Compare commits
2 commits
4cc069fba2
...
f7fbf40721
| Author | SHA1 | Date | |
|---|---|---|---|
| f7fbf40721 | |||
| 92a358a079 |
14 changed files with 253 additions and 126 deletions
|
|
@ -26,6 +26,7 @@ rustls-tls-native-roots = ["reqwest/rustls-tls-native-roots"]
|
|||
# quick-js = "0.4.1"
|
||||
quick-js = { path = "../quickjs-rs", default-features = false }
|
||||
once_cell = "1.12.0"
|
||||
regex = "1.6.0"
|
||||
fancy-regex = "0.11.0"
|
||||
thiserror = "1.0.36"
|
||||
url = "2.2.2"
|
||||
|
|
|
|||
|
|
@ -25,10 +25,10 @@ mod channel_rss;
|
|||
use std::sync::Arc;
|
||||
use std::{borrow::Cow, fmt::Debug};
|
||||
|
||||
use fancy_regex::Regex;
|
||||
use log::{debug, error, warn};
|
||||
use once_cell::sync::Lazy;
|
||||
use rand::Rng;
|
||||
use regex::Regex;
|
||||
use reqwest::{header, Client, ClientBuilder, Request, RequestBuilder, Response};
|
||||
use serde::{de::DeserializeOwned, Deserialize, Serialize};
|
||||
use time::{Duration, OffsetDateTime};
|
||||
|
|
|
|||
|
|
@ -1,8 +1,8 @@
|
|||
use std::{borrow::Cow, rc::Rc};
|
||||
|
||||
use fancy_regex::Regex;
|
||||
use futures::{stream, StreamExt};
|
||||
use once_cell::sync::Lazy;
|
||||
use regex::Regex;
|
||||
use serde::Serialize;
|
||||
|
||||
use crate::{
|
||||
|
|
@ -268,8 +268,6 @@ fn map_artist_page(
|
|||
let wikipedia_url = header.description.as_deref().and_then(|h| {
|
||||
WIKIPEDIA_REGEX
|
||||
.captures(h)
|
||||
.ok()
|
||||
.flatten()
|
||||
.and_then(|c| c.get(0))
|
||||
.map(|m| m.as_str().to_owned())
|
||||
});
|
||||
|
|
|
|||
|
|
@ -3,8 +3,8 @@ use std::{
|
|||
collections::{BTreeMap, HashMap},
|
||||
};
|
||||
|
||||
use fancy_regex::Regex;
|
||||
use once_cell::sync::Lazy;
|
||||
use regex::Regex;
|
||||
use serde::Serialize;
|
||||
use url::Url;
|
||||
|
||||
|
|
@ -530,8 +530,6 @@ fn map_audio_stream(
|
|||
Some(t) => {
|
||||
let lang = LANG_PATTERN
|
||||
.captures(&t.id)
|
||||
.ok()
|
||||
.flatten()
|
||||
.map(|m| m.get(1).unwrap().as_str().to_owned());
|
||||
|
||||
Some(AudioTrack {
|
||||
|
|
@ -557,7 +555,7 @@ fn parse_mime(mime: &str) -> Option<(&str, Vec<&str>)> {
|
|||
static PATTERN: Lazy<Regex> =
|
||||
Lazy::new(|| Regex::new(r#"(\w+/\w+);\scodecs="([a-zA-Z-0-9.,\s]*)""#).unwrap());
|
||||
|
||||
let captures = some_or_bail!(PATTERN.captures(mime).ok().flatten(), None);
|
||||
let captures = some_or_bail!(PATTERN.captures(mime), None);
|
||||
Some((
|
||||
captures.get(1).unwrap().as_str(),
|
||||
captures
|
||||
|
|
|
|||
|
|
@ -97,7 +97,7 @@ impl From<ChannelRss> for crate::model::ChannelRss {
|
|||
.uri
|
||||
.strip_prefix("https://www.youtube.com/channel/")
|
||||
.and_then(|id| {
|
||||
if util::CHANNEL_ID_REGEX.is_match(id).unwrap_or_default() {
|
||||
if util::CHANNEL_ID_REGEX.is_match(id) {
|
||||
Some(id.to_owned())
|
||||
} else {
|
||||
None
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
use fancy_regex::Regex;
|
||||
use once_cell::sync::Lazy;
|
||||
use regex::Regex;
|
||||
use serde::Deserialize;
|
||||
use serde_with::{
|
||||
json::JsonString, rust::deserialize_ignore_any, serde_as, DefaultOnError, VecSkipError,
|
||||
|
|
@ -503,17 +503,9 @@ impl<T> YouTubeListMapper<T> {
|
|||
id: video.video_id,
|
||||
