This commit is contained in:
JMARyA 2024-03-07 16:18:47 +01:00
commit 64215f5b70
Signed by: jmarya
GPG key ID: 901B2ADDF27C2263
9 changed files with 984 additions and 0 deletions

3
.gitignore vendored Normal file
View file

@ -0,0 +1,3 @@
/target
/download
download.db

665
Cargo.lock generated Normal file
View file

@ -0,0 +1,665 @@
# This file is automatically @generated by Cargo.
# It is not intended for manual editing.
version = 3
[[package]]
name = "ahash"
version = "0.8.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "77c3a9648d43b9cd48db467b3f87fdd6e146bcc88ab0180006cef2179fe11d01"
dependencies = [
"cfg-if",
"once_cell",
"version_check",
"zerocopy",
]
[[package]]
name = "aho-corasick"
version = "1.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b2969dcb958b36655471fc61f7e416fa76033bdd4bfed0678d8fee1e2d07a1f0"
dependencies = [
"memchr",
]
[[package]]
name = "allocator-api2"
version = "0.2.16"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0942ffc6dcaadf03badf6e6a2d0228460359d5e34b57ccdc720b7382dfbd5ec5"
[[package]]
name = "android-tzdata"
version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e999941b234f3131b00bc13c22d06e8c5ff726d1b6318ac7eb276997bbb4fef0"
[[package]]
name = "android_system_properties"
version = "0.1.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "819e7219dbd41043ac279b19830f2efc897156490d7fd6ea916720117ee66311"
dependencies = [
"libc",
]
[[package]]
name = "anstream"
version = "0.6.13"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d96bd03f33fe50a863e394ee9718a706f988b9079b20c3784fb726e7678b62fb"
dependencies = [
"anstyle",
"anstyle-parse",
"anstyle-query",
"anstyle-wincon",
"colorchoice",
"utf8parse",
]
[[package]]
name = "anstyle"
version = "1.0.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8901269c6307e8d93993578286ac0edf7f195079ffff5ebdeea6a59ffb7e36bc"
[[package]]
name = "anstyle-parse"
version = "0.2.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c75ac65da39e5fe5ab759307499ddad880d724eed2f6ce5b5e8a26f4f387928c"
dependencies = [
"utf8parse",
]
[[package]]
name = "anstyle-query"
version = "1.0.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e28923312444cdd728e4738b3f9c9cac739500909bb3d3c94b43551b16517648"
dependencies = [
"windows-sys",
]
[[package]]
name = "anstyle-wincon"
version = "3.0.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1cd54b81ec8d6180e24654d0b371ad22fc3dd083b6ff8ba325b72e00c87660a7"
dependencies = [
"anstyle",
"windows-sys",
]
[[package]]
name = "autocfg"
version = "1.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d468802bab17cbc0cc575e9b053f41e72aa36bfa6b7f55e3529ffa43161b97fa"
[[package]]
name = "bitflags"
version = "2.4.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ed570934406eb16438a4e976b1b4500774099c13b8cb96eec99f620f05090ddf"
[[package]]
name = "bumpalo"
version = "3.15.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8ea184aa71bb362a1157c896979544cc23974e08fd265f29ea96b59f0b4a555b"
[[package]]
name = "cc"
version = "1.0.90"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8cd6604a82acf3039f1144f54b8eb34e91ffba622051189e71b781822d5ee1f5"
[[package]]
name = "cfg-if"
version = "1.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
[[package]]
name = "chrono"
version = "0.4.35"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8eaf5903dcbc0a39312feb77df2ff4c76387d591b9fc7b04a238dcf8bb62639a"
dependencies = [
"android-tzdata",
"iana-time-zone",
"js-sys",
"num-traits",
"wasm-bindgen",
"windows-targets",
]
[[package]]
name = "colorchoice"
version = "1.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "acbf1af155f9b9ef647e42cdc158db4b64a1b61f743629225fde6f3e0be2a7c7"
[[package]]
name = "core-foundation-sys"
version = "0.8.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "06ea2b9bc92be3c2baa9334a323ebca2d6f074ff852cd1d7b11064035cd3868f"
