From c655b939a4d2be165c1ac7c25ebe96b974a85aec Mon Sep 17 00:00:00 2001
From: Bartal Laearsson <bartal@flo.fo>
Date: Thu, 13 Aug 2026 14:51:28 +0100
Subject: [PATCH] yeah works

---
 .gitignore          |    2 +
 Cargo.lock          | 2012 +++++++++++++++++++++++++++++++++++++++++++
 Cargo.toml          |   17 +
 src/config.rs       |    5 +
 src/error_logger.rs |   41 +
 src/extractor.rs    |   25 +
 src/fetcher.rs      |   99 +++
 src/main.rs         |   52 ++
 src/scraper.rs      |  135 +++
 src/url_utils.rs    |  127 +++
 10 files changed, 2515 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 Cargo.lock
 create mode 100644 Cargo.toml
 create mode 100644 src/config.rs
 create mode 100644 src/error_logger.rs
 create mode 100644 src/extractor.rs
 create mode 100644 src/fetcher.rs
 create mode 100644 src/main.rs
 create mode 100644 src/scraper.rs
 create mode 100644 src/url_utils.rs

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..4e540c8
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,2 @@
+/target
+scraped*
diff --git a/Cargo.lock b/Cargo.lock
new file mode 100644
index 0000000..e55e292
--- /dev/null
+++ b/Cargo.lock
@@ -0,0 +1,2012 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 4
+
+[[package]]
+name = "android_system_properties"
+version = "0.1.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ae221649c9976a6f6c56ae1facf410f3ddb33cc661c4b7b61020a912d4237fbc"
+dependencies = [
+ "libc",
+]
+
+[[package]]
+name = "anyhow"
+version = "1.0.104"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "330a5ed07fa54e4702c9d6c4174f74427fc0ef6e214bbd677ae50a5099946470"
+
+[[package]]
+name = "atomic-waker"
+version = "1.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1505bd5d3d116872e7271a6d4e16d81d0c8570876c8de68093a09ac269d8aac0"
+
+[[package]]
+name = "autocfg"
+version = "1.5.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f2032f911046de80f0a198e0901378627c33f59ea0ac00e363d481118bd70a53"
+
+[[package]]
+name = "base64"
+version = "0.22.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"
+
+[[package]]
+name = "bitflags"
+version = "2.13.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b588b76d00fde79687d7646a9b5bdf3cc0f655e0bbd080335a95d7e96f3587da"
+
+[[package]]
+name = "block-buffer"
+version = "0.10.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3078c7629b62d3f0439517fa394996acacc5cbc91c5a20d8c658e77abd503a71"
+dependencies = [
+ "generic-array",
+]
+
+[[package]]
+name = "bumpalo"
+version = "3.20.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "72f5acc6cb2ba439de613abc23857ec3d78374d8ed5ac84e9d11336e87da8649"
+
+[[package]]
+name = "byteorder"
+version = "1.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1fd0f2584146f6f2ef48085050886acf353beff7305ebd1ae69500e27c67f64b"
+
+[[package]]
+name = "bytes"
+version = "1.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fc652a48c352aef3ea3aed32080501cf3ef6ed5da78602a020c991775b0aff04"
+
+[[package]]
+name = "cc"
+version = "1.4.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5d262e149917187838d5b42777c8253bcb64500067342904e7d429499a6f277e"
+dependencies = [
+ "find-msvc-tools",
+ "shlex",
+]
+
+[[package]]
+name = "cfg-if"
+version = "1.0.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801"
+
+[[package]]
+name = "chrono"
+version = "0.4.45"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1aa79e62e7697b8e29b513a68abacf485adcd1fe8284a4316c5ae868e6633327"
+dependencies = [
+ "iana-time-zone",
+ "js-sys",
+ "num-traits",
+ "serde",
+ "wasm-bindgen",
+ "windows-link",
+]
+
+[[package]]
+name = "core-foundation"
+version = "0.9.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "91e195e091a93c46f7102ec7818a2aa394e1e1771c3ab4825963fa03e45afb8f"
+dependencies = [
+ "core-foundation-sys",
+ "libc",
+]
+
+[[package]]
+name = "core-foundation"
+version = "0.10.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b2a6cd9ae233e7f62ba4e9353e81a88df7fc8a5987b8d445b4d90c879bd156f6"
+dependencies = [
+ "core-foundation-sys",
+ "libc",
+]
+
+[[package]]
+name = "core-foundation-sys"
+version = "0.8.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "773648b94d0e5d620f64f280777445740e61fe701025087ec8b57f45c791888b"
+
+[[package]]
+name = "cpufeatures"
+version = "0.2.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "59ed5838eebb26a2bb2e58f6d5b5316989ae9d08bab10e0e6d103e656d1b0280"
+dependencies = [
+ "libc",
+]
+
+[[package]]
+name = "crypto-common"
+version = "0.1.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "78c8292055d1c1df0cce5d180393dc8cce0abec0a7102adb6c7b1eef6016d60a"
+dependencies = [
+ "generic-array",
+ "typenum",
+]
+
+[[package]]
+name = "cssparser"
+version = "0.34.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b7c66d1cd8ed61bf80b38432613a7a2f09401ab8d0501110655f8b341484a3e3"
+dependencies = [
+ "cssparser-macros",
+ "dtoa-short",
+ "itoa",
+ "phf",
+ "smallvec",
+]
+
+[[package]]
+name = "cssparser-macros"
+version = "0.6.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "13b588ba4ac1a99f7f2964d24b3d896ddc6bf847ee3855dbd4366f058cfcd331"
+dependencies = [
+ "quote",
+ "syn 2.0.119",
+]
+
+[[package]]
+name = "derive_more"
+version = "0.99.20"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6edb4b64a43d977b8e99788fe3a04d483834fba1215a7e02caa415b626497f7f"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.119",
+]
+
+[[package]]
+name = "digest"
+version = "0.10.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9ed9a281f7bc9b7576e61468ba615a66a5c8cfdff42420a70aa82701a3b1e292"
+dependencies = [
+ "block-buffer",
+ "crypto-common",
+]
+
+[[package]]
+name = "displaydoc"
+version = "0.2.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c6232dd377dcc64799954cbd3a9bb882e9cdc1308ccd87b1c098f1fb2eaf82a8"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 3.0.3",
+]
+
+[[package]]
+name = "dtoa"
+version = "1.0.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4c3cf4824e2d5f025c7b531afcb2325364084a16806f6d47fbc1f5fbd9960590"
+
+[[package]]
+name = "dtoa-short"
+version = "0.3.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cd1511a7b6a56299bd043a9c167a6d2bfb37bf84a6dfceaba651168adfb43c87"
+dependencies = [
+ "dtoa",
+]
+
+[[package]]
+name = "ego-tree"
+version = "0.10.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b2972feb8dffe7bc8c5463b1dacda1b0dfbed3710e50f977d965429692d74cd8"
+
+[[package]]
+name = "encoding_rs"
+version = "0.8.35"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "75030f3c4f45dafd7586dd6780965a8c7e8e285a5ecb86713e63a79c5b2766f3"
+dependencies = [
+ "cfg-if",
+]
+
+[[package]]
+name = "equivalent"
+version = "1.0.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "877a4ace8713b0bcf2a4e7eec82529c029f1d0619886d18145fea96c3ffe5c0f"
+
+[[package]]
+name = "errno"
+version = "0.3.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "39cab71617ae0d63f51a36d69f866391735b51691dbda63cf6f96d042b63efeb"
+dependencies = [
+ "libc",
+ "windows-sys 0.61.2",
+]
+
+[[package]]
+name = "fastrand"
+version = "2.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "da7c62ceae207dd37ea5b845da6a0696c799f85e97da1ab5b7910be3c1c80223"
+
+[[package]]
+name = "find-msvc-tools"
+version = "0.1.10"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "26b73573e6edcd2af0cdf47bd6cb58f0b3839491263c314eaad1ccf24430e1de"
+
+[[package]]
+name = "fnv"
+version = "1.0.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1"
+
+[[package]]
+name = "foreign-types"
+version = "0.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f6f339eb8adc052cd2ca78910fda869aefa38d22d5cb648e6485e4d3fc06f3b1"
+dependencies = [
+ "foreign-types-shared",
+]
+
+[[package]]
+name = "foreign-types-shared"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "00b0228411908ca8685dba7fc2cdd70ec9990a6e753e89b6ac91a84c40fbaf4b"
+
+[[package]]
+name = "form_urlencoded"
+version = "1.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cb4cb245038516f5f85277875cdaa4f7d2c9a0fa0468de06ed190163b1581fcf"
+dependencies = [
+ "percent-encoding",
