[release] Bump to version 58.2

- Add more robust webpage scraping - Time of Day Categories trend
[webpages] Add more robust scraping
2026-06-23 23:04:48 -04:00 · 2026-06-23 23:04:30 -04:00 · 2026-06-23 22:21:18 -04:00 · 2026-06-23 16:19:06 -04:00 · 2026-06-23 16:18:50 -04:00 · 2026-06-23 14:28:40 -04:00
26 changed files with 1364 additions and 23 deletions
--- a/PROJECT.org
+++ b/PROJECT.org
@ -604,6 +604,35 @@ 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 58.2 [2/2]
+** DONE [#B] Add more robust webpage scraping :webpages:metadata:
+:PROPERTIES:
+:ID:       84d9bfa5-75c0-0718-764e-379f7456602a
+:END:
+** DONE [#B] Time of Day Categories trend :trends:
+:PROPERTIES:
+:ID:       6598074f-2290-46db-967b-29f45d30be29
+:END:
+
+*** Description
+
+Added a "Time of Day Categories" trend that groups scrobbles for Books, Trails,
+Birding Locations, and Board Games into Early Bird (5-10:59am), Day Jay (11am-6:59pm),
+and Night Owl (7pm-4:59am) buckets. Shows both overall and per-media-type breakdowns.
+
+
+* Version 58.1 [1/1]
+** DONE [#B] Add auto genre tagging for papers :books:papers:metadata:
+:PROPERTIES:
+:ID:       e6b5c3a5-7fc6-b530-96c2-b5962a716db6
+:END:
+
+* 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:
--- a/poetry.lock
+++ b/poetry.lock
@ -654,7 +654,6 @@ description = "Foreign Function Interface for Python calling C code."
 optional = false
 python-versions = ">=3.9"
 groups = ["main"]
-markers = "platform_python_implementation != \"PyPy\" or sys_platform == \"darwin\""
 files = [
    {file = "cffi-2.0.0-cp310-cp310-macosx_10_13_x86_64.whl", hash = "sha256:0cf2d91ecc3fcc0625c2c530fe004f82c110405f101548512cce44322fa8ac44"},
    {file = "cffi-2.0.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:f73b96c41e3b2adedc34a7356e64c8eb96e03a3782b535e043a986276ce12a49"},
@ -967,6 +966,23 @@ prompt-toolkit = ">=3.0.36"
 [package.extras]
 testing = ["pytest (>=7.2.1)", "pytest-cov (>=4.0.0)", "tox (>=4.4.3)"]

+[[package]]
+name = "cloudscraper"
+version = "1.2.71"
+description = "A Python module to bypass Cloudflare's anti-bot page."
+optional = false
+python-versions = "*"
+groups = ["main"]
+files = [
+    {file = "cloudscraper-1.2.71-py2.py3-none-any.whl", hash = "sha256:76f50ca529ed2279e220837befdec892626f9511708e200d48d5bb76ded679b0"},
+    {file = "cloudscraper-1.2.71.tar.gz", hash = "sha256:429c6e8aa6916d5bad5c8a5eac50f3ea53c9ac22616f6cb21b18dcc71517d0d3"},
+]
+
+[package.dependencies]
+pyparsing = ">=2.4.7"
+requests = ">=2.9.2"
+requests-toolbelt = ">=0.9.1"
+
 [[package]]
 name = "colorama"
 version = "0.4.6"
@ -1221,6 +1237,48 @@ ssh = ["bcrypt (>=3.1.5)"]
 test = ["certifi (>=2024)", "cryptography-vectors (==46.0.6)", "pretend (>=0.7)", "pytest (>=7.4.0)", "pytest-benchmark (>=4.0)", "pytest-cov (>=2.10.1)", "pytest-xdist (>=3.5.0)"]
 test-randomorder = ["pytest-randomly"]

+[[package]]
+name = "curl-cffi"
+version = "0.15.0"
+description = "libcurl ffi bindings for Python, with impersonation support."
+optional = false
+python-versions = ">=3.10"
+groups = ["main"]
+files = [
+    {file = "curl_cffi-0.15.0-cp310-abi3-macosx_10_9_x86_64.whl", hash = "sha256:bda66404010e9ed743b1b83c20c86f24fe21a9a6873e17479d6e67e29d8ded28"},
+    {file = "curl_cffi-0.15.0-cp310-abi3-macosx_11_0_arm64.whl", hash = "sha256:a25620d9bf989c9c029a7d1642999c4c265abb0bad811deb2f77b0b5b2b12e5b"},
+    {file = "curl_cffi-0.15.0-cp310-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:582e570aa2586b96ed47cf4a17586b9a3c462cbe43f780487c3dc245c6ef1527"},
+    {file = "curl_cffi-0.15.0-cp310-abi3-manylinux2014_i686.manylinux_2_17_i686.whl", hash = "sha256:838e48212447d9c81364b04707a5c861daf08f8320f9ecb3406a8919d1d5c3b3"},
+    {file = "curl_cffi-0.15.0-cp310-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:2b6c847d86283b07ae69bb72c82eb8a59242277142aa35b89850f89e792a02fc"},
+    {file = "curl_cffi-0.15.0-cp310-abi3-manylinux_2_28_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:9e5e69eee735f659287e2c84444319d68a1fa68dd37abf228943a4074864283a"},
+    {file = "curl_cffi-0.15.0-cp310-abi3-manylinux_2_34_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:aa1323950224db24f4c510d010b3affa02196ca853fb424191fa917a513d3f4b"},
+    {file = "curl_cffi-0.15.0-cp310-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:41f80170ba844009273b2660da1964ec31e99e5719d16b3422ada87177e32e13"},
+    {file = "curl_cffi-0.15.0-cp310-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:1977e1e12cfb5c11352cbb74acef1bed24eb7d226dab61ca57c168c21acd4d61"},
+    {file = "curl_cffi-0.15.0-cp310-abi3-win_amd64.whl", hash = "sha256:5a0c1896a0d5a5ac1eb89cd24b008d2b718dd1df6fd2f75451b59ca66e49e572"},
+    {file = "curl_cffi-0.15.0-cp310-abi3-win_arm64.whl", hash = "sha256:a6d57f8389273a3a1f94370473c74897467bcc36af0a17336989780c507fa43d"},
+    {file = "curl_cffi-0.15.0-cp313-abi3-android_24_arm64_v8a.whl", hash = "sha256:4682dc38d4336e0eb0b185374db90a760efde63cbea994b4e63f3521d44c4c92"},
+    {file = "curl_cffi-0.15.0-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:967ad7355bd8e9586f8c2d02eaa99953747549e7ea4a9b25cd53353e6b67fe6d"},
+    {file = "curl_cffi-0.15.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:7e63539d0d839d0a8c5eacf86229bc68c57803547f35e0db7ee0986328b478c3"},
+    {file = "curl_cffi-0.15.0-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:08c799b89740b9bc49c09fbc3d5907f13ac1f845ca52620507ef9466d4639dd5"},
+    {file = "curl_cffi-0.15.0-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:7b7a92767a888ee90147e18964b396d8435ff42737030d6fb00824ffd6094805"},
+    {file = "curl_cffi-0.15.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:829cc357061ecb99cc2d406301f609a039e05665322f5c025ec67c38b0dc49ce"},
+    {file = "curl_cffi-0.15.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:408d6f14e346841cd889c2e0962832bb235ba3b6749ebf609f347f747da5e60f"},
+    {file = "curl_cffi-0.15.0-cp314-cp314t-win_amd64.whl", hash = "sha256:b624c7ce087bfda967a013ed0a64702a525444e5b6e97d23534d567ccc6525aa"},
+    {file = "curl_cffi-0.15.0-cp314-cp314t-win_arm64.whl", hash = "sha256:0b6c0543b993996670e9e4b78e305a2d60809d5681903ffb5568e21a387434d3"},
+    {file = "curl_cffi-0.15.0.tar.gz", hash = "sha256:ea0c67652bf6893d34ee0f82c944f37e488f6147e9421bef1771cc6545b02ded"},
+]
+
+[package.dependencies]
+certifi = ">=2024.2.2"
+cffi = ">=2.0.0"
+rich = "*"
+
+[package.extras]
+build = ["cibuildwheel", "wheel"]
+dev = ["charset_normalizer (>=3.3.2,<4.0)", "coverage (>=6.4.1,<7.0)", "cryptography (>=46.0.4,<47.0)", "httpx (==0.23.1)", "mypy (>=1.9.0,<2.0)", "pytest (>=8.1.1,<9.0)", "pytest-asyncio (>=0.23.6,<1.0)", "pytest-trio (>=0.8.0,<1.0)", "ruff (>=0.3.5,<1.0)", "trio (>=0.25.0,<1.0)", "trustme (>=1.1.0,<2.0)", "typing_extensions", "uvicorn (>=0.29.0,<1.0)", "websockets (>=14.0)"]
+extra = ["lxml_html_clean", "markdownify (>=1.1.0)", "readability-lxml (>=0.8.1)"]
+test = ["charset_normalizer (>=3.3.2,<4.0)", "cryptography (>=46.0.4,<47.0)", "httpx (==0.23.1)", "litestar (>=2.19.0,<3.0)", "proxy.py (>=2.4.3,<3.0)", "pytest (>=8.1.1,<9.0)", "pytest-asyncio (>=0.23.6,<1.0)", "pytest-trio (>=0.8.0,<1.0)", "python-multipart (>=0.0.9,<1.0)", "trio (>=0.25.0,<1.0)", "trustme (>=1.1.0,<2.0)", "typing_extensions", "uvicorn (>=0.29.0,<1.0)", "websockets (>=14.0)"]
+
 [[package]]
 name = "dacite"
 version = "1.9.2"
@ -2430,6 +2488,101 @@ files = [
 test = ["async-timeout ; python_version < \"3.11\"", "pytest", "pytest-asyncio (>=0.17)", "pytest-trio", "testpath", "trio"]
 trio = ["trio"]