[[package]]
name = "env_filter"
version = "0.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a009aa4810eb158359dda09d0c87378e4bbb89b5a801f016885a4707ba24f7ea"
dependencies = [
"log",
"regex",
]
[[package]]
name = "env_logger"
version = "0.11.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "38b35839ba51819680ba087cd351788c9a3c476841207e0b8cee0b04722343b9"
dependencies = [
"anstream",
"anstyle",
"env_filter",
"humantime",
"log",
]
[[package]]
name = "equivalent"
version = "1.0.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5443807d6dff69373d433ab9ef5378ad8df50ca6298caf15de6e52e24aaf54d5"
[[package]]
name = "fallible-iterator"
version = "0.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2acce4a10f12dc2fb14a218589d4f1f62ef011b2d0cc4b3cb1bba8e94da14649"
[[package]]
name = "fallible-streaming-iterator"
version = "0.1.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7360491ce676a36bf9bb3c56c1aa791658183a54d2744120f27285738d90465a"
[[package]]
name = "hashbrown"
version = "0.14.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "290f1a1d9242c78d09ce40a5e87e7554ee637af1351968159f4952f028f75604"
dependencies = [
"ahash",
"allocator-api2",
]
[[package]]
name = "hashlink"
version = "0.8.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e8094feaf31ff591f651a2664fb9cfd92bba7a60ce3197265e9482ebe753c8f7"
dependencies = [
"hashbrown",
]
[[package]]
name = "hoard"
version = "0.1.0"
dependencies = [
"chrono",
"env_logger",
"log",
"rusqlite",
"serde",
"serde_json",
"toml",
]
[[package]]
name = "humantime"
version = "2.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9a3a5bfb195931eeb336b2a7b4d761daec841b97f947d34394601737a7bba5e4"
[[package]]
name = "iana-time-zone"
version = "0.1.60"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e7ffbb5a1b541ea2561f8c41c087286cc091e21e556a4f09a8f6cbf17b69b141"
dependencies = [
"android_system_properties",
"core-foundation-sys",
"iana-time-zone-haiku",
"js-sys",
"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 = "indexmap"
version = "2.2.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "824b2ae422412366ba479e8111fd301f7b5faece8149317bb81925979a53f520"
dependencies = [
"equivalent",
"hashbrown",
]
[[package]]
name = "itoa"
version = "1.0.10"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b1a46d1a171d865aa5f83f92695765caa047a9b4cbae2cbf37dbd613a793fd4c"
[[package]]
name = "js-sys"
version = "0.3.69"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "29c15563dc2726973df627357ce0c9ddddbea194836909d655df6a75d2cf296d"
dependencies = [
"wasm-bindgen",
]
[[package]]
name = "libc"
version = "0.2.153"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9c198f91728a82281a64e1f4f9eeb25d82cb32a5de251c6bd1b5154d63a8e7bd"
[[package]]
name = "libsqlite3-sys"
version = "0.27.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cf4e226dcd58b4be396f7bd3c20da8fdee2911400705297ba7d2d7cc2c30f716"
dependencies = [
"pkg-config",
"vcpkg",
]
[[package]]
name = "log"
version = "0.4.21"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "90ed8c1e510134f979dbc4f070f87d4313098b704861a105fe34231c70a3901c"
[[package]]
name = "memchr"
version = "2.7.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "523dc4f511e55ab87b694dc30d0f820d60906ef06413f93d4d7a1385599cc149"
[[package]]
name = "num-traits"
version = "0.2.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "da0df0e5185db44f69b44f26786fe401b6c293d1907744beaa7fa62b2e5a517a"
dependencies = [
"autocfg",
]
[[package]]
name = "once_cell"
version = "1.19.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3fdb12b2476b595f9358c5161aa467c2438859caa136dec86c26fdd2efe17b92"
[[package]]
name = "pkg-config"
version = "0.3.29"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2900ede94e305130c13ddd391e0ab7cbaeb783945ae07a279c268cb05109c6cb"
