feat(yt_dlp): Support a DeArrow post processor

5 files changed, 604 insertions, 11 deletions

diff --git a/Cargo.lock b/Cargo.lock
index 4479cf9..aa9de48 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -159,6 +159,12 @@ dependencies = [
 ]
 
 [[package]]
+name = "atomic-waker"
+version = "1.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1505bd5d3d116872e7271a6d4e16d81d0c8570876c8de68093a09ac269d8aac0"
+
+[[package]]
 name = "autocfg"
 version = "1.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -728,6 +734,15 @@ dependencies = [
 ]
 
 [[package]]
+name = "encoding_rs"
+version = "0.8.35"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "75030f3c4f45dafd7586dd6780965a8c7e8e285a5ecb86713e63a79c5b2766f3"
+dependencies = [
+ "cfg-if",
+]
+
+[[package]]
 name = "endian-type"
 version = "0.1.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -864,6 +879,12 @@ dependencies = [
 ]
 
 [[package]]
+name = "fnv"
+version = "1.0.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1"
+
+[[package]]
 name = "foldhash"
 version = "0.1.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -1058,6 +1079,25 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a8d1add55171497b4705a648c6b583acafb01d58050a51727785f0b2c8e0a2b2"
 
 [[package]]
+name = "h2"
+version = "0.4.10"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a9421a676d1b147b16b82c9225157dc629087ef8ec4d5e2960f9437a90dac0a5"
+dependencies = [
+ "atomic-waker",
+ "bytes 1.10.1",
+ "fnv",
+ "futures-core",
+ "futures-sink",
+ "http",
+ "indexmap",
+ "slab",
+ "tokio",
+ "tokio-util",
+ "tracing",
+]
+
+[[package]]
 name = "half"
 version = "2.6.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -1139,6 +1179,124 @@ dependencies = [
 ]
 
 [[package]]
+name = "http"
+version = "1.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f4a85d31aea989eead29a3aaf9e1115a180df8282431156e533de47660892565"
+dependencies = [
+ "bytes 1.10.1",
+ "fnv",
+ "itoa",
+]
+
+[[package]]
+name = "http-body"
+version = "1.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1efedce1fb8e6913f23e0c92de8e62cd5b772a67e7b3946df930a62566c93184"
+dependencies = [
+ "bytes 1.10.1",
+ "http",
+]
+
+[[package]]
+name = "http-body-util"
+version = "0.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b021d93e26becf5dc7e1b75b1bed1fd93124b374ceb73f43d4d4eafec896a64a"
+dependencies = [
+ "bytes 1.10.1",
+ "futures-core",
+ "http",
+ "http-body",
+ "pin-project-lite",
+]
+
+[[package]]
+name = "httparse"
+version = "1.10.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6dbf3de79e51f3d586ab4cb9d5c3e2c14aa28ed23d180cf89b4df0454a69cc87"
+
+[[package]]
+name = "hyper"
+version = "1.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cc2b571658e38e0c01b1fdca3bbbe93c00d3d71693ff2770043f8c29bc7d6f80"
+dependencies = [
+ "bytes 1.10.1",
+ "futures-channel",
+ "futures-util",
+ "h2",
+ "http",
+ "http-body",
+ "httparse",
+ "itoa",
+ "pin-project-lite",
+ "smallvec",
+ "tokio",
+ "want",
+]
+
+[[package]]
+name = "hyper-rustls"
+version = "0.27.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e3c93eb611681b207e1fe55d5a71ecf91572ec8a6705cdb6857f7d8d5242cf58"
+dependencies = [
+ "http",
+ "hyper",
+ "hyper-util",
+ "rustls",
+ "rustls-pki-types",
+ "tokio",
+ "tokio-rustls",
+ "tower-service",
+]
+
+[[package]]
+name = "hyper-tls"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "70206fc6890eaca9fde8a0bf71caa2ddfc9fe045ac9e5c70df101a7dbde866e0"
+dependencies = [
+ "bytes 1.10.1",
+ "http-body-util",
+ "hyper",
+ "hyper-util",
+ "native-tls",
+ "tokio",
+ "tokio-native-tls",
+ "tower-service",
+]
+
+[[package]]
+name = "hyper-util"
+version = "0.1.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dc2fdfdbff08affe55bb779f33b053aa1fe5dd5b54c257343c17edfa55711bdb"
+dependencies = [
+ "base64",
+ "bytes 1.10.1",
+ "futures-channel",
+ "futures-core",
+ "futures-util",
+ "http",
+ "http-body",
+ "hyper",
+ "ipnet",
+ "libc",
+ "percent-encoding",
+ "pin-project-lite",
+ "socket2",
+ "system-configuration",
+ "tokio",
+ "tower-service",
+ "tracing",
+ "windows-registry",
+]
+
+[[package]]
 name = "iana-time-zone"
 version = "0.1.63"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -1300,6 +1458,22 @@ dependencies = [
 ]
 