name: video.headline,
|
||||
length: video.accessibility.and_then(|acc| {
|
||||
ACCESSIBILITY_SEP_REGEX
|
||||
.captures(&acc)
|
||||
.ok()
|
||||
.flatten()
|
||||
.and_then(|cap| {
|
||||
ACCESSIBILITY_SEP_REGEX.captures(&acc).and_then(|cap| {
|
||||
cap.get(1).and_then(|c| {
|
||||
timeago::parse_timeago_or_warn(
|
||||
self.lang,
|
||||
c.as_str(),
|
||||
&mut self.warnings,
|
||||
)
|
||||
timeago::parse_timeago_or_warn(self.lang, c.as_str(), &mut self.warnings)
|
||||
.map(|ta| Duration::from(ta).whole_seconds() as u32)
|
||||
})
|
||||
})
|
||||
|
|
|
|||
|
|
@ -112,9 +112,9 @@ impl RustyPipeQuery {
|
|||
// Album or channel
|
||||
Some("browse") => match path_split.next() {
|
||||
Some(id) => {
|
||||
if util::CHANNEL_ID_REGEX.is_match(id).unwrap_or_default() {
|
||||
if util::CHANNEL_ID_REGEX.is_match(id) {
|
||||
Ok(UrlTarget::Channel { id: id.to_owned() })
|
||||
} else if util::ALBUM_ID_REGEX.is_match(id).unwrap_or_default() {
|
||||
} else if util::ALBUM_ID_REGEX.is_match(id) {
|
||||
Ok(UrlTarget::Album { id: id.to_owned() })
|
||||
} else {
|
||||
Err(Error::Other("invalid url: no browse id".into()))
|
||||
|
|
@ -153,10 +153,7 @@ impl RustyPipeQuery {
|
|||
// If there is a timestamp parameter, it has to be a video
|
||||
// First check the innertube API if this is a channel vanity url
|
||||
// If no channel is found and the identifier has the video ID format, assume it is a video
|
||||
if !params.contains_key("t")
|
||||
&& util::VANITY_PATH_REGEX
|
||||
.is_match(url.path())
|
||||
.unwrap_or_default()
|
||||
if !params.contains_key("t") && util::VANITY_PATH_REGEX.is_match(url.path())
|
||||
{
|
||||
match self
|
||||
._navigation_resolve_url(url.path(), ClientType::Desktop)
|
||||
|
|
@ -164,7 +161,7 @@ impl RustyPipeQuery {
|
|||
{
|
||||
Ok(target) => Ok(target),
|
||||
Err(Error::Extraction(ExtractionError::ContentUnavailable(e))) => {
|
||||
match util::VIDEO_ID_REGEX.is_match(id).unwrap_or_default() {
|
||||
match util::VIDEO_ID_REGEX.is_match(id) {
|
||||
true => Ok(UrlTarget::Video {
|
||||
id: id.to_owned(),
|
||||
start_time: get_start_time(),
|
||||
|
|
@ -176,7 +173,7 @@ impl RustyPipeQuery {
|
|||
}
|
||||
Err(e) => Err(e),
|
||||
}
|
||||
} else if util::VIDEO_ID_REGEX.is_match(id).unwrap_or_default() {
|
||||
} else if util::VIDEO_ID_REGEX.is_match(id) {
|
||||
Ok(UrlTarget::Video {
|
||||
id: id.to_owned(),
|
||||
start_time: get_start_time(),
|
||||
|
|
@ -232,16 +229,16 @@ impl RustyPipeQuery {
|
|||
.await
|
||||
}
|
||||
// ID only
|
||||
else if util::VIDEO_ID_REGEX.is_match(string).unwrap_or_default() {
|
||||
else if util::VIDEO_ID_REGEX.is_match(string) {
|
||||
Ok(UrlTarget::Video {
|
||||
id: string.to_owned(),
|
||||
start_time: 0,
|
||||
})
|
||||
} else if util::CHANNEL_ID_REGEX.is_match(string).unwrap_or_default() {
|
||||
} else if util::CHANNEL_ID_REGEX.is_match(string) {
|
||||
Ok(UrlTarget::Channel {
|
||||
id: string.to_owned(),
|
||||
})
|
||||
} else if util::PLAYLIST_ID_REGEX.is_match(string).unwrap_or_default() {
|
||||
} else if util::PLAYLIST_ID_REGEX.is_match(string) {
|
||||
if resolve_albums && string.starts_with(util::PLAYLIST_ID_ALBUM_PREFIX) {
|
||||
self._navigation_resolve_url(
