From 71f42e1d88555c7e2b1cd95d26b2c421757cbd1b Mon Sep 17 00:00:00 2001 From: Michael Zhang Date: Thu, 26 Jan 2023 09:36:05 -0600 Subject: [PATCH] Initial --- .env | 1 + .envrc | 1 + .gitignore | 2 + Cargo.lock | 1832 +++++++++++++++++++++++++ Cargo.toml | 14 + README.md | 14 + default.nix | 12 + docker-compose.yml | 8 + flake.lock | 93 ++ flake.nix | 28 + migrations/20230125084829_initial.sql | 34 + rustfmt.toml | 2 + src/crawler.rs | 54 + src/main.rs | 47 + 14 files changed, 2142 insertions(+) create mode 100644 .env create mode 100644 .envrc create mode 100644 .gitignore create mode 100644 Cargo.lock create mode 100644 Cargo.toml create mode 100644 README.md create mode 100644 default.nix create mode 100644 docker-compose.yml create mode 100644 flake.lock create mode 100644 flake.nix create mode 100644 migrations/20230125084829_initial.sql create mode 100644 rustfmt.toml create mode 100644 src/crawler.rs create mode 100644 src/main.rs diff --git a/.env b/.env new file mode 100644 index 0000000..b96c9da --- /dev/null +++ b/.env @@ -0,0 +1 @@ +DATABASE_URL=postgres://postgres:example@localhost:5433/searchinblog diff --git a/.envrc b/.envrc new file mode 100644 index 0000000..3550a30 --- /dev/null +++ b/.envrc @@ -0,0 +1 @@ +use flake diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..2d5df85 --- /dev/null +++ b/.gitignore @@ -0,0 +1,2 @@ +/target +.direnv diff --git a/Cargo.lock b/Cargo.lock new file mode 100644 index 0000000..c8a9651 --- /dev/null +++ b/Cargo.lock @@ -0,0 +1,1832 @@ +# This file is automatically @generated by Cargo. +# It is not intended for manual editing. +version = 3 + +[[package]] +name = "adler" +version = "1.0.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f26201604c87b1e01bd3d98f8d5d9a8fcbb815e8cedb41ffccbeb4bf593a35fe" + +[[package]] +name = "anyhow" +version = "1.0.68" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2cb2f989d18dd141ab8ae82f64d1a8cdd37e0840f73a406896cf5e99502fab61" + +[[package]] +name = "async-compression" +version = "0.3.15" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "942c7cd7ae39e91bde4820d74132e9862e62c2f386c3aa90ccf55949f5bad63a" +dependencies = [ + "flate2", + "futures-core", + "memchr", + "pin-project-lite", + "tokio", +] + +[[package]] +name = "async-trait" +version = "0.1.63" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "eff18d764974428cf3a9328e23fc5c986f5fbed46e6cd4cdf42544df5d297ec1" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "autocfg" +version = "1.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d468802bab17cbc0cc575e9b053f41e72aa36bfa6b7f55e3529ffa43161b97fa" + +[[package]] +name = "axum" +version = "0.6.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e5694b64066a2459918d8074c2ce0d5a88f409431994c2356617c8ae0c4721fc" +dependencies = [ + "async-trait", + "axum-core", + "axum-macros", + "bitflags", + "bytes", + "futures-util", + "http", + "http-body", + "hyper", + "itoa 1.0.5", + "matchit", + "memchr", + "mime", + "percent-encoding", + "pin-project-lite", + "rustversion", + "serde", + "serde_json", + "serde_path_to_error", + "serde_urlencoded", + "sync_wrapper", + "tokio", + "tower", + "tower-http", + "tower-layer", + "tower-service", +] + +[[package]] +name = "axum-core" +version = "0.3.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1cae3e661676ffbacb30f1a824089a8c9150e71017f7e1e38f2aa32009188d34" +dependencies = [ + "async-trait", + "bytes", + "futures-util", + "http", + "http-body", + "mime", + "rustversion", + "tower-layer", + "tower-service", +] + +[[package]] +name = "axum-macros" +version = "0.3.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9dbcf61bed07d554bd5c225cd07bc41b793eab63e79c6f0ceac7e1aed2f1c670" +dependencies = [ + "heck", + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "base64" +version = "0.21.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a4a4ddaa51a5bc52a6948f74c06d20aaaddb71924eab79b8c97a8c556e942d6a" + +[[package]] +name = "bitflags" +version = "1.3.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a" + +[[package]] +name = "bumpalo" +version = "3.12.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0d261e256854913907f67ed06efbc3338dfe6179796deefc1ff763fc1aee5535" + +[[package]] +name = "byteorder" +version = "1.4.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "14c189c53d098945499cdfa7ecc63567cf3886b3332b312a5b4585d8d3a6a610" + +[[package]] +name = "bytes" +version = "1.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "dfb24e866b15a1af2a1b663f10c6b6b8f397a84aadb828f12e5b289ec23a3a3c" + +[[package]] +name = "cc" +version = "1.0.78" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a20104e2335ce8a659d6dd92a51a767a0c062599c73b343fd152cb401e828c3d" + +[[package]] +name = "cfg-if" +version = "1.0.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd" + +[[package]] +name = "clap" +version = "4.1.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f13b9c79b5d1dd500d20ef541215a6423c75829ef43117e1b4d17fd8af0b5d76" +dependencies = [ + "bitflags", + "clap_derive", + "clap_lex", + "is-terminal", + "once_cell", + "strsim", + "termcolor", +] + +[[package]] +name = "clap_derive" +version = "4.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "684a277d672e91966334af371f1a7b5833f9aa00b07c84e92fbce95e00208ce8" +dependencies = [ + "heck", + "proc-macro-error", + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "clap_lex" +version = "0.3.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "783fe232adfca04f90f56201b26d79682d4cd2625e0bc7290b95123afe558ade" +dependencies = [ + "os_str_bytes", +] + +[[package]] +name = "convert_case" +version = "0.4.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6245d59a3e82a7fc217c5828a6692dbc6dfb63a0c8c90495621f7b9d79704a0e" + +[[package]] +name = "crc32fast" +version = "1.3.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b540bd8bc810d3885c6ea91e2018302f68baba2129ab3e88f32389ee9370880d" +dependencies = [ + "cfg-if", +] + +[[package]] +name = "cssparser" +version = "0.27.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "754b69d351cdc2d8ee09ae203db831e005560fc6030da058f86ad60c92a9cb0a" +dependencies = [ + "cssparser-macros", + "dtoa-short", + "itoa 0.4.8", + "matches", + "phf 0.8.0", + "proc-macro2", + "quote", + "smallvec", + "syn", +] + +[[package]] +name = "cssparser-macros" +version = "0.6.