 [[package]]
+name = "ipnet"
+version = "2.11.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "469fb0b9cefa57e3ef31275ee7cacb78f2fdca44e4765491884a2b119d4eb130"
+
+[[package]]
+name = "iri-string"
+version = "0.7.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dbc5ebe9c3a1a7a5127f920a418f7585e9e758e911d0466ed004f393b0e380b2"
+dependencies = [
+ "memchr",
+ "serde",
+]
+
+[[package]]
 name = "is-macro"
 version = "0.3.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -1727,6 +1901,12 @@ dependencies = [
 ]
 
 [[package]]
+name = "mime"
+version = "0.3.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6877bb514081ee2a7ff5ef9de3281f14a4dd4bceac4c09388074a6b5df8a139a"
+
+[[package]]
 name = "minimal-lexical"
 version = "0.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -1763,6 +1943,23 @@ dependencies = [
 ]
 
 [[package]]
+name = "native-tls"
+version = "0.2.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "87de3442987e9dbec73158d5c715e7ad9072fda936bb03d19d7fa10e00520f0e"
+dependencies = [
+ "libc",
+ "log",
+ "openssl",
+ "openssl-probe",
+ "openssl-sys",
+ "schannel",
+ "security-framework",
+ "security-framework-sys",
+ "tempfile",
+]
+
+[[package]]
 name = "nibble_vec"
 version = "0.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -2313,6 +2510,48 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2b15c43186be67a4fd63bee50d0303afffcef381492ebe2c5d87f324e1b8815c"
 
 [[package]]
+name = "reqwest"
+version = "0.12.20"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "eabf4c97d9130e2bf606614eb937e86edac8292eaa6f422f995d7e8de1eb1813"
+dependencies = [
+ "base64",
+ "bytes 1.10.1",
+ "encoding_rs",
+ "futures-channel",
+ "futures-core",
+ "futures-util",
+ "h2",
+ "http",
+ "http-body",
+ "http-body-util",
+ "hyper",
+ "hyper-rustls",
+ "hyper-tls",
+ "hyper-util",
+ "js-sys",
+ "log",
+ "mime",
+ "native-tls",
+ "percent-encoding",
+ "pin-project-lite",
+ "rustls-pki-types",
+ "serde",
+ "serde_json",
+ "serde_urlencoded",
+ "sync_wrapper",
+ "tokio",
+ "tokio-native-tls",
+ "tower",
+ "tower-http",
+ "tower-service",
+ "url",
+ "wasm-bindgen",
+ "wasm-bindgen-futures",
+ "web-sys",
+]
+
+[[package]]
 name = "result-like"
 version = "0.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -2334,6 +2573,20 @@ dependencies = [
 ]
 
 [[package]]
+name = "ring"
+version = "0.17.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a4689e6c2294d81e88dc6261c768b63bc4fcdb852be6d1352498b114f61383b7"
+dependencies = [
+ "cc",
+ "cfg-if",
+ "getrandom 0.2.16",
+ "libc",
+ "untrusted",
+ "windows-sys 0.52.0",
+]
+
+[[package]]
 name = "rsa"
 version = "0.9.8"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -2440,6 +2693,39 @@ dependencies = [
 ]
 
