1047 lines
37 KiB
Rust
1047 lines
37 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 scraper::{Html, Selector};
|
|
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: &["studio", "networks", "models"],
|
|
};
|
|
|
|
error_chain! {
|
|
foreign_links {
|
|
Io(std::io::Error);
|
|
HttpRequest(wreq::Error);
|
|
}
|
|
}
|
|
|
|
#[derive(Debug, Clone)]
|
|
pub struct OmgxxxProvider {
|
|
url: String,
|
|
sites: Arc<RwLock<Vec<FilterOption>>>,
|
|
networks: Arc<RwLock<Vec<FilterOption>>>,
|
|
stars: Arc<RwLock<Vec<FilterOption>>>,
|
|
}
|
|
impl OmgxxxProvider {
|
|
pub fn new() -> Self {
|
|
let provider = OmgxxxProvider {
|
|
url: "https://www.omg.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(
|
|
"omgxxx",
|
|
"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(
|
|
"omgxxx",
|
|
"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(
|
|
"omgxxx",
|
|
"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(
|
|
"omgxxx",
|
|
"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: "omgxxx".to_string(),
|
|
name: "OMG XXX".to_string(),
|
|
description: "OMG look at that Collection!".to_string(),
|
|
premium: false,
|
|
favicon: "https://www.google.com/s2/favicons?sz=64&domain=www.omg.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(
|
|
"omgxxx",
|
|
"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("omgxxx", "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("omgxxx", "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(
|
|
"omgxxx",
|
|
"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(
|
|
"omgxxx",
|
|
"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 extract_tag_entries(&self, video_segment: &str) -> Vec<(String, String)> {
|
|
let fragment = Html::parse_fragment(video_segment);
|
|
let selector = Selector::parse("div.models a").expect("valid omgxxx models selector");
|
|
fragment
|
|
.select(&selector)
|
|
.filter_map(|anchor| {
|
|
let href = anchor.value().attr("href")?.to_string();
|
|
let title = anchor
|
|
.text()
|
|
.collect::<Vec<_>>()
|
|
.join(" ")
|
|
.split_whitespace()
|
|
.collect::<Vec<_>>()
|
|
.join(" ");
|
|
if title.is_empty() {
|
|
return None;
|
|
}
|
|
Some((href, title))
|
|
})
|
|
.collect()
|
|
}
|
|
|
|
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 loading")
|
|
.collect::<Vec<&str>>()
|
|
.get(1)
|
|
.copied()
|
|
.unwrap_or_default()
|
|
.contains("data-src=\"")
|
|
{
|
|
true => video_segment
|
|
.split("img loading")
|
|
.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 loading")
|
|
.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 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 = Vec::new();
|
|
for (href, tag_title) in self.extract_tag_entries(video_segment) {
|
|
if href.contains("/models/") {
|
|
let model_id = href
|
|
.split("/models/")
|
|
.nth(1)
|
|
.unwrap_or_default()
|
|
.split('/')
|
|
.next()
|
|
.unwrap_or_default()
|
|
.to_string();
|
|
if !model_id.is_empty() {
|
|
Self::push_unique(
|
|
&self.stars,
|
|
FilterOption {
|
|
id: model_id,
|
|
title: tag_title.clone(),
|
|
},
|
|
);
|
|
}
|
|
}
|
|
if href.contains("/sites/") {
|
|
