[project] Update task list with version 33

PROJECT.org

@@ -92,7 +92,7 @@ fetching and simple saving.
 :LOGBOOK:
 CLOCK: [2025-07-09 Wed 09:55]--[2025-07-09 Wed 10:15] =>  0:20
 :END:
-* Backlog [3/27]
+* Backlog [1/27]
 ** TODO [#C] Create small utility to clean up tracks scrobbled with wonky playback times :vrobbler:personal:bug:music:scrobbles:
 ** TODO [#C] Move to using more robust mopidy-webhooks pacakge form pypi :utility:improvement:
 :PROPERTIES:
@@ -479,6 +479,61 @@ https://life.lab.unbl.ink/scrobble/e39779c8-62a5-46a6-bdef-fb7662810dc6/start/
 - Note taken on [2025-09-30 Tue 09:33]
 
   This may have already been resolved ... need to just confirm it.
+** TODO [#A] Find page numbers for comic books from ComicVine :vrobbler:feature:books:personal:project:
+* Version 33.0 [3/3]
+** DONE [#A] Fix bug where scrobble is_stale only uses seconds not total_seconds :vrobbler:bug:scrobbles:personal:project:
+:PROPERTIES:
+:ID:       7f6070ac-4f67-011d-ebd5-f3dc47da46ed
+:END:
+** DONE [#B] Fix duplicatged Read next issue for Comic books :vrobbler:bug:books:personal:project:
+:PROPERTIES:
+:ID:       97943040-1f03-b0b7-b0aa-123a783e4f7b
+:END:
+** DONE [#A] Add API authentication to BGG calls :vrobbler:bug:boardgames:personal:project:
+:PROPERTIES:
+:ID:       4955cc34-0882-50db-92f7-f36a95bf57a4
+:END:
+<2025-10-28 Tue>
+* Version 32.0 [2/2]
+** DONE [#B] Save path to reading source on book scrobbles and show it on the detail page :vrobbler:feature:books:personal:project:
+:PROPERTIES:
+:ID:       f1ef3945-e6e4-66c1-b72e-3cede7a0f84a
+:END:
+** DONE [#B] Move comic resume URL to next page and check if it exists :vrobbler:feature:books:personal:project:
+:PROPERTIES:
+:ID:       9fe09567-11a3-7083-53c7-07458a9591d0
+:END:
+* Version 31.0 [3/3]
+** DONE [#A] Stop comic book webpage scrobbles from overwriting old scrobbles :vrobbler:personal:bug:books:scrobbling:
+:PROPERTIES:
+:ID:       4b2ec068-a281-a88b-c31d-6248d6eb0aa0
+:END:
+** DONE [#A] Add page calculation to manually scrobbled books :vrobbler:personal:feature:books:scrobbling:
+:PROPERTIES:
+:ID:       b2e313b3-5c35-57e7-8933-627535baf34b
+:END:
+** DONE [#A] Fix bug in scrobbling comics where google fails :vrobbler:personal:bug:books:scrobbling:
+:PROPERTIES:
+:ID:       9a870c05-6d20-0803-d35d-c03fbe1d0ee1
+:END:
+* Version 30.0 [3/3]
+** DONE [#A] Fix readcomicsonline browsing to update pages :vrobbler:books:feature:comicbook:personal:project:scrobbling:
+:PROPERTIES:
+:ID:       981b215a-6473-5fc7-d4cc-51b3eddec4c3
+:END:
+** DONE [#B] Redirect webpages back to the original page when starting or stopping :vrobbler:project:webpages:bug:
+:PROPERTIES:
+:ID:       6183d03a-452b-51d5-cceb-5bfeada947aa
+:END:
+
+** DONE [#B] Fix ComicVine as source for comic book metadata :vrobbler:books:feature:comicbook:personal:project:scrobbling:
+:PROPERTIES:
+:ID:       d22cec3f-117f-f203-33a5-efbefa8a5cee
+:END:
+* Version 29.0 [1/1]
+** DONE HOTFIX podcast lookups, final
+* Version 28.0 [1/1]
+** DONE HOTFIX podcast lookups
 * Version 27.0 [3/3]
 ** DONE [#A] Fix bug where podcast scrobbling creates duplicate Podcast :project:vrobbler:scrobbling:podcasts:bug:personal:
 :PROPERTIES:

poetry.lock

@@ -4756,6 +4756,20 @@ webencodings = ">=0.4"
 doc = ["sphinx", "sphinx_rtd_theme"]
 test = ["pytest", "ruff"]
 