+[[package]]
+name = "jellyfish"
+version = "1.2.1"
+description = ""
+optional = false
+python-versions = ">=3.9"
+groups = ["main"]
+files = [
+    {file = "jellyfish-1.2.1-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:b35d4b5b688f759ffd075190a9850b04671bad14c5b37124eb43e99306ec16ea"},
+    {file = "jellyfish-1.2.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:b37b76ea338c4a473c34a9b9e1e033a78aafb9040a8c0eea579fc5805d8e4b46"},
+    {file = "jellyfish-1.2.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:137cfcc26396d0f2e1265ac61f800bb921921ea722a43dd897e58190f767c474"},
+    {file = "jellyfish-1.2.1-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:ab1bfea271ce4bda09d975080d5465cf5a8b127e7c0ea61ea3f972417a7a2193"},
+    {file = "jellyfish-1.2.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2348f698f9c1d72023afc8d39939045421a01da9b7e3078e3029227e35f28419"},
+    {file = "jellyfish-1.2.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:4072e21ad4036af41bd57b447b1dda64fe60aa679cfa8854ba0a0338152439f1"},
+    {file = "jellyfish-1.2.1-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:cf6cd68921f2bacc547ba1cf64ad0e76bc1727f3bab13bba2e5f5869aba038b1"},
+    {file = "jellyfish-1.2.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:01647c12261bc1f7b102e918e7665497176d87f6fc96271439c8855872bc2606"},
+    {file = "jellyfish-1.2.1-cp310-cp310-win32.whl", hash = "sha256:ddf05ea471da2808d77ecfa425d8884124b4754f4d483afa7703b6655530cf5c"},
+    {file = "jellyfish-1.2.1-cp310-cp310-win_amd64.whl", hash = "sha256:e4a210a960f3917da757b0581750b6e0a8db9acef68dafbc1b6e2ae39e847ba8"},
+    {file = "jellyfish-1.2.1-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:9913789a98ccf49213fbb1dabc597847a0ec33d3b0e151689498f4b38ba9be0f"},
+    {file = "jellyfish-1.2.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:4e36d9000d4f7e1a35689a74ec7749d27a216dfa6c47cac2e5ad3de8a523bd69"},
+    {file = "jellyfish-1.2.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7853d2ed7d6929c029312ec849410f1ea7ae76ce72ad1140fb73f6e8a1e6aa4f"},
+    {file = "jellyfish-1.2.1-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:68080af234256ef943f0add6fc79816b0c643d8df291c17a85c1b6e45bdfbb96"},
+    {file = "jellyfish-1.2.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4c5acb213aa75a61bcfc176566e20f2503069667e760d83d403b59e115fef0dd"},
+    {file = "jellyfish-1.2.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:4b28fcefc0c3534277ff0306e6c10672fb050f4784b5f3be7037e80801569fb5"},
+    {file = "jellyfish-1.2.1-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:f69aeb08659a6c81d559bbe319075e3417434ae5b3a5e4a758d1c4055a03497a"},
+    {file = "jellyfish-1.2.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:63770120cc3386dcc13bcc4df508ab281a6b14c3b2c0e33586439a6c40ee122f"},
+    {file = "jellyfish-1.2.1-cp311-cp311-win32.whl", hash = "sha256:ecf62d4aad0baa8832ab60f96e7baedbe6558bd292597503d927e9c5bce745d8"},
+    {file = "jellyfish-1.2.1-cp311-cp311-win_amd64.whl", hash = "sha256:bd186c041d9be86c4fa5e2490943ce5d7f05b472f45d7f49426f259f3dd20bc4"},
+    {file = "jellyfish-1.2.1-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:32a85b752cb51463face13e2b1797cfa617cd7fb7073f15feaa4020a86a346ce"},
+    {file = "jellyfish-1.2.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:675ab43840488944899ca87f02d4813c1e32107e56afaba7489705a70214e8aa"},
+    {file = "jellyfish-1.2.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c888f624d03e55e501bc438906505c79fb307d8da37a6dda18dd1ac2e6d5ea9c"},
+    {file = "jellyfish-1.2.1-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:d2b56a1fd2c5126c4a3362ec4470291cdd3c7daa22f583da67e75e30dc425ce6"},
+    {file = "jellyfish-1.2.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1a3ccff843822e7f3ad6f91662488a3630724c8587976bce114f3c7238e8ffa1"},
+    {file = "jellyfish-1.2.1-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:10da696747e2de0336180fd5ba77ef769a7c80f9743123545f7fc0251efbbcec"},
+    {file = "jellyfish-1.2.1-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:c3c18f13175a9c90f3abd8805720b0eb3e10eca1d5d4e0cf57722b2a62d62016"},
+    {file = "jellyfish-1.2.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:0368596e176bf548b3be2979ff33e274fb6d5e13b2cebe85137b8b698b002a85"},
+    {file = "jellyfish-1.2.1-cp312-cp312-win32.whl", hash = "sha256:451ddf4094e108e33d3b86d7817a7e20a2c5e6812d08c34ee22f6a595f38dcca"},
+    {file = "jellyfish-1.2.1-cp312-cp312-win_amd64.whl", hash = "sha256:15318c13070fe6d9caeb7e10f9cdf89ff47c9d20f05a9a2c0d3b5cb8062a7033"},
+    {file = "jellyfish-1.2.1-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:4b3e3223aaad74e18aacc74775e01815e68af810258ceea6fa6a81b19f384312"},
+    {file = "jellyfish-1.2.1-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:e967e67058b78189d2b20a9586c7720a05ec4a580d6a98c796cd5cd2b7b11303"},
+    {file = "jellyfish-1.2.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:32581c50b34a09889b2d96796170e53da313a1e7fde32be63c82e50e7e791e3c"},
+    {file = "jellyfish-1.2.1-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:07b022412ebece96759006cb015d46b8218d7f896d8b327c6bbee784ddf38ed9"},
+    {file = "jellyfish-1.2.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:80a49eb817eaa6591f43a31e5c93d79904de62537f029907ef88c050d781a638"},
+    {file = "jellyfish-1.2.1-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:e1b990fb15985571616f7f40a12d6fa062897b19fb5359b6dec3cd811d802c24"},
+    {file = "jellyfish-1.2.1-cp313-cp313-musllinux_1_1_i686.whl", hash = "sha256:dd895cf63fac0a9f11b524fff810d9a6081dcf3c518b34172ac8684eb504dd43"},
+    {file = "jellyfish-1.2.1-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:6d2bac5982d7a08759ea487bfa00149e6aa8a3be7cd43c4ed1be1e3505425c69"},
+    {file = "jellyfish-1.2.1-cp313-cp313-win32.whl", hash = "sha256:509355ebedec69a8bf0cc113a6bf9c01820d12fe2eea44f47dfa809faf2d5463"},
+    {file = "jellyfish-1.2.1-cp313-cp313-win_amd64.whl", hash = "sha256:9c747ae5c0fb4bd519f6abbfe4bd704b2f1c63fd4dd3dbb8d8864478974e1571"},
+    {file = "jellyfish-1.2.1-cp314-cp314-macosx_10_12_x86_64.whl", hash = "sha256:212aaf177236192a735bbbf5938717aa8518d14a25b08b015e47e783e70be060"},
+    {file = "jellyfish-1.2.1-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:b8986d9768daddd5e87abf513ae168ea0afe690a444d4c82d5b1b14b0d045820"},
+    {file = "jellyfish-1.2.1-cp314-cp314-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5fa0ba0946f3c274f6a87aaa3c631dc70a363bd46cceea828ce777e8db653b6f"},
+    {file = "jellyfish-1.2.1-cp314-cp314-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:6e76b23431a667cd485fb562428d1ad29bae9fdd0fcdfb5a51cc8087bae0e88c"},
+    {file = "jellyfish-1.2.1-cp314-cp314-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a058f4c6a591d5e5a47569f5648a26303ba19c76a960fef7e0beba2aa959e52e"},
+    {file = "jellyfish-1.2.1-cp314-cp314-musllinux_1_1_aarch64.whl", hash = "sha256:6a49ce2a580edd3b16b69421137deef464e2f8907f9ef906d49950b1a52908c1"},
+    {file = "jellyfish-1.2.1-cp314-cp314-musllinux_1_1_i686.whl", hash = "sha256:c85aa2bc76a36d92a3197f406f86636664d5b323727dfec4fa2842a8a24a06ae"},
+    {file = "jellyfish-1.2.1-cp314-cp314-musllinux_1_1_x86_64.whl", hash = "sha256:29cfa8bfb72aacf2d611a3313b358ed4d4140fa3d3efcffea750c8e7f8acb1aa"},
+    {file = "jellyfish-1.2.1-cp314-cp314-win32.whl", hash = "sha256:f121218dc33fb318c34ddd889dc7362606ce1316af2bb63b73cc1df81523ca34"},
+    {file = "jellyfish-1.2.1-cp314-cp314-win_amd64.whl", hash = "sha256:9a73b5c6425a70ebd440579a677eb4f03b327b2f59090db34e6c937aeea5aabd"},
+    {file = "jellyfish-1.2.1-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:5335f622458aa105289a8e358bc32ecd1b9634b6ffec3e77ea3577e49c297171"},
+    {file = "jellyfish-1.2.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:6c51e565f85ce38cf9388c4f916d53888b0fa34788fcebe3aff3db24948e0960"},
+    {file = "jellyfish-1.2.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:14bbb30d988dec1d12183cf5d4621c908f98add2009c72a185e8c3e8d00b804f"},
+    {file = "jellyfish-1.2.1-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:9930e20f0e9f65ad1d57d98290c2be3abd75812d058815605f44a56056fb9a66"},
+    {file = "jellyfish-1.2.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0028857c5381c9d55e21cc6cb0d7f9545c3a9a7bb7dbca3960fe0a898c691ac2"},
+    {file = "jellyfish-1.2.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:56da7632e029912af25e25422fae3b6df318400297d552791f4b21da6d815ed6"},
+    {file = "jellyfish-1.2.1-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:a3cab91020e3ff7565e55a611ec3e3257c093ac950d55778a48bfc8c57562b6e"},
+    {file = "jellyfish-1.2.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:0b21c1596ce283fd7ee954eb0eeb007d59e480364324bcd91ad55146e91f3936"},
+    {file = "jellyfish-1.2.1-cp39-cp39-win32.whl", hash = "sha256:1098ce1f84ae3f147f0a18a6803ffb09b9c8cd5fedce42465643ca0b5c9d0224"},
+    {file = "jellyfish-1.2.1-cp39-cp39-win_amd64.whl", hash = "sha256:4b013876109d91fa6fc871ffa4e0dbfda11820c33dc4ad0e2967b3fc1187f804"},
+    {file = "jellyfish-1.2.1-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:c499ea3a134130797c50e367687a6a46a12653c59af381bee92c41a5ab0bd55d"},
+    {file = "jellyfish-1.2.1-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:91cad49a4fb731b726afc5ae385a3217a7016ed88a04da40c131cff8136a5db5"},
+    {file = "jellyfish-1.2.1-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5bda2275f31a64adf3483e39f7a4e2107f7dfe3a3f85f0d2c0cb6ae5fbe4a443"},
+    {file = "jellyfish-1.2.1-pp310-pypy310_pp73-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:98a133b40dc00cfda6609e1b0cb0ab0b77796fc2719aae886a12009514f73499"},
+    {file = "jellyfish-1.2.1-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:baa30c7b59bd1c5e105693108a6d7a98f3e7a1a59e23e15bc5897b91fd5849f5"},
+    {file = "jellyfish-1.2.1-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:db97d873f23b0c15b4ed911ece10e5cc0bb96cdc53666d5c3788bd0af81807f1"},
+    {file = "jellyfish-1.2.1-pp310-pypy310_pp73-musllinux_1_1_i686.whl", hash = "sha256:393f609fd6139ce782e747e22c399483ffc58341009e6a97e39ffe5f5b2c674c"},
+    {file = "jellyfish-1.2.1-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:fb3c6e537cb4605c22895a8d4a10cdb26611ba2bbfc7f0b4c1d06bb9d8aad648"},
+    {file = "jellyfish-1.2.1-pp311-pypy311_pp73-macosx_10_12_x86_64.whl", hash = "sha256:748dc45a0394fbe9120b8b3b9a39fab0967c7e2d6ecdd5304af018e774f80f96"},
+    {file = "jellyfish-1.2.1-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:13f1ac9caba22af10bfe42f674822643c0266009f882e0fe652079706dc5d13a"},
+    {file = "jellyfish-1.2.1-pp311-pypy311_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1ffeeb6c78c45fbb6d2a22b0173fb8a6af849001d6c26fab49c525136dbd9734"},
+    {file = "jellyfish-1.2.1-pp311-pypy311_pp73-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:1354b558a0a16597b6032dd0af64bebd24994f7e7484cf14993320eb764b06cb"},
+    {file = "jellyfish-1.2.1-pp311-pypy311_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e5977810972c6f0b2e61252c4758fd5aee21abf663ff309881195a99d37daa94"},
+    {file = "jellyfish-1.2.1-pp311-pypy311_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:536c80d8d4ec7f39cbb10b85d926ff96cef3cde4a83ca0991c07cd9835d5dc13"},
+    {file = "jellyfish-1.2.1-pp311-pypy311_pp73-musllinux_1_1_i686.whl", hash = "sha256:21baa92d4a5112167721156f6d061c2ae105f2995b3a5e19cec6662928f0c439"},
+    {file = "jellyfish-1.2.1-pp311-pypy311_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:68ea3ddd4dae1152a7f7155ef02a7bfad919611158d71b301f9aa167685819af"},
+    {file = "jellyfish-1.2.1-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:d7be8021658b46b22500a77f1707901bd98fc210f185c229b81c74efd3c1baf2"},
+    {file = "jellyfish-1.2.1-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:bcdcd603a7737cd3f5a2ab10ce9b49844329deb81c2daafcd8131e54fc730205"},
+    {file = "jellyfish-1.2.1-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2c28a4ae3e201e1c1b7bacacd40e2e76c4068b90c9ae3a0d525e0ac98206f1cc"},
+    {file = "jellyfish-1.2.1-pp39-pypy39_pp73-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:bebccd0652ac1c7e438ae1f451edefde63d14b3af6f6daa30c599919dcb92886"},
+    {file = "jellyfish-1.2.1-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:05be396aebe3dce7a8cb2f97727ecdf99e86457c48e97190775dce33f8b7e39d"},
+    {file = "jellyfish-1.2.1-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:9d4448c874959ae012cda0f6d570ac0bd7f0fcf12007714eaebf86b86919b66f"},
+    {file = "jellyfish-1.2.1-pp39-pypy39_pp73-musllinux_1_1_i686.whl", hash = "sha256:4a21d7eda5e6996772055f798e3fe1de1b33b3edad7f6cf0567097a21585a812"},
+    {file = "jellyfish-1.2.1-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:a0ef6f0ecc085c1f8fddb048f538c8bb89989e5d470eab45d4e9bd48ee73a40d"},
+    {file = "jellyfish-1.2.1.tar.gz", hash = "sha256:72d2fda61b23babe862018729be73c8b0dc12e3e6601f36f6e65d905e249f4db"},
+]
+
 [[package]]
 name = "jmespath"
 version = "1.1.0"
@ -2777,7 +2930,7 @@ version = "4.0.0"
 description = "Python port of markdown-it. Markdown parsing, done right!"
 optional = false
 python-versions = ">=3.10"
-groups = ["test"]
+groups = ["main", "test"]
 files = [
    {file = "markdown_it_py-4.0.0-py3-none-any.whl", hash = "sha256:87327c59b172c5011896038353a81343b6754500a08cd7a4973bb48c6d578147"},
    {file = "markdown_it_py-4.0.0.tar.gz", hash = "sha256:cb0a2b4aa34f932c007117b194e945bd74e0ec24133ceb5bac59009cda1cb9f3"},
@ -2873,7 +3026,7 @@ version = "0.1.2"
 description = "Markdown URL utilities"
 optional = false
 python-versions = ">=3.7"
-groups = ["test"]
+groups = ["main", "test"]
 files = [
    {file = "mdurl-0.1.2-py3-none-any.whl", hash = "sha256:84008a41e51615a49fc9966191ff91509e3c40b939176e643fd50a5c2196b8f8"},
    {file = "mdurl-0.1.2.tar.gz", hash = "sha256:bb413d29f5eea38f31dd4754dd7377d4465116fb207585f97bf925588687c1ba"},
@ -3247,6 +3400,192 @@ files = [
    {file = "ndjson-0.3.1.tar.gz", hash = "sha256:bf9746cb6bb1cb53d172cda7f154c07c786d665ff28341e4e689b796b229e5d6"},
 ]

