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

891 lines
31 KiB
Rust

use crate::DbPool;
use crate::api::ClientVersion;
use crate::providers::{Provider, report_provider_error, report_provider_error_background};
use crate::util::cache::VideoCache;
use crate::util::parse_abbreviated_number;
use crate::util::time::parse_time_to_seconds;
use crate::videos::{ServerOptions, VideoItem};
use crate::{status::*, util};
use async_trait::async_trait;
use error_chain::error_chain;
use htmlentity::entity::{ICodedDataTrait, decode};
use std::sync::{Arc, RwLock};
use std::thread;
use std::vec;
pub const CHANNEL_METADATA: crate::providers::ProviderChannelMetadata =
crate::providers::ProviderChannelMetadata {
group_id: "studio-network",
tags: &["tube", "networked", "mixed"],
};
error_chain! {
foreign_links {
Io(std::io::Error);
HttpRequest(wreq::Error);
}
}
#[derive(Debug, Clone)]
pub struct FreepornvideosxxxProvider {
url: String,
sites: Arc<RwLock<Vec<FilterOption>>>,
networks: Arc<RwLock<Vec<FilterOption>>>,
stars: Arc<RwLock<Vec<FilterOption>>>,
}
impl FreepornvideosxxxProvider {
pub fn new() -> Self {
let provider = FreepornvideosxxxProvider {
url: "https://www.freepornvideos.xxx".to_string(),
sites: Arc::new(RwLock::new(vec![FilterOption {
id: "all".to_string(),
title: "All".to_string(),
}])),
networks: Arc::new(RwLock::new(vec![FilterOption {
id: "all".to_string(),
title: "All".to_string(),
}])),
stars: Arc::new(RwLock::new(vec![FilterOption {
id: "all".to_string(),
title: "All".to_string(),
}])),
};
// Kick off the background load but return immediately
provider.spawn_initial_load();
provider
}
fn spawn_initial_load(&self) {
let url = self.url.clone();
let sites = Arc::clone(&self.sites);
let networks = Arc::clone(&self.networks);
let stars = Arc::clone(&self.stars);
thread::spawn(move || {
// Create a tiny runtime just for these async tasks
let rt = match tokio::runtime::Builder::new_current_thread()
.enable_all()
.build()
{
Ok(rt) => rt,
Err(e) => {
report_provider_error_background(
"freepornvideosxxx",
"spawn_initial_load.runtime_build",
&e.to_string(),
);
return;
}
};
rt.block_on(async move {
// If you have a streaming sites loader, call it here too
if let Err(e) = Self::load_sites(&url, sites).await {
eprintln!("load_sites_into failed: {e}");
}
if let Err(e) = Self::load_networks(&url, networks).await {
eprintln!("load_networks failed: {e}");
}
if let Err(e) = Self::load_stars(&url, stars).await {
eprintln!("load_stars failed: {e}");
}
});
});
}
async fn load_stars(base_url: &str, stars: Arc<RwLock<Vec<FilterOption>>>) -> Result<()> {
let mut requester = util::requester::Requester::new();
for page in [1..10].into_iter().flatten() {
let text = match requester
.get(
format!("{}/models/total-videos/{}/?gender_id=0", &base_url, page).as_str(),
None,
)
.await
{
Ok(text) => text,
Err(e) => {
report_provider_error_background(
"freepornvideosxxx",
"load_stars.request",
&format!("url={base_url}; page={page}; error={e}"),
);
break;
}
};
if text.contains("404 Not Found") || text.is_empty() {
break;
}
let stars_div = text
.split("<div class=\"list-models\">")
.collect::<Vec<&str>>()
.last()
.copied()
.unwrap_or_default()
.split("custom_list_models_models_list_pagination")
.collect::<Vec<&str>>()
.get(0)
.copied()
.unwrap_or_default();
for stars_element in stars_div.split("<a ").collect::<Vec<&str>>()[1..].to_vec() {
let star_url = stars_element