 [[package]]
+name = "rustls"
+version = "0.23.27"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "730944ca083c1c233a75c09f199e973ca499344a2b7ba9e755c457e86fb4a321"
+dependencies = [
+ "once_cell",
+ "rustls-pki-types",
+ "rustls-webpki",
+ "subtle",
+ "zeroize",
+]
+
+[[package]]
+name = "rustls-pki-types"
+version = "1.12.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "229a4a4c221013e7e1f1a043678c5cc39fe5171437c88fb47151a21e6f5b5c79"
+dependencies = [
+ "zeroize",
+]
+
+[[package]]
+name = "rustls-webpki"
+version = "0.103.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e4a72fe2bcf7a6ac6fd7d0b9e5cb68aeb7d4c0a0271730218b3e92d43b4eb435"
+dependencies = [
+ "ring",
+ "rustls-pki-types",
+ "untrusted",
+]
+
+[[package]]
 name = "rustpython"
 version = "0.4.0"
 source = "git+https://github.com/RustPython/RustPython.git#c968fe0fd9d7466dc9d5d97e973b82ba35e516d8"
@@ -2869,6 +3155,29 @@ dependencies = [
 ]
 
 [[package]]
+name = "security-framework"
+version = "2.11.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "897b2245f0b511c87893af39b033e5ca9cce68824c4d7e7630b5a1d339658d02"
+dependencies = [
+ "bitflags 2.9.1",
+ "core-foundation",
+ "core-foundation-sys",
+ "libc",
+ "security-framework-sys",
+]
+
+[[package]]
+name = "security-framework-sys"
+version = "2.14.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "49db231d56a190491cb4aeda9527f1ad45345af50b0851622a7adb8c03b01c32"
+dependencies = [
+ "core-foundation-sys",
+ "libc",
+]
+
+[[package]]
 name = "serde"
 version = "1.0.219"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -3317,6 +3626,15 @@ dependencies = [
 ]
 
 [[package]]
+name = "sync_wrapper"
+version = "1.0.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0bf256ce5efdfa370213c1dabab5935a12e49f2c58d15e9eac2870d3b4f27263"
+dependencies = [
+ "futures-core",
+]
+
+[[package]]
 name = "synstructure"
 version = "0.13.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -3502,6 +3820,26 @@ dependencies = [
 ]
 
 [[package]]
+name = "tokio-native-tls"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bbae76ab933c85776efabc971569dd6119c580d8f5d448769dec1764bf796ef2"
+dependencies = [
+ "native-tls",
+ "tokio",
+]
+
+[[package]]
+name = "tokio-rustls"
+version = "0.26.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8e727b36a1a0e8b74c376ac2211e40c2c8af09fb4013c60d910495810f008e9b"
+dependencies = [
+ "rustls",
+ "tokio",
+]
+
+[[package]]
 name = "tokio-stream"
 version = "0.1.17"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -3569,6 +3907,51 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5d99f8c9a7727884afe522e9bd5edbfc91a3312b36a77b5fb8926e4c31a41801"
 
 [[package]]
+name = "tower"
+version = "0.5.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d039ad9159c98b70ecfd540b2573b97f7f52c3e8d9f8ad57a24b916a536975f9"
+dependencies = [
+ "futures-core",
+ "futures-util",
+ "pin-project-lite",
+ "sync_wrapper",
+ "tokio",
+ "tower-layer",
+ "tower-service",
+]
+
+[[package]]
+name = "tower-http"
+version = "0.6.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "adc82fd73de2a9722ac5da747f12383d2bfdb93591ee6c58486e0097890f05f2"
+dependencies = [
+ "bitflags 2.9.1",
+ "bytes 1.10.1",
+ "futures-util",
+ "http",
+ "http-body",
+ "iri-string",
+ "pin-project-lite",
+ "tower",
+ "tower-layer",
+ "tower-service",
+]
+
+[[package]]
+name = "tower-layer"
+version = "0.3.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "121c2a6cda46980bb0fcd1647ffaf6cd3fc79a013de288782836f6df9c48780e"
+
+[[package]]
+name = "tower-service"
+version = "0.3.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8df9b6e13f2d32c91b9bd719c00d1958837bc7dec474d94952798cc8e69eeec3"
+
+[[package]]
 name = "tracing"
 version = "0.1.41"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -3601,6 +3984,12 @@ dependencies = [
 ]
 