+[[package]]
+name = "networkx"
+version = "3.6"
+description = "Python package for creating and manipulating graphs and networks"
+optional = false
+python-versions = ">=3.11"
+groups = ["main"]
+markers = "python_version == \"3.14\""
+files = [
+    {file = "networkx-3.6-py3-none-any.whl", hash = "sha256:cdb395b105806062473d3be36458d8f1459a4e4b98e236a66c3a48996e07684f"},
+    {file = "networkx-3.6.tar.gz", hash = "sha256:285276002ad1f7f7da0f7b42f004bcba70d381e936559166363707fdad3d72ad"},
+]
+
+[package.extras]
+benchmarking = ["asv", "virtualenv"]
+default = ["matplotlib (>=3.8)", "numpy (>=1.25)", "pandas (>=2.0)", "scipy (>=1.11.2)"]
+developer = ["mypy (>=1.15)", "pre-commit (>=4.1)"]
+doc = ["intersphinx-registry", "myst-nb (>=1.1)", "numpydoc (>=1.8.0)", "pillow (>=10)", "pydata-sphinx-theme (>=0.16)", "sphinx (>=8.0)", "sphinx-gallery (>=0.18)", "texext (>=0.6.7)"]
+example = ["cairocffi (>=1.7)", "contextily (>=1.6)", "igraph (>=0.11)", "iplotx (>=0.9.0)", "momepy (>=0.7.2)", "osmnx (>=2.0.0)", "scikit-learn (>=1.5)", "seaborn (>=0.13)"]
+extra = ["lxml (>=4.6)", "pydot (>=3.0.1)", "pygraphviz (>=1.14)", "sympy (>=1.10)"]
+release = ["build (>=0.10)", "changelist (==0.5)", "twine (>=4.0)", "wheel (>=0.40)"]
+test = ["pytest (>=7.2)", "pytest-cov (>=4.0)", "pytest-xdist (>=3.0)"]
+test-extras = ["pytest-mpl", "pytest-randomly"]
+
+[[package]]
+name = "networkx"
+version = "3.6.1"
+description = "Python package for creating and manipulating graphs and networks"
+optional = false
+python-versions = "!=3.14.1,>=3.11"
+groups = ["main"]
+markers = "python_version < \"3.14\""
+files = [
+    {file = "networkx-3.6.1-py3-none-any.whl", hash = "sha256:d47fbf302e7d9cbbb9e2555a0d267983d2aa476bac30e90dfbe5669bd57f3762"},
+    {file = "networkx-3.6.1.tar.gz", hash = "sha256:26b7c357accc0c8cde558ad486283728b65b6a95d85ee1cd66bafab4c8168509"},
+]
+
+[package.extras]
+benchmarking = ["asv", "virtualenv"]
+default = ["matplotlib (>=3.8)", "numpy (>=1.25)", "pandas (>=2.0)", "scipy (>=1.11.2)"]
+developer = ["mypy (>=1.15)", "pre-commit (>=4.1)"]
+doc = ["intersphinx-registry", "myst-nb (>=1.1)", "numpydoc (>=1.8.0)", "pillow (>=10)", "pydata-sphinx-theme (>=0.16)", "sphinx (>=8.0)", "sphinx-gallery (>=0.18)", "texext (>=0.6.7)"]
+example = ["cairocffi (>=1.7)", "contextily (>=1.6)", "igraph (>=0.11)", "iplotx (>=0.9.0)", "momepy (>=0.7.2)", "osmnx (>=2.0.0)", "scikit-learn (>=1.5)", "seaborn (>=0.13)"]
+extra = ["lxml (>=4.6)", "pydot (>=3.0.1)", "pygraphviz (>=1.14)", "sympy (>=1.10)"]
+release = ["build (>=0.10)", "changelist (==0.5)", "twine (>=4.0)", "wheel (>=0.40)"]
+test = ["pytest (>=7.2)", "pytest-cov (>=4.0)", "pytest-xdist (>=3.0)"]
+test-extras = ["pytest-mpl", "pytest-randomly"]
+
+[[package]]
+name = "numpy"
+version = "2.4.6"
+description = "Fundamental package for array computing in Python"
+optional = false
+python-versions = ">=3.11"
+groups = ["main"]
+markers = "python_version < \"3.14\""
+files = [
+    {file = "numpy-2.4.6-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:0280e0356c0829a18d9de1cb7eee50ec22ca639878d7240307ca0943d73cd2c4"},
+    {file = "numpy-2.4.6-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:110f8b71aacb688ec69062bb7f6938a0f8acb01b7c1c4beb453c65b6d234584d"},
+    {file = "numpy-2.4.6-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:4cfe66903cc32a9921a6733d96b19bb6abf310397581bbad89c228f5abaf0ee8"},
+    {file = "numpy-2.4.6-cp311-cp311-macosx_14_0_x86_64.whl", hash = "sha256:8155154c7c691289fe18f510b5d4657c68c67989f293f0535a91360392ff6538"},
+    {file = "numpy-2.4.6-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0ab0a9c4ffb1a6d95ef519fe4247dba8eb6b18ad93999f76b7f657039acabd47"},
+    {file = "numpy-2.4.6-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:89cd468399cfd2504718f0ba50e410dca55a170b61a02ad92bb18c8a65186e93"},
+    {file = "numpy-2.4.6-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:c2d37ab77531417474168eb79d6d80b14f821a966818505d03013d0833edb7a8"},
+    {file = "numpy-2.4.6-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:f407cb6b8e9d6d8c626bc73c945db1706035af8fd632295547bf1c9e46d092d6"},
+    {file = "numpy-2.4.6-cp311-cp311-win32.whl", hash = "sha256:ddea102b48f9e339f3948bf22040944184627a30fdf7f858667673b9c5f033c8"},
+    {file = "numpy-2.4.6-cp311-cp311-win_amd64.whl", hash = "sha256:1e254a00cdf42b1e4d5b3d68d33af63268d41340d8885df2ab6470f2e1500147"},
+    {file = "numpy-2.4.6-cp311-cp311-win_arm64.whl", hash = "sha256:ed9749eef4cbd126da3dc1d6bcb3a57f5eb7ac6a6484146bdbf743f552dfc577"},
+    {file = "numpy-2.4.6-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:001fbb8e08d942dd57599e781f2472269ee7f2755fae407b4f67b2f0b17da3f1"},
+    {file = "numpy-2.4.6-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:ebfb099f8dcf083deef3ac1ca4c1503f387cf76296fcb3816b66f5ecb5f54fdb"},
+    {file = "numpy-2.4.6-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:3213d622a0283a39a93d188f3cf72b26862df52fbb4ca3697f51705016523d41"},
+    {file = "numpy-2.4.6-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:357cc07a6d7b0b182ff02249616a03742827ebb1277546b5c7cd7f7620a45698"},
+    {file = "numpy-2.4.6-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5f9fb9157b4ce2971008323afe46053787b526ef624fea915b261468a8421a0f"},
+    {file = "numpy-2.4.6-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:90f9849678c75fe7afa2d348ac842c168b0a4d3d61919687216dfc547976d853"},
+    {file = "numpy-2.4.6-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:c1a2af6c6ef86344a6b0db6b97834208bf598db514f2b155042439b62605601a"},
+    {file = "numpy-2.4.6-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:e5805d5a22fd19c8ccff10a9561f9df94436b0545619ea579db2d3c35294bce2"},
+    {file = "numpy-2.4.6-cp312-cp312-win32.whl", hash = "sha256:e3eeb0aabd6bd5ce64faae67e9935203a6991b4bc2a485a767fbafb2c5125f45"},
+    {file = "numpy-2.4.6-cp312-cp312-win_amd64.whl", hash = "sha256:d8e8286dd7cea7895157318d1b91cdacac64c479f3cbc8dce548331728484751"},
+    {file = "numpy-2.4.6-cp312-cp312-win_arm64.whl", hash = "sha256:4081eb135ac24158bd51cdfbef16f1c64df7063b1143f24731387137c092bec8"},
+    {file = "numpy-2.4.6-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:511dbaf848decaaaf4b4ca48032619fb3138710c4bf7da7617765edad1ef96b0"},
+    {file = "numpy-2.4.6-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:bf162abab1c1a736333192707cef898e735a5ca00f38f27eeedf44b39d9e85eb"},
+    {file = "numpy-2.4.6-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:043191bfa8eab18c776647b62723ac9dddece59743b13f49b2016094129c2b3f"},
+    {file = "numpy-2.4.6-cp313-cp313-macosx_14_0_x86_64.whl", hash = "sha256:6180d8b35af935aed8ece3a85e0a43f87393ae0ac87c8d2c8bd2c993f7270ef3"},
+    {file = "numpy-2.4.6-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:72fbe16c6fac95aedf5937fa873445cec2110be35d8a4e9433d7501fd98dae6b"},
+    {file = "numpy-2.4.6-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:a7830bab239b79cda9c08c2da014761cafb48da6150e1da17ac06283f43b6089"},
+    {file = "numpy-2.4.6-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:ef4aea96ce4d3b074422cb4f2f64e216bf9e213004bb58ecfdf50ea02ea8eb9a"},
+    {file = "numpy-2.4.6-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:dfa20cc6ca228e6b155b11da03825975ce66aea520985dbbddf0f2a5a495c605"},
+    {file = "numpy-2.4.6-cp313-cp313-win32.whl", hash = "sha256:56b39e5e0622a09a25bf5baf62f4bcf0cb8a41ae6e2819cf49bbc5a74c083f91"},
+    {file = "numpy-2.4.6-cp313-cp313-win_amd64.whl", hash = "sha256:c4fc99836233ea196540b17ab0983aff60ed07941751930f5f4d05bc3b3b7359"},
+    {file = "numpy-2.4.6-cp313-cp313-win_arm64.whl", hash = "sha256:a7c711e21628b52034bb5ab8d1bce291f752fcc5e92accc615778acee1ff4778"},
+    {file = "numpy-2.4.6-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:112b06a867b235ef466ed3508ddf0238050df9c727cafb5301ac385b899189a1"},
+    {file = "numpy-2.4.6-cp313-cp313t-macosx_14_0_arm64.whl", hash = "sha256:eaf7fa2de5c0be8ae6ff8e9bea2ccd725e980541244521d8d4b5f3354a27babe"},
+    {file = "numpy-2.4.6-cp313-cp313t-macosx_14_0_x86_64.whl", hash = "sha256:7265a2f3d436e54ef9f2b52b5c937e6be778781bd97a590319d7348f1c1ca997"},
+    {file = "numpy-2.4.6-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:f74a575920ab21fe304421a3fc28793d82e299cae9eccb37084e9fc7f3617c20"},
+    {file = "numpy-2.4.6-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ede83e07a75dd06bc501566c1eca2afc0d61677c1472ac9ad93fdee6e638a48d"},
+    {file = "numpy-2.4.6-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:68bb27509ac1b9a3443094260f6326150663b06abe40b73a2f81160623da5b67"},
+    {file = "numpy-2.4.6-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:a0df0043bdb289bde1f62da130d20df23d58b45429f752bc7a8fc5325a225ecd"},
+    {file = "numpy-2.4.6-cp313-cp313t-win32.whl", hash = "sha256:29a287e0cf63ff528da061de6b9f64a4618da591ca1046aafc54062e40ca7eab"},
+    {file = "numpy-2.4.6-cp313-cp313t-win_amd64.whl", hash = "sha256:25c692919ac5a01f170a3bfcd62d745b24fd095c353d50812637d6fcab442e75"},
+    {file = "numpy-2.4.6-cp313-cp313t-win_arm64.whl", hash = "sha256:1e978ec1e8bd0e0e4de6bb75de9d30cbb74db6b6a2bb727618613703ca0167dd"},
+    {file = "numpy-2.4.6-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:06ca2f61ec4385a07a6977c55ba998a4466c123642b4a32694d3128fce18c079"},
+    {file = "numpy-2.4.6-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:38efbc8de75c7a0fc1ac190162d892787f3f47b57cc291231aafee36b80982b7"},
+    {file = "numpy-2.4.6-cp314-cp314-macosx_14_0_arm64.whl", hash = "sha256:d581b735e177fdcdce6fed8e7e8880a3fb6ee4e3653a3ac6af01c6f4c03effc5"},
+    {file = "numpy-2.4.6-cp314-cp314-macosx_14_0_x86_64.whl", hash = "sha256:0a041d3d761dc3c35cc56ce0351506a02bcbc25f7b169f652435141a17db9096"},
+    {file = "numpy-2.4.6-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:40fdc1ae7125e518ea98e53e69a4ebc27e1fd50510c47b7ea130cf21e5e1d42b"},
+    {file = "numpy-2.4.6-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:a2c306dea656c12c68f51f4cea133cbe78ca7435eb28c735eac1d3ebe73be6e8"},
+    {file = "numpy-2.4.6-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:33111801a01c12a8a1e3721f0a9232f8cfc8ae2c6b7098167e6f623c6073f402"},
+    {file = "numpy-2.4.6-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:ae506e6902902557576a26ff33eda8695e7ecb3cb36c3b573a0765dee114ebdb"},
+    {file = "numpy-2.4.6-cp314-cp314-win32.whl", hash = "sha256:aaf159caa35993cb1f56fb9b8e4610d35758e7ca005412eb1daa856a78c9c4b1"},
+    {file = "numpy-2.4.6-cp314-cp314-win_amd64.whl", hash = "sha256:b507f5c4c1d508876d1819b6bf9a49d365b96320b5d4993426b33a23ca4b8261"},