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "dfae75de57f2b2e85e8768c3ea840fd159c8f33e2b6522c7835b7abac81be16e" +dependencies = [ + "quote", + "syn", +] + +[[package]] +name = "derive_more" +version = "0.99.17" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4fb810d30a7c1953f91334de7244731fc3f3c10d7fe163338a35b9f640960321" +dependencies = [ + "convert_case", + "proc-macro2", + "quote", + "rustc_version", + "syn", +] + +[[package]] +name = "dtoa" +version = "0.4.8" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "56899898ce76aaf4a0f24d914c97ea6ed976d42fec6ad33fcbb0a1103e07b2b0" + +[[package]] +name = "dtoa-short" +version = "0.3.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "bde03329ae10e79ede66c9ce4dc930aa8599043b0743008548680f25b91502d6" +dependencies = [ + "dtoa", +] + +[[package]] +name = "ego-tree" +version = "0.6.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3a68a4904193147e0a8dec3314640e6db742afd5f6e634f428a6af230d9b3591" + +[[package]] +name = "encoding_rs" +version = "0.8.31" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9852635589dc9f9ea1b6fe9f05b50ef208c85c834a562f0c6abb1c475736ec2b" +dependencies = [ + "cfg-if", +] + +[[package]] +name = "errno" +version = "0.2.8" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f639046355ee4f37944e44f60642c6f3a7efa3cf6b78c78a0d989a8ce6c396a1" +dependencies = [ + "errno-dragonfly", + "libc", + "winapi", +] + +[[package]] +name = "errno-dragonfly" +version = "0.1.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "aa68f1b12764fab894d2755d2518754e71b4fd80ecfb822714a1206c2aab39bf" +dependencies = [ + "cc", + "libc", +] + +[[package]] +name = "flate2" +version = "1.0.25" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a8a2db397cb1c8772f31494cb8917e48cd1e64f0fa7efac59fbd741a0a8ce841" +dependencies = [ + "crc32fast", + "miniz_oxide", +] + +[[package]] +name = "fnv" +version = "1.0.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1" + +[[package]] +name = "form_urlencoded" +version = "1.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a9c384f161156f5260c24a097c56119f9be8c798586aecc13afbcbe7b7e26bf8" +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 = "0.3.25" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "52ba265a92256105f45b719605a571ffe2d1f0fea3807304b522c1d778f79eed" +dependencies = [ + "futures-core", +] + +[[package]] +name = "futures-core" +version = "0.3.25" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "04909a7a7e4633ae6c4a9ab280aeb86da1236243a77b694a49eacd659a4bd3ac" + +[[package]] +name = "futures-sink" +version = "0.3.25" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "39c15cf1a4aa79df40f1bb462fb39676d0ad9e366c2a33b590d7c66f4f81fcf9" + +[[package]] +name = "futures-task" +version = "0.3.25" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2ffb393ac5d9a6eaa9d3fdf37ae2776656b706e200c8e16b1bdb227f5198e6ea" + +[[package]] +name = "futures-util" +version = "0.3.25" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "197676987abd2f9cadff84926f410af1c183608d36641465df73ae8211dc65d6" +dependencies = [ + "futures-core", + "futures-task", + "pin-project-lite", + "pin-utils", +] + +[[package]] +name = "fxhash" +version = "0.2.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c31b6d751ae2c7f11320402d34e41349dd1016f8d5d45e48c4312bc8625af50c" +dependencies = [ + "byteorder", +] + +[[package]] +name = "getopts" +version = "0.2.21" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "14dbbfd5c71d70241ecf9e6f13737f7b5ce823821063188d7e46c41d371eebd5" +dependencies = [ + "unicode-width", +] + +[[package]] +name = "getrandom" +version = "0.1.16" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8fc3cb4d91f53b50155bdcfd23f6a4c39ae1969c2ae85982b135750cccaf5fce" +dependencies = [ + "cfg-if", + "libc", + "wasi 0.9.0+wasi-snapshot-preview1", +] + +[[package]] +name = "getrandom" +version = "0.2.8" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c05aeb6a22b8f62540c194aac980f2115af067bfe15a0734d7277a768d396b31" +dependencies = [ + "cfg-if", + "libc", + "wasi 0.11.0+wasi-snapshot-preview1", +] + +[[package]] +name = "h2" +version = "0.3.15" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5f9f29bc9dda355256b2916cf526ab02ce0aeaaaf2bad60d65ef3f12f11dd0f4" +dependencies = [ + "bytes", + "fnv", + "futures-core", + "futures-sink", + "futures-util", + "http", + "indexmap", + "slab", + "tokio", + "tokio-util", + "tracing", +] + +[[package]] +name = "hashbrown" +version = "0.12.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8a9ee70c43aaf417c914396645a0fa852624801b24ebb7ae78fe8272889ac888" + +[[package]] +name = "heck" +version = "0.4.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2540771e65fc8cb83cd6e8a237f70c319bd5c29f78ed1084ba5d50eeac86f7f9" + +[[package]] +name = "hermit-abi" +version = "0.2.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ee512640fe35acbfb4bb779db6f0d80704c2cacfa2e39b601ef3e3f47d1ae4c7" +dependencies = [ + "libc", +] + +[[package]] +name = "html5ever" +version = "0.26.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "bea68cab48b8459f17cf1c944c67ddc572d272d9f2b274140f223ecb1da4a3b7" +dependencies = [ + "log", + "mac", + "markup5ever", + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "http" +version = "0.2.8" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "75f43d41e26995c17e71ee126451dd3941010b0514a81a9d11f3b341debc2399" +dependencies = [ + "bytes", + "fnv", + "itoa 1.0.5", +] + +[[package]] +name = "http-body" +version = "0.4.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d5f38f16d184e36f2408a55281cd658ecbd3ca05cce6d6510a176eca393e26d1" +dependencies = [ + "bytes", + "http", + "pin-project-lite", +] + +[[package]] +name = "http-range-header" +version = "0.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0bfe8eed0a9285ef776bb792479ea3834e8b94e13d615c2f66d03dd50a435a29" + +[[package]] +name = "httparse" +version = "1.8.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d897f394bad6a705d5f4104762e116a75639e470d80901eed05a860a95cb1904" + +[[package]] +name = "httpdate" +version = "1.0.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c4a1e36c821dbe04574f602848a19f742f4fb3c98d40449f11bcad18d6b17421" + +[[package]] +name = "hyper" +version = "0.14.23" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "034711faac9d2166cb1baf1a2fb0b60b1f277f8492fd72176c17f3515e1abd3c" +dependencies = [ + "bytes", + "futures-channel", + "futures-core", + "futures-util", + "h2", + "http", + "http-body", + "httparse", + "httpdate", + "itoa 1.0.5", + "pin-project-lite", + "socket2", + "tokio", + "tower-service", + "tracing", + "want", +] + +[[package]] +name = "hyper-rustls" +version = "0.23.