.split("href=\"")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.split("\"")
.collect::<Vec<&str>>()
.get(0)
.copied()
.unwrap_or_default();
let star_id = star_url
.split("/")
.collect::<Vec<&str>>()
.get(4)
.copied()
.unwrap_or_default()
.to_string();
let star_name = stars_element
.split("<strong class=\"title\">")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.split("<")
.collect::<Vec<&str>>()
.get(0)
.copied()
.unwrap_or_default()
.to_string();
Self::push_unique(
&stars,
FilterOption {
id: star_id,
title: star_name,
},
);
}
}
return Ok(());
}
async fn load_sites(base_url: &str, sites: Arc<RwLock<Vec<FilterOption>>>) -> Result<()> {
let mut requester = util::requester::Requester::new();
let mut page = 0;
loop {
page += 1;
let text = requester
.get(format!("{}/sites/{}/", &base_url, page).as_str(), None)
.await;
let text = match text {
Ok(text) => text,
Err(e) => {
report_provider_error_background(
"freepornvideosxxx",
"load_sites.request",
&format!("url={base_url}; page={page}; error={e}"),
);
break;
}
};
if text.contains("404 Not Found") || text.is_empty() {
break;
}
let sites_div = text
.split("id=\"list_content_sources_sponsors_list_items\"")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.split("class=\"pagination\"")
.collect::<Vec<&str>>()
.get(0)
.copied()
.unwrap_or_default();
for sites_element in
sites_div.split("class=\"headline\"").collect::<Vec<&str>>()[1..].to_vec()
{
let site_url = sites_element
.split("href=\"")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.split("\"")
.collect::<Vec<&str>>()
.get(0)
.copied()
.unwrap_or_default();
let site_id = site_url
.split("/")
.collect::<Vec<&str>>()
.get(4)
.copied()
.unwrap_or_default()
.to_string();
let site_name = sites_element
.split("<h2>")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.split("<")
.collect::<Vec<&str>>()
.get(0)
.copied()
.unwrap_or_default()
.to_string();
Self::push_unique(
&sites,
FilterOption {
id: site_id,
title: site_name,
},
);
}
}
return Ok(());
}
async fn load_networks(base_url: &str, networks: Arc<RwLock<Vec<FilterOption>>>) -> Result<()> {
let mut requester = util::requester::Requester::new();
let text = match requester.get(&base_url, None).await {
Ok(text) => text,
Err(e) => {
report_provider_error_background(
"freepornvideosxxx",
"load_networks.request",
&format!("url={base_url}; error={e}"),
);
return Ok(());
}
};
let networks_div = text
.split("class=\"sites__list\"")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.split("</div>")
.collect::<Vec<&str>>()
.get(0)
.copied()
.unwrap_or_default();
for network_element in
networks_div.split("sites__item").collect::<Vec<&str>>()[1..].to_vec()
{
if network_element.contains("sites__all") {
continue;
}
let network_url = network_element
.split("href=\"")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.split("\"")
.collect::<Vec<&str>>()
.get(0)
.copied()
.unwrap_or_default();
let network_id = network_url
.split("/")
.collect::<Vec<&str>>()
.get(4)
.copied()
.unwrap_or_default()
.to_string();
let network_name = network_element
.split(">")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.split("<")
.collect::<Vec<&str>>()
.get(0)
.copied()
.unwrap_or_default()
.to_string();
Self::push_unique(
&networks,
FilterOption {
id: network_id,
title: network_name,
},
);
}
return Ok(());
}
// Push one item with minimal lock time and dedup by id
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);
// Optional: keep it sorted for nicer UX
