Add text extraction to webpages

poetry.lock

@@ -550,86 +550,101 @@ pycparser = "*"
 
 [[package]]
 name = "charset-normalizer"
-version = "3.1.0"
+version = "3.3.2"
 description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
 optional = false
 python-versions = ">=3.7.0"
 files = [
-    {file = "charset-normalizer-3.1.0.tar.gz", hash = "sha256:34e0a2f9c370eb95597aae63bf85eb5e96826d81e3dcf88b8886012906f509b5"},
-    {file = "charset_normalizer-3.1.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:e0ac8959c929593fee38da1c2b64ee9778733cdf03c482c9ff1d508b6b593b2b"},
-    {file = "charset_normalizer-3.1.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:d7fc3fca01da18fbabe4625d64bb612b533533ed10045a2ac3dd194bfa656b60"},
-    {file = "charset_normalizer-3.1.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:04eefcee095f58eaabe6dc3cc2262f3bcd776d2c67005880894f447b3f2cb9c1"},
-    {file = "charset_normalizer-3.1.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:20064ead0717cf9a73a6d1e779b23d149b53daf971169289ed2ed43a71e8d3b0"},
-    {file = "charset_normalizer-3.1.0-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1435ae15108b1cb6fffbcea2af3d468683b7afed0169ad718451f8db5d1aff6f"},
-    {file = "charset_normalizer-3.1.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c84132a54c750fda57729d1e2599bb598f5fa0344085dbde5003ba429a4798c0"},
-    {file = "charset_normalizer-3.1.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:75f2568b4189dda1c567339b48cba4ac7384accb9c2a7ed655cd86b04055c795"},
-    {file = "charset_normalizer-3.1.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:11d3bcb7be35e7b1bba2c23beedac81ee893ac9871d0ba79effc7fc01167db6c"},
-    {file = "charset_normalizer-3.1.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:891cf9b48776b5c61c700b55a598621fdb7b1e301a550365571e9624f270c203"},
-    {file = "charset_normalizer-3.1.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:5f008525e02908b20e04707a4f704cd286d94718f48bb33edddc7d7b584dddc1"},
-    {file = "charset_normalizer-3.1.0-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:b06f0d3bf045158d2fb8837c5785fe9ff9b8c93358be64461a1089f5da983137"},
-    {file = "charset_normalizer-3.1.0-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:49919f8400b5e49e961f320c735388ee686a62327e773fa5b3ce6721f7e785ce"},
-    {file = "charset_normalizer-3.1.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:22908891a380d50738e1f978667536f6c6b526a2064156203d418f4856d6e86a"},
-    {file = "charset_normalizer-3.1.0-cp310-cp310-win32.whl", hash = "sha256:12d1a39aa6b8c6f6248bb54550efcc1c38ce0d8096a146638fd4738e42284448"},
-    {file = "charset_normalizer-3.1.0-cp310-cp310-win_amd64.whl", hash = "sha256:65ed923f84a6844de5fd29726b888e58c62820e0769b76565480e1fdc3d062f8"},
-    {file = "charset_normalizer-3.1.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:9a3267620866c9d17b959a84dd0bd2d45719b817245e49371ead79ed4f710d19"},
-    {file = "charset_normalizer-3.1.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6734e606355834f13445b6adc38b53c0fd45f1a56a9ba06c2058f86893ae8017"},
-    {file = "charset_normalizer-3.1.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:f8303414c7b03f794347ad062c0516cee0e15f7a612abd0ce1e25caf6ceb47df"},
-    {file = "charset_normalizer-3.1.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:aaf53a6cebad0eae578f062c7d462155eada9c172bd8c4d250b8c1d8eb7f916a"},
-    {file = "charset_normalizer-3.1.0-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3dc5b6a8ecfdc5748a7e429782598e4f17ef378e3e272eeb1340ea57c9109f41"},
-    {file = "charset_normalizer-3.1.0-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e1b25e3ad6c909f398df8921780d6a3d120d8c09466720226fc621605b6f92b1"},
-    {file = "charset_normalizer-3.1.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0ca564606d2caafb0abe6d1b5311c2649e8071eb241b2d64e75a0d0065107e62"},
-    {file = "charset_normalizer-3.1.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b82fab78e0b1329e183a65260581de4375f619167478dddab510c6c6fb04d9b6"},
-    {file = "charset_normalizer-3.1.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:bd7163182133c0c7701b25e604cf1611c0d87712e56e88e7ee5d72deab3e76b5"},
-    {file = "charset_normalizer-3.1.0-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:11d117e6c63e8f495412d37e7dc2e2fff09c34b2d09dbe2bee3c6229577818be"},
-    {file = "charset_normalizer-3.1.0-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:cf6511efa4801b9b38dc5546d7547d5b5c6ef4b081c60b23e4d941d0eba9cbeb"},
-    {file = "charset_normalizer-3.1.0-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:abc1185d79f47c0a7aaf7e2412a0eb2c03b724581139193d2d82b3ad8cbb00ac"},
-    {file = "charset_normalizer-3.1.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:cb7b2ab0188829593b9de646545175547a70d9a6e2b63bf2cd87a0a391599324"},
-    {file = "charset_normalizer-3.1.0-cp311-cp311-win32.whl", hash = "sha256:c36bcbc0d5174a80d6cccf43a0ecaca44e81d25be4b7f90f0ed7bcfbb5a00909"},
-    {file = "charset_normalizer-3.1.0-cp311-cp311-win_amd64.whl", hash = "sha256:cca4def576f47a09a943666b8f829606bcb17e2bc2d5911a46c8f8da45f56755"},
-    {file = "charset_normalizer-3.1.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:0c95f12b74681e9ae127728f7e5409cbbef9cd914d5896ef238cc779b8152373"},
-    {file = "charset_normalizer-3.1.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fca62a8301b605b954ad2e9c3666f9d97f63872aa4efcae5492baca2056b74ab"},
-    {file = "charset_normalizer-3.1.0-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ac0aa6cd53ab9a31d397f8303f92c42f534693528fafbdb997c82bae6e477ad9"},
-    {file = "charset_normalizer-3.1.0-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c3af8e0f07399d3176b179f2e2634c3ce9c1301379a6b8c9c9aeecd481da494f"},
-    {file = "charset_normalizer-3.1.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3a5fc78f9e3f501a1614a98f7c54d3969f3ad9bba8ba3d9b438c3bc5d047dd28"},
-    {file = "charset_normalizer-3.1.0-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:628c985afb2c7d27a4800bfb609e03985aaecb42f955049957814e0491d4006d"},
-    {file = "charset_normalizer-3.1.0-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:74db0052d985cf37fa111828d0dd230776ac99c740e1a758ad99094be4f1803d"},
-    {file = "charset_normalizer-3.1.0-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:1e8fcdd8f672a1c4fc8d0bd3a2b576b152d2a349782d1eb0f6b8e52e9954731d"},
-    {file = "charset_normalizer-3.1.0-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:04afa6387e2b282cf78ff3dbce20f0cc071c12dc8f685bd40960cc68644cfea6"},
-    {file = "charset_normalizer-3.1.0-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:dd5653e67b149503c68c4018bf07e42eeed6b4e956b24c00ccdf93ac79cdff84"},
-    {file = "charset_normalizer-3.1.0-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:d2686f91611f9e17f4548dbf050e75b079bbc2a82be565832bc8ea9047b61c8c"},
-    {file = "charset_normalizer-3.1.0-cp37-cp37m-win32.whl", hash = "sha256:4155b51ae05ed47199dc5b2a4e62abccb274cee6b01da5b895099b61b1982974"},
-    {file = "charset_normalizer-3.1.0-cp37-cp37m-win_amd64.whl", hash = "sha256:322102cdf1ab682ecc7d9b1c5eed4ec59657a65e1c146a0da342b78f4112db23"},
-    {file = "charset_normalizer-3.1.0-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:e633940f28c1e913615fd624fcdd72fdba807bf53ea6925d6a588e84e1151531"},
-    {file = "charset_normalizer-3.1.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:3a06f32c9634a8705f4ca9946d667609f52cf130d5548881401f1eb2c39b1e2c"},
-    {file = "charset_normalizer-3.1.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:7381c66e0561c5757ffe616af869b916c8b4e42b367ab29fedc98481d1e74e14"},
-    {file = "charset_normalizer-3.1.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3573d376454d956553c356df45bb824262c397c6e26ce43e8203c4c540ee0acb"},
-    {file = "charset_normalizer-3.1.0-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e89df2958e5159b811af9ff0f92614dabf4ff617c03a4c1c6ff53bf1c399e0e1"},
-    {file = "charset_normalizer-3.1.0-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:78cacd03e79d009d95635e7d6ff12c21eb89b894c354bd2b2ed0b4763373693b"},
-    {file = "charset_normalizer-3.1.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:de5695a6f1d8340b12a5d6d4484290ee74d61e467c39ff03b39e30df62cf83a0"},
-    {file = "charset_normalizer-3.1.0-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1c60b9c202d00052183c9be85e5eaf18a4ada0a47d188a83c8f5c5b23252f649"},
-    {file = "charset_normalizer-3.1.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:f645caaf0008bacf349875a974220f1f1da349c5dbe7c4ec93048cdc785a3326"},
-    {file = "charset_normalizer-3.1.0-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:ea9f9c6034ea2d93d9147818f17c2a0860d41b71c38b9ce4d55f21b6f9165a11"},
-    {file = "charset_normalizer-3.1.0-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:80d1543d58bd3d6c271b66abf454d437a438dff01c3e62fdbcd68f2a11310d4b"},
-    {file = "charset_normalizer-3.1.0-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:73dc03a6a7e30b7edc5b01b601e53e7fc924b04e1835e8e407c12c037e81adbd"},
-    {file = "charset_normalizer-3.1.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:6f5c2e7bc8a4bf7c426599765b1bd33217ec84023033672c1e9a8b35eaeaaaf8"},
-    {file = "charset_normalizer-3.1.0-cp38-cp38-win32.whl", hash = "sha256:12a2b561af122e3d94cdb97fe6fb2bb2b82cef0cdca131646fdb940a1eda04f0"},
-    {file = "charset_normalizer-3.1.0-cp38-cp38-win_amd64.whl", hash = "sha256:3160a0fd9754aab7d47f95a6b63ab355388d890163eb03b2d2b87ab0a30cfa59"},
-    {file = "charset_normalizer-3.1.0-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:38e812a197bf8e71a59fe55b757a84c1f946d0ac114acafaafaf21667a7e169e"},
-    {file = "charset_normalizer-3.1.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:6baf0baf0d5d265fa7944feb9f7451cc316bfe30e8df1a61b1bb08577c554f31"},
-    {file = "charset_normalizer-3.1.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:8f25e17ab3039b05f762b0a55ae0b3632b2e073d9c8fc88e89aca31a6198e88f"},
-    {file = "charset_normalizer-3.1.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3747443b6a904001473370d7810aa19c3a180ccd52a7157aacc264a5ac79265e"},
-    {file = "charset_normalizer-3.1.0-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b116502087ce8a6b7a5f1814568ccbd0e9f6cfd99948aa59b0e241dc57cf739f"},
-    {file = "charset_normalizer-3.1.0-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d16fd5252f883eb074ca55cb622bc0bee49b979ae4e8639fff6ca3ff44f9f854"},
-    {file = "charset_normalizer-3.1.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:21fa558996782fc226b529fdd2ed7866c2c6ec91cee82735c98a197fae39f706"},
-    {file = "charset_normalizer-3.1.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6f6c7a8a57e9405cad7485f4c9d3172ae486cfef1344b5ddd8e5239582d7355e"},
-    {file = "charset_normalizer-3.1.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:ac3775e3311661d4adace3697a52ac0bab17edd166087d493b52d4f4f553f9f0"},
-    {file = "charset_normalizer-3.1.0-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:10c93628d7497c81686e8e5e557aafa78f230cd9e77dd0c40032ef90c18f2230"},
-    {file = "charset_normalizer-3.1.0-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:6f4f4668e1831850ebcc2fd0b1cd11721947b6dc7c00bf1c6bd3c929ae14f2c7"},
-    {file = "charset_normalizer-3.1.0-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:0be65ccf618c1e7ac9b849c315cc2e8a8751d9cfdaa43027d4f6624bd587ab7e"},
-    {file = "charset_normalizer-3.1.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:53d0a3fa5f8af98a1e261de6a3943ca631c526635eb5817a87a59d9a57ebf48f"},
-    {file = "charset_normalizer-3.1.0-cp39-cp39-win32.whl", hash = "sha256:a04f86f41a8916fe45ac5024ec477f41f886b3c435da2d4e3d2709b22ab02af1"},
