From a002d6cd5929ccf48a5ea7d57a5cd62becba509a Mon Sep 17 00:00:00 2001 From: clerie Date: Sun, 27 Apr 2025 11:55:02 +0200 Subject: [PATCH] Strip html tags from remote html content --- Cargo.lock | 460 +++++++++++++++++++++++++++++++++++++++++++++++----- Cargo.toml | 1 + src/main.rs | 14 +- 3 files changed, 429 insertions(+), 46 deletions(-) diff --git a/Cargo.lock b/Cargo.lock index 26d9769..d6494ee 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -102,6 +102,15 @@ version = "1.1.2" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "1505bd5d3d116872e7271a6d4e16d81d0c8570876c8de68093a09ac269d8aac0" +[[package]] +name = "autocfg" +version = "0.1.8" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0dde43e75fd43e8a1bf86103336bc699aa8d17ad1be60c76c0bdfd4828e19b78" +dependencies = [ + "autocfg 1.4.0", +] + [[package]] name = "autocfg" version = "1.4.0" @@ -129,6 +138,12 @@ version = "0.22.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6" +[[package]] +name = "bitflags" +version = "1.3.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a" + [[package]] name = "bitflags" version = "2.6.0" @@ -206,9 +221,9 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "4ac6a0c7b1a9e9a5186361f67dfa1b88213572f427fb9ab038efb2bd8c582dab" dependencies = [ "heck", - "proc-macro2", - "quote", - "syn", + "proc-macro2 1.0.92", + "quote 1.0.37", + "syn 2.0.89", ] [[package]] @@ -217,6 +232,15 @@ version = "0.7.4" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "f46ad14479a25103f283c0f10005961cf086d8dc42205bb44c46ac563475dca6" +[[package]] +name = "cloudabi" +version = "0.0.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ddfc5b9aa5d4507acaf872de71051dfd0e309860e88966e1051e462a077aac4f" +dependencies = [ + "bitflags 1.3.2", +] + [[package]] name = "colorchoice" version = "1.0.3" @@ -245,9 +269,9 @@ version = "0.2.5" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "97369cbbc041bc366949bc74d34658d6cda5621039731c6310521892a3a20ae0" dependencies = [ - "proc-macro2", - "quote", - "syn", + "proc-macro2 1.0.92", + "quote 1.0.37", + "syn 2.0.89", ] [[package]] @@ -293,7 +317,7 @@ dependencies = [ "regex", "serde", "serde_json", - "siphasher", + "siphasher 1.0.1", "url", "uuid", ] @@ -328,6 +352,22 @@ dependencies = [ "percent-encoding", ] +[[package]] +name = "fuchsia-cprng" +version = "0.1.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a06f77d526c1a601b7c4cdd98f54b5eaabffc14d5f2f0296febdc7f357c6d3ba" + +[[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 = "0.3.31" @@ -426,6 +466,20 @@ version = "0.5.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea" +[[package]] +name = "html5ever" +version = "0.22.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c213fa6a618dc1da552f54f85cba74b05d8e883c92ec4e89067736938084c26e" +dependencies = [ + "log", + "mac", + "markup5ever", + "proc-macro2 0.4.30", + "quote 0.6.13", + "syn 0.15.44", +] + [[package]] name = "http" version = "1.1.0" @@ -674,9 +728,9 @@ version = "1.5.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "1ec89e9337638ecdc08744df490b221a7399bf8d164eb52a665454e60e075ad6" dependencies = [ - "proc-macro2", - "quote", - "syn", + "proc-macro2 1.0.92", + "quote 1.0.37", + "syn 2.0.89", ] [[package]] @@ -737,6 +791,12 @@ dependencies = [ "wasm-bindgen", ] +[[package]] +name = "lazy_static" +version = "1.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "bbd2bcb4c963f2ddae06a2efc7e9f3591312473c50c6685e1f298068316e66fe" + [[package]] name = "libc" version = "0.2.167" @@ -761,6 +821,28 @@ version = "0.4.22" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "a7a70ba024b9dc04c27ea2f0c0548feb474ec5c54bba33a7f72f873a39d07b24" +[[package]] +name = "mac" +version = "0.1.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c41e0c4fef86961ac6d6f8a82609f55f31b05e4fce149ac5710e439df7619ba4" + +[[package]] +name = "markup5ever" +version = "0.7.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "897636f9850c3eef4905a5540683ed53dc9393860f0846cab2c2ddf9939862ff" +dependencies = [ + "phf", + "phf_codegen", + "serde", + "serde_derive", + "serde_json", + "string_cache", + "string_cache_codegen", + "tendril", +] + [[package]] name = "mediatype" version = "0.19.18" @@ -819,13 +901,19 @@ dependencies = [ "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", + "autocfg 1.4.0", ] [[package]] @@ -849,7 +937,7 @@ version = "0.10.68" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "6174bc48f102d208783c2c84bf931bb75927a617866870de8a4ea85597f871f5" dependencies = [ - "bitflags", + "bitflags 2.6.0", "cfg-if", "foreign-types", "libc", @@ -864,9 +952,9 @@ version = "0.1.