+]
+
+[[package]]
+name = "futf"
+version = "0.1.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "df420e2e84819663797d1ec6544b13c5be84629e7bb00dc960d6917db2987843"
+dependencies = [
+ "mac",
+ "new_debug_unreachable",
+]
+
+[[package]]
+name = "futures-channel"
+version = "0.3.34"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b1f9e3d69d39e4862ffed03ed071a76f9a13ba1d9109d355b0f0aa6b15e393c4"
+dependencies = [
+ "futures-core",
+]
+
+[[package]]
+name = "futures-core"
+version = "0.3.34"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "92d699e522242e69e3003b94ecc1f960f3a5e015aa7c5d7486e65ad01dd94f5e"
+
+[[package]]
+name = "futures-sink"
+version = "0.3.34"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1944426bf7d03f1d14f708785e4b33efd750b36d48a157b836b3efc15ede8e1d"
+
+[[package]]
+name = "futures-task"
+version = "0.3.34"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cd417de3d1d015fc3bfd2b1ea46dfc7bab72ef86f1cc7cc9c78e728b34a6d1fd"
+
+[[package]]
+name = "futures-util"
+version = "0.3.34"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0d50a92467f8ba5dd6e3ee5d4bd04d73ab2e4e1c44474a0674821dfce14b79bc"
+dependencies = [
+ "futures-core",
+ "futures-task",
+ "pin-project-lite",
+ "slab",
+]
+
+[[package]]
+name = "fxhash"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c31b6d751ae2c7f11320402d34e41349dd1016f8d5d45e48c4312bc8625af50c"
+dependencies = [
+ "byteorder",
+]
+
+[[package]]
+name = "generic-array"
+version = "0.14.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "85649ca51fd72272d7821adaf274ad91c288277713d9c18820d8499a7ff69e9a"
+dependencies = [
+ "typenum",
+ "version_check",
+]
+
+[[package]]
+name = "getopts"
+version = "0.2.24"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cfe4fbac503b8d1f88e6676011885f34b7174f46e59956bba534ba83abded4df"
+dependencies = [
+ "unicode-width",
+]
+
+[[package]]
+name = "getrandom"
+version = "0.2.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ff2abc00be7fca6ebc474524697ae276ad847ad0a6b3faa4bcb027e9a4614ad0"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "wasi",
+]
+
+[[package]]
+name = "getrandom"
+version = "0.4.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "300e883d756b2e4ec94e02791f39b04b522276138852cfc41d9fb7e904106099"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "r-efi",
+]
+
+[[package]]
+name = "h2"
+version = "0.4.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6cb093c84e8bd9b188d4c4a8cb6579fc016968d14c99882163cd3ff402a4f155"
+dependencies = [
+ "atomic-waker",
+ "bytes",
+ "fnv",
+ "futures-core",
+ "futures-sink",
+ "http",
+ "indexmap",
+ "slab",
+ "tokio",
+ "tokio-util",
+ "tracing",
+]
+
+[[package]]
+name = "hashbrown"
+version = "0.17.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ed5909b6e89a2db4456e54cd5f673791d7eca6732202bbf2a9cc504fe2f9b84a"
+
+[[package]]
+name = "hex"
+version = "0.4.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7f24254aa9a54b5c858eaee2f5bccdb46aaf0e486a595ed5fd8f86ba55232a70"
+
+[[package]]
+name = "html5ever"
+version = "0.29.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3b7410cae13cbc75623c98ac4cbfd1f0bedddf3227afc24f370cf0f50a44a11c"
+dependencies = [
+ "log",
+ "mac",
+ "markup5ever",
+ "match_token",
+]
+
+[[package]]
+name = "http"
+version = "1.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "918d3568bebf352712bc2ef3d46a8bcf1a75b373be6539de198e9105cbbf9ce0"
+dependencies = [
+ "bytes",
+ "itoa",
+]
+
+[[package]]
+name = "http-body"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ca2a8f2913ee65f60facd6a5905613afaa448497a0230cc41ce022d93290bc2c"
+dependencies = [
+ "bytes",
+ "http",
+]
+
+[[package]]
+name = "http-body-util"
+version = "0.1.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e9f41fd6a08e4d4ec69df65976da761afd5ad5e58a9d4acb46bd1c953a9e3ff2"
+dependencies = [
+ "bytes",
+ "futures-core",
+ "http",
+ "http-body",
+ "pin-project-lite",
+]
+
+[[package]]
+name = "httparse"
+version = "1.10.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6dbf3de79e51f3d586ab4cb9d5c3e2c14aa28ed23d180cf89b4df0454a69cc87"
+
+[[package]]
+name = "hyper"
+version = "1.11.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d22053281f852e11534f5198498373cbb59295120a20771d90f7ed1897490a72"
+dependencies = [
+ "atomic-waker",
+ "bytes",
+ "futures-channel",
+ "futures-core",
+ "h2",
+ "http",
+ "http-body",
+ "httparse",
+ "itoa",
+ "pin-project-lite",
+ "smallvec",
+ "tokio",
+ "want",
+]
+
+[[package]]
+name = "hyper-rustls"
+version = "0.27.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "33ca68d021ef39cf6463ab54c1d0f5daf03377b70561305bb89a8f83aab66e0f"
+dependencies = [
+ "http",
+ "hyper",
+ "hyper-util",
+ "rustls",
+ "tokio",
+ "tokio-rustls",
+ "tower-service",
+]
+
+[[package]]
+name = "hyper-tls"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "70206fc6890eaca9fde8a0bf71caa2ddfc9fe045ac9e5c70df101a7dbde866e0"
+dependencies = [
+ "bytes",
+ "http-body-util",
+ "hyper",
+ "hyper-util",
+ "native-tls",
+ "tokio",
+ "tokio-native-tls",
+ "tower-service",
+]
+
+[[package]]
+name = "hyper-util"
+version = "0.1.20"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "96547c2556ec9d12fb1578c4eaf448b04993e7fb79cbaad930a656880a6bdfa0"
+dependencies = [
+ "base64",
+ "bytes",
+ "futures-channel",
+ "futures-util",
+ "http",
+ "http-body",
+ "hyper",
+ "ipnet",
+ "libc",
+ "percent-encoding",
+ "pin-project-lite",
+ "socket2",
+ "system-configuration",
+ "tokio",
+ "tower-service",
+ "tracing",
+ "windows-registry",
+]
+
+[[package]]
+name = "iana-time-zone"
+version = "0.1.65"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e31bc9ad994ba00e440a8aa5c9ef0ec67d5cb5e5cb0cc7f8b744a35b389cc470"
+dependencies = [
+ "android_system_properties",
+ "core-foundation-sys",
+ "iana-time-zone-haiku",
+ "js-sys",
+ "log",
+ "wasm-bindgen",
+ "windows-core",
+]
+
+[[package]]
+name = "iana-time-zone-haiku"
+version = "0.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f31827a206f56af32e590ba56d5d2d085f558508192593743f16b2306495269f"
+dependencies = [
+ "cc",
+]
+
+[[package]]
+name = "icu_collections"
+version = "2.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2984d1cd16c883d7935b9e07e44071dca8d917fd52ecc02c04d5fa0b5a3f191c"
+dependencies = [
+ "displaydoc",
+ "potential_utf",
+ "utf8_iter",
+ "yoke",
+ "zerofrom",
+ "zerovec",
+]
+
+[[package]]
+name = "icu_locale_core"
+version = "2.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "92219b62b3e2b4d88ac5119f8904c10f8f61bf7e95b640d25ba3075e6cac2c29"
+dependencies = [
+ "displaydoc",
+ "litemap",
+ "tinystr",
+ "writeable",
+ "zerovec",
+]
+
+[[package]]
+name = "icu_normalizer"
+version = "2.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c56e5ee99d6e3d33bd91c5d85458b6005a22140021cc324cea84dd0e72cff3b4"
+dependencies = [
+ "icu_collections",
+ "icu_normalizer_data",
+ "icu_properties",
+ "icu_provider",
+ "smallvec",
+ "zerovec",
+]
+
+[[package]]
+name = "icu_normalizer_data"
+version = "2.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "da3be0ae77ea334f4da67c12f149704f19f81d1adf7c51cf482943e84a2bad38"
+
+[[package]]
+name = "icu_properties"
+version = "2.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bee3b67d0ea5c2cca5003417989af8996f8604e34fb9ddf96208a033901e70de"
+dependencies = [
+ "icu_collections",
+ "icu_locale_core",
+ "icu_properties_data",
+ "icu_provider",
+ "zerotrie",
+ "zerovec",
+]
+
+[[package]]
+name = "icu_properties_data"
+version = "2.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8e2bbb201e0c04f7b4b3e14382af113e17ba4f63e2c9d2ee626b720cbce54a14"
+
+[[package]]
+name = "icu_provider"
+version = "2.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "139c4cf31c8b5f33d7e199446eff9c1e02decfc2f0eec2c8d71f65befa45b421"
+dependencies = [
+ "displaydoc",
+ "icu_locale_core",
+ "writeable",
+ "yoke",
+ "zerofrom",
+ "zerotrie",
+ "zerovec",
+]
+
+[[package]]
+name = "idna"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3b0875f23caa03898994f6ddc501886a45c7d3d62d04d2d90788d47be1b1e4de"