-    {file = "charset_normalizer-3.1.0-cp39-cp39-win_amd64.whl", hash = "sha256:830d2948a5ec37c386d3170c483063798d7879037492540f10a475e3fd6f244b"},
-    {file = "charset_normalizer-3.1.0-py3-none-any.whl", hash = "sha256:3d9098b479e78c85080c98e1e35ff40b4a31d8953102bb0fd7d1b6f8a2111a3d"},
+    {file = "charset-normalizer-3.3.2.tar.gz", hash = "sha256:f30c3cb33b24454a82faecaf01b19c18562b1e89558fb6c56de4d9118a032fd5"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:25baf083bf6f6b341f4121c2f3c548875ee6f5339300e08be3f2b2ba1721cdd3"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:06435b539f889b1f6f4ac1758871aae42dc3a8c0e24ac9e60c2384973ad73027"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:9063e24fdb1e498ab71cb7419e24622516c4a04476b17a2dab57e8baa30d6e03"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6897af51655e3691ff853668779c7bad41579facacf5fd7253b0133308cf000d"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1d3193f4a680c64b4b6a9115943538edb896edc190f0b222e73761716519268e"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:cd70574b12bb8a4d2aaa0094515df2463cb429d8536cfb6c7ce983246983e5a6"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8465322196c8b4d7ab6d1e049e4c5cb460d0394da4a27d23cc242fbf0034b6b5"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a9a8e9031d613fd2009c182b69c7b2c1ef8239a0efb1df3f7c8da66d5dd3d537"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:beb58fe5cdb101e3a055192ac291b7a21e3b7ef4f67fa1d74e331a7f2124341c"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:e06ed3eb3218bc64786f7db41917d4e686cc4856944f53d5bdf83a6884432e12"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:2e81c7b9c8979ce92ed306c249d46894776a909505d8f5a4ba55b14206e3222f"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:572c3763a264ba47b3cf708a44ce965d98555f618ca42c926a9c1616d8f34269"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:fd1abc0d89e30cc4e02e4064dc67fcc51bd941eb395c502aac3ec19fab46b519"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-win32.whl", hash = "sha256:3d47fa203a7bd9c5b6cee4736ee84ca03b8ef23193c0d1ca99b5089f72645c73"},
+    {file = "charset_normalizer-3.3.2-cp310-cp310-win_amd64.whl", hash = "sha256:10955842570876604d404661fbccbc9c7e684caf432c09c715ec38fbae45ae09"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:802fe99cca7457642125a8a88a084cef28ff0cf9407060f7b93dca5aa25480db"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:573f6eac48f4769d667c4442081b1794f52919e7edada77495aaed9236d13a96"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:549a3a73da901d5bc3ce8d24e0600d1fa85524c10287f6004fbab87672bf3e1e"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f27273b60488abe721a075bcca6d7f3964f9f6f067c8c4c605743023d7d3944f"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1ceae2f17a9c33cb48e3263960dc5fc8005351ee19db217e9b1bb15d28c02574"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:65f6f63034100ead094b8744b3b97965785388f308a64cf8d7c34f2f2e5be0c4"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:753f10e867343b4511128c6ed8c82f7bec3bd026875576dfd88483c5c73b2fd8"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4a78b2b446bd7c934f5dcedc588903fb2f5eec172f3d29e52a9096a43722adfc"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:e537484df0d8f426ce2afb2d0f8e1c3d0b114b83f8850e5f2fbea0e797bd82ae"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:eb6904c354526e758fda7167b33005998fb68c46fbc10e013ca97f21ca5c8887"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:deb6be0ac38ece9ba87dea880e438f25ca3eddfac8b002a2ec3d9183a454e8ae"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:4ab2fe47fae9e0f9dee8c04187ce5d09f48eabe611be8259444906793ab7cbce"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:80402cd6ee291dcb72644d6eac93785fe2c8b9cb30893c1af5b8fdd753b9d40f"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-win32.whl", hash = "sha256:7cd13a2e3ddeed6913a65e66e94b51d80a041145a026c27e6bb76c31a853c6ab"},
+    {file = "charset_normalizer-3.3.2-cp311-cp311-win_amd64.whl", hash = "sha256:663946639d296df6a2bb2aa51b60a2454ca1cb29835324c640dafb5ff2131a77"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:0b2b64d2bb6d3fb9112bafa732def486049e63de9618b5843bcdd081d8144cd8"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:ddbb2551d7e0102e7252db79ba445cdab71b26640817ab1e3e3648dad515003b"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:55086ee1064215781fff39a1af09518bc9255b50d6333f2e4c74ca09fac6a8f6"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8f4a014bc36d3c57402e2977dada34f9c12300af536839dc38c0beab8878f38a"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a10af20b82360ab00827f916a6058451b723b4e65030c5a18577c8b2de5b3389"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8d756e44e94489e49571086ef83b2bb8ce311e730092d2c34ca8f7d925cb20aa"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:90d558489962fd4918143277a773316e56c72da56ec7aa3dc3dbbe20fdfed15b"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6ac7ffc7ad6d040517be39eb591cac5ff87416c2537df6ba3cba3bae290c0fed"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:7ed9e526742851e8d5cc9e6cf41427dfc6068d4f5a3bb03659444b4cabf6bc26"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:8bdb58ff7ba23002a4c5808d608e4e6c687175724f54a5dade5fa8c67b604e4d"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:6b3251890fff30ee142c44144871185dbe13b11bab478a88887a639655be1068"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-musllinux_1_1_s390x.whl", hash = "sha256:b4a23f61ce87adf89be746c8a8974fe1c823c891d8f86eb218bb957c924bb143"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:efcb3f6676480691518c177e3b465bcddf57cea040302f9f4e6e191af91174d4"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-win32.whl", hash = "sha256:d965bba47ddeec8cd560687584e88cf699fd28f192ceb452d1d7ee807c5597b7"},
+    {file = "charset_normalizer-3.3.2-cp312-cp312-win_amd64.whl", hash = "sha256:96b02a3dc4381e5494fad39be677abcb5e6634bf7b4fa83a6dd3112607547001"},
+    {file = "charset_normalizer-3.3.2-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:95f2a5796329323b8f0512e09dbb7a1860c46a39da62ecb2324f116fa8fdc85c"},
+    {file = "charset_normalizer-3.3.2-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c002b4ffc0be611f0d9da932eb0f704fe2602a9a949d1f738e4c34c75b0863d5"},
+    {file = "charset_normalizer-3.3.2-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a981a536974bbc7a512cf44ed14938cf01030a99e9b3a06dd59578882f06f985"},
+    {file = "charset_normalizer-3.3.2-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3287761bc4ee9e33561a7e058c72ac0938c4f57fe49a09eae428fd88aafe7bb6"},
+    {file = "charset_normalizer-3.3.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:42cb296636fcc8b0644486d15c12376cb9fa75443e00fb25de0b8602e64c1714"},
+    {file = "charset_normalizer-3.3.2-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0a55554a2fa0d408816b3b5cedf0045f4b8e1a6065aec45849de2d6f3f8e9786"},
+    {file = "charset_normalizer-3.3.2-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:c083af607d2515612056a31f0a8d9e0fcb5876b7bfc0abad3ecd275bc4ebc2d5"},
+    {file = "charset_normalizer-3.3.2-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:87d1351268731db79e0f8e745d92493ee2841c974128ef629dc518b937d9194c"},
+    {file = "charset_normalizer-3.3.2-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:bd8f7df7d12c2db9fab40bdd87a7c09b1530128315d047a086fa3ae3435cb3a8"},
+    {file = "charset_normalizer-3.3.2-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:c180f51afb394e165eafe4ac2936a14bee3eb10debc9d9e4db8958fe36afe711"},
+    {file = "charset_normalizer-3.3.2-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:8c622a5fe39a48f78944a87d4fb8a53ee07344641b0562c540d840748571b811"},
+    {file = "charset_normalizer-3.3.2-cp37-cp37m-win32.whl", hash = "sha256:db364eca23f876da6f9e16c9da0df51aa4f104a972735574842618b8c6d999d4"},
+    {file = "charset_normalizer-3.3.2-cp37-cp37m-win_amd64.whl", hash = "sha256:86216b5cee4b06df986d214f664305142d9c76df9b6512be2738aa72a2048f99"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:6463effa3186ea09411d50efc7d85360b38d5f09b870c48e4600f63af490e56a"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:6c4caeef8fa63d06bd437cd4bdcf3ffefe6738fb1b25951440d80dc7df8c03ac"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:37e55c8e51c236f95b033f6fb391d7d7970ba5fe7ff453dad675e88cf303377a"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fb69256e180cb6c8a894fee62b3afebae785babc1ee98b81cdf68bbca1987f33"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ae5f4161f18c61806f411a13b0310bea87f987c7d2ecdbdaad0e94eb2e404238"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b2b0a0c0517616b6869869f8c581d4eb2dd83a4d79e0ebcb7d373ef9956aeb0a"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:45485e01ff4d3630ec0d9617310448a8702f70e9c01906b0d0118bdf9d124cf2"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:eb00ed941194665c332bf8e078baf037d6c35d7c4f3102ea2d4f16ca94a26dc8"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:2127566c664442652f024c837091890cb1942c30937add288223dc895793f898"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:a50aebfa173e157099939b17f18600f72f84eed3049e743b68ad15bd69b6bf99"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:4d0d1650369165a14e14e1e47b372cfcb31d6ab44e6e33cb2d4e57265290044d"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:923c0c831b7cfcb071580d3f46c4baf50f174be571576556269530f4bbd79d04"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:06a81e93cd441c56a9b65d8e1d043daeb97a3d0856d177d5c90ba85acb3db087"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-win32.whl", hash = "sha256:6ef1d82a3af9d3eecdba2321dc1b3c238245d890843e040e41e470ffa64c3e25"},
+    {file = "charset_normalizer-3.3.2-cp38-cp38-win_amd64.whl", hash = "sha256:eb8821e09e916165e160797a6c17edda0679379a4be5c716c260e836e122f54b"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:c235ebd9baae02f1b77bcea61bce332cb4331dc3617d254df3323aa01ab47bd4"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:5b4c145409bef602a690e7cfad0a15a55c13320ff7a3ad7ca59c13bb8ba4d45d"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:68d1f8a9e9e37c1223b656399be5d6b448dea850bed7d0f87a8311f1ff3dabb0"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:22afcb9f253dac0696b5a4be4a1c0f8762f8239e21b99680099abd9b2b1b2269"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e27ad930a842b4c5eb8ac0016b0a54f5aebbe679340c26101df33424142c143c"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1f79682fbe303db92bc2b1136016a38a42e835d932bab5b3b1bfcfbf0640e519"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b261ccdec7821281dade748d088bb6e9b69e6d15b30652b74cbbac25e280b796"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:122c7fa62b130ed55f8f285bfd56d5f4b4a5b503609d181f9ad85e55c89f4185"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:d0eccceffcb53201b5bfebb52600a5fb483a20b61da9dbc885f8b103cbe7598c"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:9f96df6923e21816da7e0ad3fd47dd8f94b2a5ce594e00677c0013018b813458"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:7f04c839ed0b6b98b1a7501a002144b76c18fb1c1850c8b98d458ac269e26ed2"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:34d1c8da1e78d2e001f363791c98a272bb734000fcef47a491c1e3b0505657a8"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:ff8fa367d09b717b2a17a052544193ad76cd49979c805768879cb63d9ca50561"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-win32.whl", hash = "sha256:aed38f6e4fb3f5d6bf81bfa990a07806be9d83cf7bacef998ab1a9bd660a581f"},
+    {file = "charset_normalizer-3.3.2-cp39-cp39-win_amd64.whl", hash = "sha256:b01b88d45a6fcb69667cd6d2f7a9aeb4bf53760d7fc536bf679ec94fe9f3ff3d"},
+    {file = "charset_normalizer-3.3.2-py3-none-any.whl", hash = "sha256:3e4d1f6587322d2788836a99c69062fbb091331ec940e02d12d179c1d53e25fc"},
 ]
 