|
||||
&format!("/playlist?list={}", string),
|
||||
|
|
@ -253,13 +250,13 @@ impl RustyPipeQuery {
|
|||
id: string.to_owned(),
|
||||
})
|
||||
}
|
||||
} else if util::ALBUM_ID_REGEX.is_match(string).unwrap_or_default() {
|
||||
} else if util::ALBUM_ID_REGEX.is_match(string) {
|
||||
Ok(UrlTarget::Album {
|
||||
id: string.to_owned(),
|
||||
})
|
||||
}
|
||||
// Channel name only
|
||||
else if util::VANITY_PATH_REGEX.is_match(string).unwrap_or_default() {
|
||||
else if util::VANITY_PATH_REGEX.is_match(string) {
|
||||
self._navigation_resolve_url(
|
||||
&format!("/{}", string.trim_start_matches('/')),
|
||||
ClientType::Desktop,
|
||||
|
|
|
|||
|
|
@ -1,6 +1,7 @@
|
|||
use fancy_regex::Regex;
|
||||
use fancy_regex::Regex as FancyRegex;
|
||||
use log::debug;
|
||||
use once_cell::sync::Lazy;
|
||||
use regex::Regex;
|
||||
use reqwest::Client;
|
||||
use serde::{Deserialize, Serialize};
|
||||
use std::result::Result::Ok;
|
||||
|
|
@ -68,18 +69,18 @@ impl From<DeobfData> for Deobfuscator {
|
|||
const DEOBFUSCATION_FUNC_NAME: &str = "deobfuscate";
|
||||
|
||||
fn get_sig_fn_name(player_js: &str) -> Result<String> {
|
||||
static FUNCTION_REGEXES: Lazy<[Regex; 6]> = Lazy::new(|| {
|
||||
static FUNCTION_REGEXES: Lazy<[FancyRegex; 6]> = Lazy::new(|| {
|
||||
[
|
||||
Regex::new("(?:\\b|[^a-zA-Z0-9$])([a-zA-Z0-9$]{2,})\\s*=\\s*function\\(\\s*a\\s*\\)\\s*\\{\\s*a\\s*=\\s*a\\.split\\(\\s*\"\"\\s*\\)").unwrap(),
|
||||
Regex::new("\\bm=([a-zA-Z0-9$]{2,})\\(decodeURIComponent\\(h\\.s\\)\\)").unwrap(),
|
||||
Regex::new("\\bc&&\\(c=([a-zA-Z0-9$]{2,})\\(decodeURIComponent\\(c\\)\\)").unwrap(),
|
||||
Regex::new("([\\w$]+)\\s*=\\s*function\\((\\w+)\\)\\{\\s*\\2=\\s*\\2\\.split\\(\"\"\\)\\s*;").unwrap(),
|
||||
Regex::new("\\b([\\w$]{2,})\\s*=\\s*function\\((\\w+)\\)\\{\\s*\\2=\\s*\\2\\.split\\(\"\"\\)\\s*;").unwrap(),
|
||||
Regex::new("\\bc\\s*&&\\s*d\\.set\\([^,]+\\s*,\\s*(:encodeURIComponent\\s*\\()([a-zA-Z0-9$]+)\\(").unwrap(),
|
||||
FancyRegex::new("(?:\\b|[^a-zA-Z0-9$])([a-zA-Z0-9$]{2,})\\s*=\\s*function\\(\\s*a\\s*\\)\\s*\\{\\s*a\\s*=\\s*a\\.split\\(\\s*\"\"\\s*\\)").unwrap(),
|
||||
FancyRegex::new("\\bm=([a-zA-Z0-9$]{2,})\\(decodeURIComponent\\(h\\.s\\)\\)").unwrap(),
|
||||
FancyRegex::new("\\bc&&\\(c=([a-zA-Z0-9$]{2,})\\(decodeURIComponent\\(c\\)\\)").unwrap(),
|
||||
FancyRegex::new("([\\w$]+)\\s*=\\s*function\\((\\w+)\\)\\{\\s*\\2=\\s*\\2\\.split\\(\"\"\\)\\s*;").unwrap(),
|
||||
FancyRegex::new("\\b([\\w$]{2,})\\s*=\\s*function\\((\\w+)\\)\\{\\s*\\2=\\s*\\2\\.split\\(\"\"\\)\\s*;").unwrap(),
|
||||
FancyRegex::new("\\bc\\s*&&\\s*d\\.set\\([^,]+\\s*,\\s*(:encodeURIComponent\\s*\\()([a-zA-Z0-9$]+)\\(").unwrap(),
|
||||
]
|
||||
});
|
||||
|
||||
util::get_cg_from_regexes(FUNCTION_REGEXES.iter(), player_js, 1)
|
||||
util::get_cg_from_fancy_regexes(FUNCTION_REGEXES.iter(), player_js, 1)
|
||||
.ok_or(DeobfError::Extraction("deobf function name"))
|
||||
}
|
||||
|
||||
|
|
@ -98,8 +99,6 @@ fn get_sig_fn(player_js: &str) -> Result<String> {
|
|||
let deobfuscate_function = "var ".to_owned()
|
||||
+ function_pattern
|
||||
.captures(player_js)
|
||||
.ok()
|
||||
.flatten()
|
||||
.ok_or(DeobfError::Extraction("deobf function"))?