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1788965e61b367cd03a62950836d5cd41560c3577d90e40e0819373194d1661c" +dependencies = [ + "http", + "hyper", + "rustls", + "tokio", + "tokio-rustls", +] + +[[package]] +name = "idna" +version = "0.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e14ddfc70884202db2244c223200c204c2bda1bc6e0998d11b5e024d657209e6" +dependencies = [ + "unicode-bidi", + "unicode-normalization", +] + +[[package]] +name = "indexmap" +version = "1.9.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1885e79c1fc4b10f0e172c475f458b7f7b93061064d98c3293e98c5ba0c8b399" +dependencies = [ + "autocfg", + "hashbrown", +] + +[[package]] +name = "io-lifetimes" +version = "1.0.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e7d6c6f8c91b4b9ed43484ad1a938e393caf35960fce7f82a040497207bd8e9e" +dependencies = [ + "libc", + "windows-sys", +] + +[[package]] +name = "ipnet" +version = "2.7.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "30e22bd8629359895450b59ea7a776c850561b96a3b1d31321c1949d9e6c9146" + +[[package]] +name = "is-terminal" +version = "0.4.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "28dfb6c8100ccc63462345b67d1bbc3679177c75ee4bf59bf29c8b1d110b8189" +dependencies = [ + "hermit-abi", + "io-lifetimes", + "rustix", + "windows-sys", +] + +[[package]] +name = "itoa" +version = "0.4.8" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b71991ff56294aa922b450139ee08b3bfc70982c6b2c7562771375cf73542dd4" + +[[package]] +name = "itoa" +version = "1.0.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fad582f4b9e86b6caa621cabeb0963332d92eea04729ab12892c2533951e6440" + +[[package]] +name = "js-sys" +version = "0.3.60" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "49409df3e3bf0856b916e2ceaca09ee28e6871cf7d9ce97a692cacfdb2a25a47" +dependencies = [ + "wasm-bindgen", +] + +[[package]] +name = "libc" +version = "0.2.139" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "201de327520df007757c1f0adce6e827fe8562fbc28bfd9c15571c66ca1f5f79" + +[[package]] +name = "linux-raw-sys" +version = "0.1.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f051f77a7c8e6957c0696eac88f26b0117e54f52d3fc682ab19397a8812846a4" + +[[package]] +name = "lock_api" +version = "0.4.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "435011366fe56583b16cf956f9df0095b405b82d76425bc8981c0e22e60ec4df" +dependencies = [ + "autocfg", + "scopeguard", +] + +[[package]] +name = "log" +version = "0.4.17" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "abb12e687cfb44aa40f41fc3978ef76448f9b6038cad6aef4259d3c095a2382e" +dependencies = [ + "cfg-if", +] + +[[package]] +name = "mac" +version = "0.1.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c41e0c4fef86961ac6d6f8a82609f55f31b05e4fce149ac5710e439df7619ba4" + +[[package]] +name = "markup5ever" +version = "0.11.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7a2629bb1404f3d34c2e921f21fd34ba00b206124c81f65c50b43b6aaefeb016" +dependencies = [ + "log", + "phf 0.10.1", + "phf_codegen 0.10.0", + "string_cache", + "string_cache_codegen", + "tendril", +] + +[[package]] +name = "matches" +version = "0.1.10" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2532096657941c2fea9c289d370a250971c689d4f143798ff67113ec042024a5" + +[[package]] +name = "matchit" +version = "0.7.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b87248edafb776e59e6ee64a79086f65890d3510f2c656c000bf2a7e8a0aea40" + +[[package]] +name = "memchr" +version = "2.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2dffe52ecf27772e601905b7522cb4ef790d2cc203488bbd0e2fe85fcb74566d" + +[[package]] +name = "mime" +version = "0.3.16" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2a60c7ce501c71e03a9c9c0d35b861413ae925bd979cc7a4e30d060069aaac8d" + +[[package]] +name = "mime_guess" +version = "2.0.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4192263c238a5f0d0c6bfd21f336a313a4ce1c450542449ca191bb657b4642ef" +dependencies = [ + "mime", + "unicase", +] + +[[package]] +name = "miniz_oxide" +version = "0.6.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b275950c28b37e794e8c55d88aeb5e139d0ce23fdbbeda68f8d7174abdf9e8fa" +dependencies = [ + "adler", +] + +[[package]] +name = "mio" +version = "0.8.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e5d732bc30207a6423068df043e3d02e0735b155ad7ce1a6f76fe2baa5b158de" +dependencies = [ + "libc", + "log", + "wasi 0.11.0+wasi-snapshot-preview1", + "windows-sys", +] + +[[package]] +name = "new_debug_unreachable" +version = "1.0.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e4a24736216ec316047a1fc4252e27dabb04218aa4a3f37c6e7ddbf1f9782b54" + +[[package]] +name = "nodrop" +version = "0.1.14" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "72ef4a56884ca558e5ddb05a1d1e7e1bfd9a68d9ed024c21704cc98872dae1bb" + +[[package]] +name = "num_cpus" +version = "1.15.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0fac9e2da13b5eb447a6ce3d392f23a29d8694bff781bf03a16cd9ac8697593b" +dependencies = [ + "hermit-abi", + "libc", +] + +[[package]] +name = "once_cell" +version = "1.17.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6f61fba1741ea2b3d6a1e3178721804bb716a68a6aeba1149b5d52e3d464ea66" + +[[package]] +name = "os_str_bytes" +version = "6.4.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9b7820b9daea5457c9f21c69448905d723fbd21136ccf521748f23fd49e723ee" + +[[package]] +name = "parking_lot" +version = "0.12.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3742b2c103b9f06bc9fff0a37ff4912935851bee6d36f3c02bcc755bcfec228f" +dependencies = [ + "lock_api", + "parking_lot_core", +] + +[[package]] +name = "parking_lot_core" +version = "0.9.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ba1ef8814b5c993410bb3adfad7a5ed269563e4a2f90c41f5d85be7fb47133bf" +dependencies = [ + "cfg-if", + "libc", + "redox_syscall", + "smallvec", + "windows-sys", +] + +[[package]] +name = "percent-encoding" +version = "2.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "478c572c3d73181ff3c2539045f6eb99e5491218eae919370993b890cdbdd98e" + +[[package]] +name = "phf" +version = "0.8.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3dfb61232e34fcb633f43d12c58f83c1df82962dcdfa565a4e866ffc17dafe12" +dependencies = [ + "phf_macros", + "phf_shared 0.8.0", + "proc-macro-hack", +] + +[[package]] +name = "phf" +version = "0.10.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fabbf1ead8a5bcbc20f5f8b939ee3f5b0f6f281b6ad3468b84656b658b455259" +dependencies = [ + "phf_shared 0.10.0", +] + +[[package]] +name = "phf_codegen" +version = "0.8.