diff --git a/PROJECT.org b/PROJECT.org index 09320d1..fa98aa2 100644 --- a/PROJECT.org +++ b/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 [1/25] +* Backlog [2/26] ** 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: @@ -483,6 +483,10 @@ https://life.lab.unbl.ink/scrobble/e39779c8-62a5-46a6-bdef-fb7662810dc6/start/ :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: diff --git a/vrobbler/apps/books/migrations/0030_book_readcomics_url.py b/vrobbler/apps/books/migrations/0030_book_readcomics_url.py new file mode 100644 index 0000000..49be388 --- /dev/null +++ b/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), + ), + ] diff --git a/vrobbler/apps/books/migrations/0031_book_next_readcomics_url.py b/vrobbler/apps/books/migrations/0031_book_next_readcomics_url.py new file mode 100644 index 0000000..e9e1115 --- /dev/null +++ b/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), + ), + ] diff --git a/vrobbler/apps/books/models.py b/vrobbler/apps/books/models.py index 337c87c..9243450 100644 --- a/vrobbler/apps/books/models.py +++ b/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", "") @@ -63,7 +65,6 @@ class BookLogData(BaseLogData, LongPlayLogData): page_start: Optional[int] = None page_end: Optional[int] = None resume_url: Optional[str] = None - restart_url: Optional[str] = None _excluded_fields = {"koreader_hash", "page_data"} @@ -150,6 +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 @@ -171,7 +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 @@ -234,7 +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. @@ -258,9 +265,17 @@ class Book(LongPlayScrobblableMixin): ) return book - book_dict = lookup_book_from_google(title) - if not book_dict or not 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", []) diff --git a/vrobbler/apps/books/sources/comicvine.py b/vrobbler/apps/books/sources/comicvine.py index 6da21f0..ea28cd1 100644 --- a/vrobbler/apps/books/sources/comicvine.py +++ b/vrobbler/apps/books/sources/comicvine.py @@ -264,7 +264,7 @@ def lookup_comic_from_comicvine(title: str) -> dict: "comicvine_data": found_result, "summary": found_result.get("description"), "publish_date": found_result.get("cover_date"), - "first_publish_year": found_result.get("store_date").year, + "first_publish_year": found_result.get("cover_date", "")[:4] } return data_dict diff --git a/vrobbler/apps/books/utils.py b/vrobbler/apps/books/utils.py index 6912653..ad4329e 100644 --- a/vrobbler/apps/books/utils.py +++ b/vrobbler/apps/books/utils.py @@ -1,5 +1,9 @@ +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] @@ -19,3 +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 diff --git a/vrobbler/apps/scrobbles/scrobblers.py b/vrobbler/apps/scrobbles/scrobblers.py index 7a852b4..26ff58a 100644 --- a/vrobbler/apps/scrobbles/scrobblers.py +++ b/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 @@ -260,7 +265,7 @@ def manual_scrobble_book( log = {} source = "Vrobbler" page = None - url = None + url = "" if READCOMICSONLINE_URL in title: url = title @@ -287,7 +292,7 @@ def manual_scrobble_book( # 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, @@ -312,8 +317,7 @@ def manual_scrobble_book( if action == "stop": if url: - scrobble.log["resume_url"] = url - scrobble.log["restart_url"] = remove_last_part(url) + scrobble.log["resume_url"] = next_url_if_exists(url) scrobble.save(update_fields=["log"]) scrobble.stop(force_finish=True) diff --git a/vrobbler/apps/scrobbles/utils.py b/vrobbler/apps/scrobbles/utils.py index c4dbd61..fd9a83f 100644 --- a/vrobbler/apps/scrobbles/utils.py +++ b/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 @@ -414,3 +415,35 @@ def remove_last_part(url: str) -> str: 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 "" diff --git a/vrobbler/templates/books/book_detail.html b/vrobbler/templates/books/book_detail.html index 3772adb..d78d66f 100644 --- a/vrobbler/templates/books/book_detail.html +++ b/vrobbler/templates/books/book_detail.html @@ -26,11 +26,19 @@
+

Read again

+ {% if object.readcomics_url %} +

Read next issue

+ {% endif %} + {% if object.next_readcomics_url %} +

Read next issue

+ {% endif %} +

{{scrobbles.count}} scrobbles

+ {% for s in scrobbles %} {% if forloop.first %} -

Re-read

-

Resume

+

Resume reading

{% endif %} {% endfor %}