 [[package]]
@@ -740,6 +755,22 @@ colorama = {version = "*", markers = "sys_platform == \"win32\""}
 [package.extras]
 development = ["black", "flake8", "mypy", "pytest", "types-colorama"]
 
+[[package]]
+name = "courlan"
+version = "0.9.5"
+description = "Clean, filter and sample URLs to optimize data collection – includes spam, content type and language filters."
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "courlan-0.9.5-py3-none-any.whl", hash = "sha256:3c10fb06a26422b5c5e6f5f6d2c16e5d4308026f9dcea783ca6a88dae5922ee5"},
+    {file = "courlan-0.9.5.tar.gz", hash = "sha256:38dc35b2e3bf1f5d516d00d51ac12ebde543e3417c6be6f6a2273c0fc5b5b353"},
+]
+
+[package.dependencies]
+langcodes = ">=3.3.0"
+tld = {version = ">=0.13", markers = "python_version >= \"3.7\""}
+urllib3 = {version = ">=1.26,<3", markers = "python_version >= \"3.7\""}
+
 [[package]]
 name = "coverage"
 version = "7.2.2"
@@ -847,6 +878,28 @@ test = ["iso8601", "pretend", "pytest (>=6.2.0)", "pytest-benchmark", "pytest-co
 test-randomorder = ["pytest-randomly"]
 tox = ["tox"]
 