+    {file = "numpy-2.4.6-cp314-cp314-win_arm64.whl", hash = "sha256:6f41ae150c4e32db4f3310cdaf64b1593a03dbabe29eec77fc9b50fe64061df6"},
+    {file = "numpy-2.4.6-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:ece3d2cfe132e7d51f44a832b303895e6f2d499c5e74dfbdb06ee246147a304a"},
+    {file = "numpy-2.4.6-cp314-cp314t-macosx_14_0_arm64.whl", hash = "sha256:e3e5193ef5a3dc73bceee50f7fdc2c90dbb76c42df8d8fae3d1067a583df579e"},
+    {file = "numpy-2.4.6-cp314-cp314t-macosx_14_0_x86_64.whl", hash = "sha256:17f9ade344e7d9b464a084d69bcf18fc691cb1db67c62ed80820bf4926d78f0e"},
+    {file = "numpy-2.4.6-cp314-cp314t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:9cd5ffd25db4e7ba6a375693b3fc0fc1791ec636c17db3720da19bde7180ec43"},
+    {file = "numpy-2.4.6-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:7d92c3819208a60205a12a245c91ad70cb0a85336659b19b834205573ac8456e"},
+    {file = "numpy-2.4.6-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:e85b752a1e912b70eaad4fafbd4d1238007ab221de2009b9a2f5ae7461239895"},
+    {file = "numpy-2.4.6-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:29cb7f67d10b479ff07c17d33e39f78c07f71c40ef30d63c153d340e96cd3fb4"},
+    {file = "numpy-2.4.6-cp314-cp314t-win32.whl", hash = "sha256:260a5d70215b61ab4fadf5c7baacd64821842975eea312125ed3c39a6391b063"},
+    {file = "numpy-2.4.6-cp314-cp314t-win_amd64.whl", hash = "sha256:81a1cca95ed5bb92aa8b10dd2cdc9a0d3853a50fad926c28b5d7e8ea54389627"},
+    {file = "numpy-2.4.6-cp314-cp314t-win_arm64.whl", hash = "sha256:0c9136e14ed34a9e343a31c533d78a9813a69a3148332bce5e9821cb2f996e66"},
+    {file = "numpy-2.4.6-pp311-pypy311_pp73-macosx_10_15_x86_64.whl", hash = "sha256:55cced7c52e981362f708ad635198e97a752dfba412cc03c23bbf3bd8d5cd662"},
+    {file = "numpy-2.4.6-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:d6da64deb6b8ed903e7560180a92f2d804ee1ba5eeb849ac2748b8c1aba1f6d7"},
+    {file = "numpy-2.4.6-pp311-pypy311_pp73-macosx_14_0_arm64.whl", hash = "sha256:68a5124b13fa6cc2086764a20005d30bc0548146f7f5322f02fce212ca14317f"},
+    {file = "numpy-2.4.6-pp311-pypy311_pp73-macosx_14_0_x86_64.whl", hash = "sha256:948424b06129ce883307e8cff868c31396d8dc7630a59c61d70d98dbe70f222c"},
+    {file = "numpy-2.4.6-pp311-pypy311_pp73-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5dbbdb29840ca3d91ee0fece42fc29278886d908280bfec0a5846c6f901a3eb0"},
+    {file = "numpy-2.4.6-pp311-pypy311_pp73-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:8ad03c0965fb3c692200e74d458ca28c1dbb4ce96f9a479a8aa041ad5fabca02"},
+    {file = "numpy-2.4.6-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:2803abfebfc990042cd494d8ce2d5f82e9d847af6d35ec486923aa19dbad5e73"},
+    {file = "numpy-2.4.6.tar.gz", hash = "sha256:f3a3570c4a2a16746ac2c31a7c7c7b0c186b95ce902e33db6f28094ed7387dda"},
+]
+
+[[package]]
+name = "numpy"
+version = "2.5.0"
+description = "Fundamental package for array computing in Python"
+optional = false
+python-versions = ">=3.12"
+groups = ["main"]
+markers = "python_version == \"3.14\""
+files = [
+    {file = "numpy-2.5.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:489780423903667933b4ed6197b6ec3b75ea5dd17d1d8f0f38d798feb6921561"},
+    {file = "numpy-2.5.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:ece55976ced6bca95a03ae2839e2e5ccffe8eb6a3e7022415645eb154a81e4e6"},
+    {file = "numpy-2.5.0-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:c83b664b0e6eee9594fa920cf0639d8af796606d3fad6cc70180c87e4b97c7be"},
+    {file = "numpy-2.5.0-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:bf80333980bf37f523341ddd72c783f39d6829ec7736b9eb99086388a2d52cc2"},
+    {file = "numpy-2.5.0-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:a1a4874217b36d5ac8fc876f52e39df56f8182c88463e9e2dceabf7ca8b7efb8"},
+    {file = "numpy-2.5.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:aaa760137137e8d3c920d27927748215b56014f92667dc9b6c27dfc61249255a"},
+    {file = "numpy-2.5.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:7174ce8265fc7f7417d171c9ea8fe905220748893ea67a2a7abe726ec331c4b0"},
+    {file = "numpy-2.5.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:b8c3daaf99de52415d20b42f8e8155c78642cb04207d02f9d317a0dcf1b3fb54"},
+    {file = "numpy-2.5.0-cp312-cp312-win32.whl", hash = "sha256:6206db0af545d73d068add6d992279145f158428d1da6cc49adc4b630c5d6ee5"},
+    {file = "numpy-2.5.0-cp312-cp312-win_amd64.whl", hash = "sha256:6f2d6873e2940c860a309d21e25b1e69af6aaffdd80aa056b04c16380db1c4f2"},
+    {file = "numpy-2.5.0-cp312-cp312-win_arm64.whl", hash = "sha256:a55e1eb2bca2cfd17a16b213c99dfc8502d47b0d494224d2122277d0400935ca"},
+    {file = "numpy-2.5.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:520e6b8be0a4b65840ac8090d4f51cef4bed66e2b0894d5a520f099adc24a9b2"},
+    {file = "numpy-2.5.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:146b81cdd3967fdb6beca8ba25f00c58741d8f3cbd797f55af0fbe0bfec3469c"},
+    {file = "numpy-2.5.0-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:126b88d95e8ff9b00c9e717aa540469f21d6180162f84c0caec51b16215d49cd"},
+    {file = "numpy-2.5.0-cp313-cp313-macosx_14_0_x86_64.whl", hash = "sha256:d4313cef1594c5ce46c31b6e54e918338f63f16ee9322304e8c9114d6d81c8bd"},
+    {file = "numpy-2.5.0-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:750fb097caf26fa878746d9d119f6f9da12dedcbff1eea966c3e3447647c4a9e"},
+    {file = "numpy-2.5.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:3893adc2dc7c0412ba76777db55a049215d99c9aa3113003be8f49f4f1290ab9"},
+    {file = "numpy-2.5.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:835e454dd99b238cdc5a3f63bce2371296f5ebc53ca1e0f8e6ddbb6d92a29aab"},
+    {file = "numpy-2.5.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:6f9836778081a0a3c02a6a21493f3e9f5b311f8d2541934f31f05583dc999ea4"},
+    {file = "numpy-2.5.0-cp313-cp313-win32.whl", hash = "sha256:0b525be4744b60bb0557ac872d53ef07d085b5f39622bc579c98d3809d05b988"},
+    {file = "numpy-2.5.0-cp313-cp313-win_amd64.whl", hash = "sha256:44353e2878930039db472b99dc353d749826e4010bd4d2a7f835e94a97a5c748"},
+    {file = "numpy-2.5.0-cp313-cp313-win_arm64.whl", hash = "sha256:48f54b00711f83a5f796b70c518e8c2b3c5848dda03a54911f23eb68519b9b60"},
+    {file = "numpy-2.5.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:f27582c55ba4c750b7c58c8faf021d2cd9324a662b466229db8a417b41368af9"},
+    {file = "numpy-2.5.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:28e7137057d551e4a83c4ae414e3451f50568409db7569aacc7f9811ee06a446"},
+    {file = "numpy-2.5.0-cp314-cp314-macosx_14_0_arm64.whl", hash = "sha256:e1da54b53e75cd9fcfc23efcc7edab2c6aecf97b6037566d8a0fe804af8ec57c"},
+    {file = "numpy-2.5.0-cp314-cp314-macosx_14_0_x86_64.whl", hash = "sha256:694d8f74e156f7fd01179f1aa8faa2f648ab6ae0f70b6c3fe57a03249aea2303"},
+    {file = "numpy-2.5.0-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1a7569a7b53c77716f036bb28cb1c91f166a26ec7d9502cd1e4bdfe502fdec22"},
+    {file = "numpy-2.5.0-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:39a0433bd4086ebd462960cf375e19195bb07b53dc1d87dd5fcf47ad78576f03"},
+    {file = "numpy-2.5.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:929f0c79ac38bcbd7154fe631dc907abfeddbcc5027a896bd1f7767323271e7a"},
+    {file = "numpy-2.5.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:cc4f247a47bbf070bfd70be53ccdcf47b800af563535e7bbe172322197c30e21"},
+    {file = "numpy-2.5.0-cp314-cp314-win32.whl", hash = "sha256:5dc71423499fab3f46f7a7201155ade1669ea101f2f429d332df9e72f8161731"},
+    {file = "numpy-2.5.0-cp314-cp314-win_amd64.whl", hash = "sha256:ebb81d9d5443e0309d6c54894c3fbed74ad7da0714352a67b6d773cd189eae73"},
+    {file = "numpy-2.5.0-cp314-cp314-win_arm64.whl", hash = "sha256:3b94d0d0deceebfad3e67ae5c0e5eb87371e8f7a0581cd04a779928c2450cf1e"},
+    {file = "numpy-2.5.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:22f3d43e362d650bc39db1f17851302874a148ca95ba6981c1dfb5fa6862f35b"},
+    {file = "numpy-2.5.0-cp314-cp314t-macosx_14_0_arm64.whl", hash = "sha256:243563efb4cd7528a264567e9fd206c87826457322521d06206a00bfa316c927"},
+    {file = "numpy-2.5.0-cp314-cp314t-macosx_14_0_x86_64.whl", hash = "sha256:84881d825ca75249b189bbee875fcfe3238aa5c479e6100893cda566e8e86826"},
+    {file = "numpy-2.5.0-cp314-cp314t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:cda12aa4779d42b8771180aba759c96f527d43446d8f380ab59e2b35e8489efd"},
+    {file = "numpy-2.5.0-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:1c0121101093d2bd74981b10f8837d78e794a8ff57834eb27179f49e1ba11ac6"},
+    {file = "numpy-2.5.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:d371c92cfa09da00022f501ab67fafaea813d752eb30ac44336d45b1e5b0268a"},
+    {file = "numpy-2.5.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:9990713e9c38154c6861e7547f1e3fc7a87e75ff09bab24ef1cc81d81c2835e9"},
+    {file = "numpy-2.5.0-cp314-cp314t-win32.whl", hash = "sha256:edadfbd4794b1086c0d822f81863e8a68fc129d132fd0bb9e31e955d7fbbbdb7"},
+    {file = "numpy-2.5.0-cp314-cp314t-win_amd64.whl", hash = "sha256:f7e5fa4382967ae6548bd2f174219afb908e294b0d5f625af01166edd5f7d9aa"},
+    {file = "numpy-2.5.0-cp314-cp314t-win_arm64.whl", hash = "sha256:016623417bb330d719d579daf2d6b9a01ddc52e41a9ed61a47f39fde46dcd865"},
+    {file = "numpy-2.5.0.tar.gz", hash = "sha256:5a129578019311b6e56bdd714250f19b518f7dceeeb8d1af5490f4942d3f891c"},
+]
+
 [[package]]
 name = "oauthlib"
 version = "3.3.1"
@ -3889,7 +4228,7 @@ description = "C parser in Python"
 optional = false
 python-versions = ">=3.10"
 groups = ["main"]
-markers = "(platform_python_implementation != \"PyPy\" or sys_platform == \"darwin\") and implementation_name != \"PyPy\""
+markers = "implementation_name != \"PyPy\""
 files = [
    {file = "pycparser-3.0-py3-none-any.whl", hash = "sha256:b727414169a36b7d524c1c3e31839a521725078d7b2ff038656844266160a992"},
    {file = "pycparser-3.0.tar.gz", hash = "sha256:600f49d217304a5902ac3c37e1281c9fe94e4d0489de643a9504c5cdfdfc6b29"},
@ -5068,7 +5407,7 @@ version = "14.3.3"
 description = "Render rich text, tables, progress bars, syntax highlighting, markdown and more to the terminal"
 optional = false
 python-versions = ">=3.8.0"
-groups = ["test"]
+groups = ["main", "test"]
 files = [
    {file = "rich-14.3.3-py3-none-any.whl", hash = "sha256:793431c1f8619afa7d3b52b2cdec859562b950ea0d4b6b505397612db8d5362d"},
    {file = "rich-14.3.3.tar.gz", hash = "sha256:b8daa0b9e4eef54dd8cf7c86c03713f53241884e814f4e2f5fb342fe520f639b"},
@ -5256,6 +5595,21 @@ files = [
 cryptography = ">=2.0"
 jeepney = ">=0.6"