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "cbffee61585b0411840d3ece935cce9cb6321f01c45477d30066498cd5e1a815" +dependencies = [ + "phf_generator 0.8.0", + "phf_shared 0.8.0", +] + +[[package]] +name = "phf_codegen" +version = "0.10.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4fb1c3a8bc4dd4e5cfce29b44ffc14bedd2ee294559a294e2a4d4c9e9a6a13cd" +dependencies = [ + "phf_generator 0.10.0", + "phf_shared 0.10.0", +] + +[[package]] +name = "phf_generator" +version = "0.8.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "17367f0cc86f2d25802b2c26ee58a7b23faeccf78a396094c13dced0d0182526" +dependencies = [ + "phf_shared 0.8.0", + "rand 0.7.3", +] + +[[package]] +name = "phf_generator" +version = "0.10.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5d5285893bb5eb82e6aaf5d59ee909a06a16737a8970984dd7746ba9283498d6" +dependencies = [ + "phf_shared 0.10.0", + "rand 0.8.5", +] + +[[package]] +name = "phf_macros" +version = "0.8.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7f6fde18ff429ffc8fe78e2bf7f8b7a5a5a6e2a8b58bc5a9ac69198bbda9189c" +dependencies = [ + "phf_generator 0.8.0", + "phf_shared 0.8.0", + "proc-macro-hack", + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "phf_shared" +version = "0.8.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c00cf8b9eafe68dde5e9eaa2cef8ee84a9336a47d566ec55ca16589633b65af7" +dependencies = [ + "siphasher", +] + +[[package]] +name = "phf_shared" +version = "0.10.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b6796ad771acdc0123d2a88dc428b5e38ef24456743ddb1744ed628f9815c096" +dependencies = [ + "siphasher", +] + +[[package]] +name = "pin-project" +version = "1.0.12" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ad29a609b6bcd67fee905812e544992d216af9d755757c05ed2d0e15a74c6ecc" +dependencies = [ + "pin-project-internal", +] + +[[package]] +name = "pin-project-internal" +version = "1.0.12" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "069bdb1e05adc7a8990dce9cc75370895fbe4e3d58b9b73bf1aee56359344a55" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "pin-project-lite" +version = "0.2.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e0a7ae3ac2f1173085d398531c705756c94a4c56843785df85a60c1a0afac116" + +[[package]] +name = "pin-utils" +version = "0.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8b870d8c151b6f2fb93e84a13146138f05d02ed11c7e7c54f8826aaaf7c9f184" + +[[package]] +name = "ppv-lite86" +version = "0.2.17" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5b40af805b3121feab8a3c29f04d8ad262fa8e0561883e7653e024ae4479e6de" + +[[package]] +name = "precomputed-hash" +version = "0.1.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "925383efa346730478fb4838dbe9137d2a47675ad789c546d150a6e1dd4ab31c" + +[[package]] +name = "proc-macro-error" +version = "1.0.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "da25490ff9892aab3fcf7c36f08cfb902dd3e71ca0f9f9517bea02a73a5ce38c" +dependencies = [ + "proc-macro-error-attr", + "proc-macro2", + "quote", + "syn", + "version_check", +] + +[[package]] +name = "proc-macro-error-attr" +version = "1.0.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a1be40180e52ecc98ad80b184934baf3d0d29f979574e439af5a55274b35f869" +dependencies = [ + "proc-macro2", + "quote", + "version_check", +] + +[[package]] +name = "proc-macro-hack" +version = "0.5.20+deprecated" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "dc375e1527247fe1a97d8b7156678dfe7c1af2fc075c9a4db3690ecd2a148068" + +[[package]] +name = "proc-macro2" +version = "1.0.50" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6ef7d57beacfaf2d8aee5937dab7b7f28de3cb8b1828479bb5de2a7106f2bae2" +dependencies = [ + "unicode-ident", +] + +[[package]] +name = "quote" +version = "1.0.23" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8856d8364d252a14d474036ea1358d63c9e6965c8e5c1885c18f73d70bff9c7b" +dependencies = [ + "proc-macro2", +] + +[[package]] +name = "rand" +version = "0.7.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6a6b1679d49b24bbfe0c803429aa1874472f50d9b363131f0e89fc356b544d03" +dependencies = [ + "getrandom 0.1.16", + "libc", + "rand_chacha 0.2.2", + "rand_core 0.5.1", + "rand_hc", + "rand_pcg", +] + +[[package]] +name = "rand" +version = "0.8.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "34af8d1a0e25924bc5b7c43c079c942339d8f0a8b57c39049bef581b46327404" +dependencies = [ + "libc", + "rand_chacha 0.3.1", + "rand_core 0.6.4", +] + +[[package]] +name = "rand_chacha" +version = "0.2.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f4c8ed856279c9737206bf725bf36935d8666ead7aa69b52be55af369d193402" +dependencies = [ + "ppv-lite86", + "rand_core 0.5.1", +] + +[[package]] +name = "rand_chacha" +version = "0.3.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e6c10a63a0fa32252be49d21e7709d4d4baf8d231c2dbce1eaa8141b9b127d88" +dependencies = [ + "ppv-lite86", + "rand_core 0.6.4", +] + +[[package]] +name = "rand_core" +version = "0.5.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "90bde5296fc891b0cef12a6d03ddccc162ce7b2aff54160af9338f8d40df6d19" +dependencies = [ + "getrandom 0.1.16", +] + +[[package]] +name = "rand_core" +version = "0.6.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ec0be4795e2f6a28069bec0b5ff3e2ac9bafc99e6a9a7dc3547996c5c816922c" +dependencies = [ + "getrandom 0.2.8", +] + +[[package]] +name = "rand_hc" +version = "0.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ca3129af7b92a17112d59ad498c6f81eaf463253766b90396d39ea7a39d6613c" +dependencies = [ + "rand_core 0.5.1", +] + +[[package]] +name = "rand_pcg" +version = "0.2.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "16abd0c1b639e9eb4d7c50c0b8100b0d0f849be2349829c740fe8e6eb4816429" +dependencies = [ + "rand_core 0.5.1", +] + +[[package]] +name = "redox_syscall" +version = "0.2.16" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fb5a58c1855b4b6819d59012155603f0b22ad30cad752600aadfcb695265519a" +dependencies = [ + "bitflags", +] + +[[package]] +name = "reqwest" +version = "0.11.14" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "21eed90ec8570952d53b772ecf8f206aa1ec9a3d76b2521c56c42973f2d91ee9" +dependencies = [ + "async-compression", + "base64", + "bytes", + "encoding_rs", + "futures-core", + "futures-util", + "h2", + "http", + "http-body", + "hyper", + "hyper-rustls", + "ipnet", + "js-sys", + "log", + "mime", + "mime_guess", + "once_cell", + "percent-encoding", + "pin-project-lite", + "rustls", + "rustls-pemfile", + "serde", + "serde_json", + "serde_urlencoded", + "tokio", + "tokio-rustls", + "tokio-util", + "tower-service", + "url", + "wasm-bindgen", + "wasm-bindgen-futures", + "web-sys", + "webpki-roots", + "winreg", +] + +[[package]] +name = "ring" +version = "0.16.20" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3053cf52e236a3ed746dfc745aa9cacf1b791d846bdaf412f60a8d7d6e17c8fc" +dependencies = [ + "cc", + "libc", + "once_cell", + "spin", + "untrusted", + "web-sys", + "winapi", +] + +[[package]] +name = "rustc_version" +version = "0.4.