[[package]]
name = "proc-macro2"
version = "1.0.78"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e2422ad645d89c99f8f3e6b88a9fdeca7fabeac836b1002371c4367c8f984aae"
dependencies = [
"unicode-ident",
]
[[package]]
name = "quote"
version = "1.0.35"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "291ec9ab5efd934aaf503a6466c5d5251535d108ee747472c3977cc5acc868ef"
dependencies = [
"proc-macro2",
]
[[package]]
name = "regex"
version = "1.10.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b62dbe01f0b06f9d8dc7d49e05a0785f153b00b2c227856282f671e0318c9b15"
dependencies = [
"aho-corasick",
"memchr",
"regex-automata",
"regex-syntax",
]
[[package]]
name = "regex-automata"
version = "0.4.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "86b83b8b9847f9bf95ef68afb0b8e6cdb80f498442f5179a29fad448fcc1eaea"
dependencies = [
"aho-corasick",
"memchr",
"regex-syntax",
]
[[package]]
name = "regex-syntax"
version = "0.8.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c08c74e62047bb2de4ff487b251e4a92e24f48745648451635cec7d591162d9f"
[[package]]
name = "rusqlite"
version = "0.30.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a78046161564f5e7cd9008aff3b2990b3850dc8e0349119b98e8f251e099f24d"
dependencies = [
"bitflags",
"fallible-iterator",
"fallible-streaming-iterator",
"hashlink",
"libsqlite3-sys",
"smallvec",
]
[[package]]
name = "ryu"
version = "1.0.16"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f98d2aa92eebf49b69786be48e4477826b256916e84a57ff2a4f21923b48eb4c"
[[package]]
name = "serde"
version = "1.0.196"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "870026e60fa08c69f064aa766c10f10b1d62db9ccd4d0abb206472bee0ce3b32"
dependencies = [
"serde_derive",
]
[[package]]
name = "serde_derive"
version = "1.0.196"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "33c85360c95e7d137454dc81d9a4ed2b8efd8fbe19cee57357b32b9771fccb67"
dependencies = [
"proc-macro2",
"quote",
"syn",
]
[[package]]
name = "serde_json"
version = "1.0.113"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "69801b70b1c3dac963ecb03a364ba0ceda9cf60c71cfe475e99864759c8b8a79"
dependencies = [
"itoa",
"ryu",
"serde",
]
[[package]]
name = "serde_spanned"
version = "0.6.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "eb3622f419d1296904700073ea6cc23ad690adbd66f13ea683df73298736f0c1"
dependencies = [
"serde",
]
[[package]]
name = "smallvec"
version = "1.13.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e6ecd384b10a64542d77071bd64bd7b231f4ed5940fba55e98c3de13824cf3d7"
[[package]]
name = "syn"
version = "2.0.48"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0f3531638e407dfc0814761abb7c00a5b54992b849452a0646b7f65c9f770f3f"
dependencies = [
"proc-macro2",
"quote",
"unicode-ident",
]
[[package]]
name = "toml"
version = "0.8.10"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9a9aad4a3066010876e8dcf5a8a06e70a558751117a145c6ce2b82c2e2054290"
dependencies = [
"serde",
"serde_spanned",
"toml_datetime",
"toml_edit",
]
[[package]]
name = "toml_datetime"
version = "0.6.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3550f4e9685620ac18a50ed434eb3aec30db8ba93b0287467bca5826ea25baf1"
dependencies = [
"serde",
]
[[package]]
name = "toml_edit"
version = "0.22.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0c9ffdf896f8daaabf9b66ba8e77ea1ed5ed0f72821b398aba62352e95062951"
dependencies = [
"indexmap",
"serde",
"serde_spanned",
"toml_datetime",
"winnow",
]
[[package]]
name = "unicode-ident"
version = "1.0.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3354b9ac3fae1ff6755cb6db53683adb661634f67557942dea4facebec0fee4b"
[[package]]
name = "utf8parse"
version = "0.2.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "711b9620af191e0cdc7468a8d14e709c3dcdb115b36f838e601583af800a370a"
[[package]]