+[[package]]
+name = "segtok"
+version = "1.5.11"
+description = "sentence segmentation and word tokenization tools"
+optional = false
+python-versions = "*"
+groups = ["main"]
+files = [
+    {file = "segtok-1.5.11-py3-none-any.whl", hash = "sha256:910616b76198c3141b2772df530270d3b706e42ae69a5b30ef115c7bd5d1501a"},
+    {file = "segtok-1.5.11.tar.gz", hash = "sha256:8ab2dd44245bcbfec25b575dc4618473bbdf2af8c2649698cd5a370f42f3db23"},
+]
+
+[package.dependencies]
+regex = "*"
+
 [[package]]
 name = "setuptools"
 version = "82.0.1"
@ -5450,6 +5804,21 @@ files = [
    {file = "stream_sqlite-0.0.41-py3-none-any.whl", hash = "sha256:3aa1bbf4b50eb67df7e5f56b9bbe828b31750c05c9bd883be29d15b8bdc016f5"},
 ]

+[[package]]
+name = "tabulate"
+version = "0.10.0"
+description = "Pretty-print tabular data"
+optional = false
+python-versions = ">=3.10"
+groups = ["main"]
+files = [
+    {file = "tabulate-0.10.0-py3-none-any.whl", hash = "sha256:f0b0622e567335c8fabaaa659f1b33bcb6ddfe2e496071b743aa113f8774f2d3"},
+    {file = "tabulate-0.10.0.tar.gz", hash = "sha256:e2cfde8f79420f6deeffdeda9aaec3b6bc5abce947655d17ac662b126e48a60d"},
+]
+
+[package.extras]
+widechars = ["wcwidth"]
+
 [[package]]
 name = "thefuzz"
 version = "0.22.1"
@ -6197,6 +6566,31 @@ files = [
 [package.extras]
 test = ["pytest", "pytest-cov"]