 [[package]]
+name = "try-lock"
+version = "0.2.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e421abadd41a4225275504ea4d6566923418b7f05506fbc9c0fe86ba7396114b"
+
+[[package]]
 name = "twox-hash"
 version = "2.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -3800,6 +4189,12 @@ dependencies = [
 ]
 
 [[package]]
+name = "untrusted"
+version = "0.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8ecb6da28b8a351d773b68d5825ac39017e680750f980f3a1a85cd8dd28a47c1"
+
+[[package]]
 name = "url"
 version = "2.5.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -3870,6 +4265,15 @@ dependencies = [
 ]
 
 [[package]]
+name = "want"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bfa7760aed19e106de2c7c0b581b509f2f25d3dacaf737cb82ac61bc6d760b0e"
+dependencies = [
+ "try-lock",
+]
+
+[[package]]
 name = "wasi"
 version = "0.11.1+wasi-snapshot-preview1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -3917,6 +4321,19 @@ dependencies = [
 ]
 
 [[package]]
+name = "wasm-bindgen-futures"
+version = "0.4.50"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "555d470ec0bc3bb57890405e5d4322cc9ea83cebb085523ced7be4144dac1e61"
+dependencies = [
+ "cfg-if",
+ "js-sys",
+ "once_cell",
+ "wasm-bindgen",
+ "web-sys",
+]
+
+[[package]]
 name = "wasm-bindgen-macro"
 version = "0.2.100"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -3949,6 +4366,16 @@ dependencies = [
 ]
 
 [[package]]
+name = "web-sys"
+version = "0.3.77"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "33b6dd2ef9186f1f2072e409e99cd22a975331a6b3591b12c764e0e55c60d5d2"
+dependencies = [
+ "js-sys",
+ "wasm-bindgen",
+]
+
+[[package]]
 name = "which"
 version = "7.0.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -4078,6 +4505,17 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5e6ad25900d524eaabdbbb96d20b4311e1e7ae1699af4fb28c17ae66c80d798a"
 
 [[package]]
+name = "windows-registry"
+version = "0.5.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b3bab093bdd303a1240bb99b8aba8ea8a69ee19d34c9e2ef9594e708a4878820"
+dependencies = [
+ "windows-link",
+ "windows-result",
+ "windows-strings",
+]
+
+[[package]]
 name = "windows-result"
 version = "0.3.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
@@ -4431,7 +4869,9 @@ version = "1.5.0"
 dependencies = [
  "indexmap",
  "log",
+ "reqwest",
  "rustpython",
+ "serde",
  "serde_json",
  "thiserror 2.0.12",
  "url",
diff --git a/crates/yt_dlp/Cargo.toml b/crates/yt_dlp/Cargo.toml
index 90f2e10..e5d14fd 100644
--- a/crates/yt_dlp/Cargo.toml
+++ b/crates/yt_dlp/Cargo.toml
@@ -24,7 +24,9 @@ publish = true
 [dependencies]
 indexmap = { version = "2.9.0", default-features = false }
 log.workspace = true
+reqwest = { version = "0.12.20", features = ["blocking", "json"] }
 rustpython = { git = "https://github.com/RustPython/RustPython.git", features = ["threading", "stdlib", "stdio", "importlib", "ssl"], default-features = false }
+serde = { workspace = true, features = ["derive"] }
 serde_json.workspace = true
 thiserror = "2.0.12"
 url.workspace = true
diff --git a/crates/yt_dlp/src/lib.rs b/crates/yt_dlp/src/lib.rs
index 0f40f0a..16ec4ca 100644
--- a/crates/yt_dlp/src/lib.rs
+++ b/crates/yt_dlp/src/lib.rs
@@ -1,10 +1,11 @@
 //! The `yt_dlp` interface is completely contained in the [`YoutubeDL`] structure.
 