+[[package]]
+name = "titlecase"
+version = "2.4.1"
+description = "Python Port of John Gruber's titlecase.pl"
+optional = false
+python-versions = ">=3.7"
+groups = ["main"]
+files = [
+    {file = "titlecase-2.4.1.tar.gz", hash = "sha256:7d83a277ccbbda11a2944e78a63e5ccaf3d32f828c594312e4862f9a07f635f5"},
+]
+
+[package.extras]
+regex = ["regex (>=2020.4.4)"]
+
 [[package]]
 name = "tld"
 version = "0.13"
@@ -5525,4 +5539,4 @@ cffi = ["cffi (>=1.11)"]
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.9,<3.12"
-content-hash = "cd3b566597e09aa444f9af30f95f94f922bf3dca71fbd05c887fb10cbc11d7bf"
+content-hash = "2e297ef6f8c524840a381ad793946c87b601d81afd569e882fe58120a5f84626"

pyproject.toml

@@ -57,6 +57,7 @@ orgparse = "^0.4.20250520"
 tmdbv3api = "^1.9.0"
 themoviedb = "^1.0.2"
 feedparser = "^6.0.12"
+titlecase = "^2.4.1"
 
 [tool.poetry.group.test]
 optional = true

tests/scrobbles_tests/conftest.py

@@ -115,6 +115,12 @@ def mopidy_podcast_request_data():
         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"

vrobbler/apps/boardgames/bgg.py

@@ -6,6 +6,7 @@ from typing import TYPE_CHECKING, Optional
 import requests
 from bs4 import BeautifulSoup
 from django.contrib.auth import get_user_model
+from django.conf import settings
 
 User = get_user_model()
 if TYPE_CHECKING:
@@ -17,6 +18,8 @@ SEARCH_ID_URL = (
     "https://boardgamegeek.com/xmlapi/search?search={query}&exact=1"
 )
 GAME_ID_URL = "https://boardgamegeek.com/xmlapi/boardgame/{id}"
+BGG_ACCESS_TOKEN = getattr(settings, "BGG_ACCESS_TOKEN", "")
+BASE_HEADERS = {"User-Agent": "Vrobbler 31.0", "Authorization": f"Bearer {BGG_ACCESS_TOKEN}"}
 
 
 def take_first(thing: Optional[list]) -> str:
@@ -37,10 +40,9 @@ def take_first(thing: Optional[list]) -> str:
 
 def lookup_boardgame_id_from_bgg(title: str) -> Optional[int]:
     soup = None
-    headers = {"User-Agent": "Vrobbler 0.11.12"}
     game_id = None
     url = SEARCH_ID_URL.format(query=title)
-    r = requests.get(url, headers=headers)
+    r = requests.get(url, headers=BASE_HEADERS)
     if r.status_code == 200:
         soup = BeautifulSoup(r.text, "xml")
 
@@ -57,7 +59,6 @@ def lookup_boardgame_id_from_bgg(title: str) -> Optional[int]:
 def lookup_boardgame_from_bgg(lookup_id: str) -> dict:
     soup = None
     game_dict = {}
-    headers = {"User-Agent": "Vrobbler 0.11.12"}
 
     title = ""
     bgg_id = None
@@ -73,7 +74,7 @@ def lookup_boardgame_from_bgg(lookup_id: str) -> dict:
         bgg_id = lookup_boardgame_id_from_bgg(title)
 
     url = GAME_ID_URL.format(id=bgg_id)
-    r = requests.get(url, headers=headers)
+    r = requests.get(url, headers=BASE_HEADERS)
     if r.status_code == 200:
         soup = BeautifulSoup(r.text, "xml")
 
@@ -109,7 +110,8 @@ def push_scrobble_to_bgg(scrobble: "Scrobble", user: User) -> Optional[bool]:
     login_payload = {
         "credentials": {"username": bgg_username, "password": bgg_password}
     }
-    headers = {"content-type": "application/json"}
+    headers = BASE_HEADERS
+    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
 

vrobbler/apps/books/admin.py

@@ -21,7 +21,8 @@ class BookAdmin(admin.ModelAdmin):
     date_hierarchy = "created"
     list_display = (
         "title",
-        "subtitle",
+        "author",
+        "issue_or_volume",
         "isbn_13",
         "first_publish_year",
         "pages",
@@ -32,6 +33,9 @@ class BookAdmin(admin.ModelAdmin):
         ScrobbleInline,
     ]
 
+    def issue_or_volume(self, obj):
+        return obj.issue_number or obj.volume_number
+
 
