Files
hottub/src/providers/hqporner.rs
2026-03-18 12:13:28 +00:00

587 lines
19 KiB
Rust

use crate::DbPool;
use crate::api::ClientVersion;
use crate::providers::Provider;
use crate::status::*;
use crate::util::cache::VideoCache;
use crate::util::discord::{format_error_chain, send_discord_error_report};
use crate::util::requester::Requester;
use crate::util::time::parse_time_to_seconds;
use crate::videos::{ServerOptions, VideoFormat, VideoItem};
use async_trait::async_trait;
use error_chain::error_chain;
use futures::stream::{FuturesUnordered, StreamExt};
use htmlentity::entity::{ICodedDataTrait, decode};
use std::sync::{Arc, RwLock};
use std::{thread, vec};
use titlecase::Titlecase;
pub const CHANNEL_METADATA: crate::providers::ProviderChannelMetadata =
crate::providers::ProviderChannelMetadata {
group_id: "studio-network",
tags: &["studio", "hd", "scenes"],
};
error_chain! {
foreign_links {
Io(std::io::Error);
HttpRequest(wreq::Error);
Json(serde_json::Error);
}
errors {
Parse(msg: String) {
description("parse error")
display("parse error: {}", msg)
}
}
}
#[derive(Debug, Clone)]
pub struct HqpornerProvider {
url: String,
stars: Arc<RwLock<Vec<FilterOption>>>,
categories: Arc<RwLock<Vec<FilterOption>>>,
}
impl HqpornerProvider {
pub fn new() -> Self {
let provider = HqpornerProvider {
url: "https://hqporner.com".to_string(),
stars: Arc::new(RwLock::new(vec![])),
categories: Arc::new(RwLock::new(vec![])),
};
provider.spawn_initial_load();
provider
}
fn spawn_initial_load(&self) {
let url = self.url.clone();
let stars = Arc::clone(&self.stars);
let categories = Arc::clone(&self.categories);
thread::spawn(move || {
let rt = tokio::runtime::Builder::new_current_thread()
.enable_all()
.build();
if let Ok(runtime) = rt {
runtime.block_on(async move {
if let Err(e) = Self::load_stars(&url, stars).await {
eprintln!("load_stars failed: {e}");
}
if let Err(e) = Self::load_categories(&url, categories).await {
eprintln!("load_categories failed: {e}");
}
});
}
});
}
async fn load_stars(base_url: &str, stars: Arc<RwLock<Vec<FilterOption>>>) -> Result<()> {
let mut requester = Requester::new();
let text = requester
.get(&format!("{}/girls", base_url), None)
.await
.map_err(|e| Error::from(format!("Request failed: {}", e)))?;
let stars_div = text
.split("<span>Girls</span>")
.last()
.and_then(|s| s.split("</ul>").next())
.ok_or_else(|| Error::from("Could not find stars div"))?;
for stars_element in stars_div.split("<li ").skip(1) {
let star_id = stars_element
.split("href=\"/actress/")
.nth(1)
.and_then(|s| s.split('"').next())
.map(|s| s.to_string());
let star_name = stars_element
.split("<a ")
.nth(1)
.and_then(|s| s.split('>').nth(1))
.and_then(|s| s.split('<').next())
.map(|s| s.to_string());
if let (Some(id), Some(name)) = (star_id, star_name) {
Self::push_unique(&stars, FilterOption { id, title: name });
}
}
Ok(())
}
async fn load_categories(
base_url: &str,
categories: Arc<RwLock<Vec<FilterOption>>>,
) -> Result<()> {
let mut requester = Requester::new();
let text = requester
.get(&format!("{}/categories", base_url), None)
.await
.map_err(|e| Error::from(format!("Request failed: {}", e)))?;
let categories_div = text
.split("<span>Categories</span>")
.last()
.and_then(|s| s.split("</ul>").next())
.ok_or_else(|| Error::from("Could not find categories div"))?;
for categories_element in categories_div.split("<li ").skip(1) {
let category_id = categories_element
