[release] Bump to version 58.0

- Add scrobbling of Papers via webpages with doi.org links in them

PROJECT.org

@@ -604,6 +604,12 @@ independent of the email flow it was originally creatdd for
 
 ** TODO [#B] Is there way to create unique slugs for media instances :media_types:
 
+* Version 58.0 [1/1]
+** DONE [#B] Add scrobbling of Papers via webpages with doi.org links in them :feature:papers:
+:PROPERTIES:
+:ID:       d30bb8aa-eefd-002c-38d5-3f2fcef345f2
+:END:
+
 * Version 57.1 [1/1]
 ** DONE [#A] Write poetry lock file :bug:deps:
 :PROPERTIES:

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "vrobbler"
-version = "57.1"
+version = "58.0"
 description = ""
 authors = ["Colin Powell <colin@unbl.ink>"]
 

vrobbler/apps/books/admin.py

@@ -1,8 +1,19 @@
-from books.models import Author, Book, Paper
+from books.models import Author, Book, Journal, Paper
 from django.contrib import admin
 from scrobbles.admin import ScrobbleInline
 
 
+@admin.register(Journal)
+class JournalAdmin(admin.ModelAdmin):
+    date_hierarchy = "created"
+    list_display = (
+        "title",
+        "website_url",
+    )
+    search_fields = ("title",)
+    ordering = ("-created",)
+
+
 @admin.register(Author)
 class AuthorAdmin(admin.ModelAdmin):
     date_hierarchy = "created"

vrobbler/apps/books/migrations/0038_paper_pdf_file.py

@@ -0,0 +1,18 @@
+# Generated by Django 4.2.29 on 2026-06-23 14:45
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("books", "0037_book_volume_book_volume_comicvine_id"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="paper",
+            name="pdf_file",
+            field=models.FileField(blank=True, null=True, upload_to="papers/pdf/"),
+        ),
+    ]

vrobbler/apps/books/migrations/0039_journal_alter_paper_journal.py

@@ -0,0 +1,92 @@
+from django.db import migrations, models
+import django.db.models.deletion
+import django_extensions.db.fields
+import uuid
+
+
+def migrate_journal_data(apps, schema_editor):
+    Paper = apps.get_model("books", "Paper")
+    Journal = apps.get_model("books", "Journal")
+    for paper in Paper.objects.all():
+        old_journal = getattr(paper, "journal", None)
+        if old_journal:
+            journal, _ = Journal.objects.get_or_create(title=str(old_journal))
+            paper._journal_tmp = journal
+            paper.save(update_fields=["_journal_tmp"])
+
+
+def reverse_migrate_journal_data(apps, schema_editor):
+    Paper = apps.get_model("books", "Paper")
+    for paper in Paper.objects.all():
+        if paper._journal_tmp:
+            paper.journal = paper._journal_tmp.title
+            paper.save(update_fields=["journal"])
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("books", "0038_paper_pdf_file"),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="Journal",
+            fields=[
+                (
+                    "id",
+                    models.BigAutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                (
+                    "created",
+                    django_extensions.db.fields.CreationDateTimeField(
+                        auto_now_add=True, verbose_name="created"
+                    ),
+                ),
+                (
+                    "modified",
+                    django_extensions.db.fields.ModificationDateTimeField(
+                        auto_now=True, verbose_name="modified"
+                    ),
+                ),
+                (
+                    "uuid",
+                    models.UUIDField(
+                        blank=True, default=uuid.uuid4, editable=False, null=True
+                    ),
+                ),
+                ("title", models.CharField(max_length=255)),
+                ("description", models.TextField(blank=True, null=True)),
+                ("website_url", models.URLField(blank=True, max_length=500, null=True)),
+            ],
+            options={
+                "get_latest_by": "modified",
+                "abstract": False,
+            },
+        ),
+        migrations.AddField(
+            model_name="paper",
+            name="_journal_tmp",
+            field=models.ForeignKey(
+                blank=True,
+                null=True,
+                on_delete=django.db.models.deletion.DO_NOTHING,
+                to="books.journal",
+            ),
+        ),
+        migrations.RunPython(migrate_journal_data, reverse_migrate_journal_data),
+        migrations.RemoveField(
+            model_name="paper",
+            name="journal",
+        ),
+        migrations.RenameField(
+            model_name="paper",
+            old_name="_journal_tmp",
+            new_name="journal",
+        ),
+    ]