-use std::{self, env, mem, path::PathBuf};
+use std::{self, env, fmt::Display, path::PathBuf};
 
 use indexmap::IndexMap;
 use log::{Level, debug, error, info, log_enabled};
 use logging::setup_logging;
+use post_processors::PostProcessor;
 use rustpython::{
     InterpreterConfig,
     vm::{
@@ -18,6 +19,7 @@ use rustpython::{
 use url::Url;
 
 mod logging;
+pub mod post_processors;
 pub mod progress_hook;
 
 #[macro_export]
@@ -61,6 +63,7 @@ pub struct YoutubeDL {
     youtube_dl_class: PyObjectRef,
     yt_dlp_module: PyObjectRef,
     options: serde_json::Map<String, serde_json::Value>,
+    post_processors: Vec<Box<dyn PostProcessor>>,
 }
 
 impl std::fmt::Debug for YoutubeDL {
@@ -209,6 +212,7 @@ impl YoutubeDL {
             youtube_dl_class,
             yt_dlp_module,
             options: output_options,
+            post_processors: options.post_processors,
         })
     }
 
@@ -399,9 +403,18 @@ impl YoutubeDL {
 
         let result = value.downcast::<PyDict>().expect("This should stay a dict");
 
-        let json = json_dumps(result, vm);
+        let mut json = json_dumps(result, vm);
 
-        {
+        for pp in &self.post_processors {
+            if pp
+                .extractors()
+                .iter()
+                .any(|extractor| *extractor == json_get!(json, "extractor_key", as_str))
+            {
+                json = pp.process(json)?;
+            } else {
+                error!("Extractor not found for {pp:#?}");
+            }
         }
 
         Ok(json)
@@ -458,6 +471,9 @@ pub mod prepare {
     pub enum Error {
         #[error(transparent)]
         Python(#[from] PythonError),
+
+        #[error("Failed to run a post processor")]
+        PostProcessorRun(#[from] post_processors::Error),
     }
 }
 
@@ -473,15 +489,19 @@ pub type ProgressHookFunction = fn(input: FuncArgs, vm: &VirtualMachine);
 pub struct YoutubeDLOptions {
     options: serde_json::Map<String, serde_json::Value>,
     progress_hook: Option<ProgressHookFunction>,
+    post_processors: Vec<Box<dyn PostProcessor>>,
 }
 
 impl YoutubeDLOptions {
     #[must_use]
     pub fn new() -> Self {
-        Self {
+        let me = Self {
             options: serde_json::Map::new(),
             progress_hook: None,
-        }
+            post_processors: vec![],
+        };
+
+        me.with_post_processor(post_processors::dearrow::DeArrowPP)
     }
 
     #[must_use]
@@ -489,10 +509,7 @@ impl YoutubeDLOptions {
         let mut options = self.options;
         options.insert(key.into(), value.into());
 
-        Self {
-            options,
-            progress_hook: self.progress_hook,
-        }
+        Self { options, ..self }
     }
 
     #[must_use]
@@ -501,12 +518,18 @@ impl YoutubeDLOptions {
             todo!()
         } else {
             Self {
-                options: self.options,
                 progress_hook: Some(progress_hook),
+                ..self
             }
         }
     }
 
+    #[must_use]
+    pub fn with_post_processor<P: PostProcessor + 'static>(mut self, post_processor: P) -> Self {
+        self.post_processors.push(Box::new(post_processor));
+        self
+    }
+
     /// # Errors
     /// If the underlying [`YoutubeDL::from_options`] errors.
     pub fn build(self) -> Result<YoutubeDL, build::Error> {
@@ -517,7 +540,7 @@ impl YoutubeDLOptions {
     pub fn from_json_options(options: serde_json::Map<String, serde_json::Value>) -> Self {
         Self {
             options,
-            progress_hook: None,
+            ..Self::new()
         }
     }
 