+[[package]]
+name = "dateparser"
+version = "1.2.0"
+description = "Date parsing library designed to parse dates from HTML pages"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "dateparser-1.2.0-py2.py3-none-any.whl", hash = "sha256:0b21ad96534e562920a0083e97fd45fa959882d4162acc358705144520a35830"},
+    {file = "dateparser-1.2.0.tar.gz", hash = "sha256:7975b43a4222283e0ae15be7b4999d08c9a70e2d378ac87385b1ccf2cffbbb30"},
+]
+
+[package.dependencies]
+python-dateutil = "*"
+pytz = "*"
+regex = "<2019.02.19 || >2019.02.19,<2021.8.27 || >2021.8.27"
+tzlocal = "*"
+
+[package.extras]
+calendars = ["convertdate", "hijri-converter"]
+fasttext = ["fasttext"]
+langdetect = ["langdetect"]
+
 [[package]]
 name = "decorator"
 version = "5.1.1"
@@ -1391,6 +1444,31 @@ aiounittest = ">=1.4.2"
 fake_useragent = ">=1.1.0"
 requests = ">=2.28.1"
 
+[[package]]
+name = "htmldate"
+version = "1.6.0"
+description = "Fast and robust extraction of original and updated publication dates from URLs and web pages."
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "htmldate-1.6.0-py3-none-any.whl", hash = "sha256:6ee374849fe7491b3e6c0b26066e8f6940367b0215e7c4fec88774af065a4dbc"},
+    {file = "htmldate-1.6.0.tar.gz", hash = "sha256:5827c8f626a16800a29e57e8188a3d32d0b08ca4c7bd662537b73bbbf22c45a6"},
+]
+
+[package.dependencies]
+charset-normalizer = {version = ">=3.3.2", markers = "python_version >= \"3.7\""}
+dateparser = ">=1.1.2"
+lxml = [
+    {version = ">=4.9.3", markers = "platform_system != \"Darwin\""},
+    {version = "4.9.2", markers = "platform_system == \"Darwin\""},
+]
+python-dateutil = ">=2.8.2"
+urllib3 = {version = ">=1.26,<3", markers = "python_version >= \"3.7\""}
+
+[package.extras]
+all = ["backports-datetime-fromisoformat", "faust-cchardet (>=2.1.19)", "urllib3[brotli]"]
+speed = ["backports-datetime-fromisoformat", "faust-cchardet (>=2.1.19)", "urllib3[brotli]"]
+
 [[package]]
 name = "httpcore"
 version = "0.16.3"
@@ -1580,6 +1658,20 @@ files = [
     {file = "jmespath-1.0.1.tar.gz", hash = "sha256:90261b206d6defd58fdd5e85f478bf633a2901798906be2ad389150c5c60edbe"},
 ]
 
+[[package]]
+name = "justext"
+version = "3.0.0"
+description = "Heuristic based boilerplate removal tool"
+optional = false
+python-versions = "*"
+files = [
+    {file = "jusText-3.0.0-py2.py3-none-any.whl", hash = "sha256:86b48f5b1d99505acd072f5831def6cd3f1306043651c524a1c609e62e3544e4"},
+    {file = "jusText-3.0.0.tar.gz", hash = "sha256:7640e248218795f6be65f6c35fe697325a3280fcb4675d1525bcdff2b86faadf"},
+]
+
+[package.dependencies]
+lxml = ">=4.4.2"
+
 [[package]]
 name = "kombu"
 version = "5.2.4"
@@ -1611,6 +1703,20 @@ sqs = ["boto3 (>=1.9.12)", "pycurl (>=7.44.1,<7.45.0)", "urllib3 (>=1.26.7)"]
 yaml = ["PyYAML (>=3.10)"]
 zookeeper = ["kazoo (>=1.3.1)"]
 
+[[package]]
+name = "langcodes"
+version = "3.3.0"
+description = "Tools for labeling human languages with IETF language tags"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "langcodes-3.3.0-py3-none-any.whl", hash = "sha256:4d89fc9acb6e9c8fdef70bcdf376113a3db09b67285d9e1d534de6d8818e7e69"},
+    {file = "langcodes-3.3.0.tar.gz", hash = "sha256:794d07d5a28781231ac335a1561b8442f8648ca07cd518310aeb45d6f0807ef6"},
+]
+
+[package.extras]
+data = ["language-data (>=1.1,<2.0)"]
+
 [[package]]
 name = "lxml"
 version = "4.9.2"
@@ -1703,6 +1809,113 @@ html5 = ["html5lib"]
 htmlsoup = ["BeautifulSoup4"]
 source = ["Cython (>=0.29.7)"]
 