vrobbler/apps/books/models.py

@@ -27,7 +27,11 @@ from books.sources.amazon import lookup_book_from_amazon
 from books.sources.openlibrary import (
     lookup_book_from_openlibrary as lookup_book_from_ol,
 )
-from books.sources.semantic import lookup_paper_from_semantic
+from books.sources.semantic import (
+    lookup_paper_from_semantic,
+    lookup_paper_from_semantic_by_doi,
+)
+from books.sources.scihub import SciHubService
 from books.utils import get_comic_issue_url
 from django.conf import settings
 from django.contrib.auth import get_user_model
@@ -82,6 +86,16 @@ class BookLogData(BaseLogData, LongPlayLogData):
                 return int(total_duration / len(self.page_data))
 
 
+class Journal(TimeStampedModel):
+    uuid = models.UUIDField(default=uuid4, editable=False, **BNULL)
+    title = models.CharField(max_length=255)
+    description = models.TextField(**BNULL)
+    website_url = models.URLField(max_length=500, **BNULL)
+
+    def __str__(self):
+        return self.title
+
+
 class Author(TimeStampedModel):
     name = models.CharField(max_length=255)
     uuid = models.UUIDField(default=uuid4, editable=False, **BNULL)
@@ -540,6 +554,21 @@ class Book(LongPlayScrobblableMixin):
         return progress
 
 
+@dataclass
+class PaperLogData(BaseLogData):
+    @classmethod
+    def override_fields(cls) -> dict:
+        from scrobbles.forms import NotesDictField
+
+        fields = {}
+        for base in cls.mro()[1:]:
+            if hasattr(base, "override_fields"):
+                base_fields = base.override_fields()
+                fields.update(base_fields)
+        fields["notes"] = NotesDictField(required=False)
+        return fields
+
+
 class Paper(LongPlayScrobblableMixin):
     """Keeps track of Academic Papers"""
 
@@ -559,14 +588,29 @@ class Paper(LongPlayScrobblableMixin):
     language = models.CharField(max_length=4, **BNULL)
     first_publish_year = models.IntegerField(**BNULL)
     publish_date = models.DateField(**BNULL)
-    journal = models.CharField(max_length=255, **BNULL)
+    journal = models.ForeignKey(Journal, on_delete=models.DO_NOTHING, **BNULL)
     journal_volume = models.CharField(max_length=50, **BNULL)
     abstract = models.TextField(**BNULL)
     tldr = models.CharField(max_length=255, **BNULL)
     openaccess_pdf_url = models.CharField(max_length=255, **BNULL)
+    pdf_file = models.FileField(upload_to="papers/pdf/", **BNULL)
 
     genre = TaggableManager(through=ObjectWithGenres, blank=True, verbose_name="Genre")
 
+    @property
+    def logdata_cls(self):
+        return PaperLogData
+
+    @property
+    def scihub_url(self):
+        if not self.doi_id:
+            return None
+        domain = getattr(settings, "SCIHUB_DOMAIN", "sci-hub.st")
+        return f"https://{domain}/{self.doi_id}"
+
+    def get_absolute_url(self):
+        return reverse("books:paper_detail", kwargs={"slug": self.uuid})
+
     @classmethod
     def get_from_semantic(cls, title: str, overwrite: bool = False) -> "Paper":
         paper, created = cls.objects.get_or_create(title=title)
@@ -577,7 +621,7 @@ class Paper(LongPlayScrobblableMixin):
 
         if created or overwrite:
             author_list = []
-            author_dicts = paper_dict.pop("author_dicts")
+            author_dicts = paper_dict.pop("author_dicts", None)
             if author_dicts:
                 for author_dict in author_dicts:
                     if author_dict.get("authorId"):
@@ -588,8 +632,11 @@ class Paper(LongPlayScrobblableMixin):
                         if a_created:
                             author.name = author_dict.get("name")
                             author.save()
-                            # TODO enrich author?
-                            ...
+
+            journal_name = paper_dict.pop("journal_name", None)
+            if journal_name:
+                journal, _ = Journal.objects.get_or_create(title=journal_name)
+                paper.journal = journal
 
