feat: added requirements.txt for HF compat

poetry.lock

@@ -229,6 +229,14 @@ python-versions = "*"
 [package.extras]
 test = ["flake8 (3.7.8)", "hypothesis (3.55.3)"]
 
+[[package]]
+name = "cssselect"
+version = "1.1.0"
+description = "cssselect parses CSS3 Selectors and translates them to XPath 1.0"
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+
 [[package]]
 name = "cymem"
 version = "2.0.6"
@@ -302,6 +310,42 @@ python-versions = "*"
 [package.extras]
 devel = ["colorama", "jsonschema", "json-spec", "pylint", "pytest", "pytest-benchmark", "pytest-cache", "validictory"]
 
+[[package]]
+name = "feedfinder2"
+version = "0.0.4"
+description = "Find the feed URLs for a website."
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+beautifulsoup4 = "*"
+requests = "*"
+six = "*"
+
+[[package]]
+name = "feedparser"
+version = "6.0.10"
+description = "Universal feed parser, handles RSS 0.9x, RSS 1.0, RSS 2.0, CDF, Atom 0.3, and Atom 1.0 feeds"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[package.dependencies]
+sgmllib3k = "*"
+
+[[package]]
+name = "filelock"
+version = "3.7.1"
+description = "A platform independent file lock."
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.extras]
+docs = ["furo (>=2021.8.17b43)", "sphinx (>=4.1)", "sphinx-autodoc-typehints (>=1.12)"]
+testing = ["covdefaults (>=1.2.0)", "coverage (>=4)", "pytest (>=4)", "pytest-cov", "pytest-timeout (>=1.4.2)"]
+
 [[package]]
 name = "gitdb"
 version = "4.0.9"
@@ -338,7 +382,6 @@ spacy = ">=3.3.0,<3.4.0"
 [package.source]
 type = "url"
 url = "https://huggingface.co/huspacy/hu_core_news_lg/resolve/v3.3.0/hu_core_news_lg-any-py3-none-any.whl"
-
 [[package]]
 name = "idna"
 version = "3.3"
@@ -487,6 +530,14 @@ category = "main"
 optional = false
 python-versions = ">3.6"
 
+[[package]]
+name = "jieba3k"
+version = "0.35.1"
+description = "Chinese Words Segementation Utilities"
+category = "main"
+optional = false
+python-versions = "*"
+
 [[package]]
 name = "jinja2"
 version = "3.1.2"
@@ -589,6 +640,20 @@ python-versions = ">=3.6"
 [package.extras]
 data = ["language-data (>=1.1,<2.0)"]
 
+[[package]]
+name = "lxml"
+version = "4.9.0"
+description = "Powerful and Pythonic XML processing library combining libxml2/libxslt with the ElementTree API."
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, != 3.4.*"
+
+[package.extras]
+cssselect = ["cssselect (>=0.7)"]
+html5 = ["html5lib"]
+htmlsoup = ["beautifulsoup4"]
+source = ["Cython (>=0.29.7)"]
+
 [[package]]
 name = "markupsafe"
 version = "2.1.1"
@@ -715,6 +780,51 @@ doc = ["sphinx (>=4.5)", "pydata-sphinx-theme (>=0.8.1)", "sphinx-gallery (>=0.1
 extra = ["lxml (>=4.6)", "pygraphviz (>=1.9)", "pydot (>=1.4.2)", "sympy (>=1.10)"]
 test = ["pytest (>=7.1)", "pytest-cov (>=3.0)", "codecov (>=2.1)"]
 
+[[package]]
+name = "newspaper3k"
+version = "0.2.8"
+description = "Simplified python article discovery & extraction."
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+beautifulsoup4 = ">=4.4.1"
+cssselect = ">=0.9.2"
+feedfinder2 = ">=0.0.4"
+feedparser = ">=5.2.1"
+jieba3k = ">=0.35.1"
+lxml = ">=3.6.0"
+nltk = ">=3.2.1"
+Pillow = ">=3.3.0"
+python-dateutil = ">=2.5.3"
+PyYAML = ">=3.11"
+requests = ">=2.10.0"
+tinysegmenter = "0.3"
+tldextract = ">=2.0.1"
+
+[[package]]
+name = "nltk"
+version = "3.7"
+description = "Natural Language Toolkit"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.dependencies]
+click = "*"
+joblib = "*"
+regex = ">=2021.8.3"
+tqdm = "*"
+
+[package.extras]
+all = ["numpy", "pyparsing", "scipy", "matplotlib", "twython", "requests", "scikit-learn", "python-crfsuite"]
+corenlp = ["requests"]
+machine_learning = ["numpy", "python-crfsuite", "scikit-learn", "scipy"]
+plot = ["matplotlib"]
+tgrep = ["pyparsing"]
+twitter = ["twython"]
+
 [[package]]
 name = "notebook"
 version = "6.4.11"
@@ -1079,6 +1189,14 @@ category = "main"
 optional = false
 python-versions = ">=3.7"
 
+[[package]]
+name = "pyyaml"
+version = "6.0"
+description = "YAML parser and emitter for Python"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
 [[package]]
 name = "pyzmq"
 version = "23.1.0"
@@ -1091,6 +1209,14 @@ python-versions = ">=3.6"
 cffi = {version = "*", markers = "implementation_name == \"pypy\""}
 py = {version = "*", markers = "implementation_name == \"pypy\""}
 
+[[package]]
+name = "regex"
+version = "2022.6.2"
+description = "Alternative regular expression module, to replace re."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
 [[package]]
 name = "requests"
 version = "2.27.1"
@@ -1109,6 +1235,18 @@ urllib3 = ">=1.21.1,<1.27"
 socks = ["PySocks (>=1.5.6,<1.5.7 || >1.5.7)", "win-inet-pton"]
 use_chardet_on_py3 = ["chardet (>=3.0.2,<5)"]
 
+[[package]]
+name = "requests-file"
+version = "1.5.1"
+description = "File transport adapter for Requests"
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+requests = ">=1.0.0"
+six = "*"
+
 [[package]]
 name = "rich"
 version = "12.4.4"
@@ -1177,6 +1315,14 @@ nativelib = ["pyobjc-framework-cocoa", "pywin32"]
 objc = ["pyobjc-framework-cocoa"]
 win32 = ["pywin32"]
 
+[[package]]
+name = "sgmllib3k"
+version = "1.0.0"
+description = "Py3k port of sgmllib."
+category = "main"
+optional = false
+python-versions = "*"
+
 [[package]]
 name = "six"
 version = "1.16.0"
@@ -1459,6 +1605,28 @@ webencodings = ">=0.4"
 doc = ["sphinx", "sphinx-rtd-theme"]
 test = ["pytest", "pytest-cov", "pytest-flake8", "pytest-isort", "coverage"]
 