+[[package]]
+name = "yake"
+version = "0.7.3"
+description = "Keyword extraction Python package"
+optional = false
+python-versions = ">=3.10"
+groups = ["main"]
+files = [
+    {file = "yake-0.7.3-py3-none-any.whl", hash = "sha256:38f7f135ff8ed4bcdc05e16b533a9dc93299f1e694b0c308c3c086bab316c5fe"},
+    {file = "yake-0.7.3.tar.gz", hash = "sha256:8778fb2832e58d26d838d6d7ac967b4947521f1fe8cdf23dd872636161fc53ed"},
+]
+
+[package.dependencies]
+click = ">=6.0"
+jellyfish = "*"
+networkx = "*"
+numpy = ">=1.24.0"
+segtok = "*"
+tabulate = "*"
+
+[package.extras]
+benchmark = ["matplotlib (>=3.5.0)", "memory-profiler (>=0.60.0)", "pytest-benchmark (>=4.0.0)"]
+dev = ["black (>=22.0.0)", "flake8 (>=6.0.0)", "pylint (>=3.3.0)", "pytest (>=7.0.0)", "pytest-cov (>=4.0.0)", "ruff (>=0.1.0)"]
+lemmatization = ["nltk (>=3.8.0)", "spacy (>=3.8.0)"]
+
 [[package]]
 name = "yarl"
 version = "1.23.0"
@ -6476,4 +6870,4 @@ cffi = ["cffi (>=1.17,<2.0) ; platform_python_implementation != \"PyPy\" and pyt
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.11,<3.15"
-content-hash = "02f8b551a54c53fa2a51622af17ef844e40aa8505c395ed02a7b87eb05647cc5"
+content-hash = "8b1c608beddabe6884d4c2614170ccd71986daccb7db3944cb36531937fdee4e"
--- a/pyproject.toml
+++ b/pyproject.toml
@ -1,6 +1,6 @@
 [tool.poetry]
 name = "vrobbler"
-version = "57.1"
+version = "58.2"
 description = ""
 authors = ["Colin Powell <colin@unbl.ink>"]

