Files
hottub/src/providers/sxyprn.rs
2025-12-27 10:25:00 +00:00

348 lines
11 KiB
Rust

use crate::DbPool;
use crate::providers::Provider;
use crate::util::cache::VideoCache;
use crate::util::requester::Requester;
use crate::util::time::parse_time_to_seconds;
use crate::videos::ServerOptions;
use crate::videos::VideoItem;
use async_trait::async_trait;
use error_chain::error_chain;
use htmlentity::entity::{ICodedDataTrait, decode};
use scraper::{Html, Selector};
use std::vec;
error_chain! {
foreign_links {
Io(std::io::Error);
HttpRequest(wreq::Error);
JsonError(serde_json::Error);
}
}
// fn has_blacklisted_class(element: &ElementRef, blacklist: &[&str]) -> bool {
// element
// .value()
// .attr("class")
// .map(|classes| classes.split_whitespace().any(|c| blacklist.contains(&c)))
// .unwrap_or(false)
// }
#[derive(Debug, Clone)]
pub struct SxyprnProvider {
url: String,
}
impl SxyprnProvider {
pub fn new() -> Self {
SxyprnProvider {
url: "https://sxyprn.com".to_string(),
}
}
async fn get(
&self,
cache: VideoCache,
pool: DbPool,
page: u8,
sort: String,
options: ServerOptions,
) -> Result<Vec<VideoItem>> {
let sort_string = match sort.as_str() {
"views" => "views",
"rating" => "rating",
"orgasmic" => "orgasmic",
_ => "latest",
};
// Extract needed fields from options at the start
let filter = options.filter.clone().unwrap();
let filter_string = match filter.as_str() {
"other" => "other",
"all" => "all",
_ => "top",
};
let mut requester = options.requester.clone().unwrap();
let url_str = format!(
"{}/blog/all/{}.html?fl={}&sm={}",
self.url,
((page as u32) - 1) * 20,
filter_string,
sort_string
);
let old_items = match cache.get(&url_str) {
Some((time, items)) => {
if time.elapsed().unwrap_or_default().as_secs() < 60 * 60 {
return Ok(items.clone());
} else {
items.clone()
}
}
None => {
vec![]
}
};
let text = requester.get(&url_str, None).await.unwrap();
// Pass a reference to options if needed, or reconstruct as needed
let video_items: Vec<VideoItem> = self
.get_video_items_from_html(text.clone(), pool, requester)
.await;
if !video_items.is_empty() {
cache.remove(&url_str);
cache.insert(url_str.clone(), video_items.clone());
} else {
return Ok(old_items);
}
Ok(video_items)
}
async fn query(
&self,
cache: VideoCache,
pool: DbPool,
page: u8,
query: &str,
sort: String,
options: ServerOptions,
) -> Result<Vec<VideoItem>> {
let sort_string = match sort.as_str() {
"views" => "views",
"rating" => "trending",
"orgasmic" => "orgasmic",
_ => "latest",
};
// Extract needed fields from options at the start
let mut requester = options.requester.clone().unwrap();
let search_string = query.replace(" ", "-");
let url_str = format!(
"{}/{}.html?page={}&sm={}",
self.url,
search_string,
((page as u32) - 1) * 20,
sort_string
);
// Check our Video Cache. If the result is younger than 1 hour, we return it.
let old_items = match cache.get(&url_str) {
Some((time, items)) => {
if time.elapsed().unwrap_or_default().as_secs() < 60 * 60 {
return Ok(items.clone());
} else {
let _ = cache.check().await;
return Ok(items.clone());
}
}
None => {
vec![]
}
};
let text = requester.get(&url_str, None).await.unwrap();
let video_items: Vec<VideoItem> = self
.get_video_items_from_html(text.clone(), pool, requester)
.await;
if !video_items.is_empty() {
cache.remove(&url_str);
cache.insert(url_str.clone(), video_items.clone());
} else {
return Ok(old_items);
}
Ok(video_items)
}
async fn get_video_items_from_html(
&self,
html: String,
pool: DbPool,
requester: Requester,
) -> Vec<VideoItem> {
let _ = requester;
let _ = pool;
if html.is_empty() {
println!("HTML is empty");
return vec![];
}
let raw_videos = html.split("<script async").collect::<Vec<&str>>()[0]
.split("post_el_small'")
.collect::<Vec<&str>>()[1..]