+[[package]]
+name = "tinysegmenter"
+version = "0.3"
+description = "Very compact Japanese tokenizer"
+category = "main"
+optional = false
+python-versions = "*"
+
+[[package]]
+name = "tldextract"
+version = "3.3.0"
+description = "Accurately separates a URL's subdomain, domain, and public suffix, using the Public Suffix List (PSL). By default, this includes the public ICANN TLDs and their exceptions. You can optionally support the Public Suffix List's private domains as well."
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.dependencies]
+filelock = ">=3.0.8"
+idna = "*"
+requests = ">=2.1.0"
+requests-file = ">=1.4"
+
 [[package]]
 name = "toml"
 version = "0.10.2"
@@ -1649,7 +1817,7 @@ testing = ["pytest (>=6)", "pytest-checkdocs (>=2.4)", "pytest-flake8", "pytest-
 [metadata]
 lock-version = "1.1"
 python-versions = "~3.8"
-content-hash = "f4950c6f3a93af04905bf1cd400912855245417543200151f7ceed94c61f7966"
+content-hash = "df6aee0aabce896402df340d7e5c5972acb3b2c87a7dde39580dceaa31e7c8e5"
 
 [metadata.files]
 altair = [
@@ -1826,6 +1994,10 @@ commonmark = [
     {file = "commonmark-0.9.1-py2.py3-none-any.whl", hash = "sha256:da2f38c92590f83de410ba1a3cbceafbc74fee9def35f9251ba9a971d6d66fd9"},
     {file = "commonmark-0.9.1.tar.gz", hash = "sha256:452f9dc859be7f06631ddcb328b6919c67984aca654e5fefb3914d54691aed60"},
 ]
+cssselect = [
+    {file = "cssselect-1.1.0-py2.py3-none-any.whl", hash = "sha256:f612ee47b749c877ebae5bb77035d8f4202c6ad0f0fc1271b3c18ad6c4468ecf"},
+    {file = "cssselect-1.1.0.tar.gz", hash = "sha256:f95f8dedd925fd8f54edb3d2dfb44c190d9d18512377d3c1e2388d16126879bc"},
+]
 cymem = [
     {file = "cymem-2.0.6-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:700540b68e96a7056d0691d467df2bbaaf0934a3e6fe2383669998cbee19580a"},
     {file = "cymem-2.0.6-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:971cf0a8437dfb4185c3049c086e463612fe849efadc0f5cc153fc81c501da7d"},
@@ -1887,6 +2059,17 @@ fastjsonschema = [
     {file = "fastjsonschema-2.15.3-py3-none-any.whl", hash = "sha256:ddb0b1d8243e6e3abb822bd14e447a89f4ab7439342912d590444831fa00b6a0"},
     {file = "fastjsonschema-2.15.3.tar.gz", hash = "sha256:0a572f0836962d844c1fc435e200b2e4f4677e4e6611a2e3bdd01ba697c275ec"},
 ]
+feedfinder2 = [
+    {file = "feedfinder2-0.0.4.tar.gz", hash = "sha256:3701ee01a6c85f8b865a049c30ba0b4608858c803fe8e30d1d289fdbe89d0efe"},
+]
+feedparser = [
+    {file = "feedparser-6.0.10-py3-none-any.whl", hash = "sha256:79c257d526d13b944e965f6095700587f27388e50ea16fd245babe4dfae7024f"},
+    {file = "feedparser-6.0.10.tar.gz", hash = "sha256:27da485f4637ce7163cdeab13a80312b93b7d0c1b775bef4a47629a3110bca51"},
+]
+filelock = [
+    {file = "filelock-3.7.1-py3-none-any.whl", hash = "sha256:37def7b658813cda163b56fc564cdc75e86d338246458c4c28ae84cabefa2404"},
+    {file = "filelock-3.7.1.tar.gz", hash = "sha256:3a0fd85166ad9dbab54c9aec96737b744106dc5f15c0b09a6744a445299fcf04"},
+]
 gitdb = [
     {file = "gitdb-4.0.9-py3-none-any.whl", hash = "sha256:8033ad4e853066ba6ca92050b9df2f89301b8fc8bf7e9324d412a63f8bf1a8fd"},
     {file = "gitdb-4.0.9.tar.gz", hash = "sha256:bac2fd45c0a1c9cf619e63a90d62bdc63892ef92387424b855792a6cabe789aa"},
@@ -1943,6 +2126,9 @@ jellyfish = [
     {file = "jellyfish-0.9.0-cp39-cp39-win_amd64.whl", hash = "sha256:8759c6d34f1bea5860ab5807968399b9dd259c703f6c5071fcd5703bf7a00d99"},
     {file = "jellyfish-0.9.0.tar.gz", hash = "sha256:40c9a2ffd8bd3016f7611d424120442f627f56d518a106847dc93f0ead6ad79a"},
 ]
+jieba3k = [
+    {file = "jieba3k-0.35.1.zip", hash = "sha256:980a4f2636b778d312518066be90c7697d410dd5a472385f5afced71a2db1c10"},
+]
 jinja2 = [
     {file = "Jinja2-3.1.2-py3-none-any.whl", hash = "sha256:6088930bfe239f0e6710546ab9c19c9ef35e29792895fed6e6e31a023a182a61"},
     {file = "Jinja2-3.1.2.tar.gz", hash = "sha256:31351a702a408a9e7595a8fc6150fc3f43bb6bf7e319770cbc0db9df9437e852"},
@@ -1975,6 +2161,71 @@ langcodes = [
     {file = "langcodes-3.3.0-py3-none-any.whl", hash = "sha256:4d89fc9acb6e9c8fdef70bcdf376113a3db09b67285d9e1d534de6d8818e7e69"},
     {file = "langcodes-3.3.0.tar.gz", hash = "sha256:794d07d5a28781231ac335a1561b8442f8648ca07cd518310aeb45d6f0807ef6"},
 ]
+lxml = [
+    {file = "lxml-4.9.0-cp27-cp27m-macosx_10_15_x86_64.whl", hash = "sha256:b5031d151d6147eac53366d6ec87da84cd4d8c5e80b1d9948a667a7164116e39"},
+    {file = "lxml-4.9.0-cp27-cp27m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:5d52e1173f52020392f593f87a6af2d4055dd800574a5cb0af4ea3878801d307"},
+    {file = "lxml-4.9.0-cp27-cp27m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:3af00ee88376022589ceeb8170eb67dacf5f7cd625ea59fa0977d719777d4ae8"},
+    {file = "lxml-4.9.0-cp27-cp27m-win32.whl", hash = "sha256:1057356b808d149bc14eb8f37bb89129f237df488661c1e0fc0376ca90e1d2c3"},
+    {file = "lxml-4.9.0-cp27-cp27m-win_amd64.whl", hash = "sha256:f6d23a01921b741774f35e924d418a43cf03eca1444f3fdfd7978d35a5aaab8b"},
+    {file = "lxml-4.9.0-cp27-cp27mu-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:56e19fb6e4b8bd07fb20028d03d3bc67bcc0621347fbde64f248e44839771756"},
+    {file = "lxml-4.9.0-cp27-cp27mu-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:4cd69bca464e892ea4ed544ba6a7850aaff6f8d792f8055a10638db60acbac18"},
+    {file = "lxml-4.9.0-cp310-cp310-macosx_10_15_x86_64.whl", hash = "sha256:94b181dd2777890139e49a5336bf3a9a3378ce66132c665fe8db4e8b7683cde2"},
+    {file = "lxml-4.9.0-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:607224ffae9a0cf0a2f6e14f5f6bce43e83a6fbdaa647891729c103bdd6a5593"},
+    {file = "lxml-4.9.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:11d62c97ceff9bab94b6b29c010ea5fb6831743459bb759c917f49ba75601cd0"},