let site_id = href
|
|
.split("/sites/")
|
|
.nth(1)
|
|
.unwrap_or_default()
|
|
.split('/')
|
|
.next()
|
|
.unwrap_or_default()
|
|
.to_string();
|
|
if !site_id.is_empty() {
|
|
Self::push_unique(
|
|
&self.sites,
|
|
FilterOption {
|
|
id: site_id,
|
|
title: tag_title.clone(),
|
|
},
|
|
);
|
|
}
|
|
}
|
|
if !tags.iter().any(|existing| existing == &tag_title) {
|
|
tags.push(tag_title);
|
|
}
|
|
}
|
|
if !site_id.is_empty() {
|
|
Self::push_unique(
|
|
&self.sites,
|
|
FilterOption {
|
|
id: site_id,
|
|
title: site_name.to_string(),
|
|
},
|
|
);
|
|
if !tags.iter().any(|existing| existing == site_name) {
|
|
tags.push(site_name.to_string());
|
|
}
|
|
}
|
|
|
|
let video_item = VideoItem::new(
|
|
id,
|
|
title,
|
|
video_url.to_string(),
|
|
"omgxxx".to_string(),
|
|
thumb,
|
|
duration,
|
|
)
|
|
.views(views)
|
|
.preview(preview)
|
|
.tags(tags);
|
|
items.push(video_item);
|
|
}
|
|
return items;
|
|
}
|
|
}
|
|
|
|
#[cfg(test)]
|
|
mod tests {
|
|
use super::*;
|
|
|
|
fn test_provider() -> OmgxxxProvider {
|
|
OmgxxxProvider {
|
|
url: "https://www.omg.xxx".to_string(),
|
|
sites: Arc::new(RwLock::new(vec![FilterOption {
|
|
id: "clubsweethearts".to_string(),
|
|
title: "Club Sweethearts".to_string(),
|
|
}])),
|
|
networks: Arc::new(RwLock::new(vec![])),
|
|
stars: Arc::new(RwLock::new(vec![])),
|
|
}
|
|
}
|
|
|
|
#[test]
|
|
fn parses_model_and_site_tags_without_empty_strings() {
|
|
let provider = test_provider();
|
|
let html = r##"
|
|
<div class="list-videos">
|
|
<div class="item">
|
|
<a href="https://www.omg.xxx/videos/4290034/example-video/" title="[Club Sweethearts] Example Video"></a>
|
|
<img loading="lazy" data-src="https://cdn.example/thumb.jpg" />
|
|
<span class="duration">Duration 12:34</span>
|
|
<div class="views">1.2M</div>
|
|
<div class="thumb" data-preview="https://cdn.example/preview.mp4"></div>
|
|
<div class="models">
|
|
<a class="models__item thumb_cs" href="https://www.omg.xxx/sites/clubsweethearts/" style="order: 0;">
|
|
<svg class="icon icon-tv"><use xlink:href="#icon-tv"></use></svg>
|
|
<span>Club Sweethearts</span>
|
|
</a>
|
|
<a class="models__item thumb_model" href="https://www.omg.xxx/models/oliver-trunk/" style="order: 0;">
|
|
<svg class="icon icon-star"><use xlink:href="#icon-star"></use></svg>
|
|
<span>Oliver Trunk</span>
|
|
</a>
|
|
<a class="models__item thumb_model" href="https://www.omg.xxx/models/sara-bork/" style="order: 0;">
|
|
<svg class="icon icon-star"><use xlink:href="#icon-star"></use></svg>
|
|
<span>Sara Bork</span>
|
|
</a>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
"##
|
|
.to_string();
|
|
|
|
let items = provider.get_video_items_from_html(html);
|
|
assert_eq!(items.len(), 1);
|
|
assert_eq!(
|
|
items[0].tags,
|
|
Some(vec![
|
|
"Club Sweethearts".to_string(),
|
|
"Oliver Trunk".to_string(),
|
|
"Sara Bork".to_string()
|
|
])
|
|
);
|
|
assert!(
|
|
items[0]
|
|
.tags
|
|
.as_ref()
|
|
.unwrap()
|
|
.iter()
|
|
.all(|tag| !tag.is_empty())
|
|
);
|
|
|
|
let stars = provider.stars.read().unwrap().clone();
|
|
assert!(
|
|
stars
|
|
.iter()
|
|
