Files
hottub/src/providers/pornhat.rs

232 lines
8.1 KiB
Rust

use crate::util::parse_abbreviated_number;
use crate::DbPool;
use crate::providers::Provider;
use crate::util::cache::VideoCache;
use crate::util::time::parse_time_to_seconds;
use crate::videos::{ServerOptions, VideoItem};
use error_chain::error_chain;
use htmlentity::entity::{ICodedDataTrait, decode};
use std::vec;
use async_trait::async_trait;
error_chain! {
foreign_links {
Io(std::io::Error);
HttpRequest(wreq::Error);
}
}
#[derive(Debug, Clone)]
pub struct PornhatProvider {
url: String,
}
impl PornhatProvider {
pub fn new() -> Self {
PornhatProvider {
url: "https://www.pornhat.com".to_string(),
}
}
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 {
println!("Cache hit for URL: {}", video_url);
return Ok(items.clone());
} else {
items.clone()
}
}
None => {
vec![]
}
};
let mut requester = options.requester.clone().unwrap();
let text = requester.get(&video_url, None).await.unwrap();
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 search_string.starts_with("@"){
let url_part = search_string.split("@").collect::<Vec<&str>>()[1].replace(":", "/");
video_url = format!("{}/{}/", self.url, url_part);
}
// 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 = options.requester.clone().unwrap();
let text = requester.get(&video_url, None).await.unwrap();
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>>()[0]
.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>>()[1]
.split("\"")
.collect::<Vec<&str>>()[0]);
let preview_url = video_segment.split("data-preview-custom=\"").collect::<Vec<&str>>()[1]
.split("\"")
.collect::<Vec<&str>>()[0]
.to_string();
let mut title = video_segment.split("\" title=\"").collect::<Vec<&str>>()[1]
.split("\"")
.collect::<Vec<&str>>()[0]
.to_string();
// html decode
title = decode(title.as_bytes()).to_string().unwrap_or(title);
let id = video_url.split("/").collect::<Vec<&str>>()[4].to_string();
let raw_duration = video_segment.split("fa fa-clock-o").collect::<Vec<&str>>()[1]
.split("<span>").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 thumb = video_segment.split("<img class=\"thumb lazy-load\"").collect::<Vec<&str>>()[1]
.split("data-original=\"").collect::<Vec<&str>>()[1]
.split("\"")
.collect::<Vec<&str>>()[0]
.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>>()[0].to_string())
.collect::<Vec<String>>();
for tag in raw_tags {
if !tag.is_empty() {
tags.push(format!("@sites:{}",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>>()[0].to_string())
.collect::<Vec<String>>();
for tag in raw_tags {
if !tag.is_empty() {
tags.push(format!("@models:{}",tag));
}
}
}
let views_part = video_segment.split("fa fa-eye").collect::<Vec<&str>>()[1]
.split("<span>").collect::<Vec<&str>>()[1]
.split("<")
.collect::<Vec<&str>>()[0]
.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![]
}
}
}
}