@ -11,6 +11,8 @@ django-extensions = "^3.1.5"
 python-dateutil = "^2.8.2"
 python-dotenv = ">=0.20.0,<2"
 python-json-logger = "^2.0.2"
+cloudscraper = "^1.2.71"
+curl-cffi = "^0.15.0"
 colorlog = "^6.6.0"
 httpx = "<=0.27.2"
 djangorestframework = "^3.13.1"
@ -66,6 +68,7 @@ lxml = ">=5.5.0"
 vaderSentiment = "^3.3.2"
 sqids = "^0.5.2"
 python-amazon-paapi = "^6.3.0"
+yake = "^0.7.3"

 [tool.poetry.group.test]
 optional = true
--- a/vrobbler/apps/books/admin.py
+++ b/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"
--- a/vrobbler/apps/books/migrations/0038_paper_pdf_file.py
+++ b/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/"),
+        ),
+    ]
--- a/vrobbler/apps/books/migrations/0039_journal_alter_paper_journal.py
+++ b/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",
+        ),
+    ]
--- a/vrobbler/apps/books/models.py
+++ b/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
--- a/vrobbler/apps/books/sources/crossref.py
+++ b/vrobbler/apps/books/sources/crossref.py
@ -0,0 +1,149 @@
+import json
+import logging
+import re
+
+import requests
+import yake
+
+CROSSREF_WORK_URL = "https://api.crossref.org/works/{}"
+
+logger = logging.getLogger(__name__)
+
+_STOPWORDS = {
+    "this", "that", "these", "those", "the", "a", "an", "in", "on", "at",
+    "to", "for", "of", "and", "or", "is", "are", "was", "were", "be",
+    "been", "being", "have", "has", "had", "do", "does", "did", "will",
+    "would", "can", "could", "may", "might", "shall", "should", "not",
+    "no", "nor", "with", "from", "by", "as", "at", "but", "if", "because",
+    "while", "although", "however", "we", "our", "their", "its", "it",
+    "they", "them", "also", "more", "most", "new", "such", "into",
+    "across", "between", "through", "about", "after", "before", "during",
+    "within", "without", "other", "many", "some", "each", "every", "both",
+    "few", "own", "via",
+}
+
+_DROP_PHRASES = {
+    "paper", "study", "studies", "research", "introduction", "conclusion",
+    "conclusions", "background", "methods", "results", "findings",
+    "analysis", "approach", "approaches", "framework", "theory",
+    "theories", "concept", "concepts", "model", "models", "process",
+    "processes", "role", "roles", "factor", "factors", "effect",
+    "effects", "impact", "implication", "implications", "actor", "actors",
+    "article", "chapter", "section", "discussion", "review", "overview",
+    "summary", "methodology", "special issue", "implications",
+    "limitations", "findings", "purpose", "objective", "objectives",
+    "design", "setting", "participants", "sample", "data",
+    "contemporary", "little", "empirical", "theoretical",
+    "organizations", "dissent",
+}
+
+
+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 _extract_genres_from_abstract(abstract: str, max_keywords: int = 8) -> list[str]:
+    if not abstract or len(abstract) < 50:
+        return []
+    kw_extractor = yake.KeywordExtractor(lan="en", n=2, top=max_keywords)
+    keywords = kw_extractor.extract_keywords(abstract)
+    genres = []
+    seen = set()
+    for kw, score in keywords:
+        kw_lower = kw.lower().strip()
+        if kw_lower in seen or kw_lower in _DROP_PHRASES:
+            continue
+        words = [w for w in kw_lower.split() if w not in _STOPWORDS]
+        cleaned = " ".join(words)
+        if not cleaned or len(cleaned) < 3 or cleaned in seen:
+            continue
+        if cleaned in _DROP_PHRASES:
+            continue
+        seen.add(cleaned)
+        genres.append(cleaned)
+    return genres
+
+
+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:
+        stripped = _strip_jats(abstract)
+        paper_dict["abstract"] = stripped
+        genres = _extract_genres_from_abstract(stripped)
+        if genres:
+            paper_dict["genres"] = genres
+
+    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
--- a/vrobbler/apps/books/sources/scihub.py
+++ b/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
--- a/vrobbler/apps/books/sources/semantic.py
+++ b/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
--- a/vrobbler/apps/books/urls.py
+++ b/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",
+    ),
 ]
--- a/vrobbler/apps/books/views.py
+++ b/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]))
--- a/vrobbler/apps/scrobbles/constants.py
+++ b/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",
 }


--- a/vrobbler/apps/scrobbles/models.py
+++ b/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
--- a/vrobbler/apps/scrobbles/scrobblers.py
+++ b/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,
--- a/vrobbler/apps/scrobbles/views.py
+++ b/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)

--- a/vrobbler/apps/trends/templates/trends/_time_of_day_categories.html
+++ b/vrobbler/apps/trends/templates/trends/_time_of_day_categories.html
@ -0,0 +1,65 @@
+<div class="row">
+  <div class="col-12">
+    {% if data.total and data.total > 0 %}
+    <h5>Overall</h5>
+    <div class="table-responsive mb-4">
+      <table class="table table-striped table-sm">
+        <thead>
+          <tr>
+            <th>Category</th>
+            <th class="text-end">Scrobbles</th>
+            <th class="text-end">%</th>
+          </tr>
+        </thead>
+        <tbody>
+          {% for slug, info in data.categories.items %}
+          <tr>
+            <td>{{ info.label }}</td>
+            <td class="text-end">{{ info.count }}</td>
+            <td class="text-end">{{ info.pct }}%</td>
+          </tr>
+          {% endfor %}
+          <tr class="table-secondary">
+            <td><strong>Total</strong></td>
+            <td class="text-end"><strong>{{ data.total }}</strong></td>
+            <td class="text-end"></td>
+          </tr>
+        </tbody>
+      </table>
+    </div>
+
+    <h5>By Media Type</h5>
+    {% for mt, mt_data in data.by_media_type.items %}
+    <h6 class="mt-3">{{ mt }}</h6>
+    <div class="table-responsive">
+      <table class="table table-striped table-sm">
+        <thead>
+          <tr>
+            <th>Category</th>
+            <th class="text-end">Scrobbles</th>
+            <th class="text-end">%</th>
+          </tr>
+        </thead>
+        <tbody>
+          {% for slug, info in mt_data.categories.items %}
+          <tr>
+            <td>{{ info.label }}</td>
+            <td class="text-end">{{ info.count }}</td>
+            <td class="text-end">{{ info.pct }}%</td>
+          </tr>
+          {% endfor %}
+          <tr class="table-secondary">
+            <td><strong>Total</strong></td>
+            <td class="text-end"><strong>{{ mt_data.total }}</strong></td>
+            <td class="text-end"></td>
+          </tr>
+        </tbody>
+      </table>
+    </div>
+    {% endfor %}
+
+    {% else %}
+    <p class="text-muted">No data found for Books, Trails, Birding Locations, or Board Games in this period.</p>
+    {% endif %}
+  </div>
+</div>
--- a/vrobbler/apps/trends/templates/trends/trend_detail.html
+++ b/vrobbler/apps/trends/templates/trends/trend_detail.html
@ -55,6 +55,9 @@
 {% elif trend.slug == "reading-pace-vs-activity" %}
  {% include "trends/_reading_pace.html" %}

+{% elif trend.slug == "time-of-day-categories" %}
+  {% include "trends/_time_of_day_categories.html" %}
+
 {% elif trend.slug == "trending-up" %}
  {% include "trends/_trending_up.html" %}

