
+app_name = "lifeevents"
+
+
+urlpatterns = [
+    path(
+        "lifeevents/", views.LifeEventListView.as_view(), name="lifeevent_list"
+    ),
+    path(
+        "lifeevent/<slug:slug>/",
+        views.LifeEventDetailView.as_view(),
+        name="life-event_detail",
+    ),
+]

vrobbler/apps/lifeevents/views.py

@@ -0,0 +1,12 @@
+from django.views import generic
+from lifeevents.models import LifeEvent
+
+
+class LifeEventListView(generic.ListView):
+    model = LifeEvent
+    paginate_by = 20
+
+
+class LifeEventDetailView(generic.DetailView):
+    model = LifeEvent
+    slug_field = "uuid"

vrobbler/apps/locations/admin.py

@@ -1,6 +1,6 @@
 from django.contrib import admin
 
-from locations.models import GeoLocation, RawGeoLocation
+from locations.models import GeoLocation
 
 from scrobbles.admin import ScrobbleInline
 
@@ -19,18 +19,3 @@ class GeoLocationAdmin(admin.ModelAdmin):
     inlines = [
         ScrobbleInline,
     ]
-
-
-@admin.register(RawGeoLocation)
-class RawGeoLocationAdmin(admin.ModelAdmin):
-    date_hierarchy = "created"
-    list_display = (
-        "lat",
-        "lon",
-        "altitude",
-        "speed",
-    )
-    ordering = (
-        "lat",
-        "lon",
-    )