diff --git a/crates/yt_dlp/src/post_processors/dearrow.rs b/crates/yt_dlp/src/post_processors/dearrow.rs
new file mode 100644
index 0000000..110beeb
--- /dev/null
+++ b/crates/yt_dlp/src/post_processors/dearrow.rs
@@ -0,0 +1,108 @@
+use log::{info, warn};
+use serde::{Deserialize, Serialize};
+
+use crate::{InfoJson, json_get};
+
+use super::PostProcessor;
+
+#[derive(Debug, Clone, Copy)]
+pub struct DeArrowPP;
+
+impl PostProcessor for DeArrowPP {
+    fn extractors(&self) -> &'static [&'static str] {
+        &["Youtube"]
+    }
+
+    fn process(&self, mut info: InfoJson) -> Result<InfoJson, super::Error> {
+        let mut output: DeArrowApi = reqwest::blocking::get(format!(
+            "https://sponsor.ajay.app/api/branding?videoID={}",
+            json_get!(info, "id", as_str)
+        ))?
+        .json()?;
+
+        output.titles.reverse();
+
+        let title_len = output.titles.len();
+        loop {
+            let Some(title) = output.titles.pop() else {
+                break;
+            };
+
+            if (title.locked || title.votes < 1) && title_len > 1 {
+                info!(
+                    "Skipping title {:#?}, as it is not good enough",
+                    title.value
+                );
+                // Skip titles that are not “good” enough.
+                continue;
+            }
+
+            if let Some(old_title) = info.insert(
+                "title".to_owned(),
+                serde_json::Value::String(title.value.clone()),
+            ) {
+                warn!("Updating title from {:#?} to {:#?}", old_title, title.value);
+                info.insert("original_title".to_owned(), old_title);
+            } else {
+                warn!("Setting title to {:#?}", title.value);
+            }
+
+            break;
+        }
+
+        Ok(info)
+    }
+}
+
+#[derive(Serialize, Deserialize)]
+/// See: <https://wiki.sponsor.ajay.app/w/API_Docs/DeArrow>
+struct DeArrowApi {
+    titles: Vec<Title>,
+    thumbnails: Vec<Thumbnail>,
+
+    #[serde(alias = "randomTime")]
+    random_time: Option<f64>,
+
+    #[serde(alias = "videoDuration")]
+    video_duration: Option<f64>,
+
+    #[serde(alias = "casualVotes")]
+    casual_votes: Vec<String>,
+}
+
+#[derive(Serialize, Deserialize)]
+struct Title {
+    /// Note: Titles will sometimes contain > before a word.
+    /// This tells the auto-formatter to not format a word.
+    /// If you have no auto-formatter, you can ignore this and replace it with an empty string
+    #[serde(alias = "title")]
+    value: String,
+
+    original: bool,
+    votes: u64,
+    locked: bool,
+
+    #[serde(alias = "UUID")]
+    uuid: String,
+
+    /// only present if requested
+    #[serde(alias = "userID")]
+    user_id: Option<String>,
+}
+
+#[derive(Serialize, Deserialize)]
+struct Thumbnail {
+    // null if original is true
+    timestamp: Option<f64>,
+
+    original: bool,
+    votes: u64,
+    locked: bool,
+
+    #[serde(alias = "UUID")]
+    uuid: String,
+
+    /// only present if requested
+    #[serde(alias = "userID")]
+    user_id: Option<String>,
+}
diff --git a/crates/yt_dlp/src/post_processors/mod.rs b/crates/yt_dlp/src/post_processors/mod.rs
new file mode 100644
index 0000000..6067c7a
--- /dev/null
+++ b/crates/yt_dlp/src/post_processors/mod.rs
@@ -0,0 +1,20 @@
+use crate::InfoJson;
+
+pub mod dearrow;
+
+pub trait PostProcessor: std::fmt::Debug + Send {
+    /// Process a [`InfoJson`] object and return the updated one.
+    ///
+    /// # Errors
+    /// If the processing steps failed.
+    fn process(&self, info: InfoJson) -> Result<InfoJson, Error>;
+
+    /// The supported extractors for this post processor
+    fn extractors(&self) -> &'static [&'static str];
+}
+
+#[derive(thiserror::Error, Debug)]
+pub enum Error {
+    #[error("Failed to access a api: {0}")]
+    Get(#[from] reqwest::Error),
+}