.split("href=\"/category/")
.nth(1)
.and_then(|s| s.split('"').next())
.map(|s| s.to_string());
let category_name = categories_element
.split("<a ")
.nth(1)
.and_then(|s| s.split('>').nth(1))
.and_then(|s| s.split('<').next())
.map(|s| s.titlecase());
if let (Some(id), Some(name)) = (category_id, category_name) {
Self::push_unique(&categories, FilterOption { id, title: name });
}
}
Ok(())
}
fn build_channel(&self, _clientversion: ClientVersion) -> Channel {
Channel {
id: "hqporner".to_string(),
name: "HQPorner".to_string(),
description: "HD Porn Videos Tube".to_string(),
premium: false,
favicon: "https://www.google.com/s2/favicons?sz=64&domain=hqporner.com".to_string(),
status: "active".to_string(),
categories: self
.categories
.read()
.map(|c| c.iter().map(|o| o.title.clone()).collect())
.unwrap_or_default(),
options: vec![],
nsfw: true,
cacheDuration: None,
}
}
fn push_unique(target: &Arc<RwLock<Vec<FilterOption>>>, item: FilterOption) {
if let Ok(mut vec) = target.write() {
if !vec.iter().any(|x| x.id == item.id) {
vec.push(item);
}
}
}
async fn get(
&self,
cache: VideoCache,
page: u8,
_sort: &str,
options: ServerOptions,
) -> Result<Vec<VideoItem>> {
let video_url = format!("{}/hdporn/{}", self.url, page);
if let Some((time, items)) = cache.get(&video_url) {
if time.elapsed().unwrap_or_default().as_secs() < 300 {
return Ok(items.clone());
}
}
let mut requester = options.requester.clone().ok_or("No requester")?;
let text = requester
.get(&video_url, None)
.await
.map_err(|e| Error::from(format!("Request failed: {}", e)))?;
let video_items = self
.get_video_items_from_html(text, &mut requester, &options)
.await;
if !video_items.is_empty() {
cache.insert(video_url, video_items.clone());
}
Ok(video_items)
}
async fn query(
&self,
cache: VideoCache,
page: u8,
query: &str,
options: ServerOptions,
) -> Result<Vec<VideoItem>> {
let search_string = query.trim().to_lowercase();
let mut video_url = format!("{}/?q={}&p={}", self.url, search_string, page);
if let Ok(stars) = self.stars.read() {
if let Some(star) = stars
.iter()
.find(|s| s.title.to_lowercase() == search_string)
{
video_url = format!("{}/actress/{}/{}", self.url, star.id, page);
}
}
if let Ok(cats) = self.categories.read() {
if let Some(cat) = cats
.iter()
.find(|c| c.title.to_lowercase() == search_string)
{
video_url = format!("{}/category/{}/{}", self.url, cat.id, page);
}
}
if let Some((time, items)) = cache.get(&video_url) {
if time.elapsed().unwrap_or_default().as_secs() < 300 {
return Ok(items.clone());
}
}
let mut requester = options.requester.clone().ok_or("No requester")?;
let text = requester
.get(&video_url, None)
.await
.map_err(|e| Error::from(format!("Request failed: {}", e)))?;
let video_items = self
.get_video_items_from_html(text, &mut requester, &options)
.await;
if !video_items.is_empty() {
cache.insert(video_url, video_items.clone());
}
Ok(video_items)
}
async fn get_video_items_from_html(
&self,
html: String,
requester: &mut Requester,
options: &ServerOptions,
) -> Vec<VideoItem> {
if html.is_empty() || html.contains("404 Not Found") {
return vec![];
}
let raw_videos: Vec<String> = html
.split("id=\"footer\"")
.next()
.and_then(|s| s.split("<section class=\"box features\">").nth(2))
.map(|s| {
s.split("<section class=\"box feature\">")
.skip(1)
.map(|v| v.to_string())
.collect()
})
.unwrap_or_default();
// Limit concurrent detail-page requests to reduce transient connect errors.