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "a948666b637a0f465e8564c73e89d4dde00d72d4d473cc972f390fc3dcee7d9c" dependencies = [ - "proc-macro2", - "quote", - "syn", + "proc-macro2 1.0.92", + "quote 1.0.37", + "syn 2.0.89", ] [[package]] @@ -893,6 +981,44 @@ version = "2.3.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "e3148f5046208a5d56bcfc03053e3ca6334e51da8dfb19b6cdc8b306fae3283e" +[[package]] +name = "phf" +version = "0.7.24" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b3da44b85f8e8dfaec21adae67f95d93244b2ecf6ad2a692320598dcc8e6dd18" +dependencies = [ + "phf_shared", +] + +[[package]] +name = "phf_codegen" +version = "0.7.24" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b03e85129e324ad4166b06b2c7491ae27fe3ec353af72e72cd1654c7225d517e" +dependencies = [ + "phf_generator", + "phf_shared", +] + +[[package]] +name = "phf_generator" +version = "0.7.24" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "09364cc93c159b8b06b1f4dd8a4398984503483891b0c26b867cf431fb132662" +dependencies = [ + "phf_shared", + "rand", +] + +[[package]] +name = "phf_shared" +version = "0.7.24" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "234f71a15de2288bcb7e3b6515828d22af7ec8598ee6d24c3b526fa0a80b67a0" +dependencies = [ + "siphasher 0.2.3", +] + [[package]] name = "pin-project-lite" version = "0.2.15" @@ -911,6 +1037,21 @@ version = "0.3.31" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "953ec861398dccce10c670dfeaf3ec4911ca479e9c02154b3a215178c5f566f2" +[[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 = "0.4.30" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "cf3d2011ab5c909338f7887f4fc896d35932e29146c12c8d01da6b22a80ba759" +dependencies = [ + "unicode-xid", +] + [[package]] name = "proc-macro2" version = "1.0.92" @@ -930,13 +1071,22 @@ dependencies = [ "memchr", ] +[[package]] +name = "quote" +version = "0.6.13" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6ce23b6b870e8f94f81fb0a363d65d86675884b34a09043c81e5562f11c1f8e1" +dependencies = [ + "proc-macro2 0.4.30", +] + [[package]] name = "quote" version = "1.0.37" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "b5b9d34b8991d19d98081b46eacdd8eb58c6f2b201139f7c5f643cc155a633af" dependencies = [ - "proc-macro2", + "proc-macro2 1.0.92", ] [[package]] @@ -948,6 +1098,122 @@ dependencies = [ "clap", "feed-rs", "reqwest", + "soup", +] + +[[package]] +name = "rand" +version = "0.6.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6d71dacdc3c88c1fde3885a3be3fbab9f35724e6ce99467f7d9c5026132184ca" +dependencies = [ + "autocfg 0.1.8", + "libc", + "rand_chacha", + "rand_core 0.4.2", + "rand_hc", + "rand_isaac", + "rand_jitter", + "rand_os", + "rand_pcg", + "rand_xorshift", + "winapi", +] + +[[package]] +name = "rand_chacha" +version = "0.1.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "556d3a1ca6600bfcbab7c7c91ccb085ac7fbbcd70e008a98742e7847f4f7bcef" +dependencies = [ + "autocfg 0.1.8", + "rand_core 0.3.1", +] + +[[package]] +name = "rand_core" +version = "0.3.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7a6fdeb83b075e8266dcc8762c22776f6877a63111121f5f8c7411e5be7eed4b" +dependencies = [ + "rand_core 0.4.2", +] + +[[package]] +name = "rand_core" +version = "0.4.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9c33a3c44ca05fa6f1807d8e6743f3824e8509beca625669633be0acbdf509dc" + +[[package]] +name = "rand_hc" +version = "0.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7b40677c7be09ae76218dc623efbf7b18e34bced3f38883af07bb75630a21bc4" +dependencies = [ + "rand_core 0.3.1", +] + +[[package]] +name = "rand_isaac" +version = "0.1.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ded997c9d5f13925be2a6fd7e66bf1872597f759fd9dd93513dd7e92e5a5ee08" +dependencies = [ + "rand_core 0.3.1", +] + +[[package]] +name = "rand_jitter" +version = "0.1.