             for k, v in paper_dict.items():
                 setattr(paper, k, v)
@@ -601,3 +648,78 @@ class Paper(LongPlayScrobblableMixin):
             if genres:
                 paper.genre.add(*genres)
         return paper
+
+    @classmethod
+    def find_or_create_by_doi(cls, doi_url: str) -> "Paper":
+        doi = doi_url.replace("https://doi.org/", "").split("?")[0].rstrip("/")
+        paper = cls.objects.filter(doi_id=doi).first()
+        if paper:
+            return paper
+
+        paper = cls(doi_id=doi, title=f"Paper {doi}")
+        paper.save()
+
+        from books.sources.crossref import lookup_paper_from_crossref
+
+        paper_dict = lookup_paper_from_semantic_by_doi(doi)
+        if not paper_dict or not paper_dict.get("abstract"):
+            paper_dict = lookup_paper_from_crossref(doi)
+
+        if paper_dict:
+            author_list = []
+            author_dicts = paper_dict.pop("author_dicts", None)
+            if author_dicts:
+                for author_dict in author_dicts:
+                    author_id = author_dict.get("authorId")
+                    if author_id:
+                        author, a_created = Author.objects.get_or_create(
+                            semantic_id=author_id
+                        )
+                        author_list.append(author)
+                        if a_created:
+                            author.name = author_dict.get("name")
+                            author.save()
+                    else:
+                        author_name = author_dict.get("name")
+                        if author_name:
+                            author, a_created = Author.objects.get_or_create(
+                                name=author_name
+                            )
+                            author_list.append(author)
+
+            journal_name = paper_dict.pop("journal_name", None)
+            if journal_name:
+                journal, _ = Journal.objects.get_or_create(title=journal_name)
+                paper.journal = journal
+
+            for k, v in paper_dict.items():
+                if v is not None:
+                    setattr(paper, k, v)
+            paper.save()
+
+            if author_list:
+                paper.authors.add(*author_list)
+            genres = paper_dict.pop("genres", [])
+            if genres:
+                paper.genre.add(*genres)
+
+        if not paper.pdf_file:
+            service = SciHubService()
+            if paper.openaccess_pdf_url:
+                pdf_content = service.fetch_from_url(paper.openaccess_pdf_url)
+                if pdf_content:
+                    filename = f"{doi.replace('/', '_')}.pdf"
+                    paper.pdf_file.save(filename, ContentFile(pdf_content))
+            if not paper.pdf_file:
+                try:
+                    pdf_content = service.fetch_pdf(doi)
+                    if pdf_content:
+                        filename = f"{doi.replace('/', '_')}.pdf"
+                        paper.pdf_file.save(filename, ContentFile(pdf_content))
+                except Exception as e:
+                    logger.error(
+                        "[paper] sci-hub PDF download failed",
+                        extra={"doi": doi, "error": str(e)},
+                    )
+
+        return paper

