[books] Add utility urls to model and scrobbles

PROJECT.org

@@ -479,6 +479,27 @@ 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.
+** 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:

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/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.sources.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 books.sources.semantic import lookup_paper_from_semantic
-from scrobbles.dataclasses import BaseLogData, LongPlayLogData
+from vrobbler.apps.books.sources.comicvine import (
+    ComicVineClient,
+    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"}
 
@@ -148,6 +151,8 @@ class Book(LongPlayScrobblableMixin):
     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
@@ -169,7 +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
@@ -197,9 +206,8 @@ class Book(LongPlayScrobblableMixin):
     @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")
+
+        if not created:
             return book
 
         book_dict = lookup_comic_from_comicvine(title)
@@ -233,7 +241,7 @@ class Book(LongPlayScrobblableMixin):
 
     @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.
 
@@ -244,7 +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}
@@ -257,17 +265,22 @@ class Book(LongPlayScrobblableMixin):
             )
             return book
 
-        book_dict = lookup_book_from_google(title)
-        if not book_dict or book_dict.get("isbn_10"):
+        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")
-        try:
-            genres = book_dict.pop("generes")
-        except:
-            genres = []
+        authors = book_dict.pop("authors", [])
+        cover_url = book_dict.pop("cover_url", "")
+        genres = book_dict.pop("generes", [])
 
         if authors:
             for author_str in authors:
@@ -293,7 +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

@@ -227,14 +227,12 @@ def lookup_comic_from_comicvine(title: str) -> dict:
         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
@@ -264,6 +262,9 @@ def lookup_comic_from_comicvine(title: str) -> dict:
         "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

@@ -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 = ""

vrobbler/apps/books/utils.py

@@ -1,7 +1,14 @@
+import re
+from urllib.parse import urlparse, urlunparse
+
 from titlecase import titlecase
 
+
 def parse_readcomicsonline_uri(uri: str) -> tuple:
-    path = uri.split("comic/")[1]
+    try:
+        path = uri.split("comic/")[1]
+    except IndexError:
+        return "", "", ""
 
     parts = path.split('/')
     title = ""
@@ -16,3 +23,37 @@ def parse_readcomicsonline_uri(uri: str) -> tuple:
         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/scrobbles/models.py

@@ -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={
@@ -1172,7 +1172,7 @@ 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 (read_log_page and scrobble.can_be_updated)
                 or scrobble_data["playback_status"] == "stopped"
             ):
                 if read_log_page:
@@ -1181,6 +1181,7 @@ class Scrobble(TimeStampedModel):
                         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(
@@ -1198,7 +1199,7 @@ class Scrobble(TimeStampedModel):
             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())))
+            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",
@@ -1392,6 +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={
@@ -1487,3 +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

@@ -29,7 +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
@@ -260,22 +265,34 @@ def manual_scrobble_book(
     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
 
-        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
+        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, enrich=True)
+    book = Book.find_or_create(title, url=url, enrich=True)
 
     scrobble_dict = {
         "user_id": user_id,
@@ -299,6 +316,9 @@ def manual_scrobble_book(
     scrobble = Scrobble.create_or_update(book, user_id, scrobble_dict, read_log_page=page)
 
     if action == "stop":
+        if url:
+            scrobble.log["resume_url"] = next_url_if_exists(url)
+            scrobble.save(update_fields=["log"])
         scrobble.stop(force_finish=True)
 
     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
@@ -408,3 +409,41 @@ 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

@@ -625,7 +625,7 @@ 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 page")
         return HttpResponseRedirect(media_obj.url)

vrobbler/templates/books/book_detail.html

@@ -26,7 +26,21 @@
     </div>
 </div>
 <div class="row">
+    <p><a href="{{s.logdata.restart_url}}">Read again</a></p>
+    {% if object.readcomics_url %}
+    <p><a href="{{object.readcomics_url}}">Read next issue</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">