 @admin.register(Paper)
 class BookAdmin(admin.ModelAdmin):

vrobbler/apps/books/constants.py

@@ -5,3 +5,5 @@ BOOKS_TITLES_TO_IGNORE = [
     "zb2rhkSwygt9vjkAEBj7tP5KVgFqejJqsJ2W3bYsrgiiKK8XL",
     "zb2rhchGpo7P27mofV9hYjT63d9ZaQnbQ6LSfzmkvsYzvARif",
 ]
+
+READCOMICSONLINE_URL = "https://readcomicsonline.ru"

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

@@ -1,15 +1,19 @@
+import logging
 from collections import OrderedDict
 from dataclasses import dataclass
-import logging
 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
@@ -18,27 +22,25 @@ 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,
     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.comicvine import (
-    ComicVineClient,
-    lookup_comic_from_comicvine,
-)
 
 from vrobbler.apps.books.locg import (
     lookup_comic_by_locg_slug,
     lookup_comic_from_locg,
     lookup_comic_writer_by_locg_slug,
 )
-from books.sources.google import lookup_book_from_google
+from vrobbler.apps.books.sources.comicvine import (
-from books.sources.semantic import lookup_paper_from_semantic
+    ComicVineClient,
-from scrobbles.dataclasses import BaseLogData, LongPlayLogData
+    lookup_comic_from_comicvine,
+)
 
 COMICVINE_API_KEY = getattr(settings, "COMICVINE_API_KEY", "")
 
@@ -62,6 +64,7 @@ class BookLogData(BaseLogData, LongPlayLogData):
     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"}
 
@@ -135,6 +138,7 @@ class Book(LongPlayScrobblableMixin):
     )
 
     title = models.CharField(max_length=255)
+    original_title = models.CharField(max_length=255, **BNULL)
     authors = models.ManyToManyField(Author, blank=True)
     koreader_data_by_hash = models.JSONField(**BNULL)
     isbn_13 = models.CharField(max_length=255, **BNULL)
@@ -145,6 +149,13 @@ class Book(LongPlayScrobblableMixin):
     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)
     cover = models.ImageField(upload_to="books/covers/", **BNULL)
     cover_small = ImageSpecField(
@@ -163,7 +174,11 @@ 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
@@ -188,9 +203,45 @@ class Book(LongPlayScrobblableMixin):
     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, enrich: bool = False, commit: bool = True
+            cls, title: str, url: str = "", enrich: bool = False, commit: bool = True
     ):
         """Given a title, get a Book instance.
 
@@ -201,7 +252,7 @@ class Book(LongPlayScrobblableMixin):
         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(title=title)
+        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}
@@ -214,15 +265,22 @@ class Book(LongPlayScrobblableMixin):
             )
             return book
 
-        book_dict = lookup_book_from_google(title)
+        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")
+        authors = book_dict.pop("authors", [])
-        cover_url = book_dict.pop("cover_url")
+        cover_url = book_dict.pop("cover_url", "")
-        try:
+        genres = book_dict.pop("generes", [])
-            genres = book_dict.pop("generes")
-        except:
-            genres = []
 
         if authors:
             for author_str in authors:
@@ -248,7 +306,7 @@ class Book(LongPlayScrobblableMixin):
         return book
 
     def save_image_from_url(self, url: str, force_update: bool = False):
-        if not self.cover or (force_update and url):
+        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"

vrobbler/apps/books/sources/comicvine.py

@@ -3,7 +3,6 @@ ComicVine API Information & Documentation:
 https://comicvine.gamespot.com/api/
 https://comicvine.gamespot.com/api/documentation
 """
-import json
 import logging
 from django.conf import settings
 
@@ -200,34 +199,72 @@ class ComicVineClient(object):
 
 
 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.warn("No ComicVine API key configured, not looking anything up")
+        logger.warning("No ComicVine API key configured, not looking anything up")
         return {}
 
     client = ComicVineClient(
         api_key=getattr(settings, "COMICVINE_API_KEY", None)
     )
-    result = [
-        r
-        for r in client.search(title).get("results")
-        if r.get("resource_type") == "volume"
-    ][0]
 
-    if "volume" not in result.keys():
+    raw_results = client.search(title).get("results")
-        logger.warn("No result found on ComicVine", extra={"title": title})
+    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 {}
 
-    title = " ".join([result.get("volume").get("name"), result.get("name)")])
+    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,
-        "cover_url": result.get("image").get("original_url"),
+        "original_title": original_title,
-        "comicvine_data": {
+        "issue_number": found_result.get("issue_number"),
-            "id": result.get("id"),
+        "volume_number": found_result.get("volume_number"),
-            "site_detail_url": result.get("site_detail_url"),
+        "cover_url": found_result.get("image").get("original_url"),
-            "description": result.get("description"),
+        "comicvine_id": found_result.get("id"),
-            "image": result.get("image").get("original_url"),
+        "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

