[releases] Fix comic books scrobbling, mostly

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 [2/26]
+* Backlog [3/27]
 ** 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 +479,19 @@ 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.
+* 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/models.py

@@ -262,12 +262,9 @@ class Book(LongPlayScrobblableMixin):
             book_dict = lookup_comic_from_comicvine(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 +290,7 @@ 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/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 +1,10 @@
 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 = ""

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

@@ -263,15 +263,25 @@ def manual_scrobble_book(
 
     if READCOMICSONLINE_URL in 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
 

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)