+[[package]]
+name = "lxml"
+version = "4.9.3"
+description = "Powerful and Pythonic XML processing library combining libxml2/libxslt with the ElementTree API."
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, != 3.4.*"
+files = [
+    {file = "lxml-4.9.3-cp27-cp27m-macosx_11_0_x86_64.whl", hash = "sha256:b0a545b46b526d418eb91754565ba5b63b1c0b12f9bd2f808c852d9b4b2f9b5c"},
+    {file = "lxml-4.9.3-cp27-cp27m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:075b731ddd9e7f68ad24c635374211376aa05a281673ede86cbe1d1b3455279d"},
+    {file = "lxml-4.9.3-cp27-cp27m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:1e224d5755dba2f4a9498e150c43792392ac9b5380aa1b845f98a1618c94eeef"},
+    {file = "lxml-4.9.3-cp27-cp27m-win32.whl", hash = "sha256:2c74524e179f2ad6d2a4f7caf70e2d96639c0954c943ad601a9e146c76408ed7"},
+    {file = "lxml-4.9.3-cp27-cp27m-win_amd64.whl", hash = "sha256:4f1026bc732b6a7f96369f7bfe1a4f2290fb34dce00d8644bc3036fb351a4ca1"},
+    {file = "lxml-4.9.3-cp27-cp27mu-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:c0781a98ff5e6586926293e59480b64ddd46282953203c76ae15dbbbf302e8bb"},
+    {file = "lxml-4.9.3-cp27-cp27mu-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:cef2502e7e8a96fe5ad686d60b49e1ab03e438bd9123987994528febd569868e"},
+    {file = "lxml-4.9.3-cp310-cp310-macosx_11_0_x86_64.whl", hash = "sha256:b86164d2cff4d3aaa1f04a14685cbc072efd0b4f99ca5708b2ad1b9b5988a991"},
+    {file = "lxml-4.9.3-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:42871176e7896d5d45138f6d28751053c711ed4d48d8e30b498da155af39aebd"},
+    {file = "lxml-4.9.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:ae8b9c6deb1e634ba4f1930eb67ef6e6bf6a44b6eb5ad605642b2d6d5ed9ce3c"},
+    {file = "lxml-4.9.3-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:411007c0d88188d9f621b11d252cce90c4a2d1a49db6c068e3c16422f306eab8"},
+    {file = "lxml-4.9.3-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:cd47b4a0d41d2afa3e58e5bf1f62069255aa2fd6ff5ee41604418ca925911d76"},
+    {file = "lxml-4.9.3-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:0e2cb47860da1f7e9a5256254b74ae331687b9672dfa780eed355c4c9c3dbd23"},
+    {file = "lxml-4.9.3-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:1247694b26342a7bf47c02e513d32225ededd18045264d40758abeb3c838a51f"},
+    {file = "lxml-4.9.3-cp310-cp310-win32.whl", hash = "sha256:cdb650fc86227eba20de1a29d4b2c1bfe139dc75a0669270033cb2ea3d391b85"},
+    {file = "lxml-4.9.3-cp310-cp310-win_amd64.whl", hash = "sha256:97047f0d25cd4bcae81f9ec9dc290ca3e15927c192df17331b53bebe0e3ff96d"},
+    {file = "lxml-4.9.3-cp311-cp311-macosx_11_0_universal2.whl", hash = "sha256:1f447ea5429b54f9582d4b955f5f1985f278ce5cf169f72eea8afd9502973dd5"},
+    {file = "lxml-4.9.3-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:57d6ba0ca2b0c462f339640d22882acc711de224d769edf29962b09f77129cbf"},
+    {file = "lxml-4.9.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:9767e79108424fb6c3edf8f81e6730666a50feb01a328f4a016464a5893f835a"},
+    {file = "lxml-4.9.3-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:71c52db65e4b56b8ddc5bb89fb2e66c558ed9d1a74a45ceb7dcb20c191c3df2f"},
+    {file = "lxml-4.9.3-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:d73d8ecf8ecf10a3bd007f2192725a34bd62898e8da27eb9d32a58084f93962b"},
+    {file = "lxml-4.9.3-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:0a3d3487f07c1d7f150894c238299934a2a074ef590b583103a45002035be120"},
+    {file = "lxml-4.9.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:9e28c51fa0ce5674be9f560c6761c1b441631901993f76700b1b30ca6c8378d6"},
+    {file = "lxml-4.9.3-cp311-cp311-win32.whl", hash = "sha256:0bfd0767c5c1de2551a120673b72e5d4b628737cb05414f03c3277bf9bed3305"},
+    {file = "lxml-4.9.3-cp311-cp311-win_amd64.whl", hash = "sha256:25f32acefac14ef7bd53e4218fe93b804ef6f6b92ffdb4322bb6d49d94cad2bc"},
+    {file = "lxml-4.9.3-cp312-cp312-macosx_11_0_universal2.whl", hash = "sha256:d3ff32724f98fbbbfa9f49d82852b159e9784d6094983d9a8b7f2ddaebb063d4"},
+    {file = "lxml-4.9.3-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:48d6ed886b343d11493129e019da91d4039826794a3e3027321c56d9e71505be"},
+    {file = "lxml-4.9.3-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:9a92d3faef50658dd2c5470af249985782bf754c4e18e15afb67d3ab06233f13"},
+    {file = "lxml-4.9.3-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:b4e4bc18382088514ebde9328da057775055940a1f2e18f6ad2d78aa0f3ec5b9"},
+    {file = "lxml-4.9.3-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:fc9b106a1bf918db68619fdcd6d5ad4f972fdd19c01d19bdb6bf63f3589a9ec5"},
+    {file = "lxml-4.9.3-cp312-cp312-win_amd64.whl", hash = "sha256:d37017287a7adb6ab77e1c5bee9bcf9660f90ff445042b790402a654d2ad81d8"},
+    {file = "lxml-4.9.3-cp35-cp35m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:56dc1f1ebccc656d1b3ed288f11e27172a01503fc016bcabdcbc0978b19352b7"},
+    {file = "lxml-4.9.3-cp35-cp35m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:578695735c5a3f51569810dfebd05dd6f888147a34f0f98d4bb27e92b76e05c2"},
+    {file = "lxml-4.9.3-cp35-cp35m-win32.whl", hash = "sha256:704f61ba8c1283c71b16135caf697557f5ecf3e74d9e453233e4771d68a1f42d"},
+    {file = "lxml-4.9.3-cp35-cp35m-win_amd64.whl", hash = "sha256:c41bfca0bd3532d53d16fd34d20806d5c2b1ace22a2f2e4c0008570bf2c58833"},
+    {file = "lxml-4.9.3-cp36-cp36m-macosx_11_0_x86_64.whl", hash = "sha256:64f479d719dc9f4c813ad9bb6b28f8390360660b73b2e4beb4cb0ae7104f1c12"},
+    {file = "lxml-4.9.3-cp36-cp36m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:dd708cf4ee4408cf46a48b108fb9427bfa00b9b85812a9262b5c668af2533ea5"},
+    {file = "lxml-4.9.3-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5c31c7462abdf8f2ac0577d9f05279727e698f97ecbb02f17939ea99ae8daa98"},
+    {file = "lxml-4.9.3-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:e3cd95e10c2610c360154afdc2f1480aea394f4a4f1ea0a5eacce49640c9b190"},
+    {file = "lxml-4.9.3-cp36-cp36m-manylinux_2_28_x86_64.whl", hash = "sha256:4930be26af26ac545c3dffb662521d4e6268352866956672231887d18f0eaab2"},
+    {file = "lxml-4.9.3-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:4aec80cde9197340bc353d2768e2a75f5f60bacda2bab72ab1dc499589b3878c"},
+    {file = "lxml-4.9.3-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:14e019fd83b831b2e61baed40cab76222139926b1fb5ed0e79225bc0cae14584"},
+    {file = "lxml-4.9.3-cp36-cp36m-musllinux_1_1_aarch64.whl", hash = "sha256:0c0850c8b02c298d3c7006b23e98249515ac57430e16a166873fc47a5d549287"},
+    {file = "lxml-4.9.3-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:aca086dc5f9ef98c512bac8efea4483eb84abbf926eaeedf7b91479feb092458"},
+    {file = "lxml-4.9.3-cp36-cp36m-win32.whl", hash = "sha256:50baa9c1c47efcaef189f31e3d00d697c6d4afda5c3cde0302d063492ff9b477"},
+    {file = "lxml-4.9.3-cp36-cp36m-win_amd64.whl", hash = "sha256:bef4e656f7d98aaa3486d2627e7d2df1157d7e88e7efd43a65aa5dd4714916cf"},
+    {file = "lxml-4.9.3-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:46f409a2d60f634fe550f7133ed30ad5321ae2e6630f13657fb9479506b00601"},