@@ -29,6 +29,9 @@ def lookup_book_from_google(title: str) -> 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 = ""
@@ -59,13 +62,15 @@ def lookup_book_from_google(title: str) -> dict:
     book_dict["genres"] = google_result.get("categories")
     book_dict["cover_url"] = (
         google_result.get("imageLinks", {})
-        .get("thumbnail")
+        .get("thumbnail", "")
         .replace("zoom=1", "zoom=15")
         .replace("&edge=curl", "")
     )
 
-    book_dict["run_time_seconds"] = book_dict.get("pages", 10) * getattr(
+    book_dict["run_time_seconds"] = 3600
-        settings, "AVERAGE_PAGE_READING_SECONDS", 60
+    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/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/podcasts/models.py

@@ -143,13 +143,13 @@ class PodcastEpisode(ScrobblableMixin):
     def find_or_create(
         cls,
         title: str,
-        podcast_name: str,
-        podcast_description: str,
         pub_date: str,
-        number: int = 0,
+        episode_num: int = 0,
-        mopidy_uri: str = "",
-        producer_name: str = "",
         run_time_seconds: int = 1800,
+        mopidy_uri: str = "",
+        podcast_name: str = "",
+        podcast_producer: str = "",
+        podcast_description: str = "",
         enrich: bool = True,
     ) -> "PodcastEpisode":
         """Given a data dict from Mopidy, finds or creates a podcast and
@@ -158,8 +158,8 @@ class PodcastEpisode(ScrobblableMixin):
         """
         log_context={"mopidy_uri": mopidy_uri, "media_type": "Podcast"}
         producer = None
-        if producer_name:
+        if podcast_producer:
-            producer = Producer.find_or_create(producer_name)
+            producer = Producer.find_or_create(podcast_producer)
 
         podcast, created = Podcast.objects.get_or_create(name=podcast_name, defaults={"description": podcast_description})
         log_context["podcast_id"] = podcast.id
@@ -175,7 +175,7 @@ class PodcastEpisode(ScrobblableMixin):
             podcast=podcast,
             defaults={
                 "run_time_seconds": run_time_seconds,
-                "number": number,
+                "number": episode_num,
                 "pub_date": pub_date,
                 "mopidy_uri": mopidy_uri,
             }

vrobbler/apps/podcasts/utils.py

@@ -4,6 +4,7 @@ from typing import Any
 from urllib.parse import unquote
 
 import feedparser
+import requests
 from dateutil.parser import ParserError, parse
 from podcasts.models import PodcastEpisode
 
@@ -27,33 +28,43 @@ def fetch_metadata_from_rss(uri: str) -> dict[str, Any]:
     log_context = {"mopidy_uri": uri, "media_type": "Podcast"}
     podcast_data: dict[str, Any] = {}
 
+    rss_url = uri.split("#")[0].split("podcast+")[1]
+    target_guid = uri.split("#")[1]
+
+    log_context["rss_url"] = rss_url
+    log_context["target_guid"] = target_guid
+
     try:
-        feed = feedparser.parse(uri.split("#")[0])
+        resp = requests.get(rss_url, timeout=10)
-        target_guid = uri.split("#")[1]
+        feed = feedparser.parse(resp.text)
     except IndexError:
         logger.warning("Tried to parse uri as RSS feed, but no target found", extra=log_context)
         return podcast_data
 
-    podcast_publisher = feed.feed.get("itunes_publisher")
+    podcast_publisher = getattr(feed.feed, "itunes_publisher", "")
-    podcast_owner = feed.feed.itunes_owner.get("name") if isinstance(feed.feed.itunes_owner, dict) else feed.feed.itunes_owner
+    try:
-    podcast_other = feed.feed.get("managingeditor") or feed.feed.get("copyright")
+        podcast_owner = feed.feed.itunes_owner.get("name") if isinstance(feed.feed.itunes_owner, dict) else feed.feed.itunes_owner
+        podcast_other = feed.feed.get("managingeditor") or feed.feed.get("copyright")
+    except AttributeError:
+        podcast_owner = None
+        podcast_other = None
 
     podcast_data = {
-        "podcast_name": feed.feed.get("title", "Unknown Podcast"),
+        "podcast_name": getattr(feed.feed, "title", ""),
-        "podcast_description": feed.feed.get("description", ""),
+        # "podcast_description": getattr(feed.feed, "description", ""),
-        "podcast_link": feed.feed.get("link", ""),
+        # "podcast_link": getattr(feed.feed, "link", ""),
         "podcast_producer": podcast_publisher or podcast_owner or podcast_other
     }
 