--- a/vrobbler/apps/trends/trends/init.py
+++ b/vrobbler/apps/trends/trends/init.py
@ -15,6 +15,7 @@ from trends.trends.mood import (
    compute_mood_weather,
 )
 from trends.trends.reading import compute_reading_pace_vs_activity
+from trends.trends.time_of_day import compute_time_of_day_categories
 from trends.trends.trending import compute_trending_up

 TREND_REGISTRY = {}
@ -44,5 +45,8 @@ compute_peak_hours = register("peak-hours")(compute_peak_hours)
 compute_reading_pace_vs_activity = register("reading-pace-vs-activity")(
    compute_reading_pace_vs_activity
 )
+compute_time_of_day_categories = register("time-of-day-categories")(
+    compute_time_of_day_categories
+)
 compute_trending_up = register("trending-up")(compute_trending_up)
 compute_weekly_rhythm = register("weekly-rhythm")(compute_weekly_rhythm)
--- a/vrobbler/apps/trends/trends/time_of_day.py
+++ b/vrobbler/apps/trends/trends/time_of_day.py
@ -0,0 +1,89 @@
+from collections import OrderedDict
+
+from django.db.models import Count, Q
+from django.db.models.functions import Extract
+from scrobbles.models import Scrobble
+
+
+TARGET_MEDIA_TYPES = ["Book", "Trail", "BirdingLocation", "BoardGame"]
+
+CATEGORIES = OrderedDict(
+    [
+        ("early_bird", {"label": "Early Bird", "hours": {5, 6, 7, 8, 9, 10}}),
+        ("day_jay", {"label": "Day Jay", "hours": {11, 12, 13, 14, 15, 16, 17, 18}}),
+        ("night_owl", {"label": "Night Owl", "hours": {19, 20, 21, 22, 23, 0, 1, 2, 3, 4}}),
+    ]
+)
+
+
+def _categorize_hour(hour):
+    for slug, cat in CATEGORIES.items():
+        if hour in cat["hours"]:
+            return slug
+    return None
+
+
+def compute_time_of_day_categories(user, period="last_30"):
+    from trends.utils import get_date_range
+
+    start, end = get_date_range(period)
+    filters = Q(user=user, media_type__in=TARGET_MEDIA_TYPES, timestamp__isnull=False)
+    if start:
+        filters &= Q(timestamp__gte=start)
+    if end:
+        filters &= Q(timestamp__lte=end)
+
+    qs = (
+        Scrobble.objects.filter(filters)
+        .annotate(hour=Extract("timestamp", "hour"))
+        .values("media_type", "hour")
+        .annotate(count=Count("id"))
+        .order_by("media_type", "hour")
+    )
+
+    raw = {}
+    for row in qs:
+        mt = row["media_type"]
+        raw.setdefault(mt, {})[row["hour"]] = row["count"]
+
+    by_media_type = {}
+    grand_totals = {"early_bird": 0, "day_jay": 0, "night_owl": 0}
+    grand_total = 0
+
+    for mt in TARGET_MEDIA_TYPES:
+        mt_data = raw.get(mt, {})
+        cat_counts = {"early_bird": 0, "day_jay": 0, "night_owl": 0}
+        mt_total = 0
+        for hour, count in mt_data.items():
+            slug = _categorize_hour(hour)
+            if slug:
+                cat_counts[slug] += count
+                mt_total += count
+        by_media_type[mt] = {
+            "total": mt_total,
+            "categories": {},
+        }
+        for slug in CATEGORIES:
+            c = cat_counts[slug]
+            by_media_type[mt]["categories"][slug] = {
+                "count": c,
+                "pct": round((c / mt_total * 100), 1) if mt_total else 0,
+                "label": CATEGORIES[slug]["label"],
+            }
+            grand_totals[slug] += c
+        grand_total += mt_total
+
+    categories = {}
+    for slug in CATEGORIES:
+        c = grand_totals[slug]
+        categories[slug] = {
+            "count": c,
+            "pct": round((c / grand_total * 100), 1) if grand_total else 0,
+            "label": CATEGORIES[slug]["label"],
+        }
+
+    return {
+        "categories": categories,
+        "total": grand_total,
+        "by_media_type": by_media_type,
+    }
--- a/vrobbler/apps/trends/utils.py
+++ b/vrobbler/apps/trends/utils.py
@ -25,6 +25,7 @@ TIME_BOUND_TRENDS = {
    "mood-weather",
    "peak-hours",
    "reading-pace-vs-activity",
+    "time-of-day-categories",
    "trending-up",
    "weekly-rhythm",
 }
--- a/vrobbler/apps/trends/views.py
+++ b/vrobbler/apps/trends/views.py
@ -55,6 +55,11 @@ TREND_METADATA = {
        "description": "Compare how long you read per session with and without concurrent music.",
        "icon": "📊",
    },
+    "time-of-day-categories": {
+        "title": "Time of Day Categories",
+        "description": "Are you an early bird, day jay, or night owl? Categorized by Books, Trails, Birding Locations, and Board Games.",
+        "icon": "🦉",
+    },
    "trending-up": {
        "title": "Trending Media Types",
        "description": "Which media types have you been consuming more or less of recently?",
--- a/vrobbler/apps/webpages/models.py
+++ b/vrobbler/apps/webpages/models.py
@ -2,6 +2,8 @@ import logging
 from typing import Dict, Optional
 from uuid import uuid4

+import cloudscraper
+from curl_cffi import requests as curl_requests
 import pendulum
 import requests
 import trafilatura
@ -45,6 +47,37 @@ class Domain(TimeStampedModel):
        )


+def _fetch_url_raw(url: str) -> Optional[str]:
+    """Fetch raw HTML for a URL.
+
+    Tries three strategies in order:
+      1. trafilatura (standard, works for most sites)
+      2. cloudscraper   (handles basic Cloudflare JS challenges)
+      3. curl_cffi      (impersonates browser TLS fingerprint for aggressive
+                         Cloudflare / bot detection)
+    """
+    raw = trafilatura.fetch_url(url)
+    if raw:
+        return raw
+    logger.debug("trafilatura returned nothing for %s, trying cloudscraper", url)
+    try:
+        scraper = cloudscraper.create_scraper()
+        resp = scraper.get(url, timeout=30)
+        resp.raise_for_status()
+        return resp.text
+    except Exception as exc:
+        logger.debug("cloudscraper failed for %s: %s, trying curl_cffi", url, exc)
+    try:
+        resp = curl_requests.get(
+            url, impersonate="chrome124", timeout=30
+        )
+        resp.raise_for_status()
+        return resp.text
+    except Exception as e:
+        logger.warning("curl_cffi also failed for %s: %s", url, e)
+        return None
+
+
 class WebPage(ScrobblableMixin):
    COMPLETION_PERCENT = getattr(settings, "WEBSITE_COMPLETION_PERCENT", 100)

@ -80,7 +113,7 @@ class WebPage(ScrobblableMixin):

    def _update_extract_from_web(self, raw_text: str = "", force=True):
        if not raw_text:
-            raw_text = requests.get(self.url, headers=headers).text
+            raw_text = _fetch_url_raw(self.url)
        if not self.extract or force:
            self.extract = trafilatura.extract(raw_text)
            self.save(update_fields=["extract"])
@ -259,7 +292,7 @@ class WebPage(ScrobblableMixin):
            return False

    def fetch_data_from_web(self, save=True, force=True):
-        raw_text = trafilatura.fetch_url(self.url)
+        raw_text = _fetch_url_raw(self.url)
        if not self.extract or force:
            self.extract = trafilatura.extract(
                raw_text,
--- a/vrobbler/settings.py
+++ b/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"

--- a/vrobbler/templates/books/paper_detail.html
+++ b/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 %}
--- a/vrobbler/templates/books/paper_list.html
+++ b/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 %}
Author	SHA1	Message	Date
Colin Powell	5e0dffdc7a	[release] Bump to version 58.2 Some checks failed build / test (push) Successful in 2m5s Details deploy / test (push) Successful in 2m3s Details deploy / build-and-deploy (push) Failing after 25s Details - Add more robust webpage scraping - Time of Day Categories trend	2026-06-23 23:04:48 -04:00
Colin Powell	2283a6c640	[webpages] Add more robust scraping	2026-06-23 23:04:30 -04:00
Colin Powell	327ba94c63	[trends] Add new time of day trend All checks were successful build / test (push) Successful in 2m4s Details	2026-06-23 22:21:18 -04:00
Colin Powell	ee59cde882	[release] Bump to version 58.1 All checks were successful build / test (push) Successful in 2m7s Details deploy / test (push) Successful in 2m8s Details deploy / build-and-deploy (push) Successful in 1m5s Details - Add auto genre tagging for papers	2026-06-23 16:19:06 -04:00
Colin Powell	c7b4656679	[papers] Add genre tagging	2026-06-23 16:18:50 -04:00
Colin Powell	04f9e00c9c	[release] Bump to version 58.0 All checks were successful deploy / test (push) Successful in 2m7s Details build / test (push) Successful in 2m3s Details deploy / build-and-deploy (push) Successful in 1m2s Details - Add scrobbling of Papers via webpages with doi.org links in them	2026-06-23 14:28:40 -04:00
Colin Powell	c2dabd1dac	[papers] Fix scrobbling of academic papers	2026-06-23 14:28:16 -04:00