// vec.sort_by(|a,b| a.title.cmp(&b.title));
}
}
}
fn build_channel(&self, clientversion: ClientVersion) -> Channel {
let _ = clientversion;
let sites: Vec<FilterOption> = self
.sites
.read()
.map(|g| g.clone()) // or: .map(|g| g.to_vec())
.unwrap_or_default(); // or: .unwrap_or_else(|_| Vec::new())
let networks: Vec<FilterOption> = self
.networks
.read()
.map(|g| g.clone()) // or: .map(|g| g.to_vec())
.unwrap_or_default(); // or: .unwrap_or_else(|_| Vec::new())
let stars: Vec<FilterOption> = self
.stars
.read()
.map(|g| g.clone()) // or: .map(|g| g.to_vec())
.unwrap_or_default(); // or: .unwrap_or_else(|_| Vec::new())
Channel {
id: "freepornvideosxxx".to_string(),
name: "FreePornVideos XXX".to_string(),
description: "Free Porn Videos".to_string(),
premium: false,
favicon: "https://www.google.com/s2/favicons?sz=64&domain=www.freepornvideos.xxx"
.to_string(),
status: "active".to_string(),
categories: vec![],
options: vec![
ChannelOption {
id: "sort".to_string(),
title: "Sort".to_string(),
description: "Sort the Videos".to_string(),
systemImage: "list.number".to_string(),
colorName: "blue".to_string(),
options: vec![
FilterOption {
id: "latest-updates".into(),
title: "Latest".into(),
},
FilterOption {
id: "most-popular".into(),
title: "Most Viewed".into(),
},
FilterOption {
id: "top-rated".into(),
title: "Top Rated".into(),
},
],
multiSelect: false,
},
ChannelOption {
id: "sites".to_string(),
title: "Sites".to_string(),
description: "Filter for different Sites".to_string(),
systemImage: "rectangle.stack".to_string(),
colorName: "green".to_string(),
options: sites,
multiSelect: false,
},
ChannelOption {
id: "networks".to_string(),
title: "Networks".to_string(),
description: "Filter for different Networks".to_string(),
systemImage: "list.dash".to_string(),
colorName: "purple".to_string(),
options: networks,
multiSelect: false,
},
ChannelOption {
id: "stars".to_string(),
title: "Stars".to_string(),
description: "Filter for different Pornstars".to_string(),
systemImage: "star.fill".to_string(),
colorName: "yellow".to_string(),
options: stars,
multiSelect: false,
},
],
nsfw: true,
cacheDuration: None,
}
}
async fn get(
&self,
cache: VideoCache,
page: u8,
sort: &str,
options: ServerOptions,
) -> Result<Vec<VideoItem>> {
let mut sort_string: String = match sort {
"top-rated" => "top-rated".to_string(),
"most-popular" => "most-popular".to_string(),
_ => "latest-updates".to_string(),
};
let alt_sort_string: String = match sort {
"top-rated" => "/top-rated".to_string(),
"most-popular" => "/most-popular".to_string(),
_ => "".to_string(),
};
if let Some(network) = options.network.as_deref() {
if !network.is_empty() && network != "all" {
sort_string = format!("networks/{}{}", network, alt_sort_string);
}
}
if let Some(site) = options.sites.as_deref() {
if !site.is_empty() && site != "all" {
sort_string = format!("sites/{}{}", site, alt_sort_string);
}
}
if let Some(star) = options.stars.as_deref() {
if !star.is_empty() && star != "all" {
sort_string = format!("models/{}{}", star, alt_sort_string);
}
}
let video_url = format!("{}/{}/{}/", self.url, sort_string, page);
let old_items = match cache.get(&video_url) {
Some((time, items)) => {
if time.elapsed().unwrap_or_default().as_secs() < 60 * 5 {
return Ok(items.clone());
} else {
items.clone()
}
}
None => {
vec![]
}
};
let mut requester =
crate::providers::requester_or_default(&options, module_path!(), "missing_requester");