     for entry in feed.entries:
-        if target_guid in target_guid:
+        if entry.get("guid") == target_guid:
             logger.info("🎧 Episode found in RSS feed", extra=log_context)
-            podcast_data["episode_name"] = entry.title
+            podcast_data["title"] = entry.title
-            podcast_data["episode_num"] = entry.guid
+            podcast_data["episode_num"] = int(entry.get("itunes_episode", 0))
-            podcast_data["episode_pub_date"] = entry.get("published", None)
+            podcast_data["pub_date"] = parse(entry.get("published", None))
-            podcast_data["episode_description"] = entry.get("description", None)
+            podcast_data["run_time_seconds"] = parse_duration(entry.get("itunes_duration", None))
-            podcast_data["episode_url"] = entry.enclosures[0].href if entry.get("enclosures") else None
+            # podcast_data["description"] = entry.get("description", None)
-            podcast_data["episode_runtime_seconds"] = parse_duration(entry.get("itunes_duration", None))
+            # podcast_data["episode_url"] = entry.enclosures[0].href if entry.get("enclosures") else None
             return podcast_data
     else:
         logger.info("Episode not found in RSS feed.")
@@ -63,14 +74,14 @@ def parse_mopidy_uri(uri: str) -> dict[str, Any]:
     podcast_data: dict[str, Any] = {}
 
     logger.debug(f"Parsing URI: {uri}")
-    if "https://" in uri:
+    if "podcast+https" in uri:
         return fetch_metadata_from_rss(uri)
 
 
     parsed_uri = os.path.splitext(unquote(uri))[0].split("/")
 
     podcast_data = {
-        "episode_filename": parsed_uri[-1],
+        "title": parsed_uri[-1],
         "episode_num": None,
         "podcast_name": parsed_uri[-2].strip(),
         "pub_date": None,
@@ -105,30 +116,14 @@ def parse_mopidy_uri(uri: str) -> dict[str, Any]:
     if podcast_data["episode_num"]:
         gap_to_strip += episode_num_pad
 
-    podcast_data["episode_name"] = episode_str[gap_to_strip:].replace("-", " ").strip()
+    podcast_data["title"] = episode_str[gap_to_strip:].replace("-", " ").strip()
 
     return podcast_data
 
 
 def get_or_create_podcast(post_data: dict) -> PodcastEpisode:
     logger.info("Looking up podcast", extra={"post_data": post_data, "media_type": "Podcast"})
-
     mopidy_uri = post_data.get("mopidy_uri", "")
     parsed_data = parse_mopidy_uri(mopidy_uri)
-    producer_name = parsed_data.get("podcast_producer", post_data.get("artist", ""))
-    podcast_name = parsed_data.get("podcast_name", post_data.get("album", ""))
-    episode_name = parsed_data.get("episode_title", parsed_data.get("episode_filename", ""))
-    run_time_seconds = parsed_data.get("episode_runtime_seconds", post_data.get("run_time", 2700))
 
-    episode_dict = {
+    return PodcastEpisode.find_or_create(**parsed_data)
-        "title": episode_name,
-        "podcast_name": podcast_name,
-        "podcast_description": parsed_data.get("podcast_description"),
-        "pub_date": parsed_data.get("pub_date"),
-        "number": parsed_data.get("episode_num"),
-        "mopidy_uri": mopidy_uri,
-        "producer_name": producer_name,
-        "run_time_seconds": run_time_seconds,
-    }
-
-    return PodcastEpisode.find_or_create(**episode_dict)

vrobbler/apps/scrobbles/models.py

@@ -12,7 +12,7 @@ import pytz
 from beers.models import Beer
 from boardgames.models import BoardGame
 from books.koreader import process_koreader_sqlite_file
-from books.models import Book, Paper
+from books.models import Book, Paper, BookPageLogData, BookLogData
 from bricksets.models import BrickSet
 from dataclass_wizard.errors import ParseError
 from django.conf import settings
@@ -775,7 +775,7 @@ class Scrobble(TimeStampedModel):
             and user.profile.redirect_to_webpage
         ):
             logger.info(f"Redirecting to {self.media_obj.url}")
-            redirect_url = self.media_obj.get_read_url()
+            redirect_url = self.media_obj.url
 
         if (
             self.media_type == self.MediaType.VIDEO
@@ -822,7 +822,7 @@ class Scrobble(TimeStampedModel):
         """
         is_stale = False
         now = timezone.now()
-        seconds_since_last_update = (now - self.modified).seconds
+        seconds_since_last_update = (now - self.modified).total_seconds()
         if seconds_since_last_update >= self.media_obj.SECONDS_TO_STALE:
             is_stale = True
         return is_stale
@@ -991,7 +991,7 @@ class Scrobble(TimeStampedModel):
 