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "bfa0f585226d2e68097d4f95d113b15b83a82e819ab25717ec0590d9584ef366" +dependencies = [ + "semver", +] + +[[package]] +name = "rustix" +version = "0.36.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d4fdebc4b395b7fbb9ab11e462e20ed9051e7b16e42d24042c776eca0ac81b03" +dependencies = [ + "bitflags", + "errno", + "io-lifetimes", + "libc", + "linux-raw-sys", + "windows-sys", +] + +[[package]] +name = "rustls" +version = "0.20.8" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fff78fc74d175294f4e83b28343315ffcfb114b156f0185e9741cb5570f50e2f" +dependencies = [ + "log", + "ring", + "sct", + "webpki", +] + +[[package]] +name = "rustls-pemfile" +version = "1.0.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d194b56d58803a43635bdc398cd17e383d6f71f9182b9a192c127ca42494a59b" +dependencies = [ + "base64", +] + +[[package]] +name = "rustversion" +version = "1.0.11" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5583e89e108996506031660fe09baa5011b9dd0341b89029313006d1fb508d70" + +[[package]] +name = "ryu" +version = "1.0.12" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7b4b9743ed687d4b4bcedf9ff5eaa7398495ae14e61cba0a295704edbc7decde" + +[[package]] +name = "scopeguard" +version = "1.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d29ab0c6d3fc0ee92fe66e2d99f700eab17a8d57d1c1d3b748380fb20baa78cd" + +[[package]] +name = "scraper" +version = "0.14.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fc7cb4dae083699a22a65aa9d2699c27f525e35dffaec38b10801e958ed4cf27" +dependencies = [ + "cssparser", + "ego-tree", + "getopts", + "html5ever", + "matches", + "selectors", + "smallvec", + "tendril", +] + +[[package]] +name = "sct" +version = "0.7.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d53dcdb7c9f8158937a7981b48accfd39a43af418591a5d008c7b22b5e1b7ca4" +dependencies = [ + "ring", + "untrusted", +] + +[[package]] +name = "searchinblog" +version = "0.1.0" +dependencies = [ + "anyhow", + "axum", + "clap", + "reqwest", + "scraper", + "tokio", +] + +[[package]] +name = "selectors" +version = "0.22.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "df320f1889ac4ba6bc0cdc9c9af7af4bd64bb927bccdf32d81140dc1f9be12fe" +dependencies = [ + "bitflags", + "cssparser", + "derive_more", + "fxhash", + "log", + "matches", + "phf 0.8.0", + "phf_codegen 0.8.0", + "precomputed-hash", + "servo_arc", + "smallvec", + "thin-slice", +] + +[[package]] +name = "semver" +version = "1.0.16" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "58bc9567378fc7690d6b2addae4e60ac2eeea07becb2c64b9f218b53865cba2a" + +[[package]] +name = "serde" +version = "1.0.152" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "bb7d1f0d3021d347a83e556fc4683dea2ea09d87bccdf88ff5c12545d89d5efb" + +[[package]] +name = "serde_json" +version = "1.0.91" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "877c235533714907a8c2464236f5c4b2a17262ef1bd71f38f35ea592c8da6883" +dependencies = [ + "itoa 1.0.5", + "ryu", + "serde", +] + +[[package]] +name = "serde_path_to_error" +version = "0.1.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "26b04f22b563c91331a10074bda3dd5492e3cc39d56bd557e91c0af42b6c7341" +dependencies = [ + "serde", +] + +[[package]] +name = "serde_urlencoded" +version = "0.7.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d3491c14715ca2294c4d6a88f15e84739788c1d030eed8c110436aafdaa2f3fd" +dependencies = [ + "form_urlencoded", + "itoa 1.0.5", + "ryu", + "serde", +] + +[[package]] +name = "servo_arc" +version = "0.1.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d98238b800e0d1576d8b6e3de32827c2d74bee68bb97748dcf5071fb53965432" +dependencies = [ + "nodrop", + "stable_deref_trait", +] + +[[package]] +name = "signal-hook-registry" +version = "1.4.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e51e73328dc4ac0c7ccbda3a494dfa03df1de2f46018127f60c693f2648455b0" +dependencies = [ + "libc", +] + +[[package]] +name = "siphasher" +version = "0.3.10" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7bd3e3206899af3f8b12af284fafc038cc1dc2b41d1b89dd17297221c5d225de" + +[[package]] +name = "slab" +version = "0.4.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4614a76b2a8be0058caa9dbbaf66d988527d86d003c11a94fbd335d7661edcef" +dependencies = [ + "autocfg", +] + +[[package]] +name = "smallvec" +version = "1.10.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a507befe795404456341dfab10cef66ead4c041f62b8b11bbb92bffe5d0953e0" + +[[package]] +name = "socket2" +version = "0.4.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "02e2d2db9033d13a1567121ddd7a095ee144db4e1ca1b1bda3419bc0da294ebd" +dependencies = [ + "libc", + "winapi", +] + +[[package]] +name = "spin" +version = "0.5.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6e63cff320ae2c57904679ba7cb63280a3dc4613885beafb148ee7bf9aa9042d" + +[[package]] +name = "stable_deref_trait" +version = "1.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a8f112729512f8e442d81f95a8a7ddf2b7c6b8a1a6f509a95864142b30cab2d3" + +[[package]] +name = "string_cache" +version = "0.8.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "213494b7a2b503146286049378ce02b482200519accc31872ee8be91fa820a08" +dependencies = [ + "new_debug_unreachable", + "once_cell", + "parking_lot", + "phf_shared 0.10.0", + "precomputed-hash", + "serde", +] + +[[package]] +name = "string_cache_codegen" +version = "0.5.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6bb30289b722be4ff74a408c3cc27edeaad656e06cb1fe8fa9231fa59c728988" +dependencies = [ + "phf_generator 0.10.0", + "phf_shared 0.10.0", + "proc-macro2", + "quote", +] + +[[package]] +name = "strsim" +version = "0.10.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "73473c0e59e6d5812c5dfe2a064a6444949f089e20eec9a2e5506596494e4623" + +[[package]] +name = "syn" +version = "1.0.107" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1f4064b5b16e03ae50984a5a8ed5d4f8803e6bc1fd170a3cda91a1be4b18e3f5" +dependencies = [ + "proc-macro2", + "quote", + "unicode-ident", +] + +[[package]] +name = "sync_wrapper" +version = "0.1.