+    {file = "lxml-4.9.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:70a198030d26f5e569367f0f04509b63256faa76a22886280eea69a4f535dd40"},
+    {file = "lxml-4.9.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:3cf816aed8125cfc9e6e5c6c31ff94278320d591bd7970c4a0233bee0d1c8790"},
+    {file = "lxml-4.9.0-cp310-cp310-win32.whl", hash = "sha256:65b3b5f12c6fb5611e79157214f3cd533083f9b058bf2fc8a1c5cc5ee40fdc5a"},
+    {file = "lxml-4.9.0-cp310-cp310-win_amd64.whl", hash = "sha256:0aa4cce579512c33373ca4c5e23c21e40c1aa1a33533a75e51b654834fd0e4f2"},
+    {file = "lxml-4.9.0-cp35-cp35m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:63419db39df8dc5564f6f103102c4665f7e4d9cb64030e98cf7a74eae5d5760d"},
+    {file = "lxml-4.9.0-cp35-cp35m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:d8e5021e770b0a3084c30dda5901d5fce6d4474feaf0ced8f8e5a82702502fbb"},
+    {file = "lxml-4.9.0-cp35-cp35m-win32.whl", hash = "sha256:f17b9df97c5ecdfb56c5e85b3c9df9831246df698f8581c6e111ac664c7c656e"},
+    {file = "lxml-4.9.0-cp35-cp35m-win_amd64.whl", hash = "sha256:75da29a0752c8f2395df0115ac1681cefbdd4418676015be8178b733704cbff2"},
+    {file = "lxml-4.9.0-cp36-cp36m-macosx_10_15_x86_64.whl", hash = "sha256:e4d020ecf3740b7312bacab2cb966bb720fd4d3490562d373b4ad91dd1857c0d"},
+    {file = "lxml-4.9.0-cp36-cp36m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:b71c52d69b91af7d18c13aef1b0cc3baee36b78607c711eb14a52bf3aa7c815e"},
+    {file = "lxml-4.9.0-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:28cf04a1a38e961d4a764d2940af9b941b66263ed5584392ef875ee9c1e360a3"},
+    {file = "lxml-4.9.0-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:915ecf7d486df17cc65aeefdb680d5ad4390cc8c857cf8db3fe241ed234f856a"},
+    {file = "lxml-4.9.0-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:e564d5a771b4015f34166a05ea2165b7e283635c41b1347696117f780084b46d"},
+    {file = "lxml-4.9.0-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:c2a57755e366e0ac7ebdb3e9207f159c3bf1afed02392ab18453ce81f5ee92ee"},
+    {file = "lxml-4.9.0-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:00f3a6f88fd5f4357844dd91a1abac5f466c6799f1b7f1da2df6665253845b11"},
+    {file = "lxml-4.9.0-cp36-cp36m-win32.whl", hash = "sha256:9093a359a86650a3dbd6532c3e4d21a6f58ba2cb60d0e72db0848115d24c10ba"},
+    {file = "lxml-4.9.0-cp36-cp36m-win_amd64.whl", hash = "sha256:d1690c4d37674a5f0cdafbc5ed7e360800afcf06928c2a024c779c046891bf09"},
+    {file = "lxml-4.9.0-cp37-cp37m-macosx_10_15_x86_64.whl", hash = "sha256:6af7f51a6010748fc1bb71917318d953c9673e4ae3f6d285aaf93ef5b2eb11c1"},
+    {file = "lxml-4.9.0-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:eabdbe04ee0a7e760fa6cd9e799d2b020d098c580ba99107d52e1e5e538b1ecb"},
+    {file = "lxml-4.9.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:b1e22f3ee4d75ca261b6bffbf64f6f178cb194b1be3191065a09f8d98828daa9"},
+    {file = "lxml-4.9.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:53b0410b220766321759f7f9066da67b1d0d4a7f6636a477984cbb1d98483955"},
+    {file = "lxml-4.9.0-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:d76da27f5e3e9bc40eba6ed7a9e985f57547e98cf20521d91215707f2fb57e0f"},
+    {file = "lxml-4.9.0-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:686565ac77ff94a8965c11829af253d9e2ce3bf0d9225b1d2eb5c4d4666d0dca"},
+    {file = "lxml-4.9.0-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:b62d1431b4c40cda43cc986f19b8c86b1d2ae8918cfc00f4776fdf070b65c0c4"},
+    {file = "lxml-4.9.0-cp37-cp37m-win32.whl", hash = "sha256:4becd16750ca5c2a1b1588269322b2cebd10c07738f336c922b658dbab96a61c"},
+    {file = "lxml-4.9.0-cp37-cp37m-win_amd64.whl", hash = "sha256:e35a298691b9e10e5a5631f8f0ba605b30ebe19208dc8f58b670462f53753641"},
+    {file = "lxml-4.9.0-cp38-cp38-macosx_10_15_x86_64.whl", hash = "sha256:aa7447bf7c1a15ef24e2b86a277b585dd3f055e8890ac7f97374d170187daa97"},
+    {file = "lxml-4.9.0-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:612ef8f2795a89ba3a1d4c8c1af84d8453fd53ee611aa5ad460fdd2cab426fc2"},
+    {file = "lxml-4.9.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:1bfb791a8fcdbf55d1d41b8be940393687bec0e9b12733f0796668086d1a23ff"},
+    {file = "lxml-4.9.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:024684e0c5cfa121c22140d3a0898a3a9b2ea0f0fd2c229b6658af4bdf1155e5"},
+    {file = "lxml-4.9.0-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:81c29c8741fa07ecec8ec7417c3d8d1e2f18cf5a10a280f4e1c3f8c3590228b2"},
+    {file = "lxml-4.9.0-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:6467626fa74f96f4d80fc6ec2555799e97fff8f36e0bfc7f67769f83e59cff40"},
+    {file = "lxml-4.9.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:9cae837b988f44925d14d048fa6a8c54f197c8b1223fd9ee9c27084f84606143"},
+    {file = "lxml-4.9.0-cp38-cp38-win32.whl", hash = "sha256:5a49ad78543925e1a4196e20c9c54492afa4f1502c2a563f73097e2044c75190"},
+    {file = "lxml-4.9.0-cp38-cp38-win_amd64.whl", hash = "sha256:bb7c1b029e54e26e01b1d1d912fc21abb65650d16ea9a191d026def4ed0859ed"},
+    {file = "lxml-4.9.0-cp39-cp39-macosx_10_15_x86_64.whl", hash = "sha256:d0d03b9636f1326772e6854459728676354d4c7731dae9902b180e2065ba3da6"},
+    {file = "lxml-4.9.0-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:9af19eb789d674b59a9bee5005779757aab857c40bf9cc313cb01eafac55ce55"},
+    {file = "lxml-4.9.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:dd00d28d1ab5fa7627f5abc957f29a6338a7395b724571a8cbff8fbed83aaa82"},
+    {file = "lxml-4.9.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:754a1dd04bff8a509a31146bd8f3a5dc8191a8694d582dd5fb71ff09f0722c22"},