name = "vcpkg"
version = "0.2.15"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "accd4ea62f7bb7a82fe23066fb0957d48ef677f6eeb8215f372f52e48bb32426"
[[package]]
name = "version_check"
version = "0.9.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "49874b5167b65d7193b8aba1567f5c7d93d001cafc34600cee003eda787e483f"
[[package]]
name = "wasm-bindgen"
version = "0.2.92"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4be2531df63900aeb2bca0daaaddec08491ee64ceecbee5076636a3b026795a8"
dependencies = [
"cfg-if",
"wasm-bindgen-macro",
]
[[package]]
name = "wasm-bindgen-backend"
version = "0.2.92"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "614d787b966d3989fa7bb98a654e369c762374fd3213d212cfc0251257e747da"
dependencies = [
"bumpalo",
"log",
"once_cell",
"proc-macro2",
"quote",
"syn",
"wasm-bindgen-shared",
]
[[package]]
name = "wasm-bindgen-macro"
version = "0.2.92"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a1f8823de937b71b9460c0c34e25f3da88250760bec0ebac694b49997550d726"
dependencies = [
"quote",
"wasm-bindgen-macro-support",
]
[[package]]
name = "wasm-bindgen-macro-support"
version = "0.2.92"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e94f17b526d0a461a191c78ea52bbce64071ed5c04c9ffe424dcb38f74171bb7"
dependencies = [
"proc-macro2",
"quote",
"syn",
"wasm-bindgen-backend",
"wasm-bindgen-shared",
]
[[package]]
name = "wasm-bindgen-shared"
version = "0.2.92"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "af190c94f2773fdb3729c55b007a722abb5384da03bc0986df4c289bf5567e96"
[[package]]
name = "windows-core"
version = "0.52.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "33ab640c8d7e35bf8ba19b884ba838ceb4fba93a4e8c65a9059d08afcfc683d9"
dependencies = [
"windows-targets",
]
[[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-targets"
version = "0.52.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7dd37b7e5ab9018759f893a1952c9420d060016fc19a472b4bb20d1bdd694d1b"
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 = "0.52.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bcf46cf4c365c6f2d1cc93ce535f2c8b244591df96ceee75d8e83deb70a9cac9"
[[package]]
name = "windows_aarch64_msvc"
version = "0.52.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "da9f259dd3bcf6990b55bffd094c4f7235817ba4ceebde8e6d11cd0c5633b675"
[[package]]
name = "windows_i686_gnu"
version = "0.52.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b474d8268f99e0995f25b9f095bc7434632601028cf86590aea5c8a5cb7801d3"
[[package]]
name = "windows_i686_msvc"
version = "0.52.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1515e9a29e5bed743cb4415a9ecf5dfca648ce85ee42e15873c3cd8610ff8e02"
[[package]]
name = "windows_x86_64_gnu"
version = "0.52.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5eee091590e89cc02ad514ffe3ead9eb6b660aedca2183455434b93546371a03"
[[package]]
name = "windows_x86_64_gnullvm"
version = "0.52.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "77ca79f2451b49fa9e2af39f0747fe999fcda4f5e241b2898624dca97a1f2177"
[[package]]
name = "windows_x86_64_msvc"
version = "0.52.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "32b752e52a2da0ddfbdbcc6fceadfeede4c939ed16d13e648833a61dfb611ed8"
[[package]]
name = "winnow"
version = "0.5.39"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5389a154b01683d28c77f8f68f49dea75f0a4da32557a58f68ee51ebba472d29"
dependencies = [
"memchr",
]
[[package]]
name = "zerocopy"
version = "0.7.32"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "74d4d3961e53fa4c9a25a8637fc2bfaf2595b3d3ae34875568a5cf64787716be"
dependencies = [
"zerocopy-derive",
]
[[package]]
name = "zerocopy-derive"
version = "0.7.32"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9ce1b18ccd8e73a9321186f97e46f9f04b778851177567b1975109d26a08d2a6"
dependencies = [
"proc-macro2",
"quote",
"syn",
]