+dependencies = [
+ "idna_adapter",
+ "smallvec",
+ "utf8_iter",
+]
+
+[[package]]
+name = "idna_adapter"
+version = "1.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cb68373c0d6620ef8105e855e7745e18b0d00d3bdb07fb532e434244cdb9a714"
+dependencies = [
+ "icu_normalizer",
+ "icu_properties",
+]
+
+[[package]]
+name = "indexmap"
+version = "2.14.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d466e9454f08e4a911e14806c24e16fba1b4c121d1ea474396f396069cf949d9"
+dependencies = [
+ "equivalent",
+ "hashbrown",
+]
+
+[[package]]
+name = "ipnet"
+version = "2.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6a756c3fac73139e83f14c2d742155dd2b78d3ee56597b419a0579b7bdd6dd78"
+
+[[package]]
+name = "itoa"
+version = "1.0.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8f42a60cbdf9a97f5d2305f08a87dc4e09308d1276d28c869c684d7777685682"
+
+[[package]]
+name = "js-sys"
+version = "0.3.104"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0e0c1080212aad755ea003d18543e8768dd432c48819efd73a7bf1e39b7a5a3a"
+dependencies = [
+ "cfg-if",
+ "futures-util",
+ "wasm-bindgen",
+]
+
+[[package]]
+name = "libc"
+version = "0.2.189"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3eaf3ede3fee6db1a4c2ee091bf8a8b4dccdc6d17f656fb07896ee72867612f2"
+
+[[package]]
+name = "linux-raw-sys"
+version = "0.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "32a66949e030da00e8c7d4434b251670a91556f4144941d37452769c25d58a53"
+
+[[package]]
+name = "litemap"
+version = "0.8.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "92daf443525c4cce67b150400bc2316076100ce0b3686209eb8cf3c31612e6f0"
+
+[[package]]
+name = "lock_api"
+version = "0.4.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "224399e74b87b5f3557511d98dff8b14089b3dadafcab6bb93eab67d3aace965"
+dependencies = [
+ "scopeguard",
+]
+
+[[package]]
+name = "log"
+version = "0.4.33"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0ceec5bc11778974d1bcb055b18002eba7f4b3518b6a0081b3af5f21666da9ad"
+
+[[package]]
+name = "mac"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c41e0c4fef86961ac6d6f8a82609f55f31b05e4fce149ac5710e439df7619ba4"
+
+[[package]]
+name = "markup5ever"
+version = "0.14.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c7a7213d12e1864c0f002f52c2923d4556935a43dec5e71355c2760e0f6e7a18"
+dependencies = [
+ "log",
+ "phf",
+ "phf_codegen",
+ "string_cache",
+ "string_cache_codegen",
+ "tendril",
+]
+
+[[package]]
+name = "match_token"
+version = "0.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "88a9689d8d44bf9964484516275f5cd4c9b59457a6940c1d5d0ecbb94510a36b"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.119",
+]
+
+[[package]]
+name = "md-5"
+version = "0.10.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d89e7ee0cfbedfc4da3340218492196241d89eefb6dab27de5df917a6d2e78cf"
+dependencies = [
+ "cfg-if",
+ "digest",
+]
+
+[[package]]
+name = "memchr"
+version = "2.8.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cf8baf1c55e62ffcace7a9f06f4bd9cd3f0c4beb022d3b367256b91b87513d98"
+
+[[package]]
+name = "mime"
+version = "0.3.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6877bb514081ee2a7ff5ef9de3281f14a4dd4bceac4c09388074a6b5df8a139a"
+
+[[package]]
+name = "mio"
+version = "1.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "30d65c71f1ce40ab09135ce117d742b9f8a19ff91a41a8b57ed50bc2de59c427"
+dependencies = [
+ "libc",
+ "wasi",
+ "windows-sys 0.61.2",
+]
+
+[[package]]
+name = "native-tls"
+version = "0.2.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "465500e14ea162429d264d44189adc38b199b62b1c21eea9f69e4b73cb03bbf2"
+dependencies = [
+ "libc",
+ "log",
+ "openssl",
+ "openssl-probe",
+ "openssl-sys",
+ "schannel",
+ "security-framework",
+ "security-framework-sys",
+ "tempfile",
+]
+
+[[package]]
+name = "new_debug_unreachable"
+version = "1.0.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "650eef8c711430f1a879fdd01d4745a7deea475becfb90269c06775983bbf086"
+
+[[package]]
+name = "num-traits"
+version = "0.2.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "071dfc062690e90b734c0b2273ce72ad0ffa95f0c74596bc250dcfd960262841"
+dependencies = [
+ "autocfg",
+]
+
+[[package]]
+name = "once_cell"
+version = "1.21.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9f7c3e4beb33f85d45ae3e3a1792185706c8e16d043238c593331cc7cd313b50"
+
+[[package]]
+name = "openssl"
+version = "0.10.81"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "77823a27f0babb03091cb9ed9ef80af3b39dbc82f97e8fa530374b7dafd87a45"
+dependencies = [
+ "bitflags",
+ "cfg-if",
+ "foreign-types",
+ "libc",
+ "openssl-macros",
+ "openssl-sys",
+]
+
+[[package]]
+name = "openssl-macros"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a948666b637a0f465e8564c73e89d4dde00d72d4d473cc972f390fc3dcee7d9c"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.119",
+]
+
+[[package]]
+name = "openssl-probe"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7c87def4c32ab89d880effc9e097653c8da5d6ef28e6b539d313baaacfbafcbe"
+
+[[package]]
+name = "openssl-sys"
+version = "0.9.117"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b47e7e6bb2c38cd930d25a23b40fa52e068c10e85f3e03a7f5ba5aaca5713695"
+dependencies = [
+ "cc",
+ "libc",
+ "pkg-config",
+ "vcpkg",
+]
+
+[[package]]
+name = "parking_lot"
+version = "0.12.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "93857453250e3077bd71ff98b6a65ea6621a19bb0f559a85248955ac12c45a1a"
+dependencies = [
+ "lock_api",
+ "parking_lot_core",
+]
+
+[[package]]
+name = "parking_lot_core"
+version = "0.9.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2621685985a2ebf1c516881c026032ac7deafcda1a2c9b7850dc81e3dfcb64c1"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "redox_syscall",
+ "smallvec",
+ "windows-link",
+]
+
+[[package]]
+name = "percent-encoding"
+version = "2.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9b4f627cb1b25917193a259e49bdad08f671f8d9708acfd5fe0a8c1455d87220"
+
+[[package]]
+name = "phf"
+version = "0.11.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1fd6780a80ae0c52cc120a26a1a42c1ae51b247a253e4e06113d23d2c2edd078"
+dependencies = [
+ "phf_macros",
+ "phf_shared",
+]
+
+[[package]]
+name = "phf_codegen"
+version = "0.11.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "aef8048c789fa5e851558d709946d6d79a8ff88c0440c587967f8e94bfb1216a"
+dependencies = [
+ "phf_generator",
+ "phf_shared",
+]
+
+[[package]]
+name = "phf_generator"
+version = "0.11.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3c80231409c20246a13fddb31776fb942c38553c51e871f8cbd687a4cfb5843d"
+dependencies = [
+ "phf_shared",
+ "rand",
+]
+
+[[package]]
+name = "phf_macros"
+version = "0.11.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f84ac04429c13a7ff43785d75ad27569f2951ce0ffd30a3321230db2fc727216"
+dependencies = [
+ "phf_generator",
+ "phf_shared",
+ "proc-macro2",
+ "quote",
+ "syn 2.0.119",
+]
+
+[[package]]
+name = "phf_shared"
+version = "0.11.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "67eabc2ef2a60eb7faa00097bd1ffdb5bd28e62bf39990626a582201b7a754e5"
+dependencies = [
+ "siphasher",
+]
+
+[[package]]
+name = "pin-project-lite"
+version = "0.2.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a89322df9ebe1c1578d689c92318e070967d1042b512afbe49518723f4e6d5cd"
+
+[[package]]
+name = "pkg-config"
+version = "0.3.33"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "19f132c84eca552bf34cab8ec81f1c1dcc229b811638f9d283dceabe58c5569e"
+
+[[package]]
+name = "potential_utf"
+version = "0.1.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0103b1cef7ec0cf76490e969665504990193874ea05c85ff9bab8b911d0a0564"
+dependencies = [
+ "zerovec",
+]
+
+[[package]]
+name = "precomputed-hash"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "925383efa346730478fb4838dbe9137d2a47675ad789c546d150a6e1dd4ab31c"
+
+[[package]]
+name = "proc-macro2"
+version = "1.0.107"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "985e7ec9bb745e6ce6535b544d84d6cd6f7ad8bd711c398938ae983b91a766d9"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "quote"