|
||||
.get(1)
|
||||
.unwrap()
|
||||
|
|
@ -110,8 +109,6 @@ fn get_sig_fn(player_js: &str) -> Result<String> {
|
|||
Lazy::new(|| Regex::new(";([A-Za-z0-9_\\$]{2})\\...\\(").unwrap());
|
||||
let helper_object_name = HELPER_OBJECT_NAME_REGEX
|
||||
.captures(&deobfuscate_function)
|
||||
.ok()
|
||||
.flatten()
|
||||
.ok_or(DeobfError::Extraction("helper object name"))?
|
||||
.get(1)
|
||||
.unwrap()
|
||||
|
|
@ -124,8 +121,6 @@ fn get_sig_fn(player_js: &str) -> Result<String> {
|
|||
let player_js_nonl = player_js.replace('\n', "");
|
||||
let helper_object = helper_pattern
|
||||
.captures(&player_js_nonl)
|
||||
.ok()
|
||||
.flatten()
|
||||
.ok_or(DeobfError::Extraction("helper object"))?
|
||||
.get(1)
|
||||
.unwrap()
|
||||
|
|
@ -154,8 +149,6 @@ fn get_nsig_fn_name(player_js: &str) -> Result<String> {
|
|||
|
||||
let fname_match = FUNCTION_NAME_REGEX
|
||||
.captures(player_js)
|
||||
.ok()
|
||||
.flatten()
|
||||
.ok_or(DeobfError::Extraction("n_deobf function"))?;
|
||||
|
||||
let function_name = fname_match.get(1).unwrap().as_str();
|
||||
|
|
@ -171,15 +164,13 @@ fn get_nsig_fn_name(player_js: &str) -> Result<String> {
|
|||
.parse::<usize>()
|
||||
.or(Err(DeobfError::Other("could not parse array_num")))?;
|
||||
let array_pattern_str =
|
||||
"var ".to_owned() + &fancy_regex::escape(function_name) + "\\s*=\\s*\\[(.+?)];";
|
||||
"var ".to_owned() + ®ex::escape(function_name) + "\\s*=\\s*\\[(.+?)];";
|
||||
let array_pattern = Regex::new(&array_pattern_str).or(Err(DeobfError::Other(
|
||||
"could not parse helper pattern regex",
|
||||
)))?;
|
||||
|
||||
let array_str = array_pattern
|
||||
.captures(player_js)
|
||||
.ok()
|
||||
.flatten()
|
||||
.ok_or(DeobfError::Extraction("n_deobf array_str"))?
|
||||
.get(1)
|
||||
.unwrap()
|
||||
|
|
@ -274,13 +265,10 @@ async fn get_player_js_url(http: &Client) -> Result<String> {
|
|||
let text = resp.text().await?;
|
||||
|
||||
static PLAYER_HASH_PATTERN: Lazy<Regex> = Lazy::new(|| {
|
||||
Regex::new(r#"https:\\\/\\\/www\.youtube\.com\\\/s\\\/player\\\/([a-z0-9]{8})\\\/"#)
|
||||
.unwrap()
|
||||
Regex::new(r#"https:\\/\\/www\.youtube\.com\\/s\\/player\\/([a-z0-9]{8})\\/"#).unwrap()
|
||||
});
|
||||
let player_hash = PLAYER_HASH_PATTERN
|
||||
.captures(&text)
|
||||
.ok()
|
||||
.flatten()
|
||||
.ok_or(DeobfError::Extraction("player hash"))?
|
||||
.get(1)
|
||||
.unwrap()
|
||||
|
|
@ -303,8 +291,6 @@ fn get_sts(player_js: &str) -> Result<String> {
|
|||
|
||||
Ok(STS_PATTERN
|
||||
.captures(player_js)
|
||||
.ok()
|
||||
.flatten()
|
||||
.ok_or(DeobfError::Extraction("sts"))?