+    {file = "lxml-4.9.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:4c28a9144688aef80d6ea666c809b4b0e50010a2aca784c97f5e6bf143d9f129"},
+    {file = "lxml-4.9.3-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:141f1d1a9b663c679dc524af3ea1773e618907e96075262726c7612c02b149a4"},
+    {file = "lxml-4.9.3-cp37-cp37m-manylinux_2_28_x86_64.whl", hash = "sha256:53ace1c1fd5a74ef662f844a0413446c0629d151055340e9893da958a374f70d"},
+    {file = "lxml-4.9.3-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:17a753023436a18e27dd7769e798ce302963c236bc4114ceee5b25c18c52c693"},
+    {file = "lxml-4.9.3-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:7d298a1bd60c067ea75d9f684f5f3992c9d6766fadbc0bcedd39750bf344c2f4"},
+    {file = "lxml-4.9.3-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:081d32421db5df44c41b7f08a334a090a545c54ba977e47fd7cc2deece78809a"},
+    {file = "lxml-4.9.3-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:23eed6d7b1a3336ad92d8e39d4bfe09073c31bfe502f20ca5116b2a334f8ec02"},
+    {file = "lxml-4.9.3-cp37-cp37m-win32.whl", hash = "sha256:1509dd12b773c02acd154582088820893109f6ca27ef7291b003d0e81666109f"},
+    {file = "lxml-4.9.3-cp37-cp37m-win_amd64.whl", hash = "sha256:120fa9349a24c7043854c53cae8cec227e1f79195a7493e09e0c12e29f918e52"},
+    {file = "lxml-4.9.3-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:4d2d1edbca80b510443f51afd8496be95529db04a509bc8faee49c7b0fb6d2cc"},
+    {file = "lxml-4.9.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.manylinux_2_24_aarch64.whl", hash = "sha256:8d7e43bd40f65f7d97ad8ef5c9b1778943d02f04febef12def25f7583d19baac"},
+    {file = "lxml-4.9.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:71d66ee82e7417828af6ecd7db817913cb0cf9d4e61aa0ac1fde0583d84358db"},
+    {file = "lxml-4.9.3-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:6fc3c450eaa0b56f815c7b62f2b7fba7266c4779adcf1cece9e6deb1de7305ce"},
+    {file = "lxml-4.9.3-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:65299ea57d82fb91c7f019300d24050c4ddeb7c5a190e076b5f48a2b43d19c42"},
+    {file = "lxml-4.9.3-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:eadfbbbfb41b44034a4c757fd5d70baccd43296fb894dba0295606a7cf3124aa"},
+    {file = "lxml-4.9.3-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:3e9bdd30efde2b9ccfa9cb5768ba04fe71b018a25ea093379c857c9dad262c40"},
+    {file = "lxml-4.9.3-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:fcdd00edfd0a3001e0181eab3e63bd5c74ad3e67152c84f93f13769a40e073a7"},
+    {file = "lxml-4.9.3-cp38-cp38-win32.whl", hash = "sha256:57aba1bbdf450b726d58b2aea5fe47c7875f5afb2c4a23784ed78f19a0462574"},
+    {file = "lxml-4.9.3-cp38-cp38-win_amd64.whl", hash = "sha256:92af161ecbdb2883c4593d5ed4815ea71b31fafd7fd05789b23100d081ecac96"},
+    {file = "lxml-4.9.3-cp39-cp39-macosx_11_0_x86_64.whl", hash = "sha256:9bb6ad405121241e99a86efff22d3ef469024ce22875a7ae045896ad23ba2340"},
+    {file = "lxml-4.9.3-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:8ed74706b26ad100433da4b9d807eae371efaa266ffc3e9191ea436087a9d6a7"},
+    {file = "lxml-4.9.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:fbf521479bcac1e25a663df882c46a641a9bff6b56dc8b0fafaebd2f66fb231b"},
+    {file = "lxml-4.9.3-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:303bf1edce6ced16bf67a18a1cf8339d0db79577eec5d9a6d4a80f0fb10aa2da"},
+    {file = "lxml-4.9.3-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:5515edd2a6d1a5a70bfcdee23b42ec33425e405c5b351478ab7dc9347228f96e"},
+    {file = "lxml-4.9.3-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:690dafd0b187ed38583a648076865d8c229661ed20e48f2335d68e2cf7dc829d"},
+    {file = "lxml-4.9.3-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:b6420a005548ad52154c8ceab4a1290ff78d757f9e5cbc68f8c77089acd3c432"},
+    {file = "lxml-4.9.3-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:bb3bb49c7a6ad9d981d734ef7c7193bc349ac338776a0360cc671eaee89bcf69"},
+    {file = "lxml-4.9.3-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:d27be7405547d1f958b60837dc4c1007da90b8b23f54ba1f8b728c78fdb19d50"},
+    {file = "lxml-4.9.3-cp39-cp39-win32.whl", hash = "sha256:8df133a2ea5e74eef5e8fc6f19b9e085f758768a16e9877a60aec455ed2609b2"},
+    {file = "lxml-4.9.3-cp39-cp39-win_amd64.whl", hash = "sha256:4dd9a263e845a72eacb60d12401e37c616438ea2e5442885f65082c276dfb2b2"},
+    {file = "lxml-4.9.3-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:6689a3d7fd13dc687e9102a27e98ef33730ac4fe37795d5036d18b4d527abd35"},
+    {file = "lxml-4.9.3-pp37-pypy37_pp73-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:f6bdac493b949141b733c5345b6ba8f87a226029cbabc7e9e121a413e49441e0"},
+    {file = "lxml-4.9.3-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:05186a0f1346ae12553d66df1cfce6f251589fea3ad3da4f3ef4e34b2d58c6a3"},
+    {file = "lxml-4.9.3-pp37-pypy37_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:c2006f5c8d28dee289f7020f721354362fa304acbaaf9745751ac4006650254b"},
+    {file = "lxml-4.9.3-pp38-pypy38_pp73-macosx_11_0_x86_64.whl", hash = "sha256:5c245b783db29c4e4fbbbfc9c5a78be496c9fea25517f90606aa1f6b2b3d5f7b"},
+    {file = "lxml-4.9.3-pp38-pypy38_pp73-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:4fb960a632a49f2f089d522f70496640fdf1218f1243889da3822e0a9f5f3ba7"},
+    {file = "lxml-4.9.3-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:50670615eaf97227d5dc60de2dc99fb134a7130d310d783314e7724bf163f75d"},
+    {file = "lxml-4.9.3-pp38-pypy38_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:9719fe17307a9e814580af1f5c6e05ca593b12fb7e44fe62450a5384dbf61b4b"},
+    {file = "lxml-4.9.3-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:3331bece23c9ee066e0fb3f96c61322b9e0f54d775fccefff4c38ca488de283a"},
+    {file = "lxml-4.9.3-pp39-pypy39_pp73-macosx_11_0_x86_64.whl", hash = "sha256:ed667f49b11360951e201453fc3967344d0d0263aa415e1619e85ae7fd17b4e0"},
+    {file = "lxml-4.9.3-pp39-pypy39_pp73-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_24_i686.whl", hash = "sha256:8b77946fd508cbf0fccd8e400a7f71d4ac0e1595812e66025bac475a8e811694"},
+    {file = "lxml-4.9.3-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl", hash = "sha256:e4da8ca0c0c0aea88fd46be8e44bd49716772358d648cce45fe387f7b92374a7"},
+    {file = "lxml-4.9.3-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:fe4bda6bd4340caa6e5cf95e73f8fea5c4bfc55763dd42f1b50a94c1b4a2fbd4"},
+    {file = "lxml-4.9.3-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:f3df3db1d336b9356dd3112eae5f5c2b8b377f3bc826848567f10bfddfee77e9"},
+    {file = "lxml-4.9.3.tar.gz", hash = "sha256:48628bd53a426c9eb9bc066a923acaa0878d1e86129fd5359aee99285f4eed9c"},
+]
+
+[package.extras]
+cssselect = ["cssselect (>=0.7)"]
+html5 = ["html5lib"]
+htmlsoup = ["BeautifulSoup4"]
+source = ["Cython (>=0.29.35)"]
+
 [[package]]
 name = "markdown"
 version = "3.4.3"
@@ -2777,6 +2990,103 @@ async-timeout = {version = ">=4.0.2", markers = "python_version < \"3.11\""}
 hiredis = ["hiredis (>=1.0.0)"]
 ocsp = ["cryptography (>=36.0.1)", "pyopenssl (==20.0.1)", "requests (>=2.26.0)"]
 