     @property
     def can_be_updated(self) -> bool:
-        if self.media_obj.__class__.__name__ in LONG_PLAY_MEDIA.values():
+        if self.media_obj.__class__.__name__ in LONG_PLAY_MEDIA.values() and self.source != "readcomicsonline.ru":
             logger.info(
                 "[scrobbling] cannot be updated, long play media",
                 extra={
@@ -1131,6 +1131,8 @@ class Scrobble(TimeStampedModel):
         media_query = models.Q(**{key: media})
         scrobble_data[key + "_id"] = media.id
         skip_in_progress_check = kwargs.get("skip_in_progress_check", False)
+        read_log_page = kwargs.get("read_log_page", None)
+
 
         # Find our last scrobble of this media item (track, video, etc)
         scrobble = (
@@ -1154,7 +1156,7 @@ class Scrobble(TimeStampedModel):
             )
             return scrobble
 
-        if not skip_in_progress_check:
+        if not skip_in_progress_check or read_log_page:
             logger.info(
                 f"[create_or_update] check for existing scrobble to update ",
                 extra={
@@ -1170,15 +1172,35 @@ class Scrobble(TimeStampedModel):
             # If it's marked as stopped, send it through our update mechanism, which will complete it
             if scrobble and (
                 scrobble.can_be_updated
+                or (read_log_page and scrobble.can_be_updated)
                 or scrobble_data["playback_status"] == "stopped"
             ):
-                if "log" in scrobble_data.keys() and scrobble.log:
+                if read_log_page:
+                    page_list = scrobble.log.get("page_data", [])
+                    if page_list:
+                        for page in page_list:
+                            if not page.get("end_ts", None):
+                                page["end_ts"] = int(timezone.now().timestamp())
+                                page["duration"] = page["end_ts"] - page.get("start_ts")
+
+                    page_list.append(
+                        BookPageLogData(
+                            page_number=read_log_page,
+                            start_ts=int(timezone.now().timestamp())
+                        )
+                    )
+                    scrobble.log["page_data"] = page_list
+                    scrobble.save(update_fields=["log"])
+                elif "log" in scrobble_data.keys() and scrobble.log:
                     scrobble_data["log"] = scrobble.log | scrobble_data["log"]
                 return scrobble.update(scrobble_data)
 
             # Discard status before creating
             scrobble_data.pop("playback_status")
 
+        if read_log_page:
+            scrobble_data["log"] = BookLogData(page_data=[BookPageLogData(page_number=read_log_page, start_ts=int(timezone.now().timestamp()))])
+
         logger.info(
             f"[scrobbling] creating new scrobble",
             extra={
@@ -1371,6 +1393,9 @@ class Scrobble(TimeStampedModel):
         if class_name in LONG_PLAY_MEDIA.values():
             self.finish_long_play()
 
+        if class_name == "Book":
+            self.calculate_reading_stats()
+
         logger.info(
             f"[scrobbling] stopped",
             extra={
@@ -1466,3 +1491,40 @@ class Scrobble(TimeStampedModel):
             beyond_completion = False
 
         return beyond_completion
+
+    def calculate_reading_stats(self, commit=True):
+        # --- Sort safely by numeric page_number ---
+        def safe_page_number(entry):
+            try:
+                return int(getattr("page_number", entry), 0)
+            except (ValueError, TypeError):
+                return float("inf")  # push invalid entries to the end
+
+        page_data = self.log.get("page_data")
+
+        if not page_data:
+            logger.warning("No page data found to calculate")
+            return
+
+        if isinstance(page_data, dict):
+            logger.warning("Page data is dict, migrate koreader data")
+            return
+
+        page_data.sort(key=safe_page_number)
+
+        # --- Extract valid numeric page numbers ---
+        valid_pages = []
+        for page in page_data:
+            try:
+                valid_pages.append(int(page["page_number"]))
+            except (ValueError, TypeError):
+                continue
+
+        # --- Compute stats ---
+        if valid_pages:
+            self.log["page_start"] = min(valid_pages)
+            self.log["page_end"] = max(valid_pages)
+            self.log["pages_read"] = len(set(valid_pages))
+
+            if commit:
+                self.save(update_fields=["log"])