.to_vec();
let mut items: Vec<VideoItem> = Vec::new();
for video_segment in &raw_videos {
// let vid = video_segment.split("\n").collect::<Vec<&str>>();
// for (index, line) in vid.iter().enumerate() {
// println!("Line {}: {}", index, line.to_string().trim());
// }
// println!("\n\n\n");
let url = video_segment.split("/post/").collect::<Vec<&str>>()[1]
.split("'")
.collect::<Vec<&str>>()[0]
.to_string();
let video_url = format!("https://hottub.spacemoehre.de/proxy/sxyprn/post/{}", url);
let title_parts = video_segment.split("post_text").collect::<Vec<&str>>()[1]
.split("style=''>")
.collect::<Vec<&str>>()[1]
.split("</div>")
.collect::<Vec<&str>>()[0];
let document = Html::parse_document(title_parts);
let selector = Selector::parse("*").unwrap();
let mut texts = Vec::new();
for element in document.select(&selector) {
let text = element.text().collect::<Vec<_>>().join(" ");
if !text.trim().is_empty() {
texts.push(text.trim().to_string());
}
}
let mut title = texts[0].clone();
// html decode
title = decode(title.as_bytes())
.to_string()
.unwrap_or(title)
.replace(" ", " ");
title = title
.replace("\n", "")
.replace(" + ", " ")
.replace(" ", " ")
.trim().to_string();
if title.to_ascii_lowercase().starts_with("new ") {
title = title[4..].to_string();
}
// println!("Title: {}", title);
let id = video_url.split("/").collect::<Vec<&str>>()[6]
.split("?")
.collect::<Vec<&str>>()[0]
.to_string();
let thumb = format!(
"https:{}",
video_segment
.split("<img class='mini_post_vid_thumb lazyload'")
.collect::<Vec<&str>>()[1]
.split("data-src='")
.collect::<Vec<&str>>()[1]
.split("'")
.collect::<Vec<&str>>()[0]
.to_string()
);
let preview = match video_segment.contains("class='hvp_player'") {
true => Some(format!(
"https:{}",
video_segment
.split("class='hvp_player'")
.collect::<Vec<&str>>()[1]
.split(" src='")
.collect::<Vec<&str>>()[1]
.split("'")
.collect::<Vec<&str>>()[0]
.to_string()
)),
false => None,
};
let views = video_segment
.split("<strong>·</strong> ")
.collect::<Vec<&str>>()[1]
.split(" ")
.collect::<Vec<&str>>()[0]
.to_string();
let raw_duration = video_segment.split("duration_small").collect::<Vec<&str>>()[1]
.split("title='")
.collect::<Vec<&str>>()[1]
.split("'")
.collect::<Vec<&str>>()[1]
.split(">")
.collect::<Vec<&str>>()[1]
.split("<")
.collect::<Vec<&str>>()[0]
.to_string();
let duration = parse_time_to_seconds(&raw_duration).unwrap_or(0) as u32;
let stream_urls = video_segment
.split("extlink_icon extlink")
.collect::<Vec<&str>>()
.iter()
.map(|part| {
let url = part
.split("href='")
.collect::<Vec<&str>>()
.last()
.unwrap_or(&"")
.split("'")
.collect::<Vec<&str>>()[0]
.to_string();
url
})
.filter(|url| {
url.starts_with("http")
&& !url.starts_with("https://bigwarp.io/")
&& !url.starts_with("https://doodstream.com/")
&& !url.starts_with("https://strmup.")
&& !url.starts_with("https://streamtape.com/")
&& !url.starts_with("https://streamvid.net/")
&& !url.starts_with("https://vtbe.")
})
.collect::<Vec<String>>();
let video_item_url = match stream_urls.first() {
Some(u) => u.clone(),
None => format!("https://hottub.spacemoehre.de/proxy/sxyprn/post/{}", id), //video_url.clone(),
};
let mut video_item = VideoItem::new(
id,
title,
video_item_url,
"sxyprn".to_string(),
thumb,
duration,
)
.views(views.parse::<u32>().unwrap_or(0));
if let Some(p) = preview {
video_item = video_item.preview(p);
}
items.push(video_item);
}
return items;
}
}
#[async_trait]
impl Provider for SxyprnProvider {
async fn get_videos(
&self,
cache: VideoCache,
pool: DbPool,
sort: String,
query: Option<String>,
page: String,
per_page: String,
options: ServerOptions,
) -> Vec<VideoItem> {
let _ = per_page;
let videos: std::result::Result<Vec<VideoItem>, Error> = match query {
Some(q) => {
self.query(
cache,
pool,
page.parse::<u8>().unwrap_or(1),
&q,
sort,
options,
)
.await
}
None => {
self.get(cache, pool, page.parse::<u8>().unwrap_or(1), sort, options)
.await
}
};
match videos {
Ok(v) => v,
Err(e) => {
println!("Error fetching videos: {}", e);
vec![]
}
}
}
}