vrobbler/apps/books/sources/crossref.py

@@ -0,0 +1,94 @@
+import json
+import logging
+import re
+
+import requests
+
+CROSSREF_WORK_URL = "https://api.crossref.org/works/{}"
+
+logger = logging.getLogger(__name__)
+
+
+def _strip_jats(text: str) -> str:
+    if not text:
+        return ""
+    text = re.sub(r"</?jats:[^>]*>", "", text)
+    text = re.sub(r"^\s*Abstract\s*", "", text)
+    return text.strip()
+
+
+def lookup_paper_from_crossref(doi: str) -> dict:
+    url = CROSSREF_WORK_URL.format(doi)
+    headers = {"User-Agent": "Vrobbler/1.0 (mailto:hello@example.com)"}
+    response = requests.get(url, headers=headers)
+
+    if response.status_code != 200:
+        logger.warning(
+            "Bad response from Crossref",
+            extra={"doi": doi, "status": response.status_code},
+        )
+        return {"doi_id": doi}
+
+    try:
+        data = response.json()
+    except json.JSONDecodeError:
+        return {"doi_id": doi}
+
+    msg = data.get("message", {})
+    if not msg:
+        return {"doi_id": doi}
+
+    paper_dict = {"doi_id": doi}
+
+    titles = msg.get("title", [])
+    if titles:
+        paper_dict["title"] = titles[0]
+
+    abstract = msg.get("abstract", "")
+    if abstract:
+        paper_dict["abstract"] = _strip_jats(abstract)
+
+    author_dicts = []
+    for author in msg.get("author", []):
+        given = author.get("given", "")
+        family = author.get("family", "")
+        name = f"{given} {family}".strip()
+        if not name:
+            continue
+        entry = {"name": name}
+        orcid = author.get("ORCID", "")
+        if orcid:
+            orcid_id = orcid.replace("https://orcid.org/", "")
+            entry["authorId"] = orcid_id
+        author_dicts.append(entry)
+    if author_dicts:
+        paper_dict["author_dicts"] = author_dicts
+
+    container = msg.get("container-title", [])
+    if container:
+        paper_dict["journal_name"] = container[0]
+
+    volume = msg.get("volume")
+    if volume:
+        paper_dict["journal_volume"] = volume
+
+    page = msg.get("page")
+    if page:
+        try:
+            parts = page.split("-")
+            if len(parts) == 2:
+                paper_dict["pages"] = int(parts[1]) - int(parts[0])
+        except (ValueError, IndexError):
+            pass
+
+    for date_field in ("published-print", "published-online", "created"):
+        date_data = msg.get(date_field)
+        if date_data and date_data.get("date-parts"):
+            parts = date_data["date-parts"][0]
+            if len(parts) >= 1:
+                paper_dict["first_publish_year"] = int(parts[0])
+            if len(parts) >= 3:
+                paper_dict["publish_date"] = f"{parts[0]:04d}-{parts[1]:02d}-{parts[2]:02d}"
+            break
+
+    return paper_dict

vrobbler/apps/books/sources/scihub.py

@@ -0,0 +1,142 @@
+import logging
+from typing import Optional
+from urllib.parse import urljoin
+
+import requests
+from bs4 import BeautifulSoup
+from django.conf import settings
+
+logger = logging.getLogger(__name__)
+
+SCIHUB_DOMAINS = [
+    "sci-hub.ru",
+    "sci-hub.ee",
+    "sci-hub.st",
+    "sci-hub.do",
+]
+
+
+class SciHubService:
+    def __init__(self):
+        self.session = requests.Session()
+        self.session.headers.update(
+            {
+                "User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
+            }
+        )
+
+    def fetch_from_url(self, url: str) -> Optional[bytes]:
+        try:
+            resp = self.session.get(url, timeout=60)
+            if resp.status_code != 200:
+                logger.warning(
+                    "[pdf] URL download failed",
+                    extra={"status": resp.status_code, "url": url},
+                )
+                return None
+            if not self._looks_like_pdf(resp):
+                return None
+            return resp.content
+        except requests.RequestException as e:
+            logger.error(
+                "[pdf] URL download request failed",
+                extra={"url": url, "error": str(e)},
+            )
+            return None
+
+    def fetch_pdf(self, doi: str) -> Optional[bytes]:
+        configured_domain = getattr(settings, "SCIHUB_DOMAIN", None)
+        domains_to_try = (
+            [configured_domain] + SCIHUB_DOMAINS
+            if configured_domain and configured_domain not in SCIHUB_DOMAINS
+            else SCIHUB_DOMAINS
+        )
+
+        for domain in domains_to_try:
+            url = f"https://{domain}/{doi}"
+            logger.info(
+                "[scihub] trying domain",
+                extra={"domain": domain, "doi": doi},
+            )
+            try:
+                response = self.session.get(url, timeout=30)
+                if response.status_code != 200:
+                    continue
+
+                pdf_url = self._extract_pdf_url(response.text, url)
+                if not pdf_url:
+                    continue
+
+                pdf_response = self.session.get(pdf_url, timeout=60)
+                if pdf_response.status_code != 200:
+                    continue
+
+                if not self._looks_like_pdf(pdf_response):
+                    continue
+
+                logger.info(
+                    "[scihub] PDF downloaded successfully",
+                    extra={
+                        "domain": domain,
+                        "doi": doi,
+                        "size": len(pdf_response.content),
+                    },
+                )
+                return pdf_response.content
+            except requests.RequestException as e:
+                logger.debug(
+                    "[scihub] domain failed",
+                    extra={"domain": domain, "doi": doi, "error": str(e)},
+                )
+                continue
+
+        logger.warning(
+            "[scihub] all domains failed",
+            extra={"doi": doi, "tried": domains_to_try},
+        )
+        return None
+
+    def _looks_like_pdf(self, response: requests.Response) -> bool:
+        content_type = response.headers.get("Content-Type", "")
+        if "application/pdf" in content_type:
+            return True
+        if content_type.startswith("application/octet"):
+            return True
+        if response.url.endswith(".pdf"):
+            return True
+        return False
+
+    def _extract_pdf_url(self, html: str, page_url: str) -> Optional[str]:
+        soup = BeautifulSoup(html, "html.parser")
+
+        iframe = soup.find("iframe", {"id": "pdf"})
+        if iframe and iframe.get("src"):
+            src = iframe["src"]
+            if src.startswith("http"):
+                return src
+            return urljoin(page_url, src)
+
+        embed = soup.find("embed", {"type": "application/pdf"})
+        if embed and embed.get("src"):
+            src = embed["src"]
+            if src.startswith("http"):
+                return src
+            return urljoin(page_url, src)
+
+        download_div = soup.find("div", {"id": "download"})
+        if download_div:
+            link = download_div.find("a")
+            if link and link.get("href"):
+                href = link["href"]
+                if href.startswith("http"):
+                    return href
+                return urljoin(page_url, href)
+
+        for link in soup.find_all("a", href=True):
+            href = link["href"]
+            if ".pdf" in href:
+                if href.startswith("http"):
+                    return href
+                return urljoin(page_url, href)
+
+        return None