let text = match requester.get(&video_url, None).await {
Ok(text) => text,
Err(e) => {
report_provider_error(
"freepornvideosxxx",
"get.request",
&format!("url={video_url}; error={e}"),
)
.await;
return Ok(old_items);
}
};
let video_items: Vec<VideoItem> = self.get_video_items_from_html(text.clone());
if !video_items.is_empty() {
cache.remove(&video_url);
cache.insert(video_url.clone(), video_items.clone());
} else {
return Ok(old_items);
}
Ok(video_items)
}
async fn query(
&self,
cache: VideoCache,
page: u8,
query: &str,
options: ServerOptions,
) -> Result<Vec<VideoItem>> {
let mut search_type = "search";
let mut search_string = query.to_string().to_ascii_lowercase().trim().to_string();
match self.stars.read() {
Ok(stars) => {
if let Some(star) = stars
.iter()
.find(|s| s.title.to_ascii_lowercase() == search_string)
{
search_type = "models";
search_string = star.id.clone();
}
}
Err(e) => {
report_provider_error_background(
"freepornvideosxxx",
"query.stars_read",
&e.to_string(),
);
}
}
match self.sites.read() {
Ok(sites) => {
if let Some(site) = sites
.iter()
.find(|s| s.title.to_ascii_lowercase() == search_string)
{
search_type = "sites";
search_string = site.id.clone();
}
}
Err(e) => {
report_provider_error_background(
"freepornvideosxxx",
"query.sites_read",
&e.to_string(),
);
}
}
let mut video_url = format!("{}/{}/{}/{}/", self.url, search_type, search_string, page);
video_url = video_url.replace(" ", "+");
// Check our Video Cache. If the result is younger than 1 hour, we return it.
let old_items = match cache.get(&video_url) {
Some((time, items)) => {
if time.elapsed().unwrap_or_default().as_secs() < 60 * 5 {
return Ok(items.clone());
} else {
let _ = cache.check().await;
return Ok(items.clone());
}
}
None => {
vec![]
}
};
let mut requester =
crate::providers::requester_or_default(&options, module_path!(), "missing_requester");
let text = match requester.get(&video_url, None).await {
Ok(text) => text,
Err(e) => {
report_provider_error(
"freepornvideosxxx",
"query.request",
&format!("url={video_url}; error={e}"),
)
.await;
return Ok(old_items);
}
};
let video_items: Vec<VideoItem> = self.get_video_items_from_html(text.clone());
if !video_items.is_empty() {
cache.remove(&video_url);
cache.insert(video_url.clone(), video_items.clone());
} else {
return Ok(old_items);
}
Ok(video_items)
}
fn get_site_id_from_name(&self, site_name: &str) -> Option<String> {
// site_name.to_lowercase().replace(" ", "")
let sites_guard = match self.sites.read() {
Ok(guard) => guard,
Err(e) => {
report_provider_error_background(
"freepornvideosxxx",
"get_site_id_from_name.sites_read",
&e.to_string(),
);
return None;
}
};
for site in sites_guard.iter() {
if site
.title
.to_lowercase()
.replace(" ", "")
.replace(".com", "")
== site_name.to_lowercase().replace(" ", "")
{
return Some(site.id.clone());
}
}
return None;
}
fn get_video_items_from_html(&self, html: String) -> Vec<VideoItem> {
if html.is_empty() {
println!("HTML is empty");
return vec![];
}
let mut items: Vec<VideoItem> = Vec::new();
if !html.contains("class=\"item\"") {
return items;
}
let raw_videos = html
.split("videos_list_pagination")
.collect::<Vec<&str>>()
.get(0)
.copied()
.unwrap_or_default()
.split(" class=\"pagination\" ")
.collect::<Vec<&str>>()
.get(0)
.copied()
.unwrap_or_default()
.split("class=\"list-videos\"")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.split("class=\"item\"")
.collect::<Vec<&str>>()[1..]