.any(|tag| tag.id == "oliver-trunk" && tag.title == "Oliver Trunk")
|
|
);
|
|
assert!(
|
|
stars
|
|
.iter()
|
|
.any(|tag| tag.id == "sara-bork" && tag.title == "Sara Bork")
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn parses_live_item_shape_with_channel_and_pornstar_info() {
|
|
let provider = test_provider();
|
|
let html = r##"
|
|
<div class="list-videos">
|
|
<div class="item">
|
|
<a href="https://www.omg.xxx/videos/93763302/step-daughter-vol-2-scene-3/" target="_blank" title="Step Daughter Vol.2 Scene 3">
|
|
<div class="img thumb__img" data-preview="https://cast.omg.xxx/preview/93763302.mp4">
|
|
<img loading="lazy" class="thumb lazyloaded" src="https://img.omg.xxx/93763000/93763302/medium@2x/1.jpg" data-src="https://img.omg.xxx/93763000/93763302/medium@2x/1.jpg" alt="Step Daughter Vol.2 Scene 3" width="0" height="0">
|
|
<span class="duration"> Full Video 26:44 </span>
|
|
<span class="js-favourites thumb-favourites" data-action="add" data-type="video" data-object_id="93763302">
|
|
<svg class="icon icon-heart-plus"><use xlink:href="#icon-heart-plus"></use></svg>
|
|
<svg class="icon icon-trashcan"><use xlink:href="#icon-trashcan"></use></svg>
|
|
</span>
|
|
</div>
|
|
</a>
|
|
<div class="item-info">
|
|
<a href="https://www.omg.xxx/videos/93763302/step-daughter-vol-2-scene-3/" title="Step Daughter Vol.2 Scene 3">
|
|
<strong class="title"> Step Daughter Vol.2 Scene 3 </strong>
|
|
</a>
|
|
<div class="models is-truncated">
|
|
<a class="models__item thumb_cs" href="https://www.omg.xxx/sites/family-sinners/" style="order: 0;">
|
|
<svg class="icon icon-tv"><use xlink:href="#icon-tv"></use></svg>
|
|
<span>Family Sinners</span>
|
|
</a>
|
|
<a class="models__item" href="https://www.omg.xxx/models/vienna-rose/" style="order: 0;">
|
|
<svg class="icon icon-star"><use xlink:href="#icon-star"></use></svg>
|
|
<span>Vienna Rose</span>
|
|
</a>
|
|
<a class="models__item" href="https://www.omg.xxx/models/mark-wood/" style="order: 1;">
|
|
<svg class="icon icon-star"><use xlink:href="#icon-star"></use></svg>
|
|
<span>Mark Wood</span>
|
|
</a>
|
|
</div>
|
|
<div class="wrap">
|
|
<div class="rating positive "> 100% </div>
|
|
<div class="views">4.8K</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
"##
|
|
.to_string();
|
|
|
|
let items = provider.get_video_items_from_html(html);
|
|
assert_eq!(items.len(), 1);
|
|
assert_eq!(
|
|
items[0].tags,
|
|
Some(vec![
|
|
"Family Sinners".to_string(),
|
|
"Vienna Rose".to_string(),
|
|
"Mark Wood".to_string()
|
|
])
|
|
);
|
|
|
|
let sites = provider.sites.read().unwrap().clone();
|
|
assert!(
|
|
sites
|
|
.iter()
|
|
.any(|tag| tag.id == "family-sinners" && tag.title == "Family Sinners")
|
|
);
|
|
|
|
let stars = provider.stars.read().unwrap().clone();
|
|
assert!(
|
|
stars
|
|
.iter()
|
|
.any(|tag| tag.id == "vienna-rose" && tag.title == "Vienna Rose")
|
|
);
|
|
assert!(
|
|
stars
|
|
.iter()
|
|
.any(|tag| tag.id == "mark-wood" && tag.title == "Mark Wood")
|
|
);
|
|
}
|
|
}
|
|
|
|
#[async_trait]
|
|
impl Provider for OmgxxxProvider {
|
|
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))
|
|
}
|
|
}
|