vrobbler/apps/books/sources/semantic.py

@@ -9,6 +9,7 @@ PAPER_SEARCH_URL = (
     "https://api.semanticscholar.org/graph/v1/paper/search/match?query={}"
 )
 PAPER_DETAIL_URL = "https://api.semanticscholar.org/graph/v1/paper/{}?fields=title,authors,url,year,abstract,externalIds,citationCount,referenceCount,journal,fieldsOfStudy,publicationDate,openAccessPdf"
+PAPER_DOI_URL = "https://api.semanticscholar.org/graph/v1/paper/DOI:{}?fields=title,authors,url,year,abstract,externalIds,citationCount,referenceCount,journal,fieldsOfStudy,publicationDate,openAccessPdf"
 
 logger = logging.getLogger(__name__)
 
@@ -39,6 +40,18 @@ def lookup_paper_from_semantic(title: str) -> dict:
     if not result:
         return paper_dict
 
+    paper_dict.update(_parse_semantic_result(result))
+    paper_dict.setdefault("title", title)
+    if paper_dict.get("publish_date"):
+        paper_dict["publish_date"] = datetime.strptime(
+            paper_dict["publish_date"], "%Y-%m-%d"
+        )
+
+    return paper_dict
+
+
+def _parse_semantic_result(result: dict) -> dict:
+    paper_dict = {}
     page_str = result.get("journal", {}).get("pages")
     if page_str:
         try:
@@ -55,12 +68,10 @@ def lookup_paper_from_semantic(title: str) -> dict:
     paper_dict["corpus_id"] = result.get("externalIds", {}).get("CorpusId")
     paper_dict["semantic_title"] = result.get("title")
     paper_dict["first_publish_year"] = result.get("year")
-    paper_dict["publish_date"] = datetime.strptime(
-        result.get("publicationDate", "1950-01-01"), "%Y-%m-%d"
-    )
+    paper_dict["publish_date"] = result.get("publicationDate")
     paper_dict["abstract"] = result.get("abstract")
     paper_dict["tldr"] = result.get("bib", {}).get("abstract")
-    paper_dict["journal"] = result.get("journal", {}).get("name")
+    paper_dict["journal_name"] = result.get("journal", {}).get("name")
     paper_dict["journal_volume"] = result.get("journal", {}).get("volume")
     paper_dict["openaccess_pdf_url"] = result.get("openAccessPdf", {}).get("url")
     paper_dict["base_run_time_seconds"] = paper_dict.get("pages", 10) * getattr(
@@ -68,5 +79,19 @@ def lookup_paper_from_semantic(title: str) -> dict:
     )
     paper_dict["author_dicts"] = result.get("authors")
     paper_dict["genres"] = result.get("fieldsOfStudy")
-
+    return paper_dict
+
+
+def lookup_paper_from_semantic_by_doi(doi: str) -> dict:
+    response = get_api_result(PAPER_DOI_URL.format(doi))
+    if not response:
+        return {"doi_id": doi}
+
+    result = json.loads(response.content)
+    if not result:
+        return {"doi_id": doi}
+
+    paper_dict = _parse_semantic_result(result)
+    if not paper_dict.get("title"):
+        paper_dict["title"] = result.get("title", f"Paper {doi}")
     return paper_dict

