Files
hottub/src/providers/pornhat.rs
2026-04-05 20:31:38 +00:00

445 lines
15 KiB
Rust

use crate::DbPool;
use crate::api::ClientVersion;
use crate::providers::Provider;
use crate::status::*;
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 async_trait::async_trait;
use error_chain::error_chain;
use htmlentity::entity::{ICodedDataTrait, decode};
use std::collections::HashMap;
use std::sync::{Arc, RwLock};
use std::vec;
pub const CHANNEL_METADATA: crate::providers::ProviderChannelMetadata =
crate::providers::ProviderChannelMetadata {
group_id: "mainstream-tube",
tags: &["tube", "hd", "mixed"],
};
error_chain! {
foreign_links {
Io(std::io::Error);
HttpRequest(wreq::Error);
}
}
#[derive(Debug, Clone)]
pub struct PornhatProvider {
url: String,
tag_map: Arc<RwLock<HashMap<String, String>>>,
}
impl PornhatProvider {
pub fn new() -> Self {
PornhatProvider {
url: "https://www.pornhat.com".to_string(),
tag_map: Arc::new(RwLock::new(HashMap::new())),
}
}
fn normalize_key(value: &str) -> String {
value
.trim()
.to_ascii_lowercase()
.replace(['_', '-'], " ")
.split_whitespace()
.collect::<Vec<_>>()
.join(" ")
}
fn humanize_slug(value: &str) -> String {
value
.trim_matches('/')
.replace('-', " ")
.split_whitespace()
.collect::<Vec<_>>()
.join(" ")
}
fn insert_tag_mapping(&self, kind: &str, slug: &str, title: Option<&str>) {
let slug = slug.trim().trim_matches('/');
if slug.is_empty() {
return;
}
let path = format!("{kind}/{slug}");
if let Ok(mut map) = self.tag_map.write() {
map.insert(Self::normalize_key(slug), path.clone());
let normalized_title = Self::normalize_key(title.unwrap_or(slug));
if !normalized_title.is_empty() {
map.insert(normalized_title, path);
}
}
}
fn resolve_query_path(&self, query: &str) -> Option<String> {
let trimmed = query.trim().trim_start_matches('@');
if let Some((kind, raw_value)) = trimmed.split_once(':') {
let kind = kind.trim().to_ascii_lowercase();
let value = raw_value.trim().trim_matches('/').replace(' ', "-");
if !value.is_empty() && matches!(kind.as_str(), "sites" | "models") {
return Some(format!("{kind}/{value}"));
}
}
let normalized = Self::normalize_key(trimmed);
if normalized.is_empty() {
return None;
}
self.tag_map.read().ok()?.get(&normalized).cloned()
}
fn build_channel(&self, _clientversion: ClientVersion) -> Channel {
Channel {
id: "pornhat".to_string(),
name: "Pornhat".to_string(),
description: "free HD porn videos".to_string(),
premium: false,
favicon: "https://www.google.com/s2/favicons?sz=64&domain=pornhat.com".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: "new".to_string(),
title: "New".to_string(),
},
FilterOption {
id: "popular".to_string(),
title: "Popular".to_string(),
},
FilterOption {
id: "trending".to_string(),
title: "Trending".to_string(),
},
],
multiSelect: false,
}],
nsfw: true,
cacheDuration: Some(1800),
}
}
async fn get(
&self,
cache: VideoCache,
page: u8,
sort: &str,
options: ServerOptions,
) -> Result<Vec<VideoItem>> {
let sort_string = match sort {
"trending" => "/trending",
"popular" => "/popular",
_ => "",
};
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) => {
crate::providers::report_provider_error(
"pornhat",
"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 search_string = query.to_lowercase().trim().replace(" ", "-");
let mut video_url = format!("{}/search/{}/{}/", self.url, search_string, page);
if let Some(path) = self.resolve_query_path(query) {
video_url = format!("{}/{}/{}/", self.url, path, page);
}
// 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) => {
crate::providers::report_provider_error(
"pornhat",
"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_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();
let raw_videos = html
.split("<div class=\"pagination\"")
.collect::<Vec<&str>>()
.get(0)
.copied()
.unwrap_or_default()
.split("item thumb-bl thumb-bl-video video_")
.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 = format!(
"{}{}",
self.url,
video_segment
.split("<a href=\"")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.split("\"")
.collect::<Vec<&str>>()
.get(0)
.copied()
.unwrap_or_default()
);
let preview_url = video_segment
.split("data-preview-custom=\"")
.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 raw_duration = video_segment
.split("fa fa-clock-o")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.split("<span>")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.split("<")
.collect::<Vec<&str>>()
.get(0)
.copied()
.unwrap_or_default()
.to_string();
let duration = parse_time_to_seconds(&raw_duration).unwrap_or(0) as u32;
let thumb = video_segment
.split("<img class=\"thumb lazy-load\"")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.split("data-original=\"")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.split("\"")
.collect::<Vec<&str>>()
.get(0)
.copied()
.unwrap_or_default()
.to_string();
let mut tags = vec![];
if video_segment.contains("href=\"/sites/") {
let raw_tags = video_segment.split("href=\"/sites/").collect::<Vec<&str>>()[1..]
.iter()
.map(|s| {
s.split("/\"")
.collect::<Vec<&str>>()
.get(0)
.copied()
.unwrap_or_default()
.to_string()
})
.collect::<Vec<String>>();
for tag in raw_tags {
if !tag.is_empty() {
self.insert_tag_mapping("sites", &tag, None);
tags.push(Self::humanize_slug(&tag));
}
}
}
if video_segment.contains("href=\"/models/") {
let raw_tags = video_segment
.split("href=\"/models/")
.collect::<Vec<&str>>()[1..]
.iter()
.map(|s| {
s.split("/\"")
.collect::<Vec<&str>>()
.get(0)
.copied()
.unwrap_or_default()
.to_string()
})
.collect::<Vec<String>>();
for tag in raw_tags {
if !tag.is_empty() {
self.insert_tag_mapping("models", &tag, None);
tags.push(Self::humanize_slug(&tag));
}
}
}
let views_part = video_segment
.split("fa fa-eye")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.split("<span>")
.collect::<Vec<&str>>()
.get(1)
.copied()
.unwrap_or_default()
.split("<")
.collect::<Vec<&str>>()
.get(0)
.copied()
.unwrap_or_default()
.to_string();
let views = parse_abbreviated_number(&views_part).unwrap_or(0) as u32;
let video_item = VideoItem::new(
id,
title,
video_url.to_string(),
"Pornhat".to_string(),
thumb,
duration,
)
.preview(preview_url)
.views(views)
.tags(tags);
items.push(video_item);
}
return items;
}
}
#[async_trait]
impl Provider for PornhatProvider {
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<Channel> {
Some(self.build_channel(clientversion))
}
}