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "20518fe4a4c9acf048008599e464deb21beeae3d3578418951a189c235a7a9a8" + +[[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 = "termcolor" +version = "1.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "be55cf8942feac5c765c2c993422806843c9a9a45d4d5c407ad6dd2ea95eb9b6" +dependencies = [ + "winapi-util", +] + +[[package]] +name = "thin-slice" +version = "0.1.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8eaa81235c7058867fa8c0e7314f33dcce9c215f535d1913822a2b3f5e289f3c" + +[[package]] +name = "tinyvec" +version = "1.6.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "87cc5ceb3875bb20c2890005a4e226a4651264a5c75edb2421b52861a0a0cb50" +dependencies = [ + "tinyvec_macros", +] + +[[package]] +name = "tinyvec_macros" +version = "0.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "cda74da7e1a664f795bb1f8a87ec406fb89a02522cf6e50620d016add6dbbf5c" + +[[package]] +name = "tokio" +version = "1.24.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "597a12a59981d9e3c38d216785b0c37399f6e415e8d0712047620f189371b0bb" +dependencies = [ + "autocfg", + "bytes", + "libc", + "memchr", + "mio", + "num_cpus", + "parking_lot", + "pin-project-lite", + "signal-hook-registry", + "socket2", + "tokio-macros", + "windows-sys", +] + +[[package]] +name = "tokio-macros" +version = "1.8.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d266c00fde287f55d3f1c3e96c500c362a2b8c695076ec180f27918820bc6df8" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "tokio-rustls" +version = "0.23.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c43ee83903113e03984cb9e5cebe6c04a5116269e900e3ddba8f068a62adda59" +dependencies = [ + "rustls", + "tokio", + "webpki", +] + +[[package]] +name = "tokio-util" +version = "0.7.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0bb2e075f03b3d66d8d8785356224ba688d2906a371015e225beeb65ca92c740" +dependencies = [ + "bytes", + "futures-core", + "futures-sink", + "pin-project-lite", + "tokio", + "tracing", +] + +[[package]] +name = "tower" +version = "0.4.13" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b8fa9be0de6cf49e536ce1851f987bd21a43b771b09473c3549a6c853db37c1c" +dependencies = [ + "futures-core", + "futures-util", + "pin-project", + "pin-project-lite", + "tokio", + "tower-layer", + "tower-service", + "tracing", +] + +[[package]] +name = "tower-http" +version = "0.3.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f873044bf02dd1e8239e9c1293ea39dad76dc594ec16185d0a1bf31d8dc8d858" +dependencies = [ + "bitflags", + "bytes", + "futures-core", + "futures-util", + "http", + "http-body", + "http-range-header", + "pin-project-lite", + "tower", + "tower-layer", + "tower-service", +] + +[[package]] +name = "tower-layer" +version = "0.3.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c20c8dbed6283a09604c3e69b4b7eeb54e298b8a600d4d5ecb5ad39de609f1d0" + +[[package]] +name = "tower-service" +version = "0.3.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b6bc1c9ce2b5135ac7f93c72918fc37feb872bdc6a5533a8b85eb4b86bfdae52" + +[[package]] +name = "tracing" +version = "0.1.37" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8ce8c33a8d48bd45d624a6e523445fd21ec13d3653cd51f681abf67418f54eb8" +dependencies = [ + "cfg-if", + "log", + "pin-project-lite", + "tracing-core", +] + +[[package]] +name = "tracing-core" +version = "0.1.30" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "24eb03ba0eab1fd845050058ce5e616558e8f8d8fca633e6b163fe25c797213a" +dependencies = [ + "once_cell", +] + +[[package]] +name = "try-lock" +version = "0.2.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3528ecfd12c466c6f163363caf2d02a71161dd5e1cc6ae7b34207ea2d42d81ed" + +[[package]] +name = "unicase" +version = "2.6.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "50f37be617794602aabbeee0be4f259dc1778fabe05e2d67ee8f79326d5cb4f6" +dependencies = [ + "version_check", +] + +[[package]] +name = "unicode-bidi" +version = "0.3.10" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d54675592c1dbefd78cbd98db9bacd89886e1ca50692a0692baefffdeb92dd58" + +[[package]] +name = "unicode-ident" +version = "1.0.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "84a22b9f218b40614adcb3f4ff08b703773ad44fa9423e4e0d346d5db86e4ebc" + +[[package]] +name = "unicode-normalization" +version = "0.1.22" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5c5713f0fc4b5db668a2ac63cdb7bb4469d8c9fed047b1d0292cc7b0ce2ba921" +dependencies = [ + "tinyvec", +] + +[[package]] +name = "unicode-width" +version = "0.1.10" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c0edd1e5b14653f783770bce4a4dabb4a5108a5370a5f5d8cfe8710c361f6c8b" + +[[package]] +name = "untrusted" +version = "0.7.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a156c684c91ea7d62626509bce3cb4e1d9ed5c4d978f7b4352658f96a4c26b4a" + +[[package]] +name = "url" +version = "2.3.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0d68c799ae75762b8c3fe375feb6600ef5602c883c5d21eb51c09f22b83c4643" +dependencies = [ + "form_urlencoded", + "idna", + "percent-encoding", +] + +[[package]] +name = "utf-8" +version = "0.7.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "09cc8ee72d2a9becf2f2febe0205bbed8fc6615b7cb429ad062dc7b7ddd036a9" + +[[package]] +name = "version_check" +version = "0.9.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "49874b5167b65d7193b8aba1567f5c7d93d001cafc34600cee003eda787e483f" + +[[package]] +name = "want" +version = "0.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1ce8a968cb1cd110d136ff8b819a556d6fb6d919363c61534f6860c7eb172ba0" +dependencies = [ + "log", + "try-lock", +] + +[[package]] +name = "wasi" +version = "0.9.0+wasi-snapshot-preview1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "cccddf32554fecc6acb585f82a32a72e28b48f8c4c1883ddfeeeaa96f7d8e519" + +[[package]] +name = "wasi" +version = "0.11.0+wasi-snapshot-preview1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423" + +[[package]] +name = "wasm-bindgen" +version = "0.2.83" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "eaf9f5aceeec8be17c128b2e93e031fb8a4d469bb9c4ae2d7dc1888b26887268" +dependencies = [ + "cfg-if", + "wasm-bindgen-macro", +] + +[[package]] +name = "wasm-bindgen-backend" +version = "0.2.83" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4c8ffb332579b0557b52d268b91feab8df3615f265d5270fec2a8c95b17c1142" +dependencies = [ + "bumpalo", + "log", + "once_cell", + "proc-macro2", + "quote", + "syn", + "wasm-bindgen-shared", +] + +[[package]] +name = "wasm-bindgen-futures" +version = "0.4.33" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "23639446165ca5a5de86ae1d8896b737ae80319560fbaa4c2887b7da6e7ebd7d" +dependencies = [ + "cfg-if", + "js-sys", + "wasm-bindgen", + "web-sys", +] + +[[package]] +name = "wasm-bindgen-macro" +version = "0.2.83" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "052be0f94026e6cbc75cdefc9bae13fd6052cdcaf532fa6c45e7ae33a1e6c810" +dependencies = [ + "quote", + "wasm-bindgen-macro-support", +] + +[[package]] +name = "wasm-bindgen-macro-support" +version = "0.2.83" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "07bc0c051dc5f23e307b13285f9d75df86bfdf816c5721e573dec1f9b8aa193c" +dependencies = [ + "proc-macro2", + "quote", + "syn", + "wasm-bindgen-backend", + "wasm-bindgen-shared", +] + +[[package]] +name = "wasm-bindgen-shared" +version = "0.2.83" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1c38c045535d93ec4f0b4defec448e4291638ee608530863b1e2ba115d4fff7f" + +[[package]] +name = "web-sys" +version = "0.3.60" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "bcda906d8be16e728fd5adc5b729afad4e444e106ab28cd1c7256e54fa61510f" +dependencies = [ + "js-sys", + "wasm-bindgen", +] + +[[package]] +name = "webpki" +version = "0.22.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f095d78192e208183081cc07bc5515ef55216397af48b873e5edcd72637fa1bd" +dependencies = [ + "ring", + "untrusted", +] + +[[package]] +name = "webpki-roots" +version = "0.22.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b6c71e40d7d2c34a5106301fb632274ca37242cd0c9d3e64dbece371a40a2d87" +dependencies = [ + "webpki", +] + +[[package]] +name = "winapi" +version = "0.3.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5c839a674fcd7a98952e593242ea400abe93992746761e38641405d28b00f419" +dependencies = [ + "winapi-i686-pc-windows-gnu", + "winapi-x86_64-pc-windows-gnu", +] + +[[package]] +name = "winapi-i686-pc-windows-gnu" +version = "0.4.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6" + +[[package]] +name = "winapi-util" +version = "0.1.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "70ec6ce85bb158151cae5e5c87f95a8e97d2c0c4b001223f33a334e3ce5de178" +dependencies = [ + "winapi", +] + +[[package]] +name = "winapi-x86_64-pc-windows-gnu" +version = "0.4.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f" + +[[package]] +name = "windows-sys" +version = "0.42.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5a3e1820f08b8513f676f7ab6c1f99ff312fb97b553d30ff4dd86f9f15728aa7" +dependencies = [ + "windows_aarch64_gnullvm", + "windows_aarch64_msvc", + "windows_i686_gnu", + "windows_i686_msvc", + "windows_x86_64_gnu", + "windows_x86_64_gnullvm", + "windows_x86_64_msvc", +] + +[[package]] +name = "windows_aarch64_gnullvm" +version = "0.42.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8c9864e83243fdec7fc9c5444389dcbbfd258f745e7853198f365e3c4968a608" + +[[package]] +name = "windows_aarch64_msvc" +version = "0.42.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4c8b1b673ffc16c47a9ff48570a9d85e25d265735c503681332589af6253c6c7" + +[[package]] +name = "windows_i686_gnu" +version = "0.42.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "de3887528ad530ba7bdbb1faa8275ec7a1155a45ffa57c37993960277145d640" + +[[package]] +name = "windows_i686_msvc" +version = "0.42.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "bf4d1122317eddd6ff351aa852118a2418ad4214e6613a50e0191f7004372605" + +[[package]] +name = "windows_x86_64_gnu" +version = "0.42.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c1040f221285e17ebccbc2591ffdc2d44ee1f9186324dd3e84e99ac68d699c45" + +[[package]] +name = "windows_x86_64_gnullvm" +version = "0.42.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "628bfdf232daa22b0d64fdb62b09fcc36bb01f05a3939e20ab73aaf9470d0463" + +[[package]] +name = "windows_x86_64_msvc" +version = "0.42.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "447660ad36a13288b1db4d4248e857b510e8c3a225c822ba4fb748c0aafecffd" + +[[package]] +name = "winreg" +version = "0.10.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "80d0f4e272c85def139476380b12f9ac60926689dd2e01d4923222f40580869d" +dependencies = [ + "winapi", +] diff --git a/Cargo.toml b/Cargo.toml new file mode 100644 index 0000000..e50411b --- /dev/null +++ b/Cargo.toml @@ -0,0 +1,14 @@ +[package] +name = "searchinblog" +version = "0.1.0" +edition = "2021" + +# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html + +[dependencies] +anyhow = "1.0.68" +axum = { version = "0.6.4", features = ["http2", "macros"] } +clap = { version = "4.1.4", features = ["derive", "cargo"] } +reqwest = { version = "0.11.14", default-features = false, features = ["rustls-tls-webpki-roots", "json", "gzip", "mime_guess"] } +scraper = "0.14.0" +tokio = { version = "1.24.2", features = ["full"] } diff --git a/README.md b/README.md new file mode 100644 index 0000000..9261555 --- /dev/null +++ b/README.md @@ -0,0 +1,14 @@ +## Crawling requirements + +- You must serve a robots.txt to describe the terms of crawling. Otherwise, it + will be ignored by this bot. + +- You must serve an atom feed. + +## RFC References + +- **[RFC4287]**: The Atom Syndication Format +- **[RFC9309]**: Proposed Robots Exclusion Protocol + +[rfc4287]: https://www.rfc-editor.org/rfc/rfc4287 +[rfc9309]: https://www.rfc-editor.org/rfc/rfc9309 diff --git a/default.nix b/default.nix new file mode 100644 index 0000000..f427435 --- /dev/null +++ b/default.nix @@ -0,0 +1,12 @@ +{ toolchain, makeRustPlatform, pkg-config }: + +let rustPlatform = makeRustPlatform { inherit (toolchain) cargo rustc; }; + +in rustPlatform.buildRustPackage { + name = "searchinblog"; + src = ./.; + cargoLock.lockFile = ./Cargo.lock; + + nativeBuildInputs = [ pkg-config ]; + buildInputs = [ ]; +} diff --git a/docker-compose.yml b/docker-compose.yml new file mode 100644 index 0000000..0d75a44 --- /dev/null +++ b/docker-compose.yml @@ -0,0 +1,8 @@ +version: "3" + +services: + db: + image: postgres + ports: [5433:5432] + environment: + POSTGRES_PASSWORD: example diff --git a/flake.lock b/flake.lock new file mode 100644 index 0000000..d4b40ce --- /dev/null +++ b/flake.lock @@ -0,0 +1,93 @@ +{ + "nodes": { + "fenix": { + "inputs": { + "nixpkgs": "nixpkgs", + "rust-analyzer-src": "rust-analyzer-src" + }, + "locked": { + "lastModified": 1674541370, + "narHash": "sha256-L62dKDX6fIUQhlna9R8PKSAEGZ7ueU5gRGxZzZs/Zx8=", + "owner": "nix-community", + "repo": "fenix", + "rev": "4435f8e9da13581e51ba1f92a25d7d54c776ad94", + "type": "github" + }, + "original": { + "owner": "nix-community", + "repo": "fenix", + "type": "github" + } + }, + "flake-utils": { + "locked": { + "lastModified": 