+version = "1.0.47"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1fbf4db142a473a8d80c26bbf18454ed458bf8d26c8219c331daecfdbd079001"
+dependencies = [
+ "proc-macro2",
+]
+
+[[package]]
+name = "r-efi"
+version = "6.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f8dcc9c7d52a811697d2151c701e0d08956f92b0e24136cf4cf27b57a6a0d9bf"
+
+[[package]]
+name = "rand"
+version = "0.8.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "22f6172bdec972074665ed81ed53b71da00bfc44b65a753cfde883ec4c702a1a"
+dependencies = [
+ "rand_core",
+]
+
+[[package]]
+name = "rand_core"
+version = "0.6.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ec0be4795e2f6a28069bec0b5ff3e2ac9bafc99e6a9a7dc3547996c5c816922c"
+
+[[package]]
+name = "redox_syscall"
+version = "0.5.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ed2bf2547551a7053d6fdfafda3f938979645c44812fbfcda098faae3f1a362d"
+dependencies = [
+ "bitflags",
+]
+
+[[package]]
+name = "reqwest"
+version = "0.12.28"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "eddd3ca559203180a307f12d114c268abf583f59b03cb906fd0b3ff8646c1147"
+dependencies = [
+ "base64",
+ "bytes",
+ "encoding_rs",
+ "futures-core",
+ "h2",
+ "http",
+ "http-body",
+ "http-body-util",
+ "hyper",
+ "hyper-rustls",
+ "hyper-tls",
+ "hyper-util",
+ "js-sys",
+ "log",
+ "mime",
+ "native-tls",
+ "percent-encoding",
+ "pin-project-lite",
+ "rustls-pki-types",
+ "serde",
+ "serde_json",
+ "serde_urlencoded",
+ "sync_wrapper",
+ "tokio",
+ "tokio-native-tls",
+ "tower",
+ "tower-http",
+ "tower-service",
+ "url",
+ "wasm-bindgen",
+ "wasm-bindgen-futures",
+ "web-sys",
+]
+
+[[package]]
+name = "ring"
+version = "0.17.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a4689e6c2294d81e88dc6261c768b63bc4fcdb852be6d1352498b114f61383b7"
+dependencies = [
+ "cc",
+ "cfg-if",
+ "getrandom 0.2.17",
+ "libc",
+ "untrusted",
+ "windows-sys 0.52.0",
+]
+
+[[package]]
+name = "rs-scraper"
+version = "0.1.0"
+dependencies = [
+ "anyhow",
+ "chrono",
+ "hex",
+ "md-5",
+ "reqwest",
+ "scraper",
+ "serde",
+ "serde_json",
+ "sha2",
+ "tokio",
+ "url",
+]
+
+[[package]]
+name = "rustix"
+version = "1.1.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b6fe4565b9518b83ef4f91bb47ce29620ca828bd32cb7e408f0062e9930ba190"
+dependencies = [
+ "bitflags",
+ "errno",
+ "libc",
+ "linux-raw-sys",
+ "windows-sys 0.61.2",
+]
+
+[[package]]
+name = "rustls"
+version = "0.23.43"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0283386ce02abc0151e1761d08802dfe86c173b0b494af5cbc086574e453da06"
+dependencies = [
+ "once_cell",
+ "rustls-pki-types",
+ "rustls-webpki",
+ "subtle",
+ "zeroize",
+]
+
+[[package]]
+name = "rustls-pki-types"
+version = "1.15.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2f4925028c7eb5d1fcdaf196971378ed9d2c1c4efc7dc5d011256f76c99c0a96"
+dependencies = [
+ "zeroize",
+]
+
+[[package]]
+name = "rustls-webpki"
+version = "0.103.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0527518605e68109d875e248ea259b6758801cf165e4b2c2733ae3b51f12535a"
+dependencies = [
+ "ring",
+ "rustls-pki-types",
+ "untrusted",
+]
+
+[[package]]
+name = "rustversion"
+version = "1.0.23"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cf54715a573b99ac80df0bc206da022bcd442c974952c7b9720069370852e21f"
+
+[[package]]
+name = "ryu"
+version = "1.0.23"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9774ba4a74de5f7b1c1451ed6cd5285a32eddb5cccb8cc655a4e50009e06477f"
+
+[[package]]
+name = "schannel"
+version = "0.1.29"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "91c1b7e4904c873ef0710c1f407dde2e6287de2bebc1bbbf7d430bb7cbffd939"
+dependencies = [
+ "windows-sys 0.61.2",
+]
+
+[[package]]
+name = "scopeguard"
+version = "1.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49"
+
+[[package]]
+name = "scraper"
+version = "0.22.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cc3d051b884f40e309de6c149734eab57aa8cc1347992710dc80bcc1c2194c15"
+dependencies = [
+ "cssparser",
+ "ego-tree",
+ "getopts",
+ "html5ever",
+ "precomputed-hash",
+ "selectors",
+ "tendril",
+]
+
+[[package]]
+name = "security-framework"
+version = "3.7.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b7f4bc775c73d9a02cde8bf7b2ec4c9d12743edf609006c7facc23998404cd1d"
+dependencies = [
+ "bitflags",
+ "core-foundation 0.10.1",
+ "core-foundation-sys",
+ "libc",
+ "security-framework-sys",
+]
+
+[[package]]
+name = "security-framework-sys"
+version = "2.17.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6ce2691df843ecc5d231c0b14ece2acc3efb62c0a398c7e1d875f3983ce020e3"
+dependencies = [
+ "core-foundation-sys",
+ "libc",
+]
+
+[[package]]
+name = "selectors"
+version = "0.26.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fd568a4c9bb598e291a08244a5c1f5a8a6650bee243b5b0f8dbb3d9cc1d87fe8"
+dependencies = [
+ "bitflags",
+ "cssparser",
+ "derive_more",
+ "fxhash",
+ "log",
+ "new_debug_unreachable",
+ "phf",
+ "phf_codegen",
+ "precomputed-hash",
+ "servo_arc",
+ "smallvec",
+]
+
+[[package]]
+name = "serde"
+version = "1.0.229"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4148590afebada386688f18773da617792bf2ef03ffc1e4cbd2b1d45b023e0ba"
+dependencies = [
+ "serde_core",
+ "serde_derive",
+]
+
+[[package]]
+name = "serde_core"
+version = "1.0.229"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "67dca2c9c51e58a4791a4b1ed58308b39c64224d349a935ab5039aa360942a48"
+dependencies = [
+ "serde_derive",
+]
+
+[[package]]
+name = "serde_derive"
+version = "1.0.229"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e7a5d71263a5a7d47b41f6b3f06ba276f10cc18b0931f1799f710578e2309348"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 3.0.3",
+]
+
+[[package]]
+name = "serde_json"
+version = "1.0.151"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c841b55ecdae098c80dcae9cf767f6f8a0c2cdb3416bbef72181df4d0fe73f14"
+dependencies = [
+ "itoa",
+ "memchr",
+ "serde",
+ "serde_core",
+ "zmij",
+]
+
+[[package]]
+name = "serde_urlencoded"
+version = "0.7.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d3491c14715ca2294c4d6a88f15e84739788c1d030eed8c110436aafdaa2f3fd"
+dependencies = [
+ "form_urlencoded",
+ "itoa",
+ "ryu",
+ "serde",
+]
+
+[[package]]
+name = "servo_arc"
+version = "0.4.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "170fb83ab34de17dc69aa7c67482b22218ddb85da56546f9bd6b929e32a05930"
+dependencies = [
+ "stable_deref_trait",
+]
+
+[[package]]
+name = "sha2"
+version = "0.10.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a7507d819769d01a365ab707794a4084392c824f54a7a6a7862f8c3d0892b283"
+dependencies = [
+ "cfg-if",
+ "cpufeatures",
+ "digest",
+]
+
+[[package]]
+name = "shlex"
+version = "2.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f8fadd59c855ef2080decdef8ff161eb6661b86933c9d82e5ba29dc602a55aba"
+
+[[package]]
+name = "signal-hook-registry"
+version = "1.4.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c4db69cba1110affc0e9f7bcd48bbf87b3f4fc7c61fc9155afd4c469eb3d6c1b"
+dependencies = [
+ "errno",
+ "libc",
+]
+
+[[package]]
+name = "siphasher"
+version = "1.0.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8ee5873ec9cce0195efcb7a4e9507a04cd49aec9c83d0389df45b1ef7ba2e649"
+
+[[package]]
+name = "slab"
+version = "0.4.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0c790de23124f9ab44544d7ac05d60440adc586479ce501c1d6d7da3cd8c9cf5"
+
+[[package]]
+name = "smallvec"
+version = "1.15.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8ed6a63f02c8539c91a8685a86f4099661ba3da017932f6ebbea6de3f0fa7c90"
+
+[[package]]
+name = "socket2"
+version = "0.6.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c3d1e2c7f27f8d4cb10542a02c49005dbd6e93095799d6f3be745fae9f8fedd4"
+dependencies = [
+ "libc",
+ "windows-sys 0.61.2",
+]
+
+[[package]]
+name = "stable_deref_trait"
+version = "1.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6ce2be8dc25455e1f91df71bfa12ad37d7af1092ae736f3a6cd0e37bc7810596"
+
+[[package]]
+name = "string_cache"