+    {file = "lxml-4.9.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:b7679344f2270840dc5babc9ccbedbc04f7473c1f66d4676bb01680c0db85bcc"},
+    {file = "lxml-4.9.0-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:d882c2f3345261e898b9f604be76b61c901fbfa4ac32e3f51d5dc1edc89da3cb"},
+    {file = "lxml-4.9.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:4e97c8fc761ad63909198acc892f34c20f37f3baa2c50a62d5ec5d7f1efc68a1"},
+    {file = "lxml-4.9.0-cp39-cp39-win32.whl", hash = "sha256:cf9ec915857d260511399ab87e1e70fa13d6b2972258f8e620a3959468edfc32"},
+    {file = "lxml-4.9.0-cp39-cp39-win_amd64.whl", hash = "sha256:1254a79f8a67a3908de725caf59eae62d86738f6387b0a34b32e02abd6ae73db"},
+    {file = "lxml-4.9.0-pp37-pypy37_pp73-macosx_10_15_x86_64.whl", hash = "sha256:03370ec37fe562238d385e2c53089076dee53aabf8325cab964fdb04a9130fa0"},
+    {file = "lxml-4.9.0-pp37-pypy37_pp73-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:f386def57742aacc3d864169dfce644a8c396f95aa35b41b69df53f558d56dd0"},
+    {file = "lxml-4.9.0-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:ea3f2e9eb41f973f73619e88bf7bd950b16b4c2ce73d15f24a11800ce1eaf276"},
+    {file = "lxml-4.9.0-pp38-pypy38_pp73-macosx_10_15_x86_64.whl", hash = "sha256:2d10659e6e5c53298e6d718fd126e793285bff904bb71d7239a17218f6a197b7"},
+    {file = "lxml-4.9.0-pp38-pypy38_pp73-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:fcdf70191f0d1761d190a436db06a46f05af60e1410e1507935f0332280c9268"},
+    {file = "lxml-4.9.0-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:2b9c2341d96926b0d0e132e5c49ef85eb53fa92ae1c3a70f9072f3db0d32bc07"},
+    {file = "lxml-4.9.0-pp39-pypy39_pp73-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:615886ee84b6f42f1bdf1852a9669b5fe3b96b6ff27f1a7a330b67ad9911200a"},
+    {file = "lxml-4.9.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:94f2e45b054dd759bed137b6e14ae8625495f7d90ddd23cf62c7a68f72b62656"},
+    {file = "lxml-4.9.0.tar.gz", hash = "sha256:520461c36727268a989790aef08884347cd41f2d8ae855489ccf40b50321d8d7"},
+]
 markupsafe = [
     {file = "MarkupSafe-2.1.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:86b1f75c4e7c2ac2ccdaec2b9022845dbb81880ca318bb7a0a01fbf7813e3812"},
     {file = "MarkupSafe-2.1.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:f121a1420d4e173a5d96e47e9a0c0dcff965afdf1626d28de1460815f7c4ee7a"},
@@ -2063,6 +2314,14 @@ networkx = [
     {file = "networkx-2.8.2-py3-none-any.whl", hash = "sha256:51d6ae63c24dcd33901357688a2ad20d6bcd38f9a4c5307720048d3a8081059c"},
     {file = "networkx-2.8.2.tar.gz", hash = "sha256:ae99c9b0d35e5b4a62cf1cfea01e5b3633d8d02f4a0ead69685b6e7de5b85eab"},
 ]
+newspaper3k = [
+    {file = "newspaper3k-0.2.8-py3-none-any.whl", hash = "sha256:44a864222633d3081113d1030615991c3dbba87239f6bbf59d91240f71a22e3e"},
+    {file = "newspaper3k-0.2.8.tar.gz", hash = "sha256:9f1bd3e1fb48f400c715abf875cc7b0a67b7ddcd87f50c9aeeb8fcbbbd9004fb"},
+]
+nltk = [
+    {file = "nltk-3.7-py3-none-any.whl", hash = "sha256:ba3de02490308b248f9b94c8bc1ac0683e9aa2ec49ee78536d8667afb5e3eec8"},
+    {file = "nltk-3.7.zip", hash = "sha256:d6507d6460cec76d70afea4242a226a7542f85c669177b9c7f562b7cf1b05502"},
+]
 notebook = [
     {file = "notebook-6.4.11-py3-none-any.whl", hash = "sha256:b4a6baf2eba21ce67a0ca11a793d1781b06b8078f34d06c710742e55f3eee505"},
     {file = "notebook-6.4.11.tar.gz", hash = "sha256:709b1856a564fe53054796c80e17a67262071c86bfbdfa6b96aaa346113c555a"},
@@ -2414,6 +2673,41 @@ pywinpty = [
     {file = "pywinpty-2.0.5-cp39-none-win_amd64.whl", hash = "sha256:e59a508ae78374febada3e53b5bbc90b5ad07ae68cbfd72a2e965f9793ae04f3"},
     {file = "pywinpty-2.0.5.tar.gz", hash = "sha256:e125d3f1804d8804952b13e33604ad2ca8b9b2cac92b27b521c005d1604794f8"},
 ]
+pyyaml = [
+    {file = "PyYAML-6.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:d4db7c7aef085872ef65a8fd7d6d09a14ae91f691dec3e87ee5ee0539d516f53"},
+    {file = "PyYAML-6.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:9df7ed3b3d2e0ecfe09e14741b857df43adb5a3ddadc919a2d94fbdf78fea53c"},
+    {file = "PyYAML-6.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:77f396e6ef4c73fdc33a9157446466f1cff553d979bd00ecb64385760c6babdc"},
+    {file = "PyYAML-6.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a80a78046a72361de73f8f395f1f1e49f956c6be882eed58505a15f3e430962b"},
+    {file = "PyYAML-6.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:f84fbc98b019fef2ee9a1cb3ce93e3187a6df0b2538a651bfb890254ba9f90b5"},
+    {file = "PyYAML-6.0-cp310-cp310-win32.whl", hash = "sha256:2cd5df3de48857ed0544b34e2d40e9fac445930039f3cfe4bcc592a1f836d513"},
+    {file = "PyYAML-6.0-cp310-cp310-win_amd64.whl", hash = "sha256:daf496c58a8c52083df09b80c860005194014c3698698d1a57cbcfa182142a3a"},
+    {file = "PyYAML-6.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:897b80890765f037df3403d22bab41627ca8811ae55e9a722fd0392850ec4d86"},
+    {file = "PyYAML-6.0-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:50602afada6d6cbfad699b0c7bb50d5ccffa7e46a3d738092afddc1f9758427f"},
+    {file = "PyYAML-6.0-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:48c346915c114f5fdb3ead70312bd042a953a8ce5c7106d5bfb1a5254e47da92"},
+    {file = "PyYAML-6.0-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:98c4d36e99714e55cfbaaee6dd5badbc9a1ec339ebfc3b1f52e293aee6bb71a4"},
+    {file = "PyYAML-6.0-cp36-cp36m-win32.whl", hash = "sha256:0283c35a6a9fbf047493e3a0ce8d79ef5030852c51e9d911a27badfde0605293"},
+    {file = "PyYAML-6.0-cp36-cp36m-win_amd64.whl", hash = "sha256:07751360502caac1c067a8132d150cf3d61339af5691fe9e87803040dbc5db57"},