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1166d5c91dc97b88d1decc3285bb0a99ed84b05cfd0bc2341bdf2d43fc41e39b" +dependencies = [ + "libc", + "rand_core 0.4.2", + "winapi", +] + +[[package]] +name = "rand_os" +version = "0.1.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7b75f676a1e053fc562eafbb47838d67c84801e38fc1ba459e8f180deabd5071" +dependencies = [ + "cloudabi", + "fuchsia-cprng", + "libc", + "rand_core 0.4.2", + "rdrand", + "winapi", +] + +[[package]] +name = "rand_pcg" +version = "0.1.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "abf9b09b01790cfe0364f52bf32995ea3c39f4d2dd011eac241d2914146d0b44" +dependencies = [ + "autocfg 0.1.8", + "rand_core 0.4.2", +] + +[[package]] +name = "rand_xorshift" +version = "0.1.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "cbf7e9e623549b0e21f6e97cf8ecf247c1a8fd2e8a992ae265314300b2455d5c" +dependencies = [ + "rand_core 0.3.1", +] + +[[package]] +name = "rdrand" +version = "0.4.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "678054eb77286b51581ba43620cc911abf02758c91f93f479767aed0f90458b2" +dependencies = [ + "rand_core 0.3.1", ] [[package]] @@ -1050,7 +1316,7 @@ version = "0.38.41" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "d7f649912bc1495e167a6edee79151c84b1bad49748cb4f1f1167f459f6224f6" dependencies = [ - "bitflags", + "bitflags 2.6.0", "errno", "libc", "linux-raw-sys", @@ -1117,7 +1383,7 @@ version = "2.11.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "897b2245f0b511c87893af39b033e5ca9cce68824c4d7e7630b5a1d339658d02" dependencies = [ - "bitflags", + "bitflags 2.6.0", "core-foundation", "core-foundation-sys", "libc", @@ -1149,9 +1415,9 @@ version = "1.0.215" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "ad1e866f866923f252f05c889987993144fb74e722403468a4ebd70c3cd756c0" dependencies = [ - "proc-macro2", - "quote", - "syn", + "proc-macro2 1.0.92", + "quote 1.0.37", + "syn 2.0.89", ] [[package]] @@ -1184,6 +1450,12 @@ version = "1.3.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64" +[[package]] +name = "siphasher" +version = "0.2.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0b8de496cf83d4ed58b6be86c3a275b8602f6ffe98d3024a869e124147a9a3ac" + [[package]] name = "siphasher" version = "1.0.1" @@ -1196,7 +1468,7 @@ version = "0.4.9" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "8f92a496fb766b417c996b9c5e57daf2f7ad3b0bebe1ccfca4856390e3d3bb67" dependencies = [ - "autocfg", + "autocfg 1.4.0", ] [[package]] @@ -1215,6 +1487,16 @@ dependencies = [ "windows-sys 0.52.0", ] +[[package]] +name = "soup" +version = "0.5.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "aa5a5d21523f4b7a17ad04eaf534360fc908879f53f3341918cbec2fee9cfe14" +dependencies = [ + "html5ever", + "regex", +] + [[package]] name = "spin" version = "0.9.8" @@ -1227,6 +1509,40 @@ version = "1.2.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "a8f112729512f8e442d81f95a8a7ddf2b7c6b8a1a6f509a95864142b30cab2d3" +[[package]] +name = "string_cache" +version = "0.7.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "89c058a82f9fd69b1becf8c274f412281038877c553182f1d02eb027045a2d67" +dependencies = [ + "lazy_static", + "new_debug_unreachable", + "phf_shared", + "precomputed-hash", + "serde", + "string_cache_codegen", + "string_cache_shared", +] + +[[package]] +name = "string_cache_codegen" +version = "0.4.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f0f45ed1b65bf9a4bf2f7b7dc59212d1926e9eaf00fa998988e420fd124467c6" +dependencies = [ + "phf_generator", + "phf_shared", + "proc-macro2 1.0.92", + "quote 1.0.37", + "string_cache_shared", +] + +[[package]] +name = "string_cache_shared" +version = "0.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b1884d1bc09741d466d9b14e6d37ac89d6909cbcac41dd9ae982d4d063bbedfc" + [[package]] name = "strsim" version = "0.11.1" @@ -1239,14 +1555,25 @@ version = "2.6.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "13c2bddecc57b384dee18652358fb23172facb8a2c51ccc10d74c157bdea3292" +[[package]] +name = "syn" +version = "0.15.44" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9ca4b3b69a77cbe1ffc9e198781b7acb0c7365a883670e8f1c1bc66fba79a5c5" +dependencies = [ + "proc-macro2 0.4.30", + "quote 0.6.13", + "unicode-xid", +] + [[package]] name = "syn" version = "2.0.89" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "44d46482f1c1c87acd84dea20c1bf5ebff4c757009ed6bf19cfd36fb10e92c4e" dependencies = [ - "proc-macro2", - "quote", + "proc-macro2 1.0.92", + "quote 1.0.37", "unicode-ident", ] @@ -1265,9 +1592,9 @@ version = "0.13.