+[[package]]
+name = "regex"
+version = "2023.10.3"
+description = "Alternative regular expression module, to replace re."
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "regex-2023.10.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:4c34d4f73ea738223a094d8e0ffd6d2c1a1b4c175da34d6b0de3d8d69bee6bcc"},
+    {file = "regex-2023.10.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:a8f4e49fc3ce020f65411432183e6775f24e02dff617281094ba6ab079ef0915"},
+    {file = "regex-2023.10.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4cd1bccf99d3ef1ab6ba835308ad85be040e6a11b0977ef7ea8c8005f01a3c29"},
+    {file = "regex-2023.10.3-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:81dce2ddc9f6e8f543d94b05d56e70d03a0774d32f6cca53e978dc01e4fc75b8"},
+    {file = "regex-2023.10.3-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9c6b4d23c04831e3ab61717a707a5d763b300213db49ca680edf8bf13ab5d91b"},
+    {file = "regex-2023.10.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c15ad0aee158a15e17e0495e1e18741573d04eb6da06d8b84af726cfc1ed02ee"},
+    {file = "regex-2023.10.3-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6239d4e2e0b52c8bd38c51b760cd870069f0bdf99700a62cd509d7a031749a55"},
+    {file = "regex-2023.10.3-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:4a8bf76e3182797c6b1afa5b822d1d5802ff30284abe4599e1247be4fd6b03be"},
+    {file = "regex-2023.10.3-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:d9c727bbcf0065cbb20f39d2b4f932f8fa1631c3e01fcedc979bd4f51fe051c5"},
+    {file = "regex-2023.10.3-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:3ccf2716add72f80714b9a63899b67fa711b654be3fcdd34fa391d2d274ce767"},
+    {file = "regex-2023.10.3-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:107ac60d1bfdc3edb53be75e2a52aff7481b92817cfdddd9b4519ccf0e54a6ff"},
+    {file = "regex-2023.10.3-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:00ba3c9818e33f1fa974693fb55d24cdc8ebafcb2e4207680669d8f8d7cca79a"},
+    {file = "regex-2023.10.3-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:f0a47efb1dbef13af9c9a54a94a0b814902e547b7f21acb29434504d18f36e3a"},
+    {file = "regex-2023.10.3-cp310-cp310-win32.whl", hash = "sha256:36362386b813fa6c9146da6149a001b7bd063dabc4d49522a1f7aa65b725c7ec"},
+    {file = "regex-2023.10.3-cp310-cp310-win_amd64.whl", hash = "sha256:c65a3b5330b54103e7d21cac3f6bf3900d46f6d50138d73343d9e5b2900b2353"},
+    {file = "regex-2023.10.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:90a79bce019c442604662d17bf69df99090e24cdc6ad95b18b6725c2988a490e"},
+    {file = "regex-2023.10.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:c7964c2183c3e6cce3f497e3a9f49d182e969f2dc3aeeadfa18945ff7bdd7051"},
+    {file = "regex-2023.10.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4ef80829117a8061f974b2fda8ec799717242353bff55f8a29411794d635d964"},
+    {file = "regex-2023.10.3-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5addc9d0209a9afca5fc070f93b726bf7003bd63a427f65ef797a931782e7edc"},
+    {file = "regex-2023.10.3-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c148bec483cc4b421562b4bcedb8e28a3b84fcc8f0aa4418e10898f3c2c0eb9b"},
+    {file = "regex-2023.10.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8d1f21af4c1539051049796a0f50aa342f9a27cde57318f2fc41ed50b0dbc4ac"},
+    {file = "regex-2023.10.3-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0b9ac09853b2a3e0d0082104036579809679e7715671cfbf89d83c1cb2a30f58"},
+    {file = "regex-2023.10.3-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:ebedc192abbc7fd13c5ee800e83a6df252bec691eb2c4bedc9f8b2e2903f5e2a"},
+    {file = "regex-2023.10.3-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:d8a993c0a0ffd5f2d3bda23d0cd75e7086736f8f8268de8a82fbc4bd0ac6791e"},
+    {file = "regex-2023.10.3-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:be6b7b8d42d3090b6c80793524fa66c57ad7ee3fe9722b258aec6d0672543fd0"},
+    {file = "regex-2023.10.3-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:4023e2efc35a30e66e938de5aef42b520c20e7eda7bb5fb12c35e5d09a4c43f6"},
+    {file = "regex-2023.10.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:0d47840dc05e0ba04fe2e26f15126de7c755496d5a8aae4a08bda4dd8d646c54"},
+    {file = "regex-2023.10.3-cp311-cp311-win32.whl", hash = "sha256:9145f092b5d1977ec8c0ab46e7b3381b2fd069957b9862a43bd383e5c01d18c2"},
+    {file = "regex-2023.10.3-cp311-cp311-win_amd64.whl", hash = "sha256:b6104f9a46bd8743e4f738afef69b153c4b8b592d35ae46db07fc28ae3d5fb7c"},
+    {file = "regex-2023.10.3-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:bff507ae210371d4b1fe316d03433ac099f184d570a1a611e541923f78f05037"},
+    {file = "regex-2023.10.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:be5e22bbb67924dea15039c3282fa4cc6cdfbe0cbbd1c0515f9223186fc2ec5f"},
+    {file = "regex-2023.10.3-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4a992f702c9be9c72fa46f01ca6e18d131906a7180950958f766c2aa294d4b41"},
+    {file = "regex-2023.10.3-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:7434a61b158be563c1362d9071358f8ab91b8d928728cd2882af060481244c9e"},
+    {file = "regex-2023.10.3-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c2169b2dcabf4e608416f7f9468737583ce5f0a6e8677c4efbf795ce81109d7c"},
+    {file = "regex-2023.10.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a9e908ef5889cda4de038892b9accc36d33d72fb3e12c747e2799a0e806ec841"},
+    {file = "regex-2023.10.3-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:12bd4bc2c632742c7ce20db48e0d99afdc05e03f0b4c1af90542e05b809a03d9"},
+    {file = "regex-2023.10.3-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:bc72c231f5449d86d6c7d9cc7cd819b6eb30134bb770b8cfdc0765e48ef9c420"},
+    {file = "regex-2023.10.3-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:bce8814b076f0ce5766dc87d5a056b0e9437b8e0cd351b9a6c4e1134a7dfbda9"},
+    {file = "regex-2023.10.3-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:ba7cd6dc4d585ea544c1412019921570ebd8a597fabf475acc4528210d7c4a6f"},
+    {file = "regex-2023.10.3-cp312-cp312-musllinux_1_1_s390x.whl", hash = "sha256:b0c7d2f698e83f15228ba41c135501cfe7d5740181d5903e250e47f617eb4292"},
+    {file = "regex-2023.10.3-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:5a8f91c64f390ecee09ff793319f30a0f32492e99f5dc1c72bc361f23ccd0a9a"},
+    {file = "regex-2023.10.3-cp312-cp312-win32.whl", hash = "sha256:ad08a69728ff3c79866d729b095872afe1e0557251da4abb2c5faff15a91d19a"},
+    {file = "regex-2023.10.3-cp312-cp312-win_amd64.whl", hash = "sha256:39cdf8d141d6d44e8d5a12a8569d5a227f645c87df4f92179bd06e2e2705e76b"},
+    {file = "regex-2023.10.3-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:4a3ee019a9befe84fa3e917a2dd378807e423d013377a884c1970a3c2792d293"},
+    {file = "regex-2023.10.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:76066d7ff61ba6bf3cb5efe2428fc82aac91802844c022d849a1f0f53820502d"},
+    {file = "regex-2023.10.3-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:bfe50b61bab1b1ec260fa7cd91106fa9fece57e6beba05630afe27c71259c59b"},
+    {file = "regex-2023.10.3-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9fd88f373cb71e6b59b7fa597e47e518282455c2734fd4306a05ca219a1991b0"},
+    {file = "regex-2023.10.3-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b3ab05a182c7937fb374f7e946f04fb23a0c0699c0450e9fb02ef567412d2fa3"},
+    {file = "regex-2023.10.3-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:dac37cf08fcf2094159922edc7a2784cfcc5c70f8354469f79ed085f0328ebdf"},
+    {file = "regex-2023.10.3-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:e54ddd0bb8fb626aa1f9ba7b36629564544954fff9669b15da3610c22b9a0991"},
+    {file = "regex-2023.10.3-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:3367007ad1951fde612bf65b0dffc8fd681a4ab98ac86957d16491400d661302"},
+    {file = "regex-2023.10.3-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:16f8740eb6dbacc7113e3097b0a36065a02e37b47c936b551805d40340fb9971"},
+    {file = "regex-2023.10.3-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:f4f2ca6df64cbdd27f27b34f35adb640b5d2d77264228554e68deda54456eb11"},
+    {file = "regex-2023.10.3-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:39807cbcbe406efca2a233884e169d056c35aa7e9f343d4e78665246a332f597"},
+    {file = "regex-2023.10.3-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:7eece6fbd3eae4a92d7c748ae825cbc1ee41a89bb1c3db05b5578ed3cfcfd7cb"},
+    {file = "regex-2023.10.3-cp37-cp37m-win32.whl", hash = "sha256:ce615c92d90df8373d9e13acddd154152645c0dc060871abf6bd43809673d20a"},
+    {file = "regex-2023.10.3-cp37-cp37m-win_amd64.whl", hash = "sha256:0f649fa32fe734c4abdfd4edbb8381c74abf5f34bc0b3271ce687b23729299ed"},
+    {file = "regex-2023.10.3-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:9b98b7681a9437262947f41c7fac567c7e1f6eddd94b0483596d320092004533"},
+    {file = "regex-2023.10.3-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:91dc1d531f80c862441d7b66c4505cd6ea9d312f01fb2f4654f40c6fdf5cc37a"},
+    {file = "regex-2023.10.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:82fcc1f1cc3ff1ab8a57ba619b149b907072e750815c5ba63e7aa2e1163384a4"},
+    {file = "regex-2023.10.3-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:7979b834ec7a33aafae34a90aad9f914c41fd6eaa8474e66953f3f6f7cbd4368"},
+    {file = "regex-2023.10.3-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ef71561f82a89af6cfcbee47f0fabfdb6e63788a9258e913955d89fdd96902ab"},
+    {file = "regex-2023.10.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dd829712de97753367153ed84f2de752b86cd1f7a88b55a3a775eb52eafe8a94"},
+    {file = "regex-2023.10.3-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:00e871d83a45eee2f8688d7e6849609c2ca2a04a6d48fba3dff4deef35d14f07"},
+    {file = "regex-2023.10.3-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:706e7b739fdd17cb89e1fbf712d9dc21311fc2333f6d435eac2d4ee81985098c"},
+    {file = "regex-2023.10.3-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:cc3f1c053b73f20c7ad88b0d1d23be7e7b3901229ce89f5000a8399746a6e039"},
+    {file = "regex-2023.10.3-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:6f85739e80d13644b981a88f529d79c5bdf646b460ba190bffcaf6d57b2a9863"},
+    {file = "regex-2023.10.3-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:741ba2f511cc9626b7561a440f87d658aabb3d6b744a86a3c025f866b4d19e7f"},
+    {file = "regex-2023.10.3-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:e77c90ab5997e85901da85131fd36acd0ed2221368199b65f0d11bca44549711"},
+    {file = "regex-2023.10.3-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:979c24cbefaf2420c4e377ecd1f165ea08cc3d1fbb44bdc51bccbbf7c66a2cb4"},
+    {file = "regex-2023.10.3-cp38-cp38-win32.whl", hash = "sha256:58837f9d221744d4c92d2cf7201c6acd19623b50c643b56992cbd2b745485d3d"},
+    {file = "regex-2023.10.3-cp38-cp38-win_amd64.whl", hash = "sha256:c55853684fe08d4897c37dfc5faeff70607a5f1806c8be148f1695be4a63414b"},
+    {file = "regex-2023.10.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:2c54e23836650bdf2c18222c87f6f840d4943944146ca479858404fedeb9f9af"},
+    {file = "regex-2023.10.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:69c0771ca5653c7d4b65203cbfc5e66db9375f1078689459fe196fe08b7b4930"},
+    {file = "regex-2023.10.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6ac965a998e1388e6ff2e9781f499ad1eaa41e962a40d11c7823c9952c77123e"},
+    {file = "regex-2023.10.3-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1c0e8fae5b27caa34177bdfa5a960c46ff2f78ee2d45c6db15ae3f64ecadde14"},
+    {file = "regex-2023.10.3-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:6c56c3d47da04f921b73ff9415fbaa939f684d47293f071aa9cbb13c94afc17d"},
+    {file = "regex-2023.10.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7ef1e014eed78ab650bef9a6a9cbe50b052c0aebe553fb2881e0453717573f52"},
+    {file = "regex-2023.10.3-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d29338556a59423d9ff7b6eb0cb89ead2b0875e08fe522f3e068b955c3e7b59b"},
+    {file = "regex-2023.10.3-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:9c6d0ced3c06d0f183b73d3c5920727268d2201aa0fe6d55c60d68c792ff3588"},
+    {file = "regex-2023.10.3-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:994645a46c6a740ee8ce8df7911d4aee458d9b1bc5639bc968226763d07f00fa"},
+    {file = "regex-2023.10.3-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:66e2fe786ef28da2b28e222c89502b2af984858091675044d93cb50e6f46d7af"},
+    {file = "regex-2023.10.3-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:11175910f62b2b8c055f2b089e0fedd694fe2be3941b3e2633653bc51064c528"},
+    {file = "regex-2023.10.3-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:06e9abc0e4c9ab4779c74ad99c3fc10d3967d03114449acc2c2762ad4472b8ca"},
+    {file = "regex-2023.10.3-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:fb02e4257376ae25c6dd95a5aec377f9b18c09be6ebdefa7ad209b9137b73d48"},
+    {file = "regex-2023.10.3-cp39-cp39-win32.whl", hash = "sha256:3b2c3502603fab52d7619b882c25a6850b766ebd1b18de3df23b2f939360e1bd"},
+    {file = "regex-2023.10.3-cp39-cp39-win_amd64.whl", hash = "sha256:adbccd17dcaff65704c856bd29951c58a1bd4b2b0f8ad6b826dbd543fe740988"},
+    {file = "regex-2023.10.3.tar.gz", hash = "sha256:3fef4f844d2290ee0ba57addcec17eec9e3df73f10a2748485dfd6a3a188cc0f"},
+]
+
 [[package]]
 name = "requests"
 version = "2.28.2"
@@ -3188,6 +3498,17 @@ webencodings = ">=0.4"
 doc = ["sphinx", "sphinx_rtd_theme"]
 test = ["coverage[toml]", "pytest", "pytest-cov", "pytest-flake8", "pytest-isort"]
 