let mut in_flight = FuturesUnordered::new();
let mut iter = raw_videos.into_iter();
let mut items = Vec::new();
const MAX_IN_FLIGHT: usize = 6;
loop {
while in_flight.len() < MAX_IN_FLIGHT {
let Some(seg) = iter.next() else {
break;
};
in_flight.push(self.get_video_item(seg, requester.clone(), options));
}
let Some(result) = in_flight.next().await else {
break;
};
match result {
Ok(item)
if item
.formats
.as_ref()
.map(|formats| !formats.is_empty())
.unwrap_or(false) =>
{
items.push(item);
}
Ok(_) => {}
Err(e) => {
let msg = e.to_string();
let chain = format_error_chain(&e);
tokio::spawn(async move {
let _ = send_discord_error_report(
msg,
Some(chain),
Some("Hqporner Provider"),
None,
file!(),
line!(),
module_path!(),
)
.await;
});
}
}
}
items
}
async fn get_video_item(
&self,
seg: String,
mut requester: Requester,
options: &ServerOptions,
) -> Result<VideoItem> {
let video_url = format!(
"{}{}",
self.url,
seg.split("<a href=\"")
.nth(1)
.and_then(|s| s.split('"').next())
.ok_or_else(|| ErrorKind::Parse(format!("url \n{seg}").into()))?
);
let title_raw = seg
.split("<h3 class=\"meta-data-title\">")
.nth(1)
.and_then(|s| s.split('>').nth(1))
.and_then(|s| s.split('<').next())
.ok_or_else(|| ErrorKind::Parse(format!("title \n{seg}").into()))?;
let title = decode(title_raw.as_bytes())
.to_string()
.unwrap_or_else(|_| title_raw.to_string())
.titlecase();
let id = video_url
.split('/')
.nth(4)
.and_then(|s| s.split('.').next())
.ok_or_else(|| ErrorKind::Parse(format!("id \n{seg}").into()))?
.to_string();
let thumb_raw = seg
.split("onmouseleave='defaultImage(\"")
.nth(1)
.and_then(|s| s.split('"').next())
.ok_or_else(|| ErrorKind::Parse(format!("thumb \n{seg}").into()))?;
let thumb_abs = if thumb_raw.starts_with("//") {
format!("https:{}", thumb_raw)
} else if thumb_raw.starts_with("http://") || thumb_raw.starts_with("https://") {
thumb_raw.to_string()
} else {
format!("https://{}", thumb_raw.trim_start_matches('/'))
};
let thumb = match thumb_abs.strip_prefix("https://") {
Some(path) => crate::providers::build_proxy_url(options, "hqporner-thumb", path),
None => thumb_abs,
};
let raw_duration = seg
.split("<span class=\"icon fa-clock-o meta-data\">")
.nth(1)
.and_then(|s| s.split("s<").next())
.map(|s| s.replace("m ", ":"))
.unwrap_or_default();
let duration = parse_time_to_seconds(&raw_duration).unwrap_or(0) as u32;
let (tags, formats) = self.extract_media(&video_url, &mut requester).await?;
Ok(
VideoItem::new(id, title, video_url, "hqporner".into(), thumb, duration)
.formats(formats)
.tags(tags),
)
}
async fn extract_media(
&self,
url: &str,
requester: &mut Requester,
) -> Result<(Vec<String>, Vec<VideoFormat>)> {
let mut formats = vec![];
let mut tags = vec![];
let headers = vec![("Referer".to_string(), "https://hqporner.com/".into())];
let mut text = match self
.fetch_text_with_retries(requester, url, &headers, 3)
.await
{
Ok(text) => text,
Err(primary_err) => {
if url.contains("://hqporner.com/") {
let fallback_url = url.replace("://hqporner.com/", "://www.hqporner.com/");
self.fetch_text_with_retries(requester, &fallback_url, &headers, 3)
.await
.map_err(|fallback_err| {
Error::from(format!(
"Request failed: primary={primary_err}; fallback={fallback_err}"
))
})?