+version = "0.8.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bf776ba3fa74f83bf4b63c3dcbbf82173db2632ed8452cb2d891d33f459de70f"
+dependencies = [
+ "new_debug_unreachable",
+ "parking_lot",
+ "phf_shared",
+ "precomputed-hash",
+ "serde",
+]
+
+[[package]]
+name = "string_cache_codegen"
+version = "0.5.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c711928715f1fe0fe509c53b43e993a9a557babc2d0a3567d0a3006f1ac931a0"
+dependencies = [
+ "phf_generator",
+ "phf_shared",
+ "proc-macro2",
+ "quote",
+]
+
+[[package]]
+name = "subtle"
+version = "2.6.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "13c2bddecc57b384dee18652358fb23172facb8a2c51ccc10d74c157bdea3292"
+
+[[package]]
+name = "syn"
+version = "2.0.119"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "872831b642d1a07999a962a351ed35b955ea2cfc8f3862091e2a240a84f17297"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
+[[package]]
+name = "syn"
+version = "3.0.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "53e9bae58849f64dfa4f5d5ae372c8341f7305f82a3868709269343628b659a3"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
+[[package]]
+name = "sync_wrapper"
+version = "1.0.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0bf256ce5efdfa370213c1dabab5935a12e49f2c58d15e9eac2870d3b4f27263"
+dependencies = [
+ "futures-core",
+]
+
+[[package]]
+name = "synstructure"
+version = "0.13.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "728a70f3dbaf5bab7f0c4b1ac8d7ae5ea60a4b5549c8a5914361c99147a709d2"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.119",
+]
+
+[[package]]
+name = "system-configuration"
+version = "0.7.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a13f3d0daba03132c0aa9767f98351b3488edc2c100cda2d2ec2b04f3d8d3c8b"
+dependencies = [
+ "bitflags",
+ "core-foundation 0.9.4",
+ "system-configuration-sys",
+]
+
+[[package]]
+name = "system-configuration-sys"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8e1d1b10ced5ca923a1fcb8d03e96b8d3268065d724548c0211415ff6ac6bac4"
+dependencies = [
+ "core-foundation-sys",
+ "libc",
+]
+
+[[package]]
+name = "tempfile"
+version = "3.27.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "32497e9a4c7b38532efcdebeef879707aa9f794296a4f0244f6f69e9bc8574bd"
+dependencies = [
+ "fastrand",
+ "getrandom 0.4.3",
+ "once_cell",
+ "rustix",
+ "windows-sys 0.61.2",
+]
+
+[[package]]
+name = "tendril"
+version = "0.4.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d24a120c5fc464a3458240ee02c299ebcb9d67b5249c8848b09d639dca8d7bb0"
+dependencies = [
+ "futf",
+ "mac",
+ "utf-8",
+]
+
+[[package]]
+name = "tinystr"
+version = "0.8.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c8323304221c2a851516f22236c5722a72eaa19749016521d6dff0824447d96d"
+dependencies = [
+ "displaydoc",
+ "zerovec",
+]
+
+[[package]]
+name = "tokio"
+version = "1.53.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "202caea871b69668250d242070849eb495be178ed697a3e98aebce5bc81a0bed"
+dependencies = [
+ "bytes",
+ "libc",
+ "mio",
+ "parking_lot",
+ "pin-project-lite",
+ "signal-hook-registry",
+ "socket2",
+ "tokio-macros",
+ "windows-sys 0.61.2",
+]
+
+[[package]]
+name = "tokio-macros"
+version = "2.7.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "78773a2a397f451582ce068015985c33193cf6dea8b74d2a639fe457b2f07b0e"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 3.0.3",
+]
+
+[[package]]
+name = "tokio-native-tls"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bbae76ab933c85776efabc971569dd6119c580d8f5d448769dec1764bf796ef2"
+dependencies = [
+ "native-tls",
+ "tokio",
+]
+
+[[package]]
+name = "tokio-rustls"
+version = "0.26.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1729aa945f29d91ba541258c8df89027d5792d85a8841fb65e8bf0f4ede4ef61"
+dependencies = [
+ "rustls",
+ "tokio",
+]
+
+[[package]]
+name = "tokio-util"
+version = "0.7.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "494815d09bf52b5548659851081238f0ca39ff638363907596da739561c62c52"
+dependencies = [
+ "bytes",
+ "futures-core",
+ "futures-sink",
+ "libc",
+ "pin-project-lite",
+ "tokio",
+]
+
+[[package]]
+name = "tower"
+version = "0.5.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ebe5ef63511595f1344e2d5cfa636d973292adc0eec1f0ad45fae9f0851ab1d4"
+dependencies = [
+ "futures-core",
+ "futures-util",
+ "pin-project-lite",
+ "sync_wrapper",
+ "tokio",
+ "tower-layer",
+ "tower-service",
+]
+
+[[package]]
+name = "tower-http"
+version = "0.6.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4cfcf7e2740e6fc6d4d688b4ef00650406bb94adf4731e43c096c3a19fe40840"
+dependencies = [
+ "bitflags",
+ "bytes",
+ "futures-util",
+ "http",
+ "http-body",
+ "pin-project-lite",
+ "tower",
+ "tower-layer",
+ "tower-service",
+ "url",
+]
+
+[[package]]
+name = "tower-layer"
+version = "0.3.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "121c2a6cda46980bb0fcd1647ffaf6cd3fc79a013de288782836f6df9c48780e"
+
+[[package]]
+name = "tower-service"
+version = "0.3.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8df9b6e13f2d32c91b9bd719c00d1958837bc7dec474d94952798cc8e69eeec3"
+
+[[package]]
+name = "tracing"
+version = "0.1.44"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "63e71662fa4b2a2c3a26f570f037eb95bb1f85397f3cd8076caed2f026a6d100"
+dependencies = [
+ "pin-project-lite",
+ "tracing-core",
+]
+
+[[package]]
+name = "tracing-core"
+version = "0.1.36"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "db97caf9d906fbde555dd62fa95ddba9eecfd14cb388e4f491a66d74cd5fb79a"
+dependencies = [
+ "once_cell",
+]
+
+[[package]]
+name = "try-lock"
+version = "0.2.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e421abadd41a4225275504ea4d6566923418b7f05506fbc9c0fe86ba7396114b"
+
+[[package]]
+name = "typenum"
+version = "1.20.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b6f5e870be6c3b371b77fe0ee0bafb859fa4964b4404c27de1d380043c4dda20"
+
+[[package]]
+name = "unicode-ident"
+version = "1.0.24"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e6e4313cd5fcd3dad5cafa179702e2b244f760991f45397d14d4ebf38247da75"
+
+[[package]]
+name = "unicode-width"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b4ac048d71ede7ee76d585517add45da530660ef4390e49b098733c6e897f254"
+
+[[package]]
+name = "untrusted"
+version = "0.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8ecb6da28b8a351d773b68d5825ac39017e680750f980f3a1a85cd8dd28a47c1"
+
+[[package]]
+name = "url"
+version = "2.5.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ff67a8a4397373c3ef660812acab3268222035010ab8680ec4215f38ba3d0eed"
+dependencies = [
+ "form_urlencoded",
+ "idna",
+ "percent-encoding",
+ "serde",
+]
+
+[[package]]
+name = "utf-8"
+version = "0.7.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "09cc8ee72d2a9becf2f2febe0205bbed8fc6615b7cb429ad062dc7b7ddd036a9"
+
+[[package]]
+name = "utf8_iter"
+version = "1.0.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b6c140620e7ffbb22c2dee59cafe6084a59b5ffc27a8859a5f0d494b5d52b6be"
+
+[[package]]
+name = "vcpkg"
+version = "0.2.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "accd4ea62f7bb7a82fe23066fb0957d48ef677f6eeb8215f372f52e48bb32426"
+
+[[package]]
+name = "version_check"
+version = "0.9.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a"
+
+[[package]]
+name = "want"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bfa7760aed19e106de2c7c0b581b509f2f25d3dacaf737cb82ac61bc6d760b0e"
+dependencies = [
+ "try-lock",
+]
+
+[[package]]
+name = "wasi"
+version = "0.11.1+wasi-snapshot-preview1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ccf3ec651a847eb01de73ccad15eb7d99f80485de043efb2f370cd654f4ea44b"
+
+[[package]]
+name = "wasm-bindgen"
+version = "0.2.127"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1b70935747edd64d89de3efa29d73789b806c15798f8e7dca4d8ac356b50ce70"
+dependencies = [
+ "cfg-if",
+ "once_cell",
+ "rustversion",
+ "wasm-bindgen-macro",
+ "wasm-bindgen-shared",
+]
+
+[[package]]
+name = "wasm-bindgen-futures"
+version = "0.4.77"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6b7777d5cc23d0e91404e53ce2d5e8ec7acae3026b16233dba62cd3246457950"