|
||||
.get(1)
|
||||
.unwrap()
|
||||
|
|
|
|||
|
|
@ -15,3 +15,4 @@ pub mod model;
|
|||
pub mod param;
|
||||
pub mod report;
|
||||
pub mod timeago;
|
||||
pub mod validate;
|
||||
|
|
|
|||
|
|
@ -111,30 +111,22 @@ impl UrlTarget {
|
|||
/// Validate the YouTube ID from the URL target
|
||||
pub(crate) fn validate(&self) -> Result<(), Error> {
|
||||
match self {
|
||||
UrlTarget::Video { id, .. } => {
|
||||
match util::VIDEO_ID_REGEX.is_match(id).unwrap_or_default() {
|
||||
UrlTarget::Video { id, .. } => match util::VIDEO_ID_REGEX.is_match(id) {
|
||||
true => Ok(()),
|
||||
false => Err(Error::Other("invalid video id".into())),
|
||||
}
|
||||
}
|
||||
UrlTarget::Channel { id } => {
|
||||
match util::CHANNEL_ID_REGEX.is_match(id).unwrap_or_default() {
|
||||
},
|
||||
UrlTarget::Channel { id } => match util::CHANNEL_ID_REGEX.is_match(id) {
|
||||
true => Ok(()),
|
||||
false => Err(Error::Other("invalid channel id".into())),
|
||||
}
|
||||
}
|
||||
UrlTarget::Playlist { id } => {
|
||||
match util::PLAYLIST_ID_REGEX.is_match(id).unwrap_or_default() {
|
||||
},
|
||||
UrlTarget::Playlist { id } => match util::PLAYLIST_ID_REGEX.is_match(id) {
|
||||
true => Ok(()),
|
||||
false => Err(Error::Other("invalid playlist id".into())),
|
||||
}
|
||||
}
|
||||
UrlTarget::Album { id } => {
|
||||
match util::ALBUM_ID_REGEX.is_match(id).unwrap_or_default() {
|
||||
},
|
||||
UrlTarget::Album { id } => match util::ALBUM_ID_REGEX.is_match(id) {
|
||||
true => Ok(()),
|
||||
false => Err(Error::Other("invalid album id".into())),
|
||||
}
|
||||
}
|
||||
},
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
use std::convert::TryFrom;
|
||||
|
||||
use fancy_regex::Regex;
|
||||
use once_cell::sync::Lazy;
|
||||
use regex::Regex;
|
||||
use serde::{Deserialize, Deserializer};
|
||||
use serde_with::{serde_as, DeserializeAs};
|
||||
|
||||
|
|
|
|||
|
|
@ -13,9 +13,10 @@ use std::{
|
|||
};
|
||||
|
||||
use base64::Engine;
|
||||
use fancy_regex::Regex;
|
||||
use fancy_regex::Regex as FancyRegex;
|
||||
use once_cell::sync::Lazy;
|
||||
use rand::Rng;
|
||||
use regex::Regex;
|
||||
use url::Url;
|
||||
|
||||
use crate::{error::Error, param::Language};
|
||||
|
|
@ -24,11 +25,12 @@ pub static VIDEO_ID_REGEX: Lazy<Regex> = Lazy::new(|| Regex::new(r"^[A-Za-z0-9_-
|
|||
pub static CHANNEL_ID_REGEX: Lazy<Regex> =
|
||||
Lazy::new(|| Regex::new(r"^UC[A-Za-z0-9_-]{22}$").unwrap());
|
||||
pub static PLAYLIST_ID_REGEX: Lazy<Regex> =
|
||||
Lazy::new(|| Regex::new(r"^(?:PL|RD|OLAK)[A-Za-z0-9_-]{30,}$").unwrap());
|
||||
Lazy::new(|| Regex::new(r"^(?:PL|RDCLAK|OLAK)[A-Za-z0-9_-]{30,50}$").unwrap());
|
||||
pub static ALBUM_ID_REGEX: Lazy<Regex> =
|
||||
Lazy::new(|| Regex::new(r"^MPREb_[A-Za-z0-9_-]{11}$").unwrap());
|
||||
pub static VANITY_PATH_REGEX: Lazy<Regex> =
|
||||
Lazy::new(|| Regex::new(r"^/?(?:(?:c\/|user\/)?[A-z0-9]+)|(?:@[A-z0-9-_.]+)$").unwrap());
|
||||
pub static VANITY_PATH_REGEX: Lazy<Regex> = Lazy::new(|| {
|
||||
Regex::new(r"^/?(?:(?:c/|user/)?[A-z0-9]{1,100})|(?:@[A-z0-9-_.]{1,100})$").unwrap()
|
||||
});
|
||||
|
||||
/// Separator string for YouTube Music subtitles
|
||||
pub const DOT_SEPARATOR: &str = " • ";
|
||||
|
|
@ -49,6 +51,16 @@ pub struct MappingError(pub(crate) Cow<'static, str>);
|
|||
pub fn get_cg_from_regexes<'a, I>(mut regexes: I, text: &str, cg: usize) -> Option<String>
|
||||
where
|
||||
I: Iterator<Item = &'a Regex>,
|
||||
{
|
||||
regexes
|
||||
.find_map(|pattern| pattern.captures(text))
|
||||
.map(|c| c.get(cg).unwrap().as_str().to_owned())
|
||||
}
|
||||
|
||||
/// Return the given capture group that matches first in a list of fancy regexes
|
||||
pub fn get_cg_from_fancy_regexes<'a, I>(mut regexes: I, text: &str, cg: usize) -> Option<String>
|
||||
where
|
||||
I: Iterator<Item = &'a FancyRegex>,
|
||||
{
|
||||
regexes
|
||||
.find_map(|pattern| pattern.captures(text).ok().flatten())
|
||||
|
|
@ -132,7 +144,7 @@ where
|
|||
pub fn parse_video_length(text: &str) -> Option<u32> {
|
||||
static VIDEO_LENGTH_REGEX: Lazy<Regex> =
|
||||
Lazy::new(|| Regex::new(r#"(?:(\d+):)?(\d{1,2}):(\d{2})"#).unwrap());
|
||||
VIDEO_LENGTH_REGEX.captures(text).ok().flatten().map(|cap| {
|
||||
VIDEO_LENGTH_REGEX.captures(text).map(|cap| {
|
||||
let hrs = cap
|
||||
.get(1)
|
||||
.and_then(|x| x.as_str().parse::<u32>().ok())
|
||||
|
|
@ -339,8 +351,6 @@ pub fn video_id_from_thumbnail_url(url: &str) -> Option<String> {
|
|||
Lazy::new(|| Regex::new(r"^https://i.ytimg.com/vi/([A-Za-z0-9_-]{11})/").unwrap());
|
||||
URL_REGEX
|
||||
.captures(url)
|
||||
.ok()
|
||||
.flatten()
|
||||
.and_then(|cap| cap.get(1).map(|x| x.as_str().to_owned()))
|
||||
}
|
||||
|
||||
|
|
|
|||
179
src/validate.rs
Normal file
179
src/validate.rs
Normal file
|
|
@ -0,0 +1,179 @@
|
|||
//! # Input validation
|
||||
//!