+    {file = "PyYAML-6.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:819b3830a1543db06c4d4b865e70ded25be52a2e0631ccd2f6a47a2822f2fd7c"},
+    {file = "PyYAML-6.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:473f9edb243cb1935ab5a084eb238d842fb8f404ed2193a915d1784b5a6b5fc0"},
+    {file = "PyYAML-6.0-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:0ce82d761c532fe4ec3f87fc45688bdd3a4c1dc5e0b4a19814b9009a29baefd4"},
+    {file = "PyYAML-6.0-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:231710d57adfd809ef5d34183b8ed1eeae3f76459c18fb4a0b373ad56bedcdd9"},
+    {file = "PyYAML-6.0-cp37-cp37m-win32.whl", hash = "sha256:c5687b8d43cf58545ade1fe3e055f70eac7a5a1a0bf42824308d868289a95737"},
+    {file = "PyYAML-6.0-cp37-cp37m-win_amd64.whl", hash = "sha256:d15a181d1ecd0d4270dc32edb46f7cb7733c7c508857278d3d378d14d606db2d"},
+    {file = "PyYAML-6.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:0b4624f379dab24d3725ffde76559cff63d9ec94e1736b556dacdfebe5ab6d4b"},
+    {file = "PyYAML-6.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:213c60cd50106436cc818accf5baa1aba61c0189ff610f64f4a3e8c6726218ba"},
+    {file = "PyYAML-6.0-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9fa600030013c4de8165339db93d182b9431076eb98eb40ee068700c9c813e34"},
+    {file = "PyYAML-6.0-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:277a0ef2981ca40581a47093e9e2d13b3f1fbbeffae064c1d21bfceba2030287"},
+    {file = "PyYAML-6.0-cp38-cp38-win32.whl", hash = "sha256:d4eccecf9adf6fbcc6861a38015c2a64f38b9d94838ac1810a9023a0609e1b78"},
+    {file = "PyYAML-6.0-cp38-cp38-win_amd64.whl", hash = "sha256:1e4747bc279b4f613a09eb64bba2ba602d8a6664c6ce6396a4d0cd413a50ce07"},
+    {file = "PyYAML-6.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:055d937d65826939cb044fc8c9b08889e8c743fdc6a32b33e2390f66013e449b"},
+    {file = "PyYAML-6.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:e61ceaab6f49fb8bdfaa0f92c4b57bcfbea54c09277b1b4f7ac376bfb7a7c174"},
+    {file = "PyYAML-6.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d67d839ede4ed1b28a4e8909735fc992a923cdb84e618544973d7dfc71540803"},
+    {file = "PyYAML-6.0-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:cba8c411ef271aa037d7357a2bc8f9ee8b58b9965831d9e51baf703280dc73d3"},
+    {file = "PyYAML-6.0-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:40527857252b61eacd1d9af500c3337ba8deb8fc298940291486c465c8b46ec0"},
+    {file = "PyYAML-6.0-cp39-cp39-win32.whl", hash = "sha256:b5b9eccad747aabaaffbc6064800670f0c297e52c12754eb1d976c57e4f74dcb"},
+    {file = "PyYAML-6.0-cp39-cp39-win_amd64.whl", hash = "sha256:b3d267842bf12586ba6c734f89d1f5b871df0273157918b0ccefa29deb05c21c"},
+    {file = "PyYAML-6.0.tar.gz", hash = "sha256:68fb519c14306fec9720a2a5b45bc9f0c8d1b9c72adf45c37baedfcd949c35a2"},
+]
 pyzmq = [
     {file = "pyzmq-23.1.0-cp310-cp310-macosx_10_15_universal2.whl", hash = "sha256:6d346e551fa64b89d57a4ac74b9bc66703413f02f50093e089e861999ec5cccc"},
     {file = "pyzmq-23.1.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:9c7fb691fb07ec7ab99fd173bb0e7e0248d31bf83d484a87b917a342f63812c9"},
@@ -2473,10 +2767,90 @@ pyzmq = [
     {file = "pyzmq-23.1.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:05ec90a8da618f2398f9d1aa20b18a9ef332992c6ac23e8c866099faad6ef0d6"},
     {file = "pyzmq-23.1.0.tar.gz", hash = "sha256:1df26aa854bdd3a8341bf199064dd6aa6e240f2eaa3c9fa8d217e5d8b868c73e"},
 ]
+regex = [
+    {file = "regex-2022.6.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:042d122f9fee3ceb6d7e3067d56557df697d1aad4ff5f64ecce4dc13a90a7c01"},
+    {file = "regex-2022.6.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:ffef4b30785dc2d1604dfb7cf9fca5dc27cd86d65f7c2a9ec34d6d3ae4565ec2"},
+    {file = "regex-2022.6.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0afa6a601acf3c0dc6de4e8d7d8bbce4e82f8542df746226cd35d4a6c15e9456"},
+    {file = "regex-2022.6.2-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4a11cbe8eb5fb332ae474895b5ead99392a4ea568bd2a258ab8df883e9c2bf92"},
+    {file = "regex-2022.6.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9c1f62ee2ba880e221bc950651a1a4b0176083d70a066c83a50ef0cb9b178e12"},
+    {file = "regex-2022.6.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5aba3d13c77173e9bfed2c2cea7fc319f11c89a36fcec08755e8fb169cf3b0df"},
+    {file = "regex-2022.6.2-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:249437f7f5b233792234aeeecb14b0aab1566280de42dfc97c26e6f718297d68"},
+    {file = "regex-2022.6.2-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:179410c79fa86ef318d58ace233f95b87b05a1db6dc493fa29404a43f4b215e2"},
+    {file = "regex-2022.6.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:5e201b1232d81ca1a7a22ab2f08e1eccad4e111579fd7f3bbf60b21ef4a16cea"},
+    {file = "regex-2022.6.2-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:fdecb225d0f1d50d4b26ac423e0032e76d46a788b83b4e299a520717a47d968c"},
+    {file = "regex-2022.6.2-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:be57f9c7b0b423c66c266a26ad143b2c5514997c05dd32ce7ca95c8b209c2288"},
+    {file = "regex-2022.6.2-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:ed657a07d8a47ef447224ea00478f1c7095065dfe70a89e7280e5f50a5725131"},
+    {file = "regex-2022.6.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:24908aefed23dd065b4a668c0b4ca04d56b7f09d8c8e89636cf6c24e64e67a1e"},
+    {file = "regex-2022.6.2-cp310-cp310-win32.whl", hash = "sha256:775694cd0bb2c4accf2f1cdd007381b33ec8b59842736fe61bdbad45f2ac7427"},
+    {file = "regex-2022.6.2-cp310-cp310-win_amd64.whl", hash = "sha256:809bbbbbcf8258049b031d80932ba71627d2274029386f0452e9950bcfa2c6e8"},