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "c8af7666ab7b6390ab78131fb5b0fce11d6b7a6951602017c35fa82800708971" dependencies = [ - "proc-macro2", - "quote", - "syn", + "proc-macro2 1.0.92", + "quote 1.0.37", + "syn 2.0.89", ] [[package]] @@ -1276,7 +1603,7 @@ version = "0.6.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "3c879d448e9d986b661742763247d3693ed13609438cf3d006f51f5368a5ba6b" dependencies = [ - "bitflags", + "bitflags 2.6.0", "core-foundation", "system-configuration-sys", ] @@ -1304,6 +1631,17 @@ dependencies = [ "windows-sys 0.59.0", ] +[[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 = "0.7.6" @@ -1400,6 +1738,12 @@ version = "1.0.14" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "adb9e6ca4f869e1180728b7950e35922a7fc6397f7b641499e8f3ef06e50dc83" +[[package]] +name = "unicode-xid" +version = "0.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fc72304796d0818e357ead4e000d19c9c174ab23dc11093ac919054d20a6a7fc" + [[package]] name = "untrusted" version = "0.9.0" @@ -1418,6 +1762,12 @@ dependencies = [ "serde", ] +[[package]] +name = "utf-8" +version = "0.7.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "09cc8ee72d2a9becf2f2febe0205bbed8fc6615b7cb429ad062dc7b7ddd036a9" + [[package]] name = "utf16_iter" version = "1.0.5" @@ -1486,9 +1836,9 @@ dependencies = [ "bumpalo", "log", "once_cell", - "proc-macro2", - "quote", - "syn", + "proc-macro2 1.0.92", + "quote 1.0.37", + "syn 2.0.89", "wasm-bindgen-shared", ] @@ -1511,7 +1861,7 @@ version = "0.2.96" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "920b0ffe069571ebbfc9ddc0b36ba305ef65577c94b06262ed793716a1afd981" dependencies = [ - "quote", + "quote 1.0.37", "wasm-bindgen-macro-support", ] @@ -1521,9 +1871,9 @@ version = "0.2.96" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "bf59002391099644be3524e23b781fa43d2be0c5aa0719a18c0731b9d195cab6" dependencies = [ - "proc-macro2", - "quote", - "syn", + "proc-macro2 1.0.92", + "quote 1.0.37", + "syn 2.0.89", "wasm-bindgen-backend", "wasm-bindgen-shared", ] @@ -1544,6 +1894,28 @@ dependencies = [ "wasm-bindgen", ] +[[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-x86_64-pc-windows-gnu" +version = "0.4.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f" + [[package]] name = "windows-core" version = "0.52.0" @@ -1695,9 +2067,9 @@ version = "0.7.5" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "2380878cad4ac9aac1e2435f3eb4020e8374b5f13c296cb75b4620ff8e229154" dependencies = [ - "proc-macro2", - "quote", - "syn", + "proc-macro2 1.0.92", + "quote 1.0.37", + "syn 2.0.89", "synstructure", ] @@ -1716,9 +2088,9 @@ version = "0.1.5" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "595eed982f7d355beb85837f651fa22e90b3c044842dc7f2c2842c086f295808" dependencies = [ - "proc-macro2", - "quote", - "syn", + "proc-macro2 1.0.92", + "quote 1.0.37", + "syn 2.0.89", "synstructure", ] @@ -1745,7 +2117,7 @@ version = "0.10.3" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "6eafa6dfb17584ea3e2bd6e76e0cc15ad7af12b09abdd1ca55961bed9b1063c6" dependencies = [ - "proc-macro2", - "quote", - "syn", + "proc-macro2 1.0.92", + "quote 1.0.37", + "syn 2.0.89", ] diff --git a/Cargo.toml b/Cargo.toml index 9a0dfdb..fc693af 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -9,3 +9,4 @@ chrono = "0.4.38" clap = { version = "4.5.23", features = ["derive"] } feed-rs = "2.2.0" reqwest = { version = "0.12.9", features = ["blocking"] } +soup = "0.5.1" diff --git a/src/main.rs b/src/main.rs index 8beac73..749a388 100644 --- a/src/main.rs +++ b/src/main.rs @@ -13,12 +13,16 @@ use feed_rs::{ Feed, }, }; - use reqwest::{ IntoUrl, StatusCode, Url, }; +use soup::{ + prelude::{ + Soup, + }, +}; #[derive(Parser)] #[command(version, about, long_about = None)] @@ -114,6 +118,12 @@ fn make_feed_item(entry: Entry) -> Result { }) } +fn unsafe_html_to_text(unsafe_html: &str) -> String { + let soup = Soup::new(unsafe_html); + + return soup.text(); +} + fn main() -> Result<()> { let cli = Cli::parse(); @@ -173,7 +183,7 @@ fn main() -> Result<()> { out.push_str("\n");