vrobbler/apps/scrobbles/scrobblers.py

@@ -7,7 +7,9 @@ import pendulum
 import pytz
 from beers.models import Beer
 from boardgames.models import BoardGame, BoardGameDesigner, BoardGameLocation
-from books.models import Book
+from books.constants import READCOMICSONLINE_URL
+from books.models import Book, BookLogData, BookPageLogData
+from books.utils import parse_readcomicsonline_uri
 from bricksets.models import BrickSet
 from dateutil.parser import parse
 from django.utils import timezone
@@ -27,7 +29,12 @@ from scrobbles.constants import (
 )
 from scrobbles.models import Scrobble
 from scrobbles.notifications import ScrobbleNtfyNotification
-from scrobbles.utils import convert_to_seconds, extract_domain
+from scrobbles.utils import (
+    convert_to_seconds,
+    extract_domain,
+    remove_last_part,
+    next_url_if_exists,
+)
 from sports.models import SportEvent
 from sports.thesportsdb import lookup_event_from_thesportsdb
 from tasks.models import Task
@@ -56,18 +63,11 @@ def mopidy_scrobble_media(post_data: dict, user_id: int) -> Scrobble:
 
     if media_type == Scrobble.MediaType.PODCAST_EPISODE:
         parsed_data = parse_mopidy_uri(post_data.get("mopidy_uri", ""))
-        podcast_name = post_data.get(
+        if not parsed_data:
-            "album", parsed_data.get("podcast_name", "")
+            logger.warning("Tried to scrobble podcast but no uri found", extra={"post_data": post_data})
-        )
+            return Scrobble()
 
-        media_obj = PodcastEpisode.find_or_create(
+        media_obj = PodcastEpisode.find_or_create(**parsed_data)
-            title=parsed_data.get("episode_filename", ""),
-            podcast_name=podcast_name,
-            producer_name=post_data.get("artist", ""),
-            number=parsed_data.get("episode_num", ""),
-            pub_date=parsed_data.get("pub_date", ""),
-            mopidy_uri=post_data.get("mopidy_uri", ""),
-        )
     else:
         media_obj = Track.find_or_create(
             title=post_data.get("name", ""),
@@ -262,13 +262,43 @@ def manual_scrobble_video_game(
 def manual_scrobble_book(
     title: str, user_id: int, action: Optional[str] = None
 ):
-    book = Book.find_or_create(title)
+    log = {}
+    source = "Vrobbler"
+    page = None
+    url = ""
+
+    if READCOMICSONLINE_URL in title:
+        url = title
+        title, volume, page = parse_readcomicsonline_uri(title)
+        if not title:
+            logger.info(
+                "[scrobblers] manual book scrobble request failed",
+                extra={
+                    "title": title,
+                    "user_id": user_id,
+                    "media_type": Scrobble.MediaType.BOOK,
+                },
+            )
+            return
+
+        title = f"{title} - Issue {volume}"
+
+        if not page:
+            page = 1
+
+        logger.info("[scrobblers] Book page included in scrobble, should update!")
+
+        source = READCOMICSONLINE_URL.replace("https://", "")
+
+    # TODO: Check for scrobble of this book already and if so, update the page count
+
+    book = Book.find_or_create(title, url=url, enrich=True)
 
     scrobble_dict = {
         "user_id": user_id,
         "timestamp": timezone.now(),
         "playback_position_seconds": 0,
-        "source": "Vrobbler",
+        "source": source,
         "long_play_complete": False,
     }
 
@@ -282,7 +312,19 @@ def manual_scrobble_book(
         },
     )
 
-    return Scrobble.create_or_update(book, user_id, scrobble_dict)
+
+    scrobble = Scrobble.create_or_update(book, user_id, scrobble_dict, read_log_page=page)
+
+    if action == "stop":
+        if url:
+            if isinstance(scrobble.log, "BookLogData"):
+                scrobble.log.resume_url = next_url_if_exists(url)
+            else:
+                scrobble.log["resume_url"] = next_url_if_exists(url)
+            scrobble.save(update_fields=["log"])
+        scrobble.stop(force_finish=True)
+
+    return scrobble
 
 
 def manual_scrobble_board_game(
@@ -539,6 +581,8 @@ def manual_scrobble_from_url(
 
     if content_key == "-i" and "v=" in url:
         item_id = url.split("v=")[1].split("&")[0]
+    elif content_key == "-c" and "comics" in url:
+        item_id = url
     elif content_key == "-i" and "title/tt" in url:
         item_id = "tt" + str(item_id)
 
@@ -875,8 +919,13 @@ def manual_scrobble_webpage(
     )
 
     scrobble = Scrobble.create_or_update(webpage, user_id, scrobble_dict)
-    # possibly async this?
+
-    scrobble.push_to_archivebox()
+    if action == "stop":
+        scrobble.stop(force_finish=True)
+    else:
+        # possibly async this?
+        scrobble.push_to_archivebox()
+
     return scrobble
 