+    {file = "regex-2022.6.2-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:ecd2b5d983eb0adf2049d41f95205bdc3de4e6cc2350e9c80d4409d3a75229de"},
+    {file = "regex-2022.6.2-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2f4c101746a8dac0401abefa716b357c546e61ea2e3d4a564a9db9eac57ccbce"},
+    {file = "regex-2022.6.2-cp36-cp36m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:166ae7674d0a0e0f8044e7335ba86d0716c9d49465cff1b153f908e0470b8300"},
+    {file = "regex-2022.6.2-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c5eac5d8a8ac9ccf00805d02a968a36f5c967db6c7d2b747ab9ed782b3b3a28b"},
+    {file = "regex-2022.6.2-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f57823f35b18d82b201c1b27ce4e55f88e79e81d9ca07b50ce625d33823e1439"},
+    {file = "regex-2022.6.2-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4d42e3b7b23473729adbf76103e7df75f9167a5a80b1257ca30688352b4bb2dc"},
+    {file = "regex-2022.6.2-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:b2932e728bee0a634fe55ee54d598054a5a9ffe4cd2be21ba2b4b8e5f8064c2c"},
+    {file = "regex-2022.6.2-cp36-cp36m-musllinux_1_1_aarch64.whl", hash = "sha256:17764683ea01c2b8f103d99ae9de2473a74340df13ce306c49a721f0b1f0eb9e"},
+    {file = "regex-2022.6.2-cp36-cp36m-musllinux_1_1_i686.whl", hash = "sha256:2ac29b834100d2c171085ceba0d4a1e7046c434ddffc1434dbc7f9d59af1e945"},
+    {file = "regex-2022.6.2-cp36-cp36m-musllinux_1_1_ppc64le.whl", hash = "sha256:f43522fb5d676c99282ca4e2d41e8e2388427c0cf703db6b4a66e49b10b699a8"},
+    {file = "regex-2022.6.2-cp36-cp36m-musllinux_1_1_s390x.whl", hash = "sha256:9faa01818dad9111dbf2af26c6e3c45140ccbd1192c3a0981f196255bf7ec5e6"},
+    {file = "regex-2022.6.2-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:17443f99b8f255273731f915fdbfea4d78d809bb9c3aaf67b889039825d06515"},
+    {file = "regex-2022.6.2-cp36-cp36m-win32.whl", hash = "sha256:4a5449adef907919d4ce7a1eab2e27d0211d1b255bf0b8f5dd330ad8707e0fc3"},
+    {file = "regex-2022.6.2-cp36-cp36m-win_amd64.whl", hash = "sha256:4d206703a96a39763b5b45cf42645776f5553768ea7f3c2c1a39a4f59cafd4ba"},
+    {file = "regex-2022.6.2-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:fcd7c432202bcb8b642c3f43d5bcafc5930d82fe5b2bf2c008162df258445c1d"},
+    {file = "regex-2022.6.2-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:186c5a4a4c40621f64d771038ede20fca6c61a9faa8178f9e305aaa0c2442a97"},
+    {file = "regex-2022.6.2-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:047b2d1323a51190c01b6604f49fe09682a5c85d3c1b2c8b67c1cd68419ce3c4"},
+    {file = "regex-2022.6.2-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:30637e7fa4acfed444525b1ab9683f714be617862820578c9fd4e944d4d9ad1f"},
+    {file = "regex-2022.6.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3adafe6f2c6d86dbf3313866b61180530ca4dcd0c264932dc8fa1ffb10871d58"},
+    {file = "regex-2022.6.2-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:67ae3601edf86e15ebe40885e5bfdd6002d34879070be15cf18fc0d80ea24fed"},
+    {file = "regex-2022.6.2-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:48dddddce0ea7e7c3e92c1e0c5a28c13ca4dc9cf7e996c706d00479652bff76c"},
+    {file = "regex-2022.6.2-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:68e5c641645351eb9eb12c465876e76b53717f99e9b92aea7a2dd645a87aa7aa"},
+    {file = "regex-2022.6.2-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:8fd5f8ae42f789538bb634bdfd69b9aa357e76fdfd7ad720f32f8994c0d84f1e"},
+    {file = "regex-2022.6.2-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:71988a76fcb68cc091e901fddbcac0f9ad9a475da222c47d3cf8db0876cb5344"},
+    {file = "regex-2022.6.2-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:4b8838f70be3ce9e706df9d72f88a0aa7d4c1fea61488e06fdf292ccb70ad2be"},
+    {file = "regex-2022.6.2-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:663dca677bd3d2e2b5b7d0329e9f24247e6f38f3b740dd9a778a8ef41a76af41"},
+    {file = "regex-2022.6.2-cp37-cp37m-win32.whl", hash = "sha256:24963f0b13cc63db336d8da2a533986419890d128c551baacd934c249d51a779"},
+    {file = "regex-2022.6.2-cp37-cp37m-win_amd64.whl", hash = "sha256:ceff75127f828dfe7ceb17b94113ec2df4df274c4cd5533bb299cb099a18a8ca"},
+    {file = "regex-2022.6.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:1a6f2698cfa8340dfe4c0597782776b393ba2274fe4c079900c7c74f68752705"},
+    {file = "regex-2022.6.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:a8a08ace913c4101f0dc0be605c108a3761842efd5f41a3005565ee5d169fb2b"},
+    {file = "regex-2022.6.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:26dbe90b724efef7820c3cf4a0e5be7f130149f3d2762782e4e8ac2aea284a0b"},
+    {file = "regex-2022.6.2-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b5f759a1726b995dc896e86f17f9c0582b54eb4ead00ed5ef0b5b22260eaf2d0"},
+    {file = "regex-2022.6.2-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1fc26bb3415e7aa7495c000a2c13bf08ce037775db98c1a3fac9ff04478b6930"},
+    {file = "regex-2022.6.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:52684da32d9003367dc1a1c07e059b9bbaf135ad0764cd47d8ac3dba2df109bc"},
+    {file = "regex-2022.6.2-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1c1264eb40a71cf2bff43d6694ab7254438ca19ef330175060262b3c8dd3931a"},
+    {file = "regex-2022.6.2-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:bc635ab319c9b515236bdf327530acda99be995f9d3b9f148ab1f60b2431e970"},
+    {file = "regex-2022.6.2-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:27624b490b5d8880f25dac67e1e2ea93dfef5300b98c6755f585799230d6c746"},
+    {file = "regex-2022.6.2-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:555f7596fd1f123f8c3a67974c01d6ef80b9769e04d660d6c1a7cc3e6cff7069"},
