[books] Allow comic scrobbling to update per page

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

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/models.py

@@ -26,7 +26,7 @@ from scrobbles.mixins import (
 from scrobbles.utils import get_scrobbles_for_media
 from taggit.managers import TaggableManager
 from thefuzz import fuzz
-from vrobbler.apps.books.comicvine import (
+from vrobbler.apps.books.sources.comicvine import (
     ComicVineClient,
     lookup_comic_from_comicvine,
 )
@@ -135,6 +135,7 @@ 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 +146,11 @@ 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)
+    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(
@@ -188,6 +194,43 @@ 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 and not overwrite and not force_new:
+            book, created = cls.objects.get_or_create(original_title=title)
+            logger.info("Found comic by original title, use force_new=True to override")
+            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
@@ -215,6 +258,8 @@ class Book(LongPlayScrobblableMixin):
             return book
 
         book_dict = lookup_book_from_google(title)
+        if not book_dict or book_dict.get("isbn_10"):
+            book_dict = lookup_comic_from_comicvine(title)
 
         author_list = []
         authors = book_dict.pop("authors")

vrobbler/apps/books/comicvine.py → 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 +199,71 @@ 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 = [
+
+    raw_results = client.search(title).get("results")
+    results = [
         r
-        for r in client.search(title).get("results")
-        if r.get("resource_type") == "volume"
-    ][0]
+        for r in raw_results
+        if r.get("resource_type") == resource_type
+    ]
+    print(results)
+    if not results:
+        logger.warning("No comic found on ComicVine")
+        return {}
+
+    found_result = None
+    for result in results:
+        print("checking ", result.get("issue_number"), " to ", str(issue_number))
+        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 "volume" not in result.keys():
-        logger.warn("No result found on ComicVine", extra={"title": title})
+    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 = " ".join([result.get("volume").get("name"), result.get("name)")])
+    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"),
-        "comicvine_data": {
-            "id": result.get("id"),
-            "site_detail_url": result.get("site_detail_url"),
-            "description": result.get("description"),
-            "image": result.get("image").get("original_url"),
-        },
+        "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,
     }
 
     return data_dict

vrobbler/apps/books/utils.py

@@ -0,0 +1,18 @@
+from titlecase import titlecase
+
+def parse_readcomicsonline_uri(uri: str) -> tuple:
+    path = uri.split("comic/")[1]
+
+    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

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
@@ -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 +1172,34 @@ 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
                 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_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={

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
@@ -255,13 +257,31 @@ 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
+
+    if READCOMICSONLINE_URL in title:
+        title, volume, page = parse_readcomicsonline_uri(title)
+        title = f"{title} - Issue {volume}"
+
+        if not page:
+            page = 1
+
+        log = BookLogData(page_data=BookPageLogData(page_number=page, start_ts=int(timezone.now().timestamp())))
+        logger.info("[scrobblers] Book page included in scrobble, should update!")
+
+        source = READCOMICSONLINE_URL
+
+    # TODO: Check for scrobble of this book already and if so, update the page count
+
+    book = Book.find_or_create(title, enrich=True)
 
     scrobble_dict = {
         "user_id": user_id,
         "timestamp": timezone.now(),
         "playback_position_seconds": 0,
-        "source": "Vrobbler",
+        "source": source,
         "long_play_complete": False,
     }
 
@@ -275,7 +295,7 @@ def manual_scrobble_book(
         },
     )
 
-    return Scrobble.create_or_update(book, user_id, scrobble_dict)
+    return Scrobble.create_or_update(book, user_id, scrobble_dict, read_log_page=page)
 
 
 def manual_scrobble_board_game(
@@ -532,6 +552,8 @@ 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)