 

vrobbler/apps/scrobbles/utils.py

@@ -1,5 +1,6 @@
 import hashlib
 import logging
+import requests
 import re
 from datetime import date, datetime, timedelta
 from typing import TYPE_CHECKING, Optional
@@ -393,7 +394,10 @@ def get_daily_calories_for_user_by_day(user_id: int, date: date| str) -> int:
     if isinstance(date, str):
         date = pendulum.parse(date)
 
-    qs = base_scrobble_qs(user_id).filter(day=date)
+    try:
+        qs = base_scrobble_qs(user_id).filter(day=date)
+    except AttibuteError as e:
+        logger.warning(f"Can't generate calorie total: {e}")
     agg = qs.aggregate(total_calories=models.Sum("calories_int"))
 
     return agg["total_calories"] or 0
@@ -408,3 +412,41 @@ def get_daily_calorie_dict_for_user(user_id: int) -> dict[date, int]:
     )
 
     return {entry["day"]: entry["total_calories"] for entry in qs}
+
+def remove_last_part(url: str) -> str:
+    url = url.rstrip('/')
+    if '/' not in url:
+        return url
+    return url.rsplit('/', 1)[0]
+
+def next_url_if_exists(url: str) -> str:
+    # Normalize (remove trailing slash)
+    url = url.rstrip('/')
+
+    # Find last number in the URL path
+    match = re.search(r'(\d+)(?:/?$)', url)
+    if not match:
+        logger.info("No numeric segment found in the URL", extra={"url": url})
+        return ""
+
+    number = int(match.group(1))
+    new_number = number + 1
+
+    # Replace only the last occurrence of that number
+    new_url = re.sub(rf'{number}(?:/?$)', f'{new_number}/', url + '/', 1)
+
+    # Check if the new URL exists
+    try:
+        resp = requests.head(new_url, allow_redirects=True, timeout=5)
+        if resp.status_code == 200:
+            return new_url
+        else:
+            # Fallback: some sites may not support HEAD well — try GET
+            resp = requests.get(new_url, timeout=5)
+            if resp.status_code == 200:
+                return new_url
+    except requests.RequestException:
+        pass
+
+    # If it doesn’t exist
+    return ""

vrobbler/apps/scrobbles/views.py

@@ -625,9 +625,9 @@ def scrobble_start(request, uuid):
 
     if (
         user.profile.redirect_to_webpage
-        and media_obj.__class__.__name__ == Scrobble.MediaType.WEBPAGE
+        and (media_obj.__class__.__name__ == Scrobble.MediaType.WEBPAGE or media_obj.__class__.__name__ == Scrobble.MediaType.BOOK)
     ):
-        logger.info(f"Redirecting to {media_obj} detail apge")
+        logger.info(f"Redirecting to {media_obj} detail page")
         return HttpResponseRedirect(media_obj.url)
 
     return HttpResponseRedirect(success_url)

vrobbler/settings.py

@@ -68,6 +68,7 @@ LASTFM_SECRET_KEY = os.getenv("VROBBLER_LASTFM_SECRET_KEY")
 IGDB_CLIENT_ID = os.getenv("VROBBLER_IGDB_CLIENT_ID")
 IGDB_CLIENT_SECRET = os.getenv("VROBBLER_IGDB_CLIENT_SECRET")
 COMICVINE_API_KEY = os.getenv("VROBBLER_COMICVINE_API_KEY")
+BGG_ACCESS_TOKEN = os.getenv("VROBBLER_BGG_ACCESS_TOKEN", "")
 GEOLOC_ACCURACY = os.getenv("VROBBLER_GEOLOC_ACCURACY", 3)
 GEOLOC_PROXIMITY = os.getenv("VROBBLER_GEOLOC_PROXIMITY", "0.0001")
 POINTS_FOR_MOVEMENT_HISTORY = os.getenv(

vrobbler/templates/books/book_detail.html

@@ -26,7 +26,20 @@
     </div>
 </div>
 <div class="row">
+    {% if object.readcomics_url %}
+    <p><a href="{{object.readcomics_url}}">Read again</a></p>
+    {% endif %}
+    {% if object.next_readcomics_url %}
+    <p><a href="{{object.next_readcomics_url}}">Read next issue</a></p>
+    {% endif %}
+
     <p>{{scrobbles.count}} scrobbles</p>
+
+    {% for s in scrobbles %}
+    {% if forloop.first %}
+    <p><a href="{{s.logdata.resume_url}}">Resume reading</a></p>
+    {% endif %}
+    {% endfor %}
 </div>
 <div class="row">
     <div class="col-md">