+    {file = "regex-2022.6.2-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:933e72fbe1829cbd59da2bc51ccd73d73162f087f88521a87a8ec9cb0cf10fa8"},
+    {file = "regex-2022.6.2-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:cff5c87e941292c97d11dc81bd20679f56a2830f0f0e32f75b8ed6e0eb40f704"},
+    {file = "regex-2022.6.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:c757f3a27b6345de13ef3ca956aa805d7734ce68023e84d0fc74e1f09ce66f7a"},
+    {file = "regex-2022.6.2-cp38-cp38-win32.whl", hash = "sha256:a58d21dd1a2d6b50ed091554ff85e448fce3fe33a4db8b55d0eba2ca957ed626"},
+    {file = "regex-2022.6.2-cp38-cp38-win_amd64.whl", hash = "sha256:495a4165172848503303ed05c9d0409428f789acc27050fe2cf0a4549188a7d5"},
+    {file = "regex-2022.6.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:1ab5cf7d09515548044e69d3a0ec77c63d7b9dfff4afc19653f638b992573126"},
+    {file = "regex-2022.6.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:c1ea28f0ee6cbe4c0367c939b015d915aa9875f6e061ba1cf0796ca9a3010570"},
+    {file = "regex-2022.6.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3de1ecf26ce85521bf73897828b6d0687cc6cf271fb6ff32ac63d26b21f5e764"},
+    {file = "regex-2022.6.2-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:fa7c7044aabdad2329974be2246babcc21d3ede852b3971a90fd8c2056c20360"},
+    {file = "regex-2022.6.2-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:53d69d77e9cfe468b000314dd656be85bb9e96de088a64f75fe128dfe1bf30dd"},
+    {file = "regex-2022.6.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5c8d61883a38b1289fba9944a19a361875b5c0170b83cdcc95ea180247c1b7d3"},
+    {file = "regex-2022.6.2-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c5429202bef174a3760690d912e3a80060b323199a61cef6c6c29b30ce09fd17"},
+    {file = "regex-2022.6.2-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:e85b10280cf1e334a7c95629f6cbbfe30b815a4ea5f1e28d31f79eb92c2c3d93"},
+    {file = "regex-2022.6.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:c400dfed4137f32127ea4063447006d7153c974c680bf0fb1b724cce9f8567fc"},
+    {file = "regex-2022.6.2-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:7f648037c503985aed39f85088acab6f1eb6a0482d7c6c665a5712c9ad9eaefc"},
+    {file = "regex-2022.6.2-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:e7b2ff451f6c305b516281ec45425dd423223c8063218c5310d6f72a0a7a517c"},
+    {file = "regex-2022.6.2-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:be456b4313a86be41706319c397c09d9fdd2e5cdfde208292a277b867e99e3d1"},
+    {file = "regex-2022.6.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:c3db393b21b53d7e1d3f881b64c29d886cbfdd3df007e31de68b329edbab7d02"},
+    {file = "regex-2022.6.2-cp39-cp39-win32.whl", hash = "sha256:d70596f20a03cb5f935d6e4aad9170a490d88fc4633679bf00c652e9def4619e"},
+    {file = "regex-2022.6.2-cp39-cp39-win_amd64.whl", hash = "sha256:3b9b6289e03dbe6a6096880d8ac166cb23c38b4896ad235edee789d4e8697152"},
+    {file = "regex-2022.6.2.tar.gz", hash = "sha256:f7b43acb2c46fb2cd506965b2d9cf4c5e64c9c612bac26c1187933c7296bf08c"},
+]
 requests = [
     {file = "requests-2.27.1-py2.py3-none-any.whl", hash = "sha256:f22fa1e554c9ddfd16e6e41ac79759e17be9e492b3587efa038054674760e72d"},
     {file = "requests-2.27.1.tar.gz", hash = "sha256:68d7c56fd5a8999887728ef304a6d12edc7be74f1cfa47714fc8b414525c9a61"},
 ]
+requests-file = [
+    {file = "requests-file-1.5.1.tar.gz", hash = "sha256:07d74208d3389d01c38ab89ef403af0cfec63957d53a0081d8eca738d0247d8e"},
+    {file = "requests_file-1.5.1-py2.py3-none-any.whl", hash = "sha256:dfe5dae75c12481f68ba353183c53a65e6044c923e64c24b2209f6c7570ca953"},
+]
 rich = [
     {file = "rich-12.4.4-py3-none-any.whl", hash = "sha256:d2bbd99c320a2532ac71ff6a3164867884357da3e3301f0240090c5d2fdac7ec"},
     {file = "rich-12.4.4.tar.gz", hash = "sha256:4c586de507202505346f3e32d1363eb9ed6932f0c2f63184dea88983ff4971e2"},
@@ -2534,6 +2908,9 @@ send2trash = [
     {file = "Send2Trash-1.8.0-py3-none-any.whl", hash = "sha256:f20eaadfdb517eaca5ce077640cb261c7d2698385a6a0f072a4a5447fd49fa08"},
     {file = "Send2Trash-1.8.0.tar.gz", hash = "sha256:d2c24762fd3759860a0aff155e45871447ea58d2be6bdd39b5c8f966a0c99c2d"},
 ]
+sgmllib3k = [
+    {file = "sgmllib3k-1.0.0.tar.gz", hash = "sha256:7868fb1c8bfa764c1ac563d3cf369c381d1325d36124933a726f29fcdaa812e9"},
+]
 six = [
     {file = "six-1.16.0-py2.py3-none-any.whl", hash = "sha256:8abb2f1d86890a2dfb989f9a77cfcfd3e47c2a354b01111771326f8aa26e0254"},
     {file = "six-1.16.0.tar.gz", hash = "sha256:1e61c37477a1626458e36f7b1d82aa5c9b094fa4802892072e49de9c60c4c926"},
@@ -2642,6 +3019,13 @@ tinycss2 = [
     {file = "tinycss2-1.1.1-py3-none-any.whl", hash = "sha256:fe794ceaadfe3cf3e686b22155d0da5780dd0e273471a51846d0a02bc204fec8"},
     {file = "tinycss2-1.1.1.tar.gz", hash = "sha256:b2e44dd8883c360c35dd0d1b5aad0b610e5156c2cb3b33434634e539ead9d8bf"},
 ]
+tinysegmenter = [
+    {file = "tinysegmenter-0.3.tar.gz", hash = "sha256:ed1f6d2e806a4758a73be589754384cbadadc7e1a414c81a166fc9adf2d40c6d"},
+]
+tldextract = [
+    {file = "tldextract-3.3.0-py3-none-any.whl", hash = "sha256:5d88321b1b528ebb8f678c72ab023f37caf6381f6af9576b4e60fd266cff178c"},
+    {file = "tldextract-3.3.0.tar.gz", hash = "sha256:adcd24abf21ce3450417cd5a00f23b7e57554ce8ae827334dd12bfcbb6274cf1"},
+]
 toml = [
     {file = "toml-0.10.2-py2.py3-none-any.whl", hash = "sha256:806143ae5bfb6a3c6e736a764057db0e6a0e05e338b5630894a5f779cabb4f9b"},
     {file = "toml-0.10.2.tar.gz", hash = "sha256:b3bda1d108d5dd99f4a20d24d9c348e91c4db7ab1b749200bded2f839ccbe68f"},