+dependencies = [
+ "js-sys",
+ "wasm-bindgen",
+]
+
+[[package]]
+name = "wasm-bindgen-macro"
+version = "0.2.127"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "77775f8f3f7217702089053b94958f8f54061a3f663417df76e19cbdcca29bc1"
+dependencies = [
+ "quote",
+ "wasm-bindgen-macro-support",
+]
+
+[[package]]
+name = "wasm-bindgen-macro-support"
+version = "0.2.127"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e11d33f857dc2fb11b8bc75aee111aa9cbeb12cd9f25efd3d4c2a3dd4e235284"
+dependencies = [
+ "bumpalo",
+ "proc-macro2",
+ "quote",
+ "syn 2.0.119",
+ "wasm-bindgen-shared",
+]
+
+[[package]]
+name = "wasm-bindgen-shared"
+version = "0.2.127"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7ef64dbcc55df09c7e5a46182d181c2cfa3e925f3da937ea764728b4bbb9dcbf"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "web-sys"
+version = "0.3.104"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c435338968042f4f59a557f690a253676d47ce13ceb55d70100e7facf6620a30"
+dependencies = [
+ "js-sys",
+ "wasm-bindgen",
+]
+
+[[package]]
+name = "windows-core"
+version = "0.62.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b8e83a14d34d0623b51dce9581199302a221863196a1dde71a7663a4c2be9deb"
+dependencies = [
+ "windows-implement",
+ "windows-interface",
+ "windows-link",
+ "windows-result",
+ "windows-strings",
+]
+
+[[package]]
+name = "windows-implement"
+version = "0.60.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "053e2e040ab57b9dc951b72c264860db7eb3b0200ba345b4e4c3b14f67855ddf"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.119",
+]
+
+[[package]]
+name = "windows-interface"
+version = "0.59.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3f316c4a2570ba26bbec722032c4099d8c8bc095efccdc15688708623367e358"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.119",
+]
+
+[[package]]
+name = "windows-link"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f0805222e57f7521d6a62e36fa9163bc891acd422f971defe97d64e70d0a4fe5"
+
+[[package]]
+name = "windows-registry"
+version = "0.6.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "02752bf7fbdcce7f2a27a742f798510f3e5ad88dbe84871e5168e2120c3d5720"
+dependencies = [
+ "windows-link",
+ "windows-result",
+ "windows-strings",
+]
+
+[[package]]
+name = "windows-result"
+version = "0.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7781fa89eaf60850ac3d2da7af8e5242a5ea78d1a11c49bf2910bb5a73853eb5"
+dependencies = [
+ "windows-link",
+]
+
+[[package]]
+name = "windows-strings"
+version = "0.5.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7837d08f69c77cf6b07689544538e017c1bfcf57e34b4c0ff58e6c2cd3b37091"
+dependencies = [
+ "windows-link",
+]
+
+[[package]]
+name = "windows-sys"
+version = "0.52.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "282be5f36a8ce781fad8c8ae18fa3f9beff57ec1b52cb3de0789201425d9a33d"
+dependencies = [
+ "windows-targets",
+]
+
+[[package]]
+name = "windows-sys"
+version = "0.61.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ae137229bcbd6cdf0f7b80a31df61766145077ddf49416a728b02cb3921ff3fc"
+dependencies = [
+ "windows-link",
+]
+
+[[package]]
+name = "windows-targets"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9b724f72796e036ab90c1021d4780d4d3d648aca59e491e6b98e725b84e99973"
+dependencies = [
+ "windows_aarch64_gnullvm",
+ "windows_aarch64_msvc",
+ "windows_i686_gnu",
+ "windows_i686_gnullvm",
+ "windows_i686_msvc",
+ "windows_x86_64_gnu",
+ "windows_x86_64_gnullvm",
+ "windows_x86_64_msvc",
+]
+
+[[package]]
+name = "windows_aarch64_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "32a4622180e7a0ec044bb555404c800bc9fd9ec262ec147edd5989ccd0c02cd3"
+
+[[package]]
+name = "windows_aarch64_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "09ec2a7bb152e2252b53fa7803150007879548bc709c039df7627cabbd05d469"
+
+[[package]]
+name = "windows_i686_gnu"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8e9b5ad5ab802e97eb8e295ac6720e509ee4c243f69d781394014ebfe8bbfa0b"
+
+[[package]]
+name = "windows_i686_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0eee52d38c090b3caa76c563b86c3a4bd71ef1a819287c19d586d7334ae8ed66"
+
+[[package]]
+name = "windows_i686_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "240948bc05c5e7c6dabba28bf89d89ffce3e303022809e73deaefe4f6ec56c66"
+
+[[package]]
+name = "windows_x86_64_gnu"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "147a5c80aabfbf0c7d901cb5895d1de30ef2907eb21fbbab29ca94c5b08b1a78"
+
+[[package]]
+name = "windows_x86_64_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "24d5b23dc417412679681396f2b49f3de8c1473deb516bd34410872eff51ed0d"
+
+[[package]]
+name = "windows_x86_64_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec"
+
+[[package]]
+name = "writeable"
+version = "0.6.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1ffae5123b2d3fc086436f8834ae3ab053a283cfac8fe0a0b8eaae044768a4c4"
+
+[[package]]
+name = "yoke"
+version = "0.8.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "709fe23a0424b6a435d82152b1bd3fdfb0833487d5fa90d05d42762a9891fef5"
+dependencies = [
+ "stable_deref_trait",
+ "yoke-derive",
+ "zerofrom",
+]
+
+[[package]]
+name = "yoke-derive"
+version = "0.8.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "de844c262c8848816172cef550288e7dc6c7b7814b4ee56b3e1553f275f1858e"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.119",
+ "synstructure",
+]
+
+[[package]]
+name = "zerofrom"
+version = "0.1.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0ec05a11813ea801ff6d75110ad09cd0824ddba17dfe17128ea0d5f68e6c5272"
+dependencies = [
+ "zerofrom-derive",
+]
+
+[[package]]
+name = "zerofrom-derive"
+version = "0.1.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "11532158c46691caf0f2593ea8358fed6bbf68a0315e80aae9bd41fbade684a1"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.119",
+ "synstructure",
+]
+
+[[package]]
+name = "zeroize"
+version = "1.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e13c156562582aa81c60cb29407084cdb54c4164760106ab78e6c5b0858cf64e"
+
+[[package]]
+name = "zerotrie"
+version = "0.2.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0f9152d31db0792fa83f70fb2f83148effb5c1f5b8c7686c3459e361d9bc20bf"
+dependencies = [
+ "displaydoc",
+ "yoke",
+ "zerofrom",
+]
+
+[[package]]
+name = "zerovec"
+version = "0.11.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "90f911cbc359ab6af17377d242225f4d75119aec87ea711a880987b18cd7b239"
+dependencies = [
+ "yoke",
+ "zerofrom",
+ "zerovec-derive",
+]
+
+[[package]]
+name = "zerovec-derive"
+version = "0.11.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "625dc425cab0dca6dc3c3319506e6593dcb08a9f387ea3b284dbd52a92c40555"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.119",
+]
+
+[[package]]
+name = "zmij"
+version = "1.0.23"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "29666d0abbfad1e3dc4dcf6144730dd3a3ab225bbbdac83319345b1b44ccfc1b"
diff --git a/Cargo.toml b/Cargo.toml
new file mode 100644
index 0000000..a4ba20c
--- /dev/null
+++ b/Cargo.toml
@@ -0,0 +1,17 @@
+[package]
+name = "rs-scraper"
+version = "0.1.0"
+edition = "2024"
+
+[dependencies]
+anyhow = "1"
+chrono = { version = "0.4", features = ["serde"] }
+hex = "0.4"
+md-5 = "0.10"
+reqwest = "0.12"
+scraper = "0.22"
+serde = { version = "1", features = ["derive"] }
+serde_json = "1"
+sha2 = "0.10"
+tokio = { version = "1", features = ["full"] }
+url = "2"
diff --git a/src/config.rs b/src/config.rs
new file mode 100644
index 0000000..05795a3
--- /dev/null
+++ b/src/config.rs
@@ -0,0 +1,5 @@
+pub const DELAY_MS: u64 = 100;
+pub const TIMEOUT_SECS: u64 = 60;
+pub const MAX_RETRIES: u32 = 3;
+pub const RETRY_BACKOFF_SECS: u64 = 5;
+pub const USER_AGENT: &str = "web-scraper/1.0 (research)";
diff --git a/src/error_logger.rs b/src/error_logger.rs
new file mode 100644
index 0000000..f5aab5f
--- /dev/null
+++ b/src/error_logger.rs
@@ -0,0 +1,41 @@
+use chrono::{DateTime, Utc};
+use serde::Serialize;
+use std::fs::OpenOptions;
+use std::io::Write;
+use std::path::Path;
+use url::Url;
+