|
||||
//! The extraction functions of RustyPipe will produce errors when fed with invalid input data
|
||||
//! (e.g. YouTube ID's with invalid format). Therefore you will need to validate all untrusted
|
||||
//! input data beforehand. The library offers two options for this:
|
||||
//!
|
||||
//! - The [URL resolver](crate::client::RustyPipeQuery::resolve_url) or
|
||||
//! [string resolver](crate::client::RustyPipeQuery::resolve_string) is great for handling
|
||||
//! arbitrary input and returns a [`UrlTarget`](crate::model::UrlTarget) enum that tells you
|
||||
//! whether the given URL points to a video, channel, playlist, etc.
|
||||
//! - The validation functions of this module are meant vor validating concrete data (video IDs,
|
||||
//! channel IDs, playlist IDs) and return [`true`] if the given input is valid
|
||||
|
||||
use crate::util;
|
||||
use once_cell::sync::Lazy;
|
||||
use regex::Regex;
|
||||
|
||||
/// Validate the given video ID
|
||||
///
|
||||
/// YouTube video IDs are exactly 11 characters long and consist of the charactes `A-Za-z0-9_-`.
|
||||
///
|
||||
/// # Examples
|
||||
/// ```
|
||||
/// # use rustypipe::validate;
|
||||
/// assert!(validate::video_id("dQw4w9WgXcQ"));
|
||||
/// assert!(!validate::video_id("Abcd"));
|
||||
/// assert!(!validate::video_id("dQw4w9WgXc@"));
|
||||
/// ```
|
||||
pub fn video_id<S: AsRef<str>>(video_id: S) -> bool {
|
||||
util::VIDEO_ID_REGEX.is_match(video_id.as_ref())
|
||||
}
|
||||
|
||||
/// Validate the given channel ID
|
||||
///
|
||||
/// YouTube channel IDs are exactly 24 characters long, start with the characters `UC`,
|
||||
/// followed by 22 of these characters: `A-Za-z0-9_-`.
|
||||
///
|
||||
/// # Examples
|
||||
/// ```
|
||||
/// # use rustypipe::validate;
|
||||
/// assert!(validate::channel_id("UC2DjFE7Xf11URZqWBigcVOQ"));
|
||||
/// assert!(!validate::channel_id("Abcd"));
|
||||
/// assert!(!validate::channel_id("XY2DjFE7Xf11URZqWBigcVOQ"));
|
||||
/// ```
|
||||
pub fn channel_id<S: AsRef<str>>(channel_id: S) -> bool {
|
||||
util::CHANNEL_ID_REGEX.is_match(channel_id.as_ref())
|
||||
}
|
||||
|
||||
/// Validate the given playlist ID
|
||||
///
|
||||
/// YouTube playlist IDs start with the characters `PL` (user-created playlist),
|
||||
/// `RDCLAK` (YouTube Music-curated playlist) or `OLAK` (YouTube Music album),
|
||||
/// followed by at least 30 of these characters: `A-Za-z0-9_-`.
|
||||
///
|
||||
/// # Examples
|
||||
/// ```
|
||||
/// # use rustypipe::validate;
|
||||
/// assert!(validate::playlist_id("PL4lEESSgxM_5O81EvKCmBIm_JT5Q7JeaI"));
|
||||
/// assert!(validate::playlist_id("RDCLAK5uy_kFQXdnqMaQCVx2wpUM4ZfbsGCDibZtkJk"));
|
||||
/// assert!(validate::playlist_id("OLAK5uy_k0yFrZlFRgCf3rLPza-lkRmCrtLPbK9pE"));
|
||||
///
|
||||
/// assert!(!validate::playlist_id("Abcd"));
|
||||
/// ```
|
||||
pub fn playlist_id<S: AsRef<str>>(playlist_id: S) -> bool {
|
||||
util::PLAYLIST_ID_REGEX.is_match(playlist_id.as_ref())
|
||||
}
|
||||
|
||||
/// Validate the given album ID
|
||||
///
|
||||
/// YouTube Music album IDs are exactly 17 characters long, start with the characters `MPREB_`,
|
||||
/// followed by 11 of these characters: `A-Za-z0-9_-`.