vrobbler/apps/books/urls.py

@@ -16,4 +16,15 @@ urlpatterns = [
         views.AuthorDetailView.as_view(),
         name="author_detail",
     ),
+    path("papers/", views.PaperListView.as_view(), name="paper_list"),
+    path(
+        "papers/<slug:slug>/",
+        views.PaperDetailView.as_view(),
+        name="paper_detail",
+    ),
+    path(
+        "papers/<slug:slug>/upload_pdf/",
+        views.PaperUploadPdfView.as_view(),
+        name="paper_upload_pdf",
+    ),
 ]

vrobbler/apps/books/views.py

@@ -1,5 +1,8 @@
+from django.http import HttpResponseRedirect
+from django.urls import reverse
+from django.views import View
 from django.views import generic
-from books.models import Book, Author
+from books.models import Book, Author, Paper
 
 from scrobbles.views import ScrobbleableListView, ScrobbleableDetailView
 
@@ -15,3 +18,24 @@ class BookDetailView(ScrobbleableDetailView):
 class AuthorDetailView(generic.DetailView):
     model = Author
     slug_field = "uuid"
+
+
+class PaperListView(ScrobbleableListView):
+    model = Paper
+
+
+class PaperDetailView(ScrobbleableDetailView):
+    model = Paper
+
+
+class PaperUploadPdfView(View):
+    def post(self, request, slug):
+        paper = Paper.objects.filter(uuid=slug).first()
+        if not paper or not request.user.is_authenticated:
+            return HttpResponseRedirect(reverse("books:paper_detail", args=[slug]))
+
+        pdf_file = request.FILES.get("pdf_file")
+        if pdf_file:
+            paper.pdf_file.save(pdf_file.name, pdf_file)
+
+        return HttpResponseRedirect(reverse("books:paper_detail", args=[slug]))

vrobbler/apps/scrobbles/constants.py

@@ -14,6 +14,7 @@ LONG_PLAY_MEDIA = {
     "books": "Book",
     "bricksets": "BrickSet",
     "tasks": "Task",
+    "papers": "Paper",
 }
 
 # Media types that should just be finished if they go over time
@@ -61,6 +62,7 @@ SCROBBLE_CONTENT_URLS = {
     "-b": ["https://www.amazon.com/"],
     "-t": ["https://app.todoist.com/app/task/{id}"],
     "-p": ["https://www.ipdb.plus/IPDb/puzzle.php?id="],
+    "-pp": ["https://doi.org/"],
     "-l": ["https://brickset.com/sets/"],
     "-c": ["https://readcomicsonline.ru"],
     "-h": ["https://www.twitch.tv/"],
@@ -83,6 +85,7 @@ MANUAL_SCROBBLE_FNS = {
     "-f": "manual_scrobble_food",
     "-h": "manual_scrobble_twitch_channel",
     "-dg": "manual_scrobble_discgolf",
+    "-pp": "manual_scrobble_paper",
 }
 