+#[derive(Serialize)]
+pub struct ErrorEntry {
+    pub timestamp: DateTime<Utc>,
+    pub url: String,
+    pub error_type: String,
+    pub message: String,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub status_code: Option<u16>,
+}
+
+pub fn log_error(
+    log_path: &Path,
+    url: &Url,
+    error_type: &str,
+    message: &str,
+    status_code: Option<u16>,
+) {
+    let entry = ErrorEntry {
+        timestamp: Utc::now(),
+        url: url.to_string(),
+        error_type: error_type.to_string(),
+        message: message.to_string(),
+        status_code,
+    };
+
+    let line = serde_json::to_string(&entry).unwrap_or_default() + "\n";
+
+    if let Ok(mut file) = OpenOptions::new().append(true).create(true).open(log_path) {
+        let _ = file.write_all(line.as_bytes());
+        let _ = file.flush();
+    }
+
+    println!("  LOGGED ERROR [{}]: {}", error_type, message);
+}
diff --git a/src/extractor.rs b/src/extractor.rs
new file mode 100644
index 0000000..4a35f13
--- /dev/null
+++ b/src/extractor.rs
@@ -0,0 +1,25 @@
+use scraper::{Html, Selector};
+use std::collections::HashSet;
+use url::Url;
+
+pub fn extract_links(html: &str, base_url: &Url, base_domain: &str) -> HashSet<Url> {
+    let document = Html::parse_document(html);
+    let selector = Selector::parse("a[href]").unwrap();
+
+    document
+        .select(&selector)
+        .filter_map(|el| el.value().attr("href"))
+        .filter(|href| !href.is_empty())
+        .filter(|href| {
+            !href.starts_with("mailto:")
+                && !href.starts_with("tel:")
+                && !href.starts_with("javascript:")
+        })
+        .filter_map(|href| base_url.join(href).ok())
+        .filter(|url| crate::url_utils::is_internal(url, base_domain))
+        .map(|mut url| {
+            url.set_fragment(None);
+            url
+        })
+        .collect()
+}
diff --git a/src/fetcher.rs b/src/fetcher.rs
new file mode 100644
index 0000000..5c8852e
--- /dev/null
+++ b/src/fetcher.rs
@@ -0,0 +1,99 @@
+use crate::config::{MAX_RETRIES, RETRY_BACKOFF_SECS, TIMEOUT_SECS, USER_AGENT};
+use anyhow::{Result, anyhow};
+use reqwest::Client;
+use std::time::Duration;
+use url::Url;
+
+pub struct Fetcher {
+    client: Client,
+}
+
+impl Fetcher {
+    pub fn new() -> Self {
+        let client = Client::builder()
+            .timeout(Duration::from_secs(TIMEOUT_SECS))
+            .user_agent(USER_AGENT)
+            .redirect(reqwest::redirect::Policy::limited(10))
+            .build()
+            .expect("Failed to create HTTP client");
+
+        Self { client }
+    }
+
+    pub async fn fetch_with_retry(&self, url: &Url) -> Result<FetchResult> {
+        for attempt in 1..=MAX_RETRIES {
+            match self.client.get(url.as_str()).send().await {
+                Ok(resp) => {
+                    let status = resp.status();
+                    let final_url = resp.url().clone();
+                    let content_type = resp
+                        .headers()
+                        .get("content-type")
+                        .and_then(|h| h.to_str().ok())
+                        .unwrap_or("")
+                        .to_string();
+
+                    let bytes = match resp.bytes().await {
+                        Ok(b) => b.to_vec(),
+                        Err(e) => {
+                            if attempt < MAX_RETRIES {
+                                self.print_retry(attempt, &e.to_string());
+                                tokio::time::sleep(Duration::from_secs(
+                                    RETRY_BACKOFF_SECS * attempt as u64,
+                                ))
+                                .await;
+                                continue;
+                            }
+                            return Err(anyhow!(
+                                "Body read failed after {} retries: {}",
+                                MAX_RETRIES,
+                                e
+                            ));
+                        }
+                    };
+
+                    if !status.is_success() {
+                        return Err(anyhow!("HTTP {}", status.as_u16()));
+                    }
+
+                    return Ok(FetchResult {
+                        bytes,
+                        content_type,
+                        final_url,
+                    });
+                }
+                Err(e) => {
+                    if attempt < MAX_RETRIES {
+                        self.print_retry(attempt, &e.to_string());
+                        tokio::time::sleep(Duration::from_secs(
+                            RETRY_BACKOFF_SECS * attempt as u64,
+                        ))
+                        .await;
+                        continue;
+                    }
+                    return Err(anyhow!(
+                        "Request failed after {} retries: {}",
+                        MAX_RETRIES,
+                        e
+                    ));
+                }
+            }
+        }
+
+        Err(anyhow!("Exhausted all {} retries", MAX_RETRIES))
+    }
+
+    fn print_retry(&self, attempt: u32, error: &str) {
+        let wait = RETRY_BACKOFF_SECS * attempt as u64;
+        println!(
+            "  retry {}/{} in {}s... ({})",
+            attempt, MAX_RETRIES, wait, error
+        );
+    }
+}
+
+pub struct FetchResult {
+    pub bytes: Vec<u8>,
+    pub content_type: String,
+    pub final_url: Url,
+}
diff --git a/src/main.rs b/src/main.rs
new file mode 100644
index 0000000..87b6436
--- /dev/null
+++ b/src/main.rs
@@ -0,0 +1,52 @@
+// src/main.rs
+
+mod config;
+mod error_logger;
+mod extractor;
+mod fetcher;
+mod scraper;
+mod url_utils;
+
+use scraper::Scraper;
+use std::fs;
+use std::path::PathBuf;
+use url::Url;
+
+#[tokio::main]
+async fn main() -> anyhow::Result<()> {
+    let args: Vec<String> = std::env::args().collect();
+
+    if args.len() < 2 {
+        eprintln!("Usage: site-scraper <start-url>");
+        eprintln!("Example: site-scraper https://www.logting.fo");
+        std::process::exit(1);
+    }
+
+    let start_url = &args[1];
+    let url = Url::parse(start_url)?;
+
+    let base_domain = url_utils::derive_base_domain(&url)
+        .ok_or_else(|| anyhow::anyhow!("Could not parse hostname from {}", start_url))?;
+
+    let output_dir_name = format!("scraped_{}", base_domain.replace('.', "_"));
+    let output_dir = PathBuf::from(&output_dir_name);
+    let logs_dir = output_dir.join("logs");
+
+    fs::create_dir_all(&logs_dir)?;
+
+    let log_path = logs_dir.join("scrape_errors.jsonl");
+    fs::remove_file(&log_path).ok();
+
+    println!("Scraping: {}", start_url);
+    println!("Base domain: {}", base_domain);
+    println!("Output dir: {}", output_dir.display());
+    println!();
+
+    let scraper = Scraper::new(output_dir, log_path, base_domain);
+    let (count, errors) = scraper.run(&url).await;
+
+    println!("\nDone. Fetched {} URLs. Errors: {}.", count, errors);
+    println!("Error log: {}/logs/scrape_errors.jsonl", output_dir_name);
+
+    Ok(())
+}
diff --git a/src/scraper.rs b/src/scraper.rs
new file mode 100644
index 0000000..fff4933
--- /dev/null
+++ b/src/scraper.rs
@@ -0,0 +1,135 @@
+// src/scraper.rs
+
+use crate::error_logger::log_error;
+use crate::extractor::extract_links;
+use crate::fetcher::{FetchResult, Fetcher};
+use crate::url_utils::{normalize_url, url_to_filename};
+use anyhow::Result;
+use std::collections::HashSet;
+use std::collections::VecDeque;
+use std::fs;
+use std::sync::Arc;
+use std::time::Duration;
+use tokio::sync::Mutex;
+use url::Url;
+
+pub struct Scraper {
+    fetcher: Fetcher,
+    seen: Arc<Mutex<HashSet<String>>>,
+    output_dir: std::path::PathBuf,
+    log_path: std::path::PathBuf,
+    base_domain: String,
+}
+
+impl Scraper {
+    pub fn new(
+        output_dir: std::path::PathBuf,
+        log_path: std::path::PathBuf,
+        base_domain: String,
+    ) -> Self {
+        Self {
+            fetcher: Fetcher::new(),