|
||||
///
|
||||
/// # Examples
|
||||
/// ```
|
||||
/// # use rustypipe::validate;
|
||||
/// assert!(validate::album_id("MPREb_GyH43gCvdM5"));
|
||||
/// assert!(!validate::album_id("Abcd_GyH43gCvdM5"));
|
||||
/// ```
|
||||
///
|
||||
/// # Note
|
||||
///
|
||||
/// Albums on YouTube Music have an album ID (`MPREB_...`) and a playlist ID
|
||||
/// (`OLAK...`). If you open an album on the YouTube Music website, the address bar shows
|
||||
/// the playlist ID, not the album ID.
|
||||
///
|
||||
/// If you have the playlist ID of an album and need the album ID, you can use the
|
||||
/// [string resolver](crate::client::RustyPipeQuery::resolve_string) with the `resolve_albums`
|
||||
/// option enabled.
|
||||
pub fn album_id<S: AsRef<str>>(album_id: S) -> bool {
|
||||
util::ALBUM_ID_REGEX.is_match(album_id.as_ref())
|
||||
}
|
||||
|
||||
/// Validate the given radio ID
|
||||
///
|
||||
/// YouTube radio IDs start with the characters `RD`,
|
||||
/// followed by at least 22 of these characters: `A-Za-z0-9_-`.
|
||||
///
|
||||
/// # Radio types
|
||||
///
|
||||
/// - Artist radio: `RDEMSuoM_jxfse1_g8uCO7MCtg`
|
||||
/// - Genre radio: `RDQM1xqCV6EdPUw`
|
||||
/// - Shuffle radio: `RDAOVeZA-2uzuUKdoB81Ha3srw`
|
||||
/// - Playlist radio (`RDAMPL` + playlist ID): `RDAMPLPL4lEESSgxM_5O81EvKCmBIm_JT5Q7JeaI`
|
||||
/// - Track radio (`RDAMVM` + video ID): `RDAMVMZeerrnuLi5E`
|
||||
///
|
||||
/// # Examples
|
||||
///
|
||||
/// ```
|
||||
/// # use rustypipe::validate;
|
||||
/// assert!(validate::radio_id("RDEMSuoM_jxfse1_g8uCO7MCtg"));
|
||||
/// assert!(!validate::radio_id("Abcd"));
|
||||
/// assert!(!validate::radio_id("XYEMSuoM_jxfse1_g8uCO7MCtg"));
|
||||
/// ```
|
||||
pub fn radio_id<S: AsRef<str>>(radio_id: S) -> bool {
|
||||
static RADIO_ID_REGEX: Lazy<Regex> =
|
||||
Lazy::new(|| Regex::new(r"^RD[A-Za-z0-9_-]{22,50}$").unwrap());
|
||||
|
||||
RADIO_ID_REGEX.is_match(radio_id.as_ref())
|
||||
}
|
||||
|
||||
/// Validate the given genre ID
|
||||
///
|
||||
/// YouTube genre IDs are exactly 24 characters long, start with the characters `ggMPO`,
|
||||
/// followed by 19 of these characters: `A-Za-z0-9_-`.
|
||||
///
|
||||
/// # Examples
|
||||
///
|
||||
/// ```
|
||||
/// # use rustypipe::validate;
|
||||
/// assert!(validate::genre_id("ggMPOg1uX1JOQWZFeDByc2Jm"));
|
||||
/// assert!(!validate::genre_id("Abcd"));
|
||||
/// assert!(!validate::genre_id("ggAbcg1uX1JOQWZFeDByc2Jm"));
|
||||
/// ```
|
||||
pub fn genre_id<S: AsRef<str>>(genre_id: S) -> bool {
|
||||
static GENRE_ID_REGEX: Lazy<Regex> =
|
||||
Lazy::new(|| Regex::new(r"^ggMPO[A-Za-z0-9_-]{19}$").unwrap());
|
||||
|
||||
GENRE_ID_REGEX.is_match(genre_id.as_ref())
|
||||
}
|
||||
|
||||
/// Validate the given related ID
|
||||
///
|
||||
/// YouTube related IDs are exactly 17 characters long, start with the characters `MPTRt_`,
|
||||
/// followed by 11 of these characters: `A-Za-z0-9_-`.