} else {
return Err(Error::from(format!("Request failed: {}", primary_err)));
}
}
};
if text.is_empty() && url.contains("://hqporner.com/") {
let fallback_url = url.replace("://hqporner.com/", "://www.hqporner.com/");
text = self
.fetch_text_with_retries(requester, &fallback_url, &headers, 3)
.await
.unwrap_or_default();
}
if text.contains("Why do I see it?") {
return Ok((tags, formats));
}
// Extract Stars & Tags
if let Some(stars_block) = text
.split("icon fa-star-o")
.nth(1)
.and_then(|s| s.split("</li>").next())
{
for star_el in stars_block.split("href=\"/actress/").skip(1) {
let id = star_el.split('"').next().unwrap_or("").to_string();
let name = star_el
.split("\">")
.nth(1)
.and_then(|s| s.split('<').next())
.unwrap_or("")
.to_string();
if !name.is_empty() {
tags.push(name.clone());
Self::push_unique(&self.stars, FilterOption { id, title: name });
}
}
}
// Player / Video Extraction
let player_url = format!(
"https:{}",
text.split("url: '/blocks/altplayer.php?i=")
.nth(1)
.and_then(|s| s.split('\'').next())
.ok_or("No player link")?
);
let response_text = match self
.fetch_text_with_retries(requester, &player_url, &headers, 2)
.await
{
Ok(text) => text,
Err(e) => {
let err = format!("altplayer request failed: {e}");
send_discord_error_report(
err.clone(),
None,
Some("Hqporner Provider"),
Some(&player_url),
file!(),
line!(),
module_path!(),
)
.await;
return Ok((tags, formats));
}
};
let text2 = response_text;
// Check for error response
if text2.starts_with("ERR:") {
return Ok((tags, formats));
}
let video_element = text2
.split("<video ")
.nth(2)
.and_then(|s| s.split("</video>").next())
.ok_or(format!("No video element\n{player_url}\n{text2}"))?;
for source in video_element.split("<source ").skip(1) {
let title = source
.split("title=\\\"")
.nth(1)
.and_then(|s| s.split("\\\"").next())
.unwrap_or("")
.to_string();
let quality = title.split(' ').next().unwrap_or("HD").to_string();
let media_url = format!(
"https:{}",
source
.split("src=\\\"")
.nth(1)
.and_then(|s| s.split("\\\"").next())
.unwrap_or("")
);
formats.push(
VideoFormat::new(media_url, quality, "mp4".into())
.format_id(title.clone())
.format_note(title),
);
}
Ok((tags, formats))
}
async fn fetch_text_with_retries(
&self,
requester: &mut Requester,
url: &str,
headers: &[(String, String)],
max_attempts: u8,
) -> std::result::Result<String, String> {
let mut last_err = String::new();
for attempt in 1..=max_attempts {
match requester.get_raw_with_headers(url, headers.to_vec()).await {
Ok(resp) => match resp.text().await {
Ok(text) => return Ok(text),
Err(e) => {
last_err =
format!("text read failed (attempt {attempt}/{max_attempts}): {e}");
}
},
Err(e) => {
last_err = format!("request failed (attempt {attempt}/{max_attempts}): {e}");
}
}
if attempt < max_attempts {
tokio::time::sleep(std::time::Duration::from_millis(250 * attempt as u64)).await;
}
}
Err(last_err)
}
}
#[async_trait]
impl Provider for HqpornerProvider {
async fn get_videos(
&self,
cache: VideoCache,
_pool: DbPool,
sort: String,
query: Option<String>,
page: String,
_per_page: String,
options: ServerOptions,
) -> Vec<VideoItem> {
let page_num = page.parse::<u8>().unwrap_or(1);
let res = match query {
Some(q) => self.query(cache, page_num, &q, options).await,
None => self.get(cache, page_num, &sort, options).await,
};
res.unwrap_or_else(|e| {
eprintln!("Hqporner error: {e}");
let _ = send_discord_error_report(
e.to_string(),
Some(format_error_chain(&e)),
None,
None,
file!(),
line!(),
module_path!(),
);
vec![]
})
}
fn get_channel(&self, v: ClientVersion) -> Option<Channel> {
Some(self.build_channel(v))
}
}