+            seen: Arc::new(Mutex::new(HashSet::new())),
+            output_dir,
+            log_path,
+            base_domain,
+        }
+    }
+
+    pub async fn run(&self, start_url: &Url) -> (usize, usize) {
+        let mut queue: VecDeque<Url> = VecDeque::new();
+        queue.push_back(start_url.clone());
+
+        let mut count = 0usize;
+        let mut error_count = 0usize;
+
+        while let Some(raw_url) = queue.pop_front() {
+            let url = match normalize_url(raw_url.as_str()) {
+                Some(u) => u,
+                None => continue,
+            };
+
+            let url_key = url.as_str().to_string();
+
+            {
+                let mut seen = self.seen.lock().await;
+                if seen.contains(&url_key) {
+                    continue;
+                }
+                seen.insert(url_key.clone());
+            }
+
+            println!("[{}] fetching: {}", count, url);
+
+            match self.fetcher.fetch_with_retry(&url).await {
+                Ok(result) => {
+                    let is_html = result.content_type.contains("text/html");
+
+                    match self.save(&result).await {
+                        Ok(()) => {
+                            if is_html {
+                                if let Ok(html) = std::str::from_utf8(&result.bytes) {
+                                    let links =
+                                        extract_links(html, &result.final_url, &self.base_domain);
+
+                                    // Only queue links not already seen — do NOT insert into seen here.
+                                    // They get inserted when actually fetched, matching the Python version.
+                                    let mut new_links = Vec::new();
+
+                                    {
+                                        let seen = self.seen.lock().await;
+                                        for link in &links {
+                                            if !seen.contains(link.as_str()) {
+                                                new_links.push(link.clone());
+                                            }
+                                        }
+                                    }
+
+                                    let new_count = new_links.len();
+
+                                    for link in new_links {
+                                        queue.push_back(link);
+                                    }
+
+                                    println!("  found {} links ({} new)", links.len(), new_count);
+                                }
+                            } else {
+                                println!("  binary: {}", result.content_type);
+                            }
+                        }
+                        Err(e) => {
+                            log_error(
+                                &self.log_path,
+                                &result.final_url,
+                                "save_error",
+                                &e.to_string(),
+                                None,
+                            );
+                            error_count += 1;
+                        }
+                    }
+                }
+                Err(e) => {
+                    log_error(&self.log_path, &url, "fetch_error", &e.to_string(), None);
+                    error_count += 1;
+                }
+            }
+
+            count += 1;
+            tokio::time::sleep(Duration::from_millis(crate::config::DELAY_MS)).await;
+        }
+
+        (count, error_count)
+    }
+
+    async fn save(&self, result: &FetchResult) -> Result<()> {
+        let filename = url_to_filename(&result.final_url, &result.content_type);
+        let filepath = self.output_dir.join(&filename);
+        fs::write(&filepath, &result.bytes)?;
+        println!(
+            "  saved -> {}",
+            filepath.file_name().unwrap_or_default().to_string_lossy()
+        );
+        Ok(())
+    }
+}
diff --git a/src/url_utils.rs b/src/url_utils.rs
new file mode 100644
index 0000000..ebbbff7
--- /dev/null
+++ b/src/url_utils.rs
@@ -0,0 +1,127 @@
+// src/url_utils.rs
+
+use md5::Md5;
+use sha2::{Digest, Sha256};
+use url::Url;
+
+pub fn derive_base_domain(url: &Url) -> Option<String> {
+    let host = url.host_str()?;
+    let parts: Vec<&str> = host.split('.').collect();
+    if parts.len() >= 2 {
+        Some(parts[parts.len() - 2..].join("."))
+    } else {
+        Some(host.to_string())
+    }
+}
+
+pub fn is_internal(url: &Url, base_domain: &str) -> bool {
+    match url.host_str() {
+        Some(host) => host == base_domain || host.ends_with(&format!(".{}", base_domain)),
+        None => false,
+    }
+}
+
+pub fn normalize_url(url: &str) -> Option<Url> {
+    let cleaned = url.split('#').next().unwrap_or(url);
+    let cleaned = cleaned.trim_end_matches(['?', '&']);
+    let mut parsed = Url::parse(cleaned).ok()?;
+    parsed.set_fragment(None);
+    Some(parsed)
+}
+
+fn get_extension(url: &Url, content_type: &str) -> String {
+    let path = url.path();
+    let last_segment = path.rsplit('/').next().unwrap_or(path);
+
+    if let Some(dot_pos) = last_segment.rfind('.') {
+        if dot_pos > 0 {
+            return last_segment[dot_pos..].to_lowercase();
+        }
+    }
+
+    let ct = content_type
+        .split(';')
+        .next()
+        .unwrap_or("")
+        .trim()
+        .to_lowercase();
+
+    match ct.as_str() {
+        "text/html" => ".html",
+        "application/pdf" => ".pdf",
+        "application/json" => ".json",
+        "application/xml" | "text/xml" => ".xml",
+        "text/plain" => ".txt",
+        "text/css" => ".css",
+        "application/javascript" | "text/javascript" => ".js",
+        "image/png" => ".png",
+        "image/jpeg" => ".jpg",
+        "image/gif" => ".gif",
+        "image/svg+xml" => ".svg",
+        "image/webp" => ".webp",
+        "application/vnd.ms-excel" => ".xls",
+        "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet" => ".xlsx",
+        "application/msword" => ".doc",
+        "application/vnd.openxmlformats-officedocument.wordprocessingml.document" => ".docx",
+        "application/zip" => ".zip",
+        "application/octet-stream" => ".bin",
+        _ => ".bin",
+    }
+    .to_string()
+}
+
+pub fn url_to_filename(url: &Url, content_type: &str) -> String {
+    let url_str = url.as_str();
+
+    if url_str.len() > 200 {
+        let mut hasher = Sha256::new();
+        hasher.update(url_str.as_bytes());
+        let hash = hex::encode(hasher.finalize());
+        let ext = get_extension(url, content_type);
+        return format!("{}{}", &hash[..16], ext);
+    }
+
+    let host = url
+        .host_str()
+        .unwrap_or("unknown")
+        .replace('.', "_")
+        .replace(':', "_");
+
+    let path = url.path().trim_start_matches('/');
+    let path = if path.is_empty() { "index" } else { path };
+
+    let last_segment = path.rsplit('/').next().unwrap_or(path);
+
+    let (stem, ext_from_path) = match last_segment.rfind('.') {
+        Some(pos) if pos > 0 => (&last_segment[..pos], Some(&last_segment[pos..])),
+        _ => (last_segment, None),
+    };
+
+    let ext = match ext_from_path {
+        Some(e) => e.to_lowercase(),
+        None => get_extension(url, content_type),
+    };
+
+    let query_suffix = match url.query() {
+        Some(q) if !q.is_empty() => {
+            let mut hasher = Md5::new();
+            hasher.update(q.as_bytes());
+            let hash = hex::encode(hasher.finalize());
+            format!("_{}", &hash[..8])
+        }
+        _ => String::new(),
+    };
+
+    let filename = format!("{}_{}{}{}", host, stem, query_suffix, ext);
+
+    filename
+        .chars()
+        .map(|c| {
+            if c.is_alphanumeric() || "._-".contains(c) {
+                c
+            } else {
+                '_'
+            }
+        })
+        .collect()
+}