 

vrobbler/apps/scrobbles/models.py

@@ -1377,6 +1377,8 @@ class Scrobble(TimeStampedModel):
             media_obj = self.channel
         if self.birding_location:
             media_obj = self.birding_location
+        if self.paper:
+            media_obj = self.paper
         if self.disc_golf_course:
             media_obj = self.disc_golf_course
         return media_obj

vrobbler/apps/scrobbles/scrobblers.py

@@ -9,7 +9,7 @@ import requests
 from beers.models import Beer
 from boardgames.models import BoardGame, BoardGameDesigner, BoardGameLocation
 from books.constants import READCOMICSONLINE_URL
-from books.models import Book, BookLogData, BookPageLogData
+from books.models import Book, BookLogData, BookPageLogData, Paper
 from books.utils import parse_readcomicsonline_uri
 from bricksets.models import BrickSet
 from dateutil.parser import parse
@@ -641,6 +641,8 @@ def manual_scrobble_from_url(
         item_id = "tt" + str(item_id)
     elif content_key == "-h" and "twitch.tv" in url:
         item_id = url
+    elif content_key == "-pp" and "doi.org" in url:
+        item_id = url
 
     scrobble_fn = MANUAL_SCROBBLE_FNS[content_key]
     return eval(scrobble_fn)(item_id, user_id, source=source, action=action)
@@ -995,6 +997,38 @@ def manual_scrobble_task(
     return scrobble
 
 
+def manual_scrobble_paper(
+    doi_url: str,
+    user_id: int,
+    source: str = "Bookmarklet",
+    action: Optional[str] = None,
+):
+    paper = Paper.find_or_create_by_doi(doi_url)
+
+    scrobble_dict = {
+        "user_id": user_id,
+        "timestamp": timezone.now(),
+        "playback_position_seconds": 0,
+        "source": source,
+    }
+    logger.info(
+        "[vrobbler-scrobble] paper scrobble request received",
+        extra={
+            "paper_id": paper.id,
+            "user_id": user_id,
+            "scrobble_dict": scrobble_dict,
+            "media_type": Scrobble.MediaType.PAPER,
+        },
+    )
+
+    scrobble = Scrobble.create_or_update(paper, user_id, scrobble_dict)
+
+    if action == "stop":
+        scrobble.stop(force_finish=True)
+
+    return scrobble
+
+
 def manual_scrobble_webpage(
     url: str,
     user_id: int,

vrobbler/apps/scrobbles/views.py

@@ -610,7 +610,12 @@ class ManualScrobbleView(FormView):
         item_str = form.cleaned_data.get("item_id")
         logger.debug(f"Looking for scrobblable media with input {item_str}")
 
-        key, item_id = item_str[:2], item_str[3:]
+        if len(item_str) > 2 and item_str[:3] in MANUAL_SCROBBLE_FNS:
+            key = item_str[:3]
+            item_id = item_str[4:]
+        else:
+            key = item_str[:2]
+            item_id = item_str[3:]
         scrobble_fn = MANUAL_SCROBBLE_FNS[key]
         scrobble = eval(scrobble_fn)(item_id, self.request.user.id)
 

vrobbler/settings.py

@@ -397,6 +397,8 @@ else:
     MEDIA_URL = os.getenv("VROBBLER_MEDIA_URL", "/media/")
 
 
+SCIHUB_DOMAIN = os.getenv("VROBBLER_SCIHUB_DOMAIN", "sci-hub.st")
+
 JSON_LOGGING = os.getenv("VROBBLER_JSON_LOGGING", "false").lower() in TRUTHY
 LOG_TYPE = "json" if JSON_LOGGING else "log"
 