+[[package]]
+name = "tld"
+version = "0.13"
+description = "Extract the top-level domain (TLD) from the URL given."
+optional = false
+python-versions = ">=3.7, <4"
+files = [
+    {file = "tld-0.13-py2.py3-none-any.whl", hash = "sha256:f75b2be080f767ed17c2338a339eaa4fab5792586319ca819119da252f9f3749"},
+    {file = "tld-0.13.tar.gz", hash = "sha256:93dde5e1c04bdf1844976eae440706379d21f4ab235b73c05d7483e074fb5629"},
+]
+
 [[package]]
 name = "toml"
 version = "0.10.2"
@@ -3210,6 +3531,33 @@ files = [
     {file = "tomli-2.0.1.tar.gz", hash = "sha256:de526c12914f0c550d15924c62d72abc48d6fe7364aa87328337a31007fe8a4f"},
 ]
 
+[[package]]
+name = "trafilatura"
+version = "1.6.3"
+description = "Python package and command-line tool designed to gather text on the Web. It includes discovery, extraction and text processing components. Its main applications are web crawling, downloads, scraping, and extraction of main texts, metadata and comments."
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "trafilatura-1.6.3-py3-none-any.whl", hash = "sha256:4f879045c6854d71e488cc669c42ee83b97fe584684bd288c752b7e5ae7402cf"},
+    {file = "trafilatura-1.6.3.tar.gz", hash = "sha256:671dd6e0000e101c4bce8d70f4408bcb79fcbf2275ee25591efe33e2c8a1600d"},
+]
+
+[package.dependencies]
+certifi = "*"
+charset-normalizer = {version = ">=3.2.0", markers = "python_version >= \"3.7\""}
+courlan = ">=0.9.5"
+htmldate = ">=1.6.0"
+justext = ">=3.0.0"
+lxml = [
+    {version = ">=4.9.3", markers = "platform_system != \"Darwin\""},
+    {version = "4.9.2", markers = "platform_system == \"Darwin\""},
+]
+urllib3 = {version = ">=1.26,<3", markers = "python_version >= \"3.7\""}
+
+[package.extras]
+all = ["brotli", "cchardet (>=2.1.7)", "faust-cchardet (>=2.1.18)", "htmldate[speed] (>=1.6.0)", "py3langid (>=0.2.2)", "pycurl (>=7.45.2)"]
+gui = ["Gooey (>=1.0.1)"]
+
 [[package]]
 name = "traitlets"
 version = "5.9.0"
@@ -3320,6 +3668,23 @@ files = [
     {file = "tzdata-2023.2.tar.gz", hash = "sha256:c3b51b235b07f9f1889089c2264bcbeaaba260a63f89bea09e350ea4205eb95f"},
 ]
 
+[[package]]
+name = "tzlocal"
+version = "5.2"
+description = "tzinfo object for the local timezone"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "tzlocal-5.2-py3-none-any.whl", hash = "sha256:49816ef2fe65ea8ac19d19aa7a1ae0551c834303d5014c6d5a62e4cbda8047b8"},
+    {file = "tzlocal-5.2.tar.gz", hash = "sha256:8d399205578f1a9342816409cc1e46a93ebd5755e39ea2d85334bea911bf0e6e"},
+]
+
+[package.dependencies]
+tzdata = {version = "*", markers = "platform_system == \"Windows\""}
+
+[package.extras]
+devenv = ["check-manifest", "pytest (>=4.3)", "pytest-cov", "pytest-mock (>=3.3)", "zest.releaser"]
+
 [[package]]
 name = "urllib3"
 version = "1.26.15"
@@ -3589,4 +3954,4 @@ testing = ["big-O", "flake8 (<5)", "jaraco.functools", "jaraco.itertools", "more
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.9,<4.0"
-content-hash = "4ef175b6d350e61e6152d335f3825318d0647be9c21f81c168441a1e17440bbb"
+content-hash = "47f7ab7850d11723274d6fafdf072a90618898a66d9dc6c845d1424df1944d77"

pyproject.toml

@@ -42,6 +42,7 @@ boto3 = "^1.26.98"
 stream-sqlite = "^0.0.41"
 ipython = "^8.14.0"
 pendulum = "^2.1.2"
+trafilatura = "^1.6.3"
 
 [tool.poetry.dev-dependencies]
 Werkzeug = "2.0.3"

vrobbler/apps/webpages/migrations/0002_webpage_domain_webpage_extract.py

@@ -0,0 +1,23 @@
+# Generated by Django 4.1.7 on 2023-11-30 17:15
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ("webpages", "0001_initial"),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name="webpage",
+            name="domain",
+            field=models.CharField(blank=True, max_length=200, null=True),
+        ),
+        migrations.AddField(
+            model_name="webpage",
+            name="extract",
+            field=models.TextField(blank=True, null=True),
+        ),
+    ]

vrobbler/apps/webpages/models.py

@@ -1,6 +1,7 @@
 import requests
 import logging
 from typing import Dict
+import trafilatura
 from uuid import uuid4
 
 from django.contrib.auth import get_user_model
@@ -19,6 +20,8 @@ class WebPage(ScrobblableMixin):
 
     uuid = models.UUIDField(default=uuid4, editable=False, **BNULL)
     url = models.URLField(max_length=500)
+    domain = models.CharField(max_length=200, **BNULL)
+    extract = models.TextField(**BNULL)
 
     def __str__(self):
         if self.title:
@@ -26,14 +29,22 @@ class WebPage(ScrobblableMixin):
 
         return self.domain
 
-    @property
-    def domain(self):
+    def _raw_domain(self):
         self.url.split("//")[-1].split("/")[0]
 
+    def _update_extract_from_web(self, force=True):
+        headers = {
+            "headers": "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:51.0) Gecko/20100101 Firefox/51.0"
+        }
+        raw_text = requests.get(self.url, headers=headers).text
+        if not self.extract or force:
+            self.extract = trafilatura.extract(raw_text)
+            self.save(update_fields=["extract"])
+
     def get_absolute_url(self):
         return reverse("webpages:webpage_detail", kwargs={"slug": self.uuid})
 
-    def _update_title_from_web(self, force=False):
+    def _update_data_from_web(self, force=True):
         headers = {
             "headers": "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:51.0) Gecko/20100101 Firefox/51.0"
         }
@@ -42,7 +53,14 @@ class WebPage(ScrobblableMixin):
             self.title = raw_text[
                 raw_text.find("<title>") + 7 : raw_text.find("</title>")
             ]
-            self.save(update_fields=["title"])
+
+        if not self.extract or force:
+            self.extract = trafilatura.extract(raw_text)
+
+        if not self.domain or force:
+            self.domain = self.url.split("//")[-1].split("/")[0]
+
+        self.save(update_fields=["title", "domain", "extract"])
 
     @classmethod
     def find_or_create(cls, data_dict: Dict) -> "GeoLocation":
@@ -60,5 +78,5 @@ class WebPage(ScrobblableMixin):
         if not webpage:
             webpage = cls.objects.create(url=data_dict.get("url"))
             webpage.run_time_seconds = settings.get("WEBSITE_READ_TIME", 600)
-            webpage._update_title_from_web()
+            webpage._update_data_from_web()
         return webpage