requirements.txt

@@ -0,0 +1,152 @@
+altair==4.2.0
+appnope==0.1.3; platform_system == "Darwin"
+argon2-cffi-bindings==21.2.0
+argon2-cffi==21.3.0
+asttokens==2.0.5
+attrs==21.4.0
+backcall==0.2.0
+backports.zoneinfo==0.2.1; python_version >= "3.6" and python_version < "3.9"
+beautifulsoup4==4.11.1
+bleach==5.0.0
+blinker==1.4
+blis==0.7.7
+cachetools==5.2.0
+catalogue==2.0.7
+certifi==2022.5.18.1
+cffi==1.15.0
+cffi==1.15.0; implementation_name == "pypy"
+charset-normalizer==2.0.12; python_version >= "3"
+click==8.1.3
+colorama==0.4.4; platform_system == "Windows"
+commonmark==0.9.1
+cssselect==1.1.0
+cymem==2.0.6
+cytoolz==0.11.2
+debugpy==1.6.0
+decorator==5.1.1
+defusedxml==0.7.1
+entrypoints==0.4
+executing==0.8.3
+fastjsonschema==2.15.3
+feedfinder2==0.0.4
+feedparser==6.0.10
+filelock==3.7.1
+gitdb==4.0.9
+gitpython==3.1.27
+hu-core-news-lg @ https://huggingface.co/huspacy/hu_core_news_lg/resolve/v3.3.0/hu_core_news_lg-any-py3-none-any.whl
+idna==3.3
+idna==3.3; python_version >= "3"
+importlib-metadata==4.11.4
+importlib-resources==5.7.1; python_version < "3.9"
+ipykernel==6.13.0
+ipykernel==6.13.0; python_version >= "3.4"
+ipython-genutils==0.2.0
+ipython==8.4.0
+ipython==8.4.0; python_version >= "3.3"
+ipywidgets==7.7.0
+jedi==0.18.1
+jellyfish==0.9.0
+jieba3k==0.35.1
+jinja2==3.1.2
+joblib==1.1.0
+jsonschema==4.6.0
+jupyter-client==7.3.1
+jupyter-core==4.10.0
+jupyterlab-pygments==0.2.2
+jupyterlab-widgets==1.1.0; python_version >= "3.6"
+langcodes==3.3.0
+lxml==4.9.0
+markupsafe==2.1.1
+matplotlib-inline==0.1.3
+mistune==0.8.4
+murmurhash==1.0.7
+nbclient==0.6.4
+nbconvert==6.5.0
+nbformat==5.4.0
+nest-asyncio==1.5.5
+networkx==2.8.2
+newspaper3k==0.2.8
+nltk==3.7
+notebook==6.4.11
+numpy==1.22.4
+numpy==1.22.4; platform_machine != "aarch64" and platform_machine != "arm64" and python_version < "3.10"
+numpy==1.22.4; platform_machine == "aarch64" and python_version < "3.10"
+numpy==1.22.4; platform_machine == "arm64" and python_version < "3.10"
+packaging==21.3
+pandas==1.4.2
+pandocfilters==1.5.0
+parso==0.8.3
+pathy==0.6.1
+pexpect==4.8.0; sys_platform != "win32"
+pickleshare==0.7.5
+pillow==9.1.1
+preshed==3.0.6
+prometheus-client==0.14.1
+prompt-toolkit==3.0.29
+protobuf==3.20.1
+psutil==5.9.1
+ptyprocess==0.7.0
+ptyprocess==0.7.0; os_name != "nt"
+pure-eval==0.2.2
+py==1.11.0; implementation_name == "pypy"
+pyarrow==8.0.0
+pycparser==2.21
+pydantic==1.8.2
+pydeck==0.7.1
+pygments==2.12.0
+pympler==1.0.1
+pyparsing==3.0.9
+pyphen==0.12.0
+pyrsistent==0.18.1
+python-dateutil==2.8.2
+pytz-deprecation-shim==0.1.0.post0
+pytz==2022.1
+pywin32==304; sys_platform == "win32" and platform_python_implementation != "PyPy"
+pywinpty==2.0.5; os_name == "nt"
+pyyaml==6.0
+pyzmq==23.1.0
+regex==2022.6.2
+requests-file==1.5.1
+requests==2.27.1
+rich==12.4.4
+scikit-learn==1.1.1
+scipy==1.8.1
+semver==2.13.0
+send2trash==1.8.0
+sgmllib3k==1.0.0
+six==1.16.0
+smart-open==5.2.1
+smmap==5.0.0
+soupsieve==2.3.2.post1
+spacy-legacy==3.0.9
+spacy-loggers==1.0.2
+spacy==3.3.0
+srsly==2.4.3
+stack-data==0.2.0
+streamlit==1.10.0
+terminado==0.15.0
+textacy==0.12.0
+thinc==8.0.17
+threadpoolctl==3.1.0
+tinycss2==1.1.1
+tinysegmenter==0.3
+tldextract==3.3.0
+toml==0.10.2
+toolz==0.11.2
+tornado==6.1
+tqdm==4.64.0
+traitlets==5.2.2.post1
+typer==0.4.1
+typing-extensions==4.2.0
+typing-extensions==4.2.0; python_version < "3.9"
+tzdata==2022.1; python_version >= "3.6"
+tzlocal==4.2
+urllib3==1.26.9
+validators==0.19.0
+wasabi==0.9.1
+watchdog==2.1.8; platform_system != "Darwin"
+wcwidth==0.2.5
+webencodings==0.5.1
+widgetsnbextension==3.6.0
+zipp==3.8.0
+zipp==3.8.0; python_version < "3.10"