.to_vec();
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);
// }
let video_url: String = video_segment
.split("<a href=\"")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.split("\"")
.collect::<Vec<&str>>()
.get(0)
.copied()
.unwrap_or_default()
.to_string();
let mut title = video_segment
.split(" title=\"")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.split("\"")
.collect::<Vec<&str>>()
.get(0)
.copied()
.unwrap_or_default()
.to_string();
// html decode
title = decode(title.as_bytes()).to_string().unwrap_or(title);
let id = video_url
.split("/")
.collect::<Vec<&str>>()
.get(4)
.copied()
.unwrap_or_default()
.to_string();
let thumb = match video_segment
.split("<img ")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.contains("data-src=\"")
{
true => video_segment
.split("<img ")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.split("data-src=\"")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.split("\"")
.collect::<Vec<&str>>()
.get(0)
.copied()
.unwrap_or_default()
.to_string(),
false => video_segment
.split("<img ")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.split("src=\"")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.split("\"")
.collect::<Vec<&str>>()
.get(0)
.copied()
.unwrap_or_default()
.to_string(),
};
let raw_duration = video_segment
.split("<span class=\"duration\">")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.split("<")
.collect::<Vec<&str>>()
.get(0)
.copied()
.unwrap_or_default()
.split(" ")
.collect::<Vec<&str>>()
.last()
.unwrap_or(&"")
.to_string();
let duration = parse_time_to_seconds(raw_duration.as_str()).unwrap_or(0) as u32;
let views = parse_abbreviated_number(
video_segment
.split("<div class=\"views\">")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.split("<")
.collect::<Vec<&str>>()
.get(0)
.copied()
.unwrap_or_default()
.to_string()
.as_str(),
)
.unwrap_or(0) as u32;
let preview = video_segment
.split("data-preview=\"")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.split("\"")
.collect::<Vec<&str>>()
.get(0)
.copied()
.unwrap_or_default()
.to_string();
let site_name = title
.split("]")
.collect::<Vec<&str>>()
.first()
.unwrap_or(&"")
.trim_start_matches("[");
let site_id = self
.get_site_id_from_name(site_name)
.unwrap_or("".to_string());
let mut tags = match video_segment.contains("class=\"models\">") {
true => video_segment
.split("class=\"models\">")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.split("</div>")
.collect::<Vec<&str>>()
.get(0)
.copied()
.unwrap_or_default()
.split("href=\"")
.collect::<Vec<&str>>()[1..]
.into_iter()
.map(|s| {
Self::push_unique(
&self.stars,
FilterOption {
id: s
.split("/")
.collect::<Vec<&str>>()
.get(4)
.copied()
.unwrap_or_default()
.to_string(),
title: s
.split(">")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.split("<")
.collect::<Vec<&str>>()
.get(0)
.copied()
.unwrap_or_default()
.trim()
.to_string(),
},
);
s.split(">")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.split("<")
.collect::<Vec<&str>>()
.get(0)
.copied()
.unwrap_or_default()
.trim()
.to_string()
})
.collect::<Vec<String>>()
.to_vec(),
false => vec![],
};
if !site_id.is_empty() {
Self::push_unique(
&self.sites,
FilterOption {
id: site_id,
title: site_name.to_string(),
},
);
tags.push(site_name.to_string());
}
let video_item = VideoItem::new(
id,
title,
video_url.to_string(),
"freepornvideosxxx".to_string(),
thumb,
duration,
)
.views(views)
.preview(preview)
.tags(tags);
items.push(video_item);
}
return items;
}
}
#[async_trait]
impl Provider for FreepornvideosxxxProvider {
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 _ = pool;
let videos: std::result::Result<Vec<VideoItem>, Error> = match query {
Some(q) => {
self.query(cache, page.parse::<u8>().unwrap_or(1), &q, options)
.await
}
None => {
self.get(cache, page.parse::<u8>().unwrap_or(1), &sort, options)
.await
}
};
match videos {
Ok(v) => v,
Err(e) => {
println!("Error fetching videos: {}", e);
vec![]
}
}
}
fn get_channel(&self, clientversion: ClientVersion) -> Option<crate::status::Channel> {
Some(self.build_channel(clientversion))
}
}