15
Cargo.toml Normal file
View file

@ -0,0 +1,15 @@
[package]
name = "hoard"
version = "0.1.0"
edition = "2021"
# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
[dependencies]
chrono = "0.4.35"
env_logger = "0.11.3"
log = "0.4.21"
rusqlite = "0.30.0"
serde = { version = "1.0.196", features = ["derive"] }
serde_json = "1.0.113"
toml = "0.8.10"

8
README.md Normal file
View file

@ -0,0 +1,8 @@
# Hoard
This project aims to provide a simple and automated way of hoarding lots of data.
It provides a daemon which can be configured via a config file and download content from multiple sources.
It should automatically download new content as soon as it becomes available but not download content twice.
It will dump everything it finds into a directory from which you can organize the content in any way you see fit.
## Supported Sources
- YouTube

15
config.toml Normal file
View file

@ -0,0 +1,15 @@
[hoard]
# Data Download Directory
data_dir = "./download"
[youtube]
# Interval in minutes for checking
interval = 2
# Format of the thumbnail image
thumbnail_format = "jpg"
# Output Template
output_format = "%(title)s [%(id)s].%(ext)s"
[youtube.channels]
# Channel Mappings
MentalOutlaw = "https://www.youtube.com/@MentalOutlaw"

17
src/config.rs Normal file
View file

@ -0,0 +1,17 @@
use std::path::PathBuf;
use serde::{Deserialize, Serialize};
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct HoardConfig {
// Top level data download directory
pub data_dir: PathBuf,
}
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct GlobalConfig {
// Hoard Configuration
pub hoard: HoardConfig,
// Configuration for the YouTube Module
pub youtube: Option<crate::youtube::YouTubeConfig>,
}

45
src/db.rs Normal file
View file

@ -0,0 +1,45 @@
use rusqlite::Connection;
use std::error::Error;
// todo : make db singleton
#[derive(Debug, Clone)]
pub struct Database {
file: String,
}
impl Database {
pub fn new(file: &str) -> Self {
let conn = Connection::open(file).unwrap();
conn.execute(
"CREATE TABLE IF NOT EXISTS urls (
id INTEGER PRIMARY KEY,
url TEXT NOT NULL,
timestamp TEXT NOT NULL
)",
[],
)
.unwrap();
Self {
file: file.to_string(),
}
}
pub fn insert_url(&self, url: &str) -> Result<(), Box<dyn Error>> {
let conn = Connection::open(&self.file)?;
let timestamp = chrono::Local::now().to_rfc3339();
conn.execute(
"INSERT INTO urls (url, timestamp) VALUES (?, ?)",
[url, &timestamp],
)?;
Ok(())
}
pub fn check_for_url(&self, url: &str) -> Result<bool, Box<dyn Error>> {
let conn = Connection::open(&self.file)?;
let mut stmt = conn.prepare("SELECT COUNT(*) FROM urls WHERE url = ?")?;
let count: i64 = stmt.query_row([url], |row| row.get(0))?;
Ok(count > 0)
}
}

65
src/main.rs Normal file
View file

@ -0,0 +1,65 @@
use std::path::PathBuf;
mod config;
mod db;
mod youtube;
use config::GlobalConfig;
// todo : migrate to async code?
pub fn ensure_dir_exists(dir_path: &PathBuf) {
let path = std::path::Path::new(dir_path);
if !path.exists() {
std::fs::create_dir_all(path).unwrap();
}
}
trait Module: Send {
fn name(&self) -> String;
fn run(&self);
}
fn main() {
#[cfg(debug_assertions)]
{
std::env::set_var("RUST_LOG", "trace");
std::env::set_var("RUST_BACKTRACE", "1");
}
#[cfg(not(debug_assertions))]
{
if std::env::var("RUST_LOG").is_err() {
std::env::set_var("RUST_LOG", "warn");
}
}
env_logger::init();
log::info!("Starting hoard");
let db = db::Database::new("download.db");
let config: GlobalConfig =
toml::from_str(&std::fs::read_to_string("config.toml").unwrap()).unwrap();
ensure_dir_exists(&config.hoard.data_dir);
let modules: Vec<Box<dyn Module>> = vec![Box::new(youtube::YouTubeModule::new(
config.youtube.unwrap(),
db,
config.hoard.data_dir.join("youtube"),
))];
let threads: Vec<_> = modules
.into_iter()
.map(|x| {
std::thread::spawn(move || {
x.run();
})
})
.collect();
for t in threads {
// todo : fix dying threads
t.join().unwrap();
}
}