|
||||
///
|
||||
/// # Examples
|
||||
///
|
||||
/// ```
|
||||
/// # use rustypipe::validate;
|
||||
/// assert!(validate::track_related_id("MPTRt_wrKjTn9hmry"));
|
||||
/// assert!(!validate::track_related_id("Abcd"));
|
||||
/// assert!(!validate::track_related_id("Abcdt_wrKjTn9hmry"));
|
||||
/// ```
|
||||
pub fn track_related_id<S: AsRef<str>>(related_id: S) -> bool {
|
||||
static RELATED_ID_REGEX: Lazy<Regex> =
|
||||
Lazy::new(|| Regex::new(r"^MPTRt_[A-Za-z0-9_-]{11}$").unwrap());
|
||||
|
||||
RELATED_ID_REGEX.is_match(related_id.as_ref())
|
||||
}
|
||||
|
||||
/// Validate the given lyrics ID
|
||||
///
|
||||
/// YouTube lyrics IDs are exactly 17 characters long, start with the characters `MPLYt_`,
|
||||
/// followed by 11 of these characters: `A-Za-z0-9_-`.
|
||||
///
|
||||
/// # Examples
|
||||
///
|
||||
/// ```
|
||||
/// # use rustypipe::validate;
|
||||
/// assert!(validate::track_lyrics_id("MPLYt_wrKjTn9hmry"));
|
||||
/// assert!(!validate::track_lyrics_id("Abcd"));
|
||||
/// assert!(!validate::track_lyrics_id("Abcdt_wrKjTn9hmry"));
|
||||
/// ```
|
||||
pub fn track_lyrics_id<S: AsRef<str>>(lyrics_id: S) -> bool {
|
||||
static LYRICS_ID_REGEX: Lazy<Regex> =
|
||||
Lazy::new(|| Regex::new(r"^MPLYt_[A-Za-z0-9_-]{11}$").unwrap());
|
||||
|
||||
LYRICS_ID_REGEX.is_match(lyrics_id.as_ref())
|
||||
}
|
||||
|
|
@ -1,9 +1,8 @@
|
|||
use std::collections::HashSet;
|
||||
use std::fmt::Display;
|
||||
|
||||
use fancy_regex::Regex;
|
||||
use once_cell::sync::Lazy;
|
||||
use rstest::rstest;
|
||||
use rustypipe::validate;
|
||||
use time::macros::date;
|
||||
use time::OffsetDateTime;
|
||||
|
||||
|
|
@ -2121,6 +2120,7 @@ async fn music_genres() {
|
|||
assert!(!pop.is_mood);
|
||||
|
||||
genres.iter().for_each(|g| {
|
||||
assert!(validate::genre_id(&g.id));
|
||||
assert_gte(g.color, 0xff000000, "color");
|
||||
});
|
||||
}
|
||||
|
|
@ -2270,44 +2270,17 @@ async fn assert_next_items<T: FromYtItem, Q: AsRef<RustyPipeQuery>>(
|
|||
}
|
||||
|
||||
fn assert_video_id(id: &str) {
|
||||
static VIDEO_ID_REGEX: Lazy<Regex> = Lazy::new(|| Regex::new(r"^[A-Za-z0-9_-]{11}$").unwrap());
|
||||
|
||||
assert!(
|
||||
VIDEO_ID_REGEX.is_match(id).unwrap_or_default(),
|
||||
"invalid video id: `{}`",
|
||||
id
|
||||
);
|
||||
assert!(validate::video_id(id), "invalid video id: `{}`", id)
|
||||
}
|
||||
|
||||
fn assert_channel_id(id: &str) {
|
||||
static CHANNEL_ID_REGEX: Lazy<Regex> =
|
||||
Lazy::new(|| Regex::new(r"^UC[A-Za-z0-9_-]{22}$").unwrap());
|
||||
|
||||
assert!(
|
||||
CHANNEL_ID_REGEX.is_match(id).unwrap_or_default(),
|
||||
"invalid channel id: `{}`",
|
||||
id
|
||||
);
|
||||
assert!(validate::channel_id(id), "invalid channel id: `{}`", id);
|
||||
}
|
||||
|
||||
fn assert_album_id(id: &str) {
|
||||
static ALBUM_ID_REGEX: Lazy<Regex> =
|
||||
Lazy::new(|| Regex::new(r"^MPREb_[A-Za-z0-9_-]{11}$").unwrap());
|
||||
|
||||
assert!(
|
||||
ALBUM_ID_REGEX.is_match(id).unwrap_or_default(),
|
||||
"invalid album id: `{}`",
|
||||
id
|
||||
);
|
||||
assert!(validate::album_id(id), "invalid album id: `{}`", id);
|
||||
}
|
||||
|
||||
fn assert_playlist_id(id: &str) {
|
||||
static PLAYLIST_ID_REGEX: Lazy<Regex> =
|
||||
Lazy::new(|| Regex::new(r"^(?:PL|RD|OLAK)[A-Za-z0-9_-]{30,}$").unwrap());
|
||||
|
||||
assert!(
|
||||
PLAYLIST_ID_REGEX.is_match(id).unwrap_or_default(),
|
||||
"invalid album id: `{}`",
|
||||
id
|
||||
);
|
||||
assert!(validate::playlist_id(id), "invalid playlist id: `{}`", id);
|
||||
}
|
||||
|
|
|
|||
Loading…
Reference in a new issue