1667395993, + "narHash": "sha256-nuEHfE/LcWyuSWnS8t12N1wc105Qtau+/OdUAjtQ0rA=", + "owner": "numtide", + "repo": "flake-utils", + "rev": "5aed5285a952e0b949eb3ba02c12fa4fcfef535f", + "type": "github" + }, + "original": { + "id": "flake-utils", + "type": "indirect" + } + }, + "nixpkgs": { + "locked": { + "lastModified": 1674211260, + "narHash": "sha256-xU6Rv9sgnwaWK7tgCPadV6HhI2Y/fl4lKxJoG2+m9qs=", + "owner": "nixos", + "repo": "nixpkgs", + "rev": "5ed481943351e9fd354aeb557679624224de38d5", + "type": "github" + }, + "original": { + "owner": "nixos", + "ref": "nixos-unstable", + "repo": "nixpkgs", + "type": "github" + } + }, + "nixpkgs_2": { + "locked": { + "lastModified": 1667629849, + "narHash": "sha256-P+v+nDOFWicM4wziFK9S/ajF2lc0N2Rg9p6Y35uMoZI=", + "owner": "nixos", + "repo": "nixpkgs", + "rev": "3bacde6273b09a21a8ccfba15586fb165078fb62", + "type": "github" + }, + "original": { + "id": "nixpkgs", + "type": "indirect" + } + }, + "root": { + "inputs": { + "fenix": "fenix", + "flake-utils": "flake-utils", + "nixpkgs": "nixpkgs_2" + } + }, + "rust-analyzer-src": { + "flake": false, + "locked": { + "lastModified": 1674491573, + "narHash": "sha256-1hMPOn2dlMfWRWvuaWcSxNquKpvjGVXq2rVw6UJy75Q=", + "owner": "rust-lang", + "repo": "rust-analyzer", + "rev": "c552e5a55f13b2f08d506bb46fb74dbc11702d0d", + "type": "github" + }, + "original": { + "owner": "rust-lang", + "ref": "nightly", + "repo": "rust-analyzer", + "type": "github" + } + } + }, + "root": "root", + "version": 7 +} diff --git a/flake.nix b/flake.nix new file mode 100644 index 0000000..7e8ef87 --- /dev/null +++ b/flake.nix @@ -0,0 +1,28 @@ +{ + inputs = { fenix.url = "github:nix-community/fenix"; }; + + outputs = { self, nixpkgs, flake-utils, fenix }: + flake-utils.lib.eachDefaultSystem (system: + let + pkgs = import nixpkgs { + inherit system; + overlays = [ fenix.overlays.default ]; + }; + + toolchain = pkgs.fenix.stable; + + flakePkgs = { + searchinblog = pkgs.callPackage ./. { inherit toolchain; }; + }; + in rec { + packages = flake-utils.lib.flattenTree flakePkgs; + defaultPackage = packages.searchinblog; + + devShell = pkgs.mkShell { + inputsFrom = with packages; [ searchinblog ]; + packages = (with pkgs; [ cargo-watch cargo-deny cargo-edit sqlx-cli ]) + ++ (with toolchain; [ cargo rustc rustfmt ]); + CARGO_UNSTABLE_SPARSE_REGISTRY = "true"; + }; + }); +} diff --git a/migrations/20230125084829_initial.sql b/migrations/20230125084829_initial.sql new file mode 100644 index 0000000..c01ac6b --- /dev/null +++ b/migrations/20230125084829_initial.sql @@ -0,0 +1,34 @@ +CREATE TABLE websites ( + id INTEGER PRIMARY KEY, + domain TEXT UNIQUE, + last_collected TIMESTAMP WITHOUT TIME ZONE +); + +CREATE TABLE posts ( + id INTEGER PRIMARY KEY, + url TEXT UNIQUE, + last_updated_by_version TEXT, + content TEXT, + content_tsv TSVECTOR +); + +CREATE INDEX "posts_fti_idx" ON posts USING GIN(content_tsv); +CREATE TRIGGER "posts_fti_trigger" AFTER UPDATE OR INSERT OR DELETE + ON posts FOR EACH ROW + EXECUTE PROCEDURE tsvector_update_trigger(posts_fti, content_tsv, 'pg_catalog.english', content); + +CREATE TABLE authors ( + id INTEGER PRIMARY KEY, + url TEXT UNIQUE +); + +CREATE TABLE posts_keywords ( + post_id INTEGER, + keyword TEXT, + + PRIMARY KEY(post_id, keyword), + CONSTRAINT fk_post FOREIGN KEY(post_id) REFERENCES posts(id) + -- CONSTRAINT fk_keyword FOREIGN KEY(keyword) REFERENCES keywords(keyword) +); + +CREATE INDEX "posts_keywords_idx" ON posts_keywords(keyword); diff --git a/rustfmt.toml b/rustfmt.toml new file mode 100644 index 0000000..4c1eefa --- /dev/null +++ b/rustfmt.toml @@ -0,0 +1,2 @@ +max_width = 80 +tab_spaces = 2 diff --git a/src/crawler.rs b/src/crawler.rs new file mode 100644 index 0000000..394d4ca --- /dev/null +++ b/src/crawler.rs @@ -0,0 +1,54 @@ +//! Crawler +//! === +//! +//! The crawler design is built upon an important Postgres feature: Pubsub. It always waits on 2 +//! events: +//! +//! - One that listens to Postgres pubsub triggers +//! - One that waits on a timer based on the next available job +//! +//! Once one of these events fires, it retrieves the job from the database and performs the crawl. +//! The crawl will try to perform a retrieval and populate the database and fill the full text +//! index. + +use anyhow::Result; +use reqwest::Url; +use scraper::{Html, Selector}; + +pub async fn crawler() -> Result<()> { + Ok(()) +} + +#[derive(Debug, Parser)] +pub struct CrawlSingleSiteOpts { + /// The domain to crawl + #[clap(name = "domain", long)] + domain: String, +} + +/// Crawl a single site. +pub async fn crawl_single_site(opts: CrawlSingleSiteOpts) -> Result<()> { + let CrawlSingleSiteOpts { domain, .. } = opts; + + // Check the robots.txt of the site to see if or how we can crawl + let url = Url::parse(&format!("https://{domain}/robots.txt"))?; + let response = reqwest::get(url).await?; + println!("Response: {response:?}"); + + // Try to look for an atom feed by parsing HTML headers + let url = Url::parse(&format!("https://{domain}"))?; + let response = reqwest::get(url).await?; + let body = response.text().await?; + let html = Html::parse_document(&body); + let tag = Selector::parse("link[type=\"application/atom+xml\"]").unwrap(); + for element in html.select(&tag) { + let attrs = element.value().attrs(); + for attr in attrs { + println!("Attrs: {attr:?}"); + } + } + + // Go through each of the files in the atom feed + + Ok(()) +} diff --git a/src/main.rs b/src/main.rs new file mode 100644 index 0000000..4100d20 --- /dev/null +++ b/src/main.rs @@ -0,0 +1,47 @@ +#[macro_use] +extern crate clap; + +mod crawler; + +use anyhow::Result; +use clap::Parser; + +use crate::crawler::{crawl_single_site, crawler, CrawlSingleSiteOpts}; + +#[derive(Parser, Debug)] +struct Opt { + #[clap(subcommand)] + command: Subcommand, +} + +#[derive(Parser, Debug)] +enum Subcommand { + #[clap(name = "crawler")] + Crawler, + + #[clap(name = "web")] + Web, + + /// Crawl just a single site + #[clap(name = "crawl-single-site")] + CrawlSingleSite(CrawlSingleSiteOpts), +} + +#[tokio::main] +async fn main() -> Result<()> { + let opt = Opt::parse(); + + println!("Hello, world! {opt:?}"); + + match opt.command { + Subcommand::Web => {} + Subcommand::Crawler => { + crawler().await?; + } + Subcommand::CrawlSingleSite(opts) => { + crawl_single_site(opts).await?; + } + } + + Ok(()) +}