151
src/youtube/mod.rs Normal file
View file

@ -0,0 +1,151 @@
use std::{
collections::HashMap,
io::{BufRead, BufReader},
path::PathBuf,
process::Command,
};
use serde::{Deserialize, Serialize};
use crate::{ensure_dir_exists, Module};
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct YouTubeConfig {
// Interval in minutes between checks
interval: u64,
// Channels to check
channels: HashMap<String, String>,
// Format of the Thumbnail
thumbnail_format: Option<String>,
// Output Template for yt-dlp
output_format: Option<String>,
}
impl YouTubeConfig {
pub fn download_options(&self) -> DownloadOptions {
DownloadOptions {
thumbnail_format: self.thumbnail_format.clone(),
output_format: self.output_format.clone(),
}
}
}
#[derive(Clone, Debug)]
pub struct YouTubeModule {
config: YouTubeConfig,
db: crate::db::Database,
root_dir: PathBuf,
}
impl YouTubeModule {
pub const fn new(config: YouTubeConfig, db: crate::db::Database, root_dir: PathBuf) -> Self {
Self {
config,
db,
root_dir,
}
}
}
impl Module for YouTubeModule {
fn name(&self) -> String {
"YouTube".to_string()
}
fn run(&self) {
log::info!("Running YouTube Module");
let download_options = self.config.download_options();
for (channel, channel_url) in &self.config.channels {
log::info!("Fetching {channel} videos");
match Self::get_latest_channel_videos(channel_url) {
Ok(latest_videos) => {
for (video_title, video_url) in latest_videos {
if self.db.check_for_url(&video_url).unwrap() {
log::trace!("Skipping {video_title} because it was already downloaded");
} else {
match Self::download_video(
&video_url,
&self.root_dir.join(channel),
&download_options,
) {
Ok(()) => {
// mark as downloaded
self.db.insert_url(&video_url).unwrap();
log::info!("Downloaded {video_title}");
}
Err(e) => {
log::error!("Error downloading {video_title}; Reason: {e}");
// todo : error handling
}
}
}
}
}
Err(e) => {
log::error!("Could not get videos from {channel}. Reason: {e}");
}
}
}
std::thread::sleep(std::time::Duration::from_secs(self.config.interval * 60));
}
}
impl YouTubeModule {
fn get_latest_channel_videos(channel: &str) -> Result<Vec<(String, String)>, String> {
let output = Command::new("yt-dlp")
.arg("--no-warnings")
.arg("--flat-playlist")
.arg("--skip-download")
.arg("--print")
.arg("title,webpage_url")
.arg("--playlist-end")
.arg("10")
.arg(channel)
.output()
.expect("Failed to execute yt-dlp");
if !output.status.success() {
return Err(String::from_utf8(output.stderr).unwrap());
}
let reader = BufReader::new(&output.stdout[..]);
let mut videos = Vec::new();
let mut lines = reader.lines();
while let (Some(title), Some(url)) = (lines.next(), lines.next()) {
if let (Ok(title), Ok(url)) = (title, url) {
videos.push((title, url));
}
}
Ok(videos)
}
fn download_video(video_url: &str, cwd: &PathBuf, opt: &DownloadOptions) -> Result<(), String> {
ensure_dir_exists(cwd);
let output = Command::new("yt-dlp")
.current_dir(cwd)
.arg("--write-thumbnail")
.arg("-o")
.arg(opt.output_format.as_deref().unwrap_or("%(title)s.%(ext)s"))
.arg("--embed-thumbnail")
.arg("--embed-chapters")
.arg("--embed-info-json")
.arg("--convert-thumbnails")
.arg(opt.thumbnail_format.as_deref().unwrap_or("jpg"))
.arg(video_url)
.output()
.map_err(|_| "yt-dlp command failed".to_string())?;
if !output.status.success() {
let error_message = String::from_utf8_lossy(&output.stderr).to_string();
return Err(error_message);
}
Ok(())
}
}
pub struct DownloadOptions {
thumbnail_format: Option<String>,
output_format: Option<String>,
}