vrobbler/templates/books/paper_detail.html

@@ -0,0 +1,62 @@
+{% extends "base_list.html" %}
+
+{% block title %}{{object.title}}{% endblock %}
+
+{% block lists %}
+<div class="row">
+    <div class="col">
+        <h1>{{object.title}}</h1>
+        {% if object.authors.all %}
+        <p>{{object.authors.all|join:", "}}</p>
+        {% endif %}
+        {% if object.journal %}
+        <p><em>{{object.journal.title}}{% if object.journal_volume %}, vol. {{object.journal_volume}}{% endif %}</em></p>
+        {% endif %}
+        {% if object.doi_id %}
+        <p><a href="https://doi.org/{{object.doi_id}}">doi: {{object.doi_id}}</a></p>
+        {% endif %}
+        {% if object.abstract %}
+        <p>{{object.abstract|linebreaks|truncatewords:200}}</p>
+        {% endif %}
+        {% if object.pdf_file %}
+        <button class="btn btn-outline-secondary btn-sm" onclick="togglePdf()">Show/Hide PDF</button>
+        <div id="pdf-embed" style="display:none; margin-top:0.5rem;">
+            <iframe src="{{object.pdf_file.url}}" style="width:100%;height:600px;border:1px solid #ccc;"></iframe>
+        </div>
+        <script>
+        function togglePdf() {
+            var el = document.getElementById('pdf-embed');
+            el.style.display = el.style.display === 'none' ? 'block' : 'none';
+        }
+        </script>
+        {% endif %}
+        {% if object.openaccess_pdf_url %}
+        <p><a href="{{object.openaccess_pdf_url}}">Open Access PDF</a></p>
+        {% endif %}
+        {% if object.pdf_file %}
+        <a href="{{object.pdf_file.url}}">
+            <svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" fill="currentColor" class="text-danger" viewBox="0 0 16 16">
+                <path d="M14 14V4.5L9.5 0H4a2 2 0 0 0-2 2v12a2 2 0 0 0 2 2h8a2 2 0 0 0 2-2zM9.5 3A1.5 1.5 0 0 0 11 4.5h2V14a1 1 0 0 1-1 1H4a1 1 0 0 1-1-1V2a1 1 0 0 1 1-1h5.5v2z"/>
+                <path d="M4.603 14.087a.81.81 0 0 1-.438-.42c-.195-.388-.13-.776.08-1.102.197-.307.526-.568.897-.707.07-.024.15-.023.222 0l.044.014a.27.27 0 0 1 .152.295.7.7 0 0 1-.128.416c-.159.206-.344.388-.544.555-.357.299-.592.527-.406.623.08.04.272.045.578-.057a.93.93 0 0 0 .363-.226.8.8 0 0 0 .194-.277.28.28 0 0 1 .414-.112.3.3 0 0 1 .065.422 1.3 1.3 0 0 1-.67.522c-.38.147-.746.103-1.04.02zM7.12 11.5c.16-.186.34-.34.486-.514.294-.35.628-.617.947-.786.204-.108.546-.206.715-.153.087.027.135.068.16.126a.6.6 0 0 1-.003.27 1 1 0 0 1-.158.354c-.163.242-.349.47-.7.769-.332.283-.598.483-.793.607a1.1 1.1 0 0 1-.582.214c-.136 0-.234-.038-.298-.11-.05-.056-.076-.134-.07-.236a.99.99 0 0 1 .098-.45c.08-.17.21-.35.378-.57zm5.09 2.013c-.135.06-.277.104-.428.116-.205.015-.39-.048-.553-.177-.104-.082-.226-.196-.317-.325a1 1 0 0 1-.17-.572c0-.15.035-.27.095-.36.04-.063.089-.098.153-.112.138-.028.316.04.477.174.074.061.145.136.228.232.174.2.302.37.397.515.108.164.153.285.121.345a.25.25 0 0 1-.003.053c0 .079-.05.147-.198.262z"/>
+            </svg>
+        </a>
+        {% endif %}
+        {% if object.scihub_url %}
+        <p><a href="{{object.scihub_url}}">View on Sci-Hub</a></p>
+        {% endif %}
+    </div>
+</div>
+<hr>
+<div class="row">
+    <div class="col">
+        <form method="post" enctype="multipart/form-data" action="{% url 'books:paper_upload_pdf' slug=object.uuid %}">
+            {% csrf_token %}
+            <div class="form-group">
+                <label for="pdf_file">Upload PDF</label>
+                <input type="file" class="form-control-file" id="pdf_file" name="pdf_file" accept=".pdf,application/pdf">
+            </div>
+            <button type="submit" class="btn btn-primary btn-sm">Upload</button>
+        </form>
+    </div>
+</div>
+{% endblock %}

vrobbler/templates/books/paper_list.html

@@ -0,0 +1,13 @@
+{% extends "base_list.html" %}
+
+{% block title %}Papers{% endblock %}
+
+{% block lists %}
+<div class="row">
+    <div class="col-md">
+        <div class="table-responsive">
+            {% include "_longplay_scrobblable_list.html